System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring initial hearing information of a user and storing the initial hearing information in a database; means for collecting life data of the user and data from a wearable device and creating a profile of the user; means for analyzing a thinking pattern of the user based on the profile; means for generating an improvement proposal for each user based on an analysis result of the thinking pattern; and means for notifying a terminal of the user of the improvement proposal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern society, many young people lead busy lives, both at work and in their personal lives, making them susceptible to stress. This stress reduces work efficiency, disrupts lifestyle habits, and reduces overall quality of life. While it is expected that these problems can be solved by consulting with professional consultants or counselors, this comes with a significant psychological and financial burden. Furthermore, it is difficult to receive specific improvement suggestions tailored to individual needs. Therefore, there is a need for a method that can improve work and personal performance and reduce stress by providing personalized suggestions for improving thinking patterns for each user. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for acquiring a user's initial hearing information and storing it in a database, a means for collecting the user's lifestyle data and data from a wearable device to create a user profile, a means for analyzing the user's thought patterns based on the profile, and a means for generating improvement suggestions for each user based on the analysis of the thought patterns. The system also includes a means for notifying the user of the improvement suggestions via a terminal. This allows each user to receive personalized improvement suggestions, leading to improved stress management, work efficiency, lifestyle habits, decision-making quality, and communication.

[0006] "User" refers to an individual who uses this system.

[0007] "Initial hearing information" refers to basic information that a user first enters into the system, and includes name, age, occupation, stress level, current lifestyle habits, etc.

[0008] A "database" is a collection of digital data used to store user information, profiles, improvement suggestions, etc.

[0009] "Lifestyle data" is information about a user's daily activities, including web usage history and app usage history.

[0010] A "wearable device" is a device that can collect physical data when worn by a user, and includes smart watches and the like.

[0011] A "profile" is a collection of information about a user's thought patterns and behavioral tendencies, generated based on collected lifestyle data and data from wearable devices.

[0012] "Thinking patterns" indicate the tendency of a user to act and think in certain situations.

[0013] "Improvement suggestions" are specific suggestions for improving the user's behavior and life based on the analysis of thought patterns.

[0014] A "terminal" is a device used by a user, including a smartphone, PC, etc.

[0015] "Notification" refers to a means for the system to notify the user of information, and includes push notifications and emails. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a 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 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an 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 process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0037] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0038] Obtaining initial hearing information

[0039] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0040] Data Collection and Profiling

[0041] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smart watches) (such as activity level, heart rate, and sleep data). This data is used to record the user's activity and health status in detail and create a user profile.

[0042] Analyzing your thinking patterns

[0043] The server creates a user profile based on the data collected periodically, and then runs an algorithm to analyze the user's thought patterns based on the profile, such as stress levels in specific situations, efficient work times, and resting habits.

[0044] Generate improvement suggestions

[0045] The server generates optimal improvement proposals for the user based on the analysis results. These improvement proposals aim to help the user manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet the user's needs.

[0046] Notification of improvement proposals

[0047] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[0048] Specific examples

[0049] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch) and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[0050] In this way, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[0054] Step 2:

[0055] The terminal receives the input initial hearing information and transmits it to the server.

[0056] Step 3:

[0057] The server stores the received initial hearing information in a database.

[0058] Step 4:

[0059] With the user's permission, the server runs a script to periodically collect web usage history and app usage history.

[0060] Step 5:

[0061] The server collects physical data (activity level, heart rate, sleep data, etc.) from the user's wearable device (e.g., smart watch).

[0062] Step 6:

[0063] The server combines the collected web and app history with wearable data to create a user profile.

[0064] Step 7:

[0065] The server runs an algorithm to analyze the user's thought patterns based on the created profile.

[0066] Step 8:

[0067] The server generates improvement proposals customized for each user based on the analysis results of the thought patterns.

[0068] Step 9:

[0069] The server sends the generated improvement proposals to the user's device (smartphone, PC, etc.).

[0070] Step 10:

[0071] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods for implementing the suggestions.

[0072] Step 11:

[0073] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[0074] Example 1

[0075] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0076] Until now, there has been no system that can accurately grasp a user's thought patterns and daily stress factors and provide optimal individualized improvement suggestions. As a result, many users lack a means to obtain specific advice on improving their lifestyle habits and work performance. The present invention aims to solve this problem and improve the quality of users' lives.

[0077] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0078] In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting lifestyle data of the user and data from the wearable device to create a user profile, and means for analyzing the user's thought patterns based on the profile, thereby making it possible to provide optimal improvement suggestions for each user.

[0079] "User" refers to an individual who uses the system.

[0080] "Terminal" refers to the device operated by the user, such as a smartphone or PC.

[0081] "Server" refers to a computer system that receives, processes, and stores data sent by users.

[0082] "Initial hearing information" refers to basic information that the user initially enters, such as name, age, occupation, stress level, and current lifestyle habits.

[0083] "Database" refers to an electronic information collection system for systematically storing and managing collected information.

[0084] A "profile" refers to information that indicates a user's characteristics and behavioral patterns, generated based on collected data.

[0085] A "wearable device" refers to a device worn by a user, such as a smartwatch, that collects data such as activity levels and heart rate.

[0086] "Thought patterns" refer to the user's daily thought tendencies and patterns, which are analyzed by an algorithm.

[0087] "Generative AI model" refers to an artificial intelligence model that generates improvement suggestions for each user based on collected data.

[0088] "Improvement suggestions" refer to advice aimed at helping users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[0089] "Notification" refers to the act of sending a message to a device to inform the user of improvement suggestions or other important information.

[0090] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0091] This system consists of three entities: the user, the terminal, and the server. The user logs in to the system and inputs the necessary information. The terminal is the device operated by the user and communicates with the server. The server processes and stores the data, and generates and provides optimal improvement proposals to the user.

[0092] Obtaining initial hearing information

[0093] Users log in to the system through a web browser or a dedicated application and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. The device receives this information and sends it to the server using an HTTP request. The server stores the received information in a database. This allows the user's basic information to be managed within the system.

[0094] Data Collection and Profiling

[0095] With permission from the user, the server collects the user's web usage history, app usage history, and activity, heart rate, and sleep data from wearable devices (e.g., smart watches). During this collection process, the server obtains permission from the user through OAuth authentication and then calls the APIs of each data source to obtain the data. The server then integrates this data to create a detailed profile of the user's activity and health status.

[0096] Analyzing your thinking patterns

[0097] The server uses an AI model to analyze the user's thought patterns based on the collected data. This analysis tool uses machine learning algorithms to analyze stress levels in specific situations, efficient work times, how to take breaks, etc. The analysis results are stored in a database and used for future analysis and improvement suggestions.

[0098] Generate improvement suggestions

[0099] The server uses a generative AI model to analyze the user's thought patterns and generate optimal improvement suggestions for the user. These suggestions include stress management, improving work efficiency, lifestyle improvements, improving decision-making quality, and improving communication. The generated improvement suggestions are customized to each user's individual needs.

[0100] Notification of improvement proposals

[0101] The server sends the generated improvement proposals to the user's device using a notification API. The device receives the notification and displays specific implementation methods and schedules to the user, allowing the user to receive practical advice that can be applied in their daily lives and work.

[0102] Specific examples

[0103] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device and creates a profile based on their web usage history and app usage. After inputting the collected data into an AI model and analyzing it, it is determined that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance on how to implement the suggestions.

[0104] Prompt Sentence Examples

[0105] As an example of a prompt sentence, enter "I've been feeling stressed a lot recently." Analysis and notification will then be performed.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1:

[0108] Obtaining initial hearing information

[0109] Input: The user logs into the system and enters their name, age, occupation, stress level, current lifestyle habits, etc.

[0110] How it works: A user enters information using a web browser or dedicated application and sends it to the device, which then generates an HTTP request and sends this information to the server.

[0111] Data processing: The server accurately analyzes the received information and converts it into a format that can be stored in the database.

[0112] Output: Initial hearing information is stored in a database.

[0113] Step 2:

[0114] Data collection and integration

[0115] Input: User's web usage history, app usage history, activity, heart rate, and sleep data from wearable devices (such as smartwatches).

[0116] How it works: The server obtains permission from the user through OAuth authentication and collects data using the API of each data source.

[0117] Data processing: The collected data is integrated and processed to create a detailed record of the user's activity and health status.

[0118] Output: The consolidated data is stored in a database and the user's profile is completed.

[0119] Step 3:

[0120] Analyzing your thinking patterns

[0121] Input: User's integrated data (web usage history, app usage history, activity level, heart rate, sleep data, etc.).

[0122] How it works: An AI model on the server uses this data to analyze the user's thought patterns.

[0123] Data calculations: Using machine learning algorithms, it analyzes stress levels in specific situations, efficient work times, resting habits, and more.

[0124] Output: Analysis results are generated and stored in a database.

[0125] Step 4:

[0126] Generate improvement suggestions

[0127] Input: Thought pattern analysis results.

[0128] How it works: The server uses a generative AI model to generate customized improvement suggestions for each user.

[0129] Data calculation: Based on the analysis results, the AI ​​model generates suggestions for stress management, efficiency improvement, lifestyle improvements, etc.

[0130] Output: The generated improvement suggestions are stored in a database.

[0131] Step 5:

[0132] Notification of improvement proposals

[0133] Input: Generated improvement suggestions.

[0134] How it works: The server uses the notification API to send improvement suggestions to the user's device, which processes the received notification and displays the suggestions through its user interface.

[0135] Data processing: The terminal converts the received proposals into an appropriate format and presents them to the user in an easy-to-understand form.

[0136] Output: A guide is provided for the user to review and implement the improvement suggestions.

[0137] In this way, a system has been constructed that processes specific input data at each step and ultimately provides appropriate improvement suggestions to the user.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] In modern factory environments, managing worker stress and proposing efficient work patterns are important. However, current management systems have difficulty fully understanding the individual conditions of workers, making it difficult to make appropriate improvement proposals. Furthermore, while real-time information collection and analysis is essential to improving on-site work efficiency, the tools and systems available to achieve this are limited. As a result, worker stress and inefficient work patterns remain unresolved, preventing the optimization of the work environment.

[0141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0142] In this invention, the server includes means for acquiring initial user information and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, and means for notifying the user of the improvement suggestions on the user's display device and providing visual guidance. This enables stress management and improved work efficiency tailored to each worker's individual situation. Furthermore, a generative AI model can be used to analyze the user's thought patterns from their body surface signals and behavioral history, and to generate improvement suggestions based on prompts, thereby providing more accurate suggestions in real time.

[0143] "Initial interview information" refers to basic information such as the user's name, age, role at work, stress level, and lifestyle habits.

[0144] A "user profile" is a data set that indicates the user's individual characteristics, generated based on the user's initial hearing information, lifestyle data, and data from wearable devices.

[0145] "Thinking patterns" are an analysis of the tendencies and habits that indicate how a user thinks and behaves in specific situations.

[0146] "Improvement suggestions" are specific advice or guidelines for action that are generated based on the analysis of the user's thought patterns and are intended to help the user manage stress and improve work efficiency.

[0147] "User display device" refers to a device used by a user to display visual information, such as smart glasses.

[0148] A "wearable device" is a device that is worn on the user's body and has the function of collecting data such as activity level and heart rate.

[0149] A "generative AI model" is a machine learning model that learns from large amounts of data and analyzes a user's behavior and body surface signals to infer thought patterns.

[0150] A "prompt" is an instruction given to a generative AI model, which serves as a basis for generating output for a specific purpose.

[0151] The "database" is an information management system for storing the user's initial hearing information and data from the wearable device.

[0152] "Lifestyle data" refers to data related to the user's daily life, including web usage history and app usage history.

[0153] The present invention relates to a system for managing the stress of factory workers and improving their work efficiency. Specific embodiments for carrying out the present invention will be described below.

[0154] Obtaining initial hearing information

[0155] The user logs in to the system through a display device (smart glasses) and inputs initial hearing information (such as name, age, role at work, stress level, current lifestyle habits, etc.). The display device receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0156] Data Collection and Profiling

[0157] With the user's permission, the server collects data such as heart rate, activity level, and working hours from the wearable device (e.g., a helmet-type smart device). This data is received by the server and automatically stored in a database. The server also collects the user's web usage history and app usage history. Based on this data, the server creates a user profile.

[0158] Analyzing your thinking patterns

[0159] The server periodically updates the user's profile based on collected data and analyzes the user's thought patterns using a generative AI model that analyzes, for example, the user's stress level and work efficiency at specific times and in specific situations.

[0160] Generate improvement suggestions

[0161] The server generates optimal improvement proposals for each user based on the analysis of their thought patterns. These improvement proposals aim to help users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet their needs.

[0162] Notification of improvement proposals

[0163] The server notifies the user of the generated improvement proposals on their display device (smart glasses). The display device visually notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily work and life.

[0164] Specific examples

[0165] For example, a factory worker logs into the system and enters the information that "I feel particularly tired in the afternoon." The display device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's helmet-type smart device and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly tired after 2:00 PM. The server then generates improvement suggestions, such as "stretch for 10 minutes at 1:00 PM," and notifies the display device. The display device then displays a pop-up in the user's field of vision guiding them on how to stretch.

[0166] Hardware and software used

[0167] Hardware: Smart glasses, smart helmet devices

[0168] Software: Data extraction tool (Apache Kafka), data analysis tool (Apache Spark), notification system (Firebase Cloud Messaging)

[0169] Prompt Sentence Examples

[0170] Use the data below to generate suggestions to improve stress and efficiency for factory workers.

[0171] Data: Heart rate (1:00 PM - 3:00 PM), work hours (9:00 AM - 5:00 PM), interview information (stress level: high, time of day when you feel unwell: afternoon)

[0172] Goal: Stress management, improved work efficiency

[0173] As described above, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement proposals, thereby improving factory work efficiency and reducing worker stress.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] Entering initial hearing information

[0177] Subject: User

[0178] Specific operation: The user puts on the smart glasses and logs in to the system. The system prompts the user to enter initial information such as name, age, role at work, stress level, and lifestyle habits.

[0179] Input: Initial hearing information provided by the user

[0180] Output: The initial hearing information is sent from the display device to the server and stored in a database.

[0181] Step 2:

[0182] Data collection

[0183] Subject: Server

[0184] Specific operation: With the user's permission, the server collects data such as heart rate, activity level, and working time in real time from a wearable device (such as a helmet-type smart device).

[0185] Input: Data such as heart rate, activity level, and working hours from wearable devices

[0186] Output: The collected data is stored in a database on the server.

[0187] Step 3:

[0188] Creating a User Profile

[0189] Subject: Server

[0190] Specific operation: The server combines the collected data with the initial hearing information to create a profile of the user.

[0191] Input: Initial hearing information and lifestyle data stored in a database, data from wearable devices

[0192] Output: A user profile is generated and stored in a database.

[0193] Step 4:

[0194] Analyzing your thinking patterns

[0195] Subject: Server

[0196] How it works: The server uses the generative AI model to analyze the user's profile stored in the database. Specifically, it analyzes the user's stress level and work efficiency based on their heart rate and activity level during specific times and situations.

[0197] Input: User profile

[0198] Output: The analysis results in the user's thought patterns.

[0199] Step 5:

[0200] Generate improvement suggestions

[0201] Subject: Server

[0202] Specific operation: Based on the analysis of thought patterns, the server uses a generative AI model to generate prompt sentences, and then creates improvement suggestions customized for each user.

[0203] Input: Thought pattern analysis results

[0204] Output: User-optimized improvement suggestions

[0205] Step 6:

[0206] Notification of improvement proposals

[0207] Subject: Server and terminal

[0208] Specific operation: The server notifies the device (smart glasses) of the generated improvement proposal. The device displays the improvement proposal in the user's field of vision and provides a visual of the specific implementation method and schedule.

[0209] Input: Improvement suggestion

[0210] Output: The contents of the improvement proposal are notified to the terminal and visually displayed to the user.

[0211] For example, if a user feels particularly tired in the afternoon, the server will analyze the data and generate specific improvement suggestions, such as "stretch for 10 minutes at 1 p.m.", and notify the user through the smart glasses. By using a generative AI model, more accurate suggestions can be provided in real time.

[0212] Example prompt sentence:

[0213] "Based on the following data, please generate a proposal to improve the stress and efficiency of factory workers. Data: Heart rate (1:00 PM - 3:00 PM), working hours (9:00 AM - 5:00 PM), interview information (stress level: high, bad time: afternoon). Goal: Stress management, improving work efficiency."

[0214] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0215] The present invention combines an emotion engine with a system that analyzes a user's thought patterns and makes appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0216] Obtaining initial hearing information

[0217] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0218] Data Collection and Profiling

[0219] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smartwatches) (such as activity level, heart rate, and sleep data). The server also runs an emotion engine to analyze the user's emotions based on their facial expressions, voice, and biometric data. This data is used to create a user profile by recording the user's activity, health, and emotional state in detail.

[0220] Analysis of thought patterns and emotions

[0221] The server creates a user profile based on the periodically collected data. The profile includes lifestyle data, data from the wearable device, and emotional data. Based on this profile, an algorithm is run to analyze the user's thought and emotional patterns. For example, the algorithm can analyze stress levels in specific situations, efficient work schedules, rest habits, and emotional fluctuations.

[0222] Generate improvement suggestions

[0223] The server generates optimal improvement suggestions for each user based on the analysis of their thought patterns and emotional patterns. These improvement suggestions are aimed at managing the user's stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication. The generated improvement suggestions are customized for each user and designed to meet their needs.

[0224] Notification of improvement proposals

[0225] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[0226] Specific examples

[0227] For example, a user logs into the system and inputs information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch), as well as web usage history, app usage, and emotional data from the user's facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after afternoon meetings. Furthermore, the emotion engine reveals that emotions tend to become unstable after afternoon meetings. The server then generates improvement suggestions, such as "take a short break to relax before and after afternoon meetings" or "take a walk after lunch," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[0228] In this way, the system based on the present invention analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[0229] The processing flow will be explained below.

[0230] Step 1:

[0231] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[0232] Step 2:

[0233] The terminal receives the input initial hearing information and transmits it to the server.

[0234] Step 3:

[0235] The server stores the received initial hearing information in a database.

[0236] Step 4:

[0237] With the user's permission, the server collects the user's web usage history and app usage history.

[0238] Step 5:

[0239] The server collects physical data (activity level, heart rate, sleep data, etc.) from a wearable device (e.g., a smart watch) worn by the user.

[0240] Step 6:

[0241] The server integrates the collected web usage history, app usage history, and physical data to create a user profile.

[0242] Step 7:

[0243] The server analyzes the user's facial expressions, voice, and biometric data in real time and uses an emotion engine to identify the user's emotional state.

[0244] Step 8:

[0245] The server runs algorithms to analyze the user's thought and emotional patterns based on emotion data from the emotion engine and existing profile data.

[0246] Step 9:

[0247] The server generates an optimal improvement proposal for the user based on the analysis results of the thought patterns and emotion patterns.

[0248] Step 10:

[0249] The server notifies the user's device (smartphone, PC, etc.) of the generated improvement proposals.

[0250] Step 11:

[0251] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods and schedules for implementing the suggestions.

[0252] Step 12:

[0253] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[0254] Example 2

[0255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] In modern society, users lead busy lives and are required to manage stress, improve their lifestyles, and increase work efficiency. However, conventional methods have difficulty effectively providing improvement suggestions tailored to individual users. In particular, there is a lack of means to provide improvement suggestions that take into account the user's thought patterns and emotional patterns, so the suggestions are often general and ineffective.

[0257] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns and emotional patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns and emotional patterns, and means for notifying the user's terminal of the improvement suggestions. This makes it possible to provide improvement suggestions customized to the individual state of the user.

[0258] "Initial hearing information" is information obtained in the initial stage of system use, such as the user's name, age, occupation, stress level, and current lifestyle.

[0259] "Database" means a digital storage system for storing and managing collected user information and profile data.

[0260] A "wearable device" is an electronic device worn on the body that collects activity levels, heart rate, sleep data, and other data.

[0261] A "profile" is detailed information about a user that is created based on collected lifestyle data about the user and data from wearable devices.

[0262] "Thought patterns" refer to the mental and behavioral characteristics of users, such as stress levels in specific situations, efficient work times, and how they take rest.

[0263] An "emotion pattern" represents the fluctuations and tendencies of a user's emotional state, and is analyzed from data such as facial expressions and voice.

[0264] "Improvement suggestions" are suggestions generated based on the user's profile, aimed at managing stress, improving work efficiency, improving lifestyle habits, and the like.

[0265] The "emotion engine" is software that analyzes emotions from a user's facial expressions and voice, and uses machine learning algorithms.

[0266] "Natural language generation technology" is a technology that automatically generates sentences that are easy for humans to understand based on collected data.

[0267] A "machine learning algorithm" is a mathematical model or computational method used to analyze collected data and extract patterns and trends.

[0268] "Notification" refers to a communication method such as email, pop-up, or push notification that notifies the user of the content of the improvement proposal on their device.

[0269] A "terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[0270] The present invention relates to a system for analyzing a user's thought patterns and emotional patterns and providing improvement suggestions suited to the user. Specific embodiments will be described below.

[0271] Obtaining initial hearing information

[0272] The user logs into the system and enters initial interview information such as name, age, occupation, stress level, and current lifestyle habits. The terminal provides this information as an input form and sends it to an API endpoint that sends the entered information to a database. The server receives this information and stores it in the database. At this stage, the data is validated, and only reliable data is saved in the database.

[0273] Data Collection and Profiling

[0274] With your permission, the server collects the following data:

[0275] "Web Usage History": Collects the user's web page browsing history through browser extensions.

[0276] "App usage history": Collects usage history of applications installed on smartphones and PCs.

[0277] "Data from wearable devices": For example, activity, heart rate, and sleep data from a smartwatch can be obtained through an API.

[0278] The server then runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The output of the emotion engine is stored in a database and becomes part of the user's profile.

[0279] Analysis of thought and emotional patterns

[0280] The server creates and updates a user profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server then uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in specific situations, efficient work schedules, how to take breaks, and emotional fluctuations, and finds patterns customized for each user.

[0281] Generate improvement suggestions

[0282] Based on the analysis results, the server generates optimal improvement suggestions for the user. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate optimal sentences for the user. The generated improvement suggestions aim to manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[0283] Notification of improvement proposals

[0284] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. The notification provides the specific content of the suggestion, how to implement it, and a timeline. This allows the user to put the suggestions into practice in their daily lives or work.

[0285] Specific examples

[0286] For example, a user logs into the system and enters, "I've been feeling stressed a lot recently." The device receives this information and sends it to the server. The server stores it in a database. The server then collects heart rate and activity data, web usage history, and app usage from the user's wearable device (smartwatch), as well as emotional data from facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after an afternoon meeting. Furthermore, the emotion engine's results reveal that emotions become unstable after an afternoon meeting. The server then generates improvement suggestions, such as "take a short relaxation break before or after an afternoon meeting" or "take a walk after lunch," and notifies the device. The device displays these suggestions to the user and provides specific guidance for implementing the suggestions.

[0287] Prompt Sentence Examples

[0288] A system description can be generated by inputting the following prompts into the generative AI model:

[0289] "Please explain the system that analyzes the user's thought and emotional patterns and makes appropriate suggestions for improvement."

[0290] "Please tell me more about the system that collects and profiles user data."

[0291] "Give us an example of a system that generates recommendations for users to manage stress or improve their lifestyle habits."

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] Step 1: Obtaining initial hearing information

[0294] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits). The device provides this information as an input form, and the entered data is sent to the server via API. The server receives this information and stores it in a database. Specifically, it validates the data, confirms its accuracy, and then issues an INSERT query to the database. The input data is the initial interview information, and the output is the user information stored in the database.

[0295] Step 2: Data collection and profiling

[0296] With your permission, the server collects the following data:

[0297] Web usage history: Collects user's web page browsing history through browser extensions.

[0298] App usage history: Collects usage history of applications installed on smartphones and PCs.

[0299] Data from wearable devices: Activity, heart rate, and sleep data are obtained from smartwatches via API.

[0300] The server also runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The input data is various user and emotional data, and the output is a detailed user profile. This profile is then stored in a database.

[0301] Step 3: Analyze your thinking and emotional patterns

[0302] The server periodically updates the user's profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in a particular situation, efficient working times, how to take rest, and emotional fluctuations. The input data is the collected user data and profile information, and the output is the analyzed thought and emotional patterns. Specific operations include data cleansing, feature extraction, and application of machine learning models.

[0303] Step 4: Generate improvement suggestions

[0304] The server generates optimal improvement suggestions for the user based on the analysis of thought patterns and emotional patterns. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate specific improvement suggestions in text format. The input data are the analysis results and user profile information, and the output is the optimal improvement suggestions for the user. The generated improvement suggestions are aimed at managing stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication.

[0305] Step 5: Notification of improvement proposals

[0306] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. This notification includes the specific content of the suggestion, how to implement it, and a timeline. The input data is the generated improvement suggestions, and the output is the notification sent to the user's device. This allows the user to follow specific guidance on how to put the suggestions into practice.

[0307] Through these processing steps, the system analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving performance at work and in private life and reducing stress.

[0308] (Application example 2)

[0309] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0310] In modern logistics centers, the working environment is stressful, and employee stress and fatigue are serious issues that reduce work efficiency and safety. However, there is no system that can closely monitor the condition of each employee in real time and make appropriate improvement proposals. New technology is needed to simultaneously manage employee health and optimize work efficiency.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0312] In this invention, the server includes means for acquiring initial hearing information from the user and storing it in a database, means for collecting user lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, means for notifying the user's terminal of the improvement suggestions, and means for monitoring the activity data of workers at the logistics center in real time and recommending optimal work schedules and break timings, thereby optimizing both the health and work efficiency of employees at the logistics center.

[0313] "User" refers to a person who uses this system, and primarily refers to an employee of the logistics center.

[0314] "Initial hearing information" refers to basic information that is entered when a user first logs into the system, such as the user's name, age, occupation, stress level, and current lifestyle.

[0315] "Database" refers to an information management system for storing users' initial hearing information, collected lifestyle data, and data from wearable devices.

[0316] "Lifestyle data" refers to data related to a user's daily life, such as information collected from smartphones and web usage history.

[0317] A "wearable device" refers to a device worn by a user that can collect biometric information such as heart rate and activity level. An example of this is a smartwatch.

[0318] A "profile" refers to a data set that represents a user's behavioral, thought, and emotional patterns, created based on collected lifestyle data and data from wearable devices.

[0319] "Thinking patterns" are data that indicate the user's thinking tendencies and habits, and include stress levels in specific situations and efficient working times.

[0320] "Improvement suggestions" refer to recommendations regarding stress management, improving work efficiency, improving lifestyle habits, etc., that are generated based on the analysis of the user's thought patterns and emotional patterns.

[0321] "Terminal" refers to a device used by a user, such as a computer or smartphone, that can receive notifications of improvement suggestions.

[0322] A "logistics center" refers to a physical facility that manages logistics and products, and is the place where logistics operations are carried out.

[0323] "Activity data" is information about the user's physical activity, including the number of steps, distance traveled, and working hours.

[0324] "Real-time" refers to a state in which data is processed immediately after it is generated and the results are reflected.

[0325] "Work schedule" refers to the timetable and order of work that a user must perform at a logistics center.

[0326] "Rest timing" refers to the time for the user to take an appropriate rest.

[0327] "Server" refers to the central computer that processes and manages data for the entire system.

[0328] This invention is a system that collects activity data and emotion data of employees in a logistics center, monitors them in real time, and notifies them of optimal work schedules and break timings. Specific embodiments will be described below.

[0329] Obtaining initial hearing information

[0330] Employees (users) first log in to the system and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. This information is sent to the server via their device (smartphone or PC) and stored in a database. This initial information becomes the basis for creating the user's profile.

[0331] Data Collection and Profiling

[0332] With the user's permission, the server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). It also collects web usage history and app usage history. Furthermore, the server uses an emotion engine to analyze emotional data from the user's facial expressions and voice. Based on this data, a user profile is created.

[0333] Analysis of thought patterns and emotions

[0334] Using the profile data, the server analyzes the user's thought and emotional patterns. This analysis involves collecting lifestyle data, data from wearable devices, and emotional data. For example, it analyzes stress levels at specific times and in specific situations, and the most efficient working hours.

[0335] Generate improvement suggestions

[0336] The server generates optimal improvement suggestions for users based on the analysis of their thought patterns and emotional patterns. These improvement suggestions include stress management, improving work efficiency, and optimizing break timing. Specific examples of improvement suggestions for a logistics center include "encouraging short breaks every 30 minutes" and "stretching at a specific time in the afternoon."

[0337] Notification of improvement proposals

[0338] The generated improvement suggestions are notified to the user via the device, for example, a notification message is sent to a smartwatch or smartphone, allowing the user to check the suggestions and implement them.

[0339] Specific examples

[0340] Specifically, if a user's stress level is measured as high while working at a logistics center, the server analyzes the situation and generates an improvement suggestion such as "take a short break every 30 minutes." This suggestion is notified to the user via their smartwatch, allowing them to take a break at an appropriate time.

[0341] Example of input prompt for generative AI model

[0342] "Create a notification message that suggests the best time to take a break based on the user's stress level and activity level."

[0343] This will enable the optimization of both the health and work efficiency of employees at logistics centers.

[0344] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0345] Step 1:

[0346] Users log in to the system using a device (smartphone or PC) and enter initial interview information. This information includes name, age, occupation, stress level, current lifestyle habits, etc. The device sends this data to the server, which stores the received information in a database and creates an initial profile for each user.

[0347] Input: Name, age, occupation, stress level, lifestyle

[0348] Output: Initial hearing information and initial profile stored in a database

[0349] Step 2:

[0350] The server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). With the user's permission, it also collects their web and app usage history. This data is used to analyze the user's behavioral patterns and physical condition in detail.

[0351] Input: Activity data from wearable devices, heart rate data, web usage history, app usage history

[0352] Output: User profile update data

[0353] Step 3:

[0354] The server uses an emotion engine to analyze the user's emotions from the collected facial and voice data. The emotion data is used to evaluate the situations in which the user is likely to feel stressed, the time periods in which their emotions become unstable, and so on.

[0355] Input: facial expression data, voice data

[0356] Output: Emotion pattern data

[0357] Step 4:

[0358] The server creates a detailed profile of the user by combining collected lifestyle data, activity data, heart rate data, web usage history, app usage history, emotional patterns, etc. This profile includes the user's behavioral patterns, thought patterns, and emotional patterns. The server uses this data to analyze the user's thought patterns.

[0359] Input: Various collected data

[0360] Output: Detailed user profile

[0361] Step 5:

[0362] The server uses a generative AI model to generate optimal improvement proposals for each user based on a detailed user profile and various data, including specific action plans for improving work efficiency and stress management.

[0363] Input: User profile, thought pattern data, emotion pattern data

[0364] Output: Improvement suggestions

[0365] Step 6:

[0366] Once an improvement suggestion is generated, the server notifies the user's device. For example, a notification such as "Take a break in the next 30 minutes" is sent to a smartwatch. The user can then take appropriate action based on this.

[0367] Input: Improvement suggestion

[0368] Output: Notification message to terminal

[0369] Through the above processing steps, logistics center employees can achieve real-time health management and optimize work efficiency.

[0370] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0376] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0377] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0378] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0379] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0380] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0381] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0382] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0383] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0384] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0385] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0386] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0387] Obtaining initial hearing information

[0388] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0389] Data Collection and Profiling

[0390] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smart watches) (such as activity level, heart rate, and sleep data). This data is used to record the user's activity and health status in detail and create a user profile.

[0391] Analyzing your thinking patterns

[0392] The server creates a user profile based on the data collected periodically, and then runs an algorithm to analyze the user's thought patterns based on the profile, such as stress levels in specific situations, efficient work times, and resting habits.

[0393] Generate improvement suggestions

[0394] The server generates optimal improvement proposals for the user based on the analysis results. These improvement proposals aim to help the user manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet the user's needs.

[0395] Notification of improvement proposals

[0396] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[0397] Specific examples

[0398] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch) and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[0399] In this way, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[0400] The processing flow will be explained below.

[0401] Step 1:

[0402] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[0403] Step 2:

[0404] The terminal receives the input initial hearing information and transmits it to the server.

[0405] Step 3:

[0406] The server stores the received initial hearing information in a database.

[0407] Step 4:

[0408] With the user's permission, the server runs a script to periodically collect web usage history and app usage history.

[0409] Step 5:

[0410] The server collects physical data (activity level, heart rate, sleep data, etc.) from the user's wearable device (e.g., smart watch).

[0411] Step 6:

[0412] The server combines the collected web and app history with wearable data to create a user profile.

[0413] Step 7:

[0414] The server runs an algorithm to analyze the user's thought patterns based on the created profile.

[0415] Step 8:

[0416] The server generates improvement proposals customized for each user based on the analysis results of the thought patterns.

[0417] Step 9:

[0418] The server sends the generated improvement proposals to the user's device (smartphone, PC, etc.).

[0419] Step 10:

[0420] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods for implementing the suggestions.

[0421] Step 11:

[0422] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[0423] Example 1

[0424] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0425] Until now, there has been no system that can accurately grasp a user's thought patterns and daily stress factors and provide optimal individualized improvement suggestions. As a result, many users lack a means to obtain specific advice on improving their lifestyle habits and work performance. The present invention aims to solve this problem and improve the quality of users' lives.

[0426] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0427] In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting lifestyle data of the user and data from the wearable device to create a user profile, and means for analyzing the user's thought patterns based on the profile, thereby making it possible to provide optimal improvement suggestions for each user.

[0428] "User" refers to an individual who uses the system.

[0429] "Terminal" refers to the device operated by the user, such as a smartphone or PC.

[0430] "Server" refers to a computer system that receives, processes, and stores data sent by users.

[0431] "Initial hearing information" refers to basic information that the user initially enters, such as name, age, occupation, stress level, and current lifestyle habits.

[0432] "Database" refers to an electronic information collection system for systematically storing and managing collected information.

[0433] A "profile" refers to information that indicates a user's characteristics and behavioral patterns, generated based on collected data.

[0434] A "wearable device" refers to a device worn by a user, such as a smartwatch, that collects data such as activity levels and heart rate.

[0435] "Thought patterns" refer to the user's daily thought tendencies and patterns, which are analyzed by an algorithm.

[0436] "Generative AI model" refers to an artificial intelligence model that generates improvement suggestions for each user based on collected data.

[0437] "Improvement suggestions" refer to advice aimed at helping users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[0438] "Notification" refers to the act of sending a message to a device to inform the user of improvement suggestions or other important information.

[0439] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0440] This system consists of three entities: the user, the terminal, and the server. The user logs in to the system and inputs the necessary information. The terminal is the device operated by the user and communicates with the server. The server processes and stores the data, and generates and provides optimal improvement proposals to the user.

[0441] Obtaining initial hearing information

[0442] Users log in to the system through a web browser or a dedicated application and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. The device receives this information and sends it to the server using an HTTP request. The server stores the received information in a database. This allows the user's basic information to be managed within the system.

[0443] Data Collection and Profiling

[0444] With permission from the user, the server collects the user's web usage history, app usage history, and activity, heart rate, and sleep data from wearable devices (e.g., smart watches). During this collection process, the server obtains permission from the user through OAuth authentication and then calls the APIs of each data source to obtain the data. The server then integrates this data to create a detailed profile of the user's activity and health status.

[0445] Analyzing your thinking patterns

[0446] The server uses an AI model to analyze the user's thought patterns based on the collected data. This analysis tool uses machine learning algorithms to analyze stress levels in specific situations, efficient work times, how to take breaks, etc. The analysis results are stored in a database and used for future analysis and improvement suggestions.

[0447] Generate improvement suggestions

[0448] The server uses a generative AI model to analyze the user's thought patterns and generate optimal improvement suggestions for the user. These suggestions include stress management, improving work efficiency, lifestyle improvements, improving decision-making quality, and improving communication. The generated improvement suggestions are customized to each user's individual needs.

[0449] Notification of improvement proposals

[0450] The server sends the generated improvement proposals to the user's device using a notification API. The device receives the notification and displays specific implementation methods and schedules to the user, allowing the user to receive practical advice that can be applied in their daily lives and work.

[0451] Specific examples

[0452] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device and creates a profile based on their web usage history and app usage. After inputting the collected data into an AI model and analyzing it, it is determined that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance on how to implement the suggestions.

[0453] Prompt Sentence Examples

[0454] As an example of a prompt sentence, enter "I've been feeling stressed a lot recently." Analysis and notification will then be performed.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1:

[0457] Obtaining initial hearing information

[0458] Input: The user logs into the system and enters their name, age, occupation, stress level, current lifestyle habits, etc.

[0459] How it works: A user enters information using a web browser or dedicated application and sends it to the device, which then generates an HTTP request and sends this information to the server.

[0460] Data processing: The server accurately analyzes the received information and converts it into a format that can be stored in the database.

[0461] Output: Initial hearing information is stored in a database.

[0462] Step 2:

[0463] Data collection and integration

[0464] Input: User's web usage history, app usage history, activity, heart rate, and sleep data from wearable devices (such as smartwatches).

[0465] How it works: The server obtains permission from the user through OAuth authentication and collects data using the API of each data source.

[0466] Data processing: The collected data is integrated and processed to create a detailed record of the user's activity and health status.

[0467] Output: The consolidated data is stored in a database and the user's profile is completed.

[0468] Step 3:

[0469] Analyzing your thinking patterns

[0470] Input: User's integrated data (web usage history, app usage history, activity level, heart rate, sleep data, etc.).

[0471] How it works: An AI model on the server uses this data to analyze the user's thought patterns.

[0472] Data calculations: Using machine learning algorithms, it analyzes stress levels in specific situations, efficient work times, resting habits, and more.

[0473] Output: Analysis results are generated and stored in a database.

[0474] Step 4:

[0475] Generate improvement suggestions

[0476] Input: Thought pattern analysis results.

[0477] How it works: The server uses a generative AI model to generate customized improvement suggestions for each user.

[0478] Data calculation: Based on the analysis results, the AI ​​model generates suggestions for stress management, efficiency improvement, lifestyle improvements, etc.

[0479] Output: The generated improvement suggestions are stored in a database.

[0480] Step 5:

[0481] Notification of improvement proposals

[0482] Input: Generated improvement suggestions.

[0483] How it works: The server uses the notification API to send improvement suggestions to the user's device, which processes the received notification and displays the suggestions through its user interface.

[0484] Data processing: The terminal converts the received proposals into an appropriate format and presents them to the user in an easy-to-understand form.

[0485] Output: A guide is provided for the user to review and implement the improvement suggestions.

[0486] In this way, a system has been constructed that processes specific input data at each step and ultimately provides appropriate improvement suggestions to the user.

[0487] (Application example 1)

[0488] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] In modern factory environments, managing worker stress and proposing efficient work patterns are important. However, current management systems have difficulty fully understanding the individual conditions of workers, making it difficult to make appropriate improvement proposals. Furthermore, while real-time information collection and analysis is essential to improving on-site work efficiency, the tools and systems available to achieve this are limited. As a result, worker stress and inefficient work patterns remain unresolved, preventing the optimization of the work environment.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0491] In this invention, the server includes means for acquiring initial user information and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, and means for notifying the user of the improvement suggestions on the user's display device and providing visual guidance. This enables stress management and improved work efficiency tailored to each worker's individual situation. Furthermore, a generative AI model can be used to analyze the user's thought patterns from their body surface signals and behavioral history, and to generate improvement suggestions based on prompts, thereby providing more accurate suggestions in real time.

[0492] "Initial interview information" refers to basic information such as the user's name, age, role at work, stress level, and lifestyle habits.

[0493] A "user profile" is a data set that indicates the user's individual characteristics, generated based on the user's initial hearing information, lifestyle data, and data from wearable devices.

[0494] "Thinking patterns" are an analysis of the tendencies and habits that indicate how a user thinks and behaves in specific situations.

[0495] "Improvement suggestions" are specific advice or guidelines for action that are generated based on the analysis of the user's thought patterns and are intended to help the user manage stress and improve work efficiency.

[0496] "User display device" refers to a device used by a user to display visual information, such as smart glasses.

[0497] A "wearable device" is a device that is worn on the user's body and has the function of collecting data such as activity level and heart rate.

[0498] A "generative AI model" is a machine learning model that learns from large amounts of data and analyzes a user's behavior and body surface signals to infer thought patterns.

[0499] A "prompt" is an instruction given to a generative AI model, which serves as a basis for generating output for a specific purpose.

[0500] The "database" is an information management system for storing the user's initial hearing information and data from the wearable device.

[0501] "Lifestyle data" refers to data related to the user's daily life, including web usage history and app usage history.

[0502] The present invention relates to a system for managing the stress of factory workers and improving their work efficiency. Specific embodiments for carrying out the present invention will be described below.

[0503] Obtaining initial hearing information

[0504] The user logs in to the system through a display device (smart glasses) and inputs initial hearing information (such as name, age, role at work, stress level, current lifestyle habits, etc.). The display device receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0505] Data Collection and Profiling

[0506] With the user's permission, the server collects data such as heart rate, activity level, and working hours from the wearable device (e.g., a helmet-type smart device). This data is received by the server and automatically stored in a database. The server also collects the user's web usage history and app usage history. Based on this data, the server creates a user profile.

[0507] Analyzing your thinking patterns

[0508] The server periodically updates the user's profile based on collected data and analyzes the user's thought patterns using a generative AI model that analyzes, for example, the user's stress level and work efficiency at specific times and in specific situations.

[0509] Generate improvement suggestions

[0510] The server generates optimal improvement proposals for each user based on the analysis of their thought patterns. These improvement proposals aim to help users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet their needs.

[0511] Notification of improvement proposals

[0512] The server notifies the user of the generated improvement proposals on their display device (smart glasses). The display device visually notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily work and life.

[0513] Specific examples

[0514] For example, a factory worker logs into the system and enters the information that "I feel particularly tired in the afternoon." The display device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's helmet-type smart device and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly tired after 2:00 PM. The server then generates improvement suggestions, such as "stretch for 10 minutes at 1:00 PM," and notifies the display device. The display device then displays a pop-up in the user's field of vision guiding them on how to stretch.

[0515] Hardware and software used

[0516] Hardware: Smart glasses, smart helmet devices

[0517] Software: Data extraction tool (Apache Kafka), data analysis tool (Apache Spark), notification system (Firebase Cloud Messaging)

[0518] Prompt Sentence Examples

[0519] Use the data below to generate suggestions to improve stress and efficiency for factory workers.

[0520] Data: Heart rate (1:00 PM - 3:00 PM), work hours (9:00 AM - 5:00 PM), interview information (stress level: high, time of day when you feel unwell: afternoon)

[0521] Goal: Stress management, improved work efficiency

[0522] As described above, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement proposals, thereby improving factory work efficiency and reducing worker stress.

[0523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0524] Step 1:

[0525] Entering initial hearing information

[0526] Subject: User

[0527] Specific operation: The user puts on the smart glasses and logs in to the system. The system prompts the user to enter initial information such as name, age, role at work, stress level, and lifestyle habits.

[0528] Input: Initial hearing information provided by the user

[0529] Output: The initial hearing information is sent from the display device to the server and stored in a database.

[0530] Step 2:

[0531] Data collection

[0532] Subject: Server

[0533] Specific operation: With the user's permission, the server collects data such as heart rate, activity level, and working time in real time from a wearable device (such as a helmet-type smart device).

[0534] Input: Data such as heart rate, activity level, and working hours from wearable devices

[0535] Output: The collected data is stored in a database on the server.

[0536] Step 3:

[0537] Creating a User Profile

[0538] Subject: Server

[0539] Specific operation: The server combines the collected data with the initial hearing information to create a profile of the user.

[0540] Input: Initial hearing information and lifestyle data stored in a database, data from wearable devices

[0541] Output: A user profile is generated and stored in a database.

[0542] Step 4:

[0543] Analyzing your thinking patterns

[0544] Subject: Server

[0545] How it works: The server uses the generative AI model to analyze the user's profile stored in the database. Specifically, it analyzes the user's stress level and work efficiency based on their heart rate and activity level during specific times and situations.

[0546] Input: User profile

[0547] Output: The analysis results in the user's thought patterns.

[0548] Step 5:

[0549] Generate improvement suggestions

[0550] Subject: Server

[0551] Specific operation: Based on the analysis of thought patterns, the server uses a generative AI model to generate prompt sentences, and then creates improvement suggestions customized for each user.

[0552] Input: Thought pattern analysis results

[0553] Output: User-optimized improvement suggestions

[0554] Step 6:

[0555] Notification of improvement proposals

[0556] Subject: Server and terminal

[0557] Specific operation: The server notifies the device (smart glasses) of the generated improvement proposal. The device displays the improvement proposal in the user's field of vision and provides a visual of the specific implementation method and schedule.

[0558] Input: Improvement suggestion

[0559] Output: The contents of the improvement proposal are notified to the terminal and visually displayed to the user.

[0560] For example, if a user feels particularly tired in the afternoon, the server will analyze the data and generate specific improvement suggestions, such as "stretch for 10 minutes at 1 p.m.", and notify the user through the smart glasses. By using a generative AI model, more accurate suggestions can be provided in real time.

[0561] Example prompt sentence:

[0562] "Based on the following data, please generate a proposal to improve the stress and efficiency of factory workers. Data: Heart rate (1:00 PM - 3:00 PM), working hours (9:00 AM - 5:00 PM), interview information (stress level: high, bad time: afternoon). Goal: Stress management, improving work efficiency."

[0563] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0564] The present invention combines an emotion engine with a system that analyzes a user's thought patterns and makes appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0565] Obtaining initial hearing information

[0566] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0567] Data Collection and Profiling

[0568] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smartwatches) (such as activity level, heart rate, and sleep data). The server also runs an emotion engine to analyze the user's emotions based on their facial expressions, voice, and biometric data. This data is used to create a user profile by recording the user's activity, health, and emotional state in detail.

[0569] Analysis of thought patterns and emotions

[0570] The server creates a user profile based on the periodically collected data. The profile includes lifestyle data, data from the wearable device, and emotional data. Based on this profile, an algorithm is run to analyze the user's thought and emotional patterns. For example, the algorithm can analyze stress levels in specific situations, efficient work schedules, rest habits, and emotional fluctuations.

[0571] Generate improvement suggestions

[0572] The server generates optimal improvement suggestions for each user based on the analysis of their thought patterns and emotional patterns. These improvement suggestions are aimed at managing the user's stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication. The generated improvement suggestions are customized for each user and designed to meet their needs.

[0573] Notification of improvement proposals

[0574] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[0575] Specific examples

[0576] For example, a user logs into the system and inputs information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch), as well as web usage history, app usage, and emotional data from the user's facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after afternoon meetings. Furthermore, the emotion engine reveals that emotions tend to become unstable after afternoon meetings. The server then generates improvement suggestions, such as "take a short break to relax before and after afternoon meetings" or "take a walk after lunch," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[0577] In this way, the system based on the present invention analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[0578] The processing flow will be explained below.

[0579] Step 1:

[0580] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[0581] Step 2:

[0582] The terminal receives the input initial hearing information and transmits it to the server.

[0583] Step 3:

[0584] The server stores the received initial hearing information in a database.

[0585] Step 4:

[0586] With the user's permission, the server collects the user's web usage history and app usage history.

[0587] Step 5:

[0588] The server collects physical data (activity level, heart rate, sleep data, etc.) from a wearable device (e.g., a smart watch) worn by the user.

[0589] Step 6:

[0590] The server integrates the collected web usage history, app usage history, and physical data to create a user profile.

[0591] Step 7:

[0592] The server analyzes the user's facial expressions, voice, and biometric data in real time and uses an emotion engine to identify the user's emotional state.

[0593] Step 8:

[0594] The server runs algorithms to analyze the user's thought and emotional patterns based on emotion data from the emotion engine and existing profile data.

[0595] Step 9:

[0596] The server generates an optimal improvement proposal for the user based on the analysis results of the thought patterns and emotion patterns.

[0597] Step 10:

[0598] The server notifies the user's device (smartphone, PC, etc.) of the generated improvement proposals.

[0599] Step 11:

[0600] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods and schedules for implementing the suggestions.

[0601] Step 12:

[0602] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[0603] Example 2

[0604] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0605] In modern society, users lead busy lives and are required to manage stress, improve their lifestyles, and increase work efficiency. However, conventional methods have difficulty effectively providing improvement suggestions tailored to individual users. In particular, there is a lack of means to provide improvement suggestions that take into account the user's thought patterns and emotional patterns, so the suggestions are often general and ineffective.

[0606] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns and emotional patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns and emotional patterns, and means for notifying the user's terminal of the improvement suggestions. This makes it possible to provide improvement suggestions customized to the individual state of the user.

[0607] "Initial hearing information" is information obtained in the initial stage of system use, such as the user's name, age, occupation, stress level, and current lifestyle.

[0608] "Database" means a digital storage system for storing and managing collected user information and profile data.

[0609] A "wearable device" is an electronic device worn on the body that collects activity levels, heart rate, sleep data, and other data.

[0610] A "profile" is detailed information about a user that is created based on collected lifestyle data about the user and data from wearable devices.

[0611] "Thought patterns" refer to the mental and behavioral characteristics of users, such as stress levels in specific situations, efficient work times, and how they take rest.

[0612] An "emotion pattern" represents the fluctuations and tendencies of a user's emotional state, and is analyzed from data such as facial expressions and voice.

[0613] "Improvement suggestions" are suggestions generated based on the user's profile, aimed at managing stress, improving work efficiency, improving lifestyle habits, and the like.

[0614] The "emotion engine" is software that analyzes emotions from a user's facial expressions and voice, and uses machine learning algorithms.

[0615] "Natural language generation technology" is a technology that automatically generates sentences that are easy for humans to understand based on collected data.

[0616] A "machine learning algorithm" is a mathematical model or computational method used to analyze collected data and extract patterns and trends.

[0617] "Notification" refers to a communication method such as email, pop-up, or push notification that notifies the user of the content of the improvement proposal on their device.

[0618] A "terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[0619] The present invention relates to a system for analyzing a user's thought patterns and emotional patterns and providing improvement suggestions suited to the user. Specific embodiments will be described below.

[0620] Obtaining initial hearing information

[0621] The user logs into the system and enters initial interview information such as name, age, occupation, stress level, and current lifestyle habits. The terminal provides this information as an input form and sends it to an API endpoint that sends the entered information to a database. The server receives this information and stores it in the database. At this stage, the data is validated, and only reliable data is saved in the database.

[0622] Data Collection and Profiling

[0623] With your permission, the server collects the following data:

[0624] "Web Usage History": Collects the user's web page browsing history through browser extensions.

[0625] "App usage history": Collects usage history of applications installed on smartphones and PCs.

[0626] "Data from wearable devices": For example, activity, heart rate, and sleep data from a smartwatch can be obtained through an API.

[0627] The server then runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The output of the emotion engine is stored in a database and becomes part of the user's profile.

[0628] Analysis of thought and emotional patterns

[0629] The server creates and updates a user profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server then uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in specific situations, efficient work schedules, how to take breaks, and emotional fluctuations, and finds patterns customized for each user.

[0630] Generate improvement suggestions

[0631] Based on the analysis results, the server generates optimal improvement suggestions for the user. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate optimal sentences for the user. The generated improvement suggestions aim to manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[0632] Notification of improvement proposals

[0633] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. The notification provides the specific content of the suggestion, how to implement it, and a timeline. This allows the user to put the suggestions into practice in their daily lives or work.

[0634] Specific examples

[0635] For example, a user logs into the system and enters, "I've been feeling stressed a lot recently." The device receives this information and sends it to the server. The server stores it in a database. The server then collects heart rate and activity data, web usage history, and app usage from the user's wearable device (smartwatch), as well as emotional data from facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after an afternoon meeting. Furthermore, the emotion engine's results reveal that emotions become unstable after an afternoon meeting. The server then generates improvement suggestions, such as "take a short relaxation break before or after an afternoon meeting" or "take a walk after lunch," and notifies the device. The device displays these suggestions to the user and provides specific guidance for implementing the suggestions.

[0636] Prompt Sentence Examples

[0637] A system description can be generated by inputting the following prompts into the generative AI model:

[0638] "Please explain the system that analyzes the user's thought and emotional patterns and makes appropriate suggestions for improvement."

[0639] "Please tell me more about the system that collects and profiles user data."

[0640] "Give us an example of a system that generates recommendations for users to manage stress or improve their lifestyle habits."

[0641] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0642] Step 1: Obtaining initial hearing information

[0643] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits). The device provides this information as an input form, and the entered data is sent to the server via API. The server receives this information and stores it in a database. Specifically, it validates the data, confirms its accuracy, and then issues an INSERT query to the database. The input data is the initial interview information, and the output is the user information stored in the database.

[0644] Step 2: Data collection and profiling

[0645] With your permission, the server collects the following data:

[0646] Web usage history: Collects user's web page browsing history through browser extensions.

[0647] App usage history: Collects usage history of applications installed on smartphones and PCs.

[0648] Data from wearable devices: Activity, heart rate, and sleep data are obtained from smartwatches via API.

[0649] The server also runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The input data is various user and emotional data, and the output is a detailed user profile. This profile is then stored in a database.

[0650] Step 3: Analyze your thinking and emotional patterns

[0651] The server periodically updates the user's profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in a particular situation, efficient working times, how to take rest, and emotional fluctuations. The input data is the collected user data and profile information, and the output is the analyzed thought and emotional patterns. Specific operations include data cleansing, feature extraction, and application of machine learning models.

[0652] Step 4: Generate improvement suggestions

[0653] The server generates optimal improvement suggestions for the user based on the analysis of thought patterns and emotional patterns. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate specific improvement suggestions in text format. The input data are the analysis results and user profile information, and the output is the optimal improvement suggestions for the user. The generated improvement suggestions are aimed at managing stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication.

[0654] Step 5: Notification of improvement proposals

[0655] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. This notification includes the specific content of the suggestion, how to implement it, and a timeline. The input data is the generated improvement suggestions, and the output is the notification sent to the user's device. This allows the user to follow specific guidance on how to put the suggestions into practice.

[0656] Through these processing steps, the system analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving performance at work and in private life and reducing stress.

[0657] (Application example 2)

[0658] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0659] In modern logistics centers, the working environment is stressful, and employee stress and fatigue are serious issues that reduce work efficiency and safety. However, there is no system that can closely monitor the condition of each employee in real time and make appropriate improvement proposals. New technology is needed to simultaneously manage employee health and optimize work efficiency.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0661] In this invention, the server includes means for acquiring initial hearing information from the user and storing it in a database, means for collecting user lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, means for notifying the user's terminal of the improvement suggestions, and means for monitoring the activity data of workers at the logistics center in real time and recommending optimal work schedules and break timings, thereby optimizing both the health and work efficiency of employees at the logistics center.

[0662] "User" refers to a person who uses this system, and primarily refers to an employee of the logistics center.

[0663] "Initial hearing information" refers to basic information that is entered when a user first logs into the system, such as the user's name, age, occupation, stress level, and current lifestyle.

[0664] "Database" refers to an information management system for storing users' initial hearing information, collected lifestyle data, and data from wearable devices.

[0665] "Lifestyle data" refers to data related to a user's daily life, such as information collected from smartphones and web usage history.

[0666] A "wearable device" refers to a device worn by a user that can collect biometric information such as heart rate and activity level. An example of this is a smartwatch.

[0667] A "profile" refers to a data set that represents a user's behavioral, thought, and emotional patterns, created based on collected lifestyle data and data from wearable devices.

[0668] "Thinking patterns" are data that indicate the user's thinking tendencies and habits, and include stress levels in specific situations and efficient working times.

[0669] "Improvement suggestions" refer to recommendations regarding stress management, improving work efficiency, improving lifestyle habits, etc., that are generated based on the analysis of the user's thought patterns and emotional patterns.

[0670] "Terminal" refers to a device used by a user, such as a computer or smartphone, that can receive notifications of improvement suggestions.

[0671] A "logistics center" refers to a physical facility that manages logistics and products, and is the place where logistics operations are carried out.

[0672] "Activity data" is information about the user's physical activity, including the number of steps, distance traveled, and working hours.

[0673] "Real-time" refers to a state in which data is processed immediately after it is generated and the results are reflected.

[0674] "Work schedule" refers to the timetable and order of work that a user must perform at a logistics center.

[0675] "Rest timing" refers to the time for the user to take an appropriate rest.

[0676] "Server" refers to the central computer that processes and manages data for the entire system.

[0677] This invention is a system that collects activity data and emotion data of employees in a logistics center, monitors them in real time, and notifies them of optimal work schedules and break timings. Specific embodiments will be described below.

[0678] Obtaining initial hearing information

[0679] Employees (users) first log in to the system and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. This information is sent to the server via their device (smartphone or PC) and stored in a database. This initial information becomes the basis for creating the user's profile.

[0680] Data Collection and Profiling

[0681] With the user's permission, the server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). It also collects web usage history and app usage history. Furthermore, the server uses an emotion engine to analyze emotional data from the user's facial expressions and voice. Based on this data, a user profile is created.

[0682] Analysis of thought patterns and emotions

[0683] Using the profile data, the server analyzes the user's thought and emotional patterns. This analysis involves collecting lifestyle data, data from wearable devices, and emotional data. For example, it analyzes stress levels at specific times and in specific situations, and the most efficient working hours.

[0684] Generate improvement suggestions

[0685] The server generates optimal improvement suggestions for users based on the analysis of their thought patterns and emotional patterns. These improvement suggestions include stress management, improving work efficiency, and optimizing break timing. Specific examples of improvement suggestions for a logistics center include "encouraging short breaks every 30 minutes" and "stretching at a specific time in the afternoon."

[0686] Notification of improvement proposals

[0687] The generated improvement suggestions are notified to the user via the device, for example, a notification message is sent to a smartwatch or smartphone, allowing the user to check the suggestions and implement them.

[0688] Specific examples

[0689] Specifically, if a user's stress level is measured as high while working at a logistics center, the server analyzes the situation and generates an improvement suggestion such as "take a short break every 30 minutes." This suggestion is notified to the user via their smartwatch, allowing them to take a break at an appropriate time.

[0690] Example of input prompt for generative AI model

[0691] "Create a notification message that suggests the best time to take a break based on the user's stress level and activity level."

[0692] This will enable the optimization of both the health and work efficiency of employees at logistics centers.

[0693] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0694] Step 1:

[0695] Users log in to the system using a device (smartphone or PC) and enter initial interview information. This information includes name, age, occupation, stress level, current lifestyle habits, etc. The device sends this data to the server, which stores the received information in a database and creates an initial profile for each user.

[0696] Input: Name, age, occupation, stress level, lifestyle

[0697] Output: Initial hearing information and initial profile stored in a database

[0698] Step 2:

[0699] The server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). With the user's permission, it also collects their web and app usage history. This data is used to analyze the user's behavioral patterns and physical condition in detail.

[0700] Input: Activity data from wearable devices, heart rate data, web usage history, app usage history

[0701] Output: User profile update data

[0702] Step 3:

[0703] The server uses an emotion engine to analyze the user's emotions from the collected facial and voice data. The emotion data is used to evaluate the situations in which the user is likely to feel stressed, the time periods in which their emotions become unstable, and so on.

[0704] Input: facial expression data, voice data

[0705] Output: Emotion pattern data

[0706] Step 4:

[0707] The server creates a detailed profile of the user by combining collected lifestyle data, activity data, heart rate data, web usage history, app usage history, emotional patterns, etc. This profile includes the user's behavioral patterns, thought patterns, and emotional patterns. The server uses this data to analyze the user's thought patterns.

[0708] Input: Various collected data

[0709] Output: Detailed user profile

[0710] Step 5:

[0711] The server uses a generative AI model to generate optimal improvement proposals for each user based on a detailed user profile and various data, including specific action plans for improving work efficiency and stress management.

[0712] Input: User profile, thought pattern data, emotion pattern data

[0713] Output: Improvement suggestions

[0714] Step 6:

[0715] Once an improvement suggestion is generated, the server notifies the user's device. For example, a notification such as "Take a break in the next 30 minutes" is sent to a smartwatch. The user can then take appropriate action based on this.

[0716] Input: Improvement suggestion

[0717] Output: Notification message to terminal

[0718] Through the above processing steps, logistics center employees can achieve real-time health management and optimize work efficiency.

[0719] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0720] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0721] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0722] [Third embodiment]

[0723] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0724] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0725] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0726] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0727] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0728] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0729] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0730] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0731] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0732] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0733] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0734] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0735] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0736] Obtaining initial hearing information

[0737] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0738] Data Collection and Profiling

[0739] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smart watches) (such as activity level, heart rate, and sleep data). This data is used to record the user's activity and health status in detail and create a user profile.

[0740] Analyzing your thinking patterns

[0741] The server creates a user profile based on the data collected periodically, and then runs an algorithm to analyze the user's thought patterns based on the profile, such as stress levels in specific situations, efficient work times, and resting habits.

[0742] Generate improvement suggestions

[0743] The server generates optimal improvement proposals for the user based on the analysis results. These improvement proposals aim to help the user manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet the user's needs.

[0744] Notification of improvement proposals

[0745] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[0746] Specific examples

[0747] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch) and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[0748] In this way, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[0752] Step 2:

[0753] The terminal receives the input initial hearing information and transmits it to the server.

[0754] Step 3:

[0755] The server stores the received initial hearing information in a database.

[0756] Step 4:

[0757] With the user's permission, the server runs a script to periodically collect web usage history and app usage history.

[0758] Step 5:

[0759] The server collects physical data (activity level, heart rate, sleep data, etc.) from the user's wearable device (e.g., smart watch).

[0760] Step 6:

[0761] The server combines the collected web and app history with wearable data to create a user profile.

[0762] Step 7:

[0763] The server runs an algorithm to analyze the user's thought patterns based on the created profile.

[0764] Step 8:

[0765] The server generates improvement proposals customized for each user based on the analysis results of the thought patterns.

[0766] Step 9:

[0767] The server sends the generated improvement proposals to the user's device (smartphone, PC, etc.).

[0768] Step 10:

[0769] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods for implementing the suggestions.

[0770] Step 11:

[0771] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[0772] Example 1

[0773] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0774] Until now, there has been no system that can accurately grasp a user's thought patterns and daily stress factors and provide optimal individualized improvement suggestions. As a result, many users lack a means to obtain specific advice on improving their lifestyle habits and work performance. The present invention aims to solve this problem and improve the quality of users' lives.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0776] In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting lifestyle data of the user and data from the wearable device to create a user profile, and means for analyzing the user's thought patterns based on the profile, thereby making it possible to provide optimal improvement suggestions for each user.

[0777] "User" refers to an individual who uses the system.

[0778] "Terminal" refers to the device operated by the user, such as a smartphone or PC.

[0779] "Server" refers to a computer system that receives, processes, and stores data sent by users.

[0780] "Initial hearing information" refers to basic information that the user initially enters, such as name, age, occupation, stress level, and current lifestyle habits.

[0781] "Database" refers to an electronic information collection system for systematically storing and managing collected information.

[0782] A "profile" refers to information that indicates a user's characteristics and behavioral patterns, generated based on collected data.

[0783] A "wearable device" refers to a device worn by a user, such as a smartwatch, that collects data such as activity levels and heart rate.

[0784] "Thought patterns" refer to the user's daily thought tendencies and patterns, which are analyzed by an algorithm.

[0785] "Generative AI model" refers to an artificial intelligence model that generates improvement suggestions for each user based on collected data.

[0786] "Improvement suggestions" refer to advice aimed at helping users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[0787] "Notification" refers to the act of sending a message to a device to inform the user of improvement suggestions or other important information.

[0788] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0789] This system consists of three entities: the user, the terminal, and the server. The user logs in to the system and inputs the necessary information. The terminal is the device operated by the user and communicates with the server. The server processes and stores the data, and generates and provides optimal improvement proposals to the user.

[0790] Obtaining initial hearing information

[0791] Users log in to the system through a web browser or a dedicated application and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. The device receives this information and sends it to the server using an HTTP request. The server stores the received information in a database. This allows the user's basic information to be managed within the system.

[0792] Data Collection and Profiling

[0793] With permission from the user, the server collects the user's web usage history, app usage history, and activity, heart rate, and sleep data from wearable devices (e.g., smart watches). During this collection process, the server obtains permission from the user through OAuth authentication and then calls the APIs of each data source to obtain the data. The server then integrates this data to create a detailed profile of the user's activity and health status.

[0794] Analyzing your thinking patterns

[0795] The server uses an AI model to analyze the user's thought patterns based on the collected data. This analysis tool uses machine learning algorithms to analyze stress levels in specific situations, efficient work times, how to take breaks, etc. The analysis results are stored in a database and used for future analysis and improvement suggestions.

[0796] Generate improvement suggestions

[0797] The server uses a generative AI model to analyze the user's thought patterns and generate optimal improvement suggestions for the user. These suggestions include stress management, improving work efficiency, lifestyle improvements, improving decision-making quality, and improving communication. The generated improvement suggestions are customized to each user's individual needs.

[0798] Notification of improvement proposals

[0799] The server sends the generated improvement proposals to the user's device using a notification API. The device receives the notification and displays specific implementation methods and schedules to the user, allowing the user to receive practical advice that can be applied in their daily lives and work.

[0800] Specific examples

[0801] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device and creates a profile based on their web usage history and app usage. After inputting the collected data into an AI model and analyzing it, it is determined that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance on how to implement the suggestions.

[0802] Prompt Sentence Examples

[0803] As an example of a prompt sentence, enter "I've been feeling stressed a lot recently." Analysis and notification will then be performed.

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Step 1:

[0806] Obtaining initial hearing information

[0807] Input: The user logs into the system and enters their name, age, occupation, stress level, current lifestyle habits, etc.

[0808] How it works: A user enters information using a web browser or dedicated application and sends it to the device, which then generates an HTTP request and sends this information to the server.

[0809] Data processing: The server accurately analyzes the received information and converts it into a format that can be stored in the database.

[0810] Output: Initial hearing information is stored in a database.

[0811] Step 2:

[0812] Data collection and integration

[0813] Input: User's web usage history, app usage history, activity, heart rate, and sleep data from wearable devices (such as smartwatches).

[0814] How it works: The server obtains permission from the user through OAuth authentication and collects data using the API of each data source.

[0815] Data processing: The collected data is integrated and processed to create a detailed record of the user's activity and health status.

[0816] Output: The consolidated data is stored in a database and the user's profile is completed.

[0817] Step 3:

[0818] Analyzing your thinking patterns

[0819] Input: User's integrated data (web usage history, app usage history, activity level, heart rate, sleep data, etc.).

[0820] How it works: An AI model on the server uses this data to analyze the user's thought patterns.

[0821] Data calculations: Using machine learning algorithms, it analyzes stress levels in specific situations, efficient work times, resting habits, and more.

[0822] Output: Analysis results are generated and stored in a database.

[0823] Step 4:

[0824] Generate improvement suggestions

[0825] Input: Thought pattern analysis results.

[0826] How it works: The server uses a generative AI model to generate customized improvement suggestions for each user.

[0827] Data calculation: Based on the analysis results, the AI ​​model generates suggestions for stress management, efficiency improvement, lifestyle improvements, etc.

[0828] Output: The generated improvement suggestions are stored in a database.

[0829] Step 5:

[0830] Notification of improvement proposals

[0831] Input: Generated improvement suggestions.

[0832] How it works: The server uses the notification API to send improvement suggestions to the user's device, which processes the received notification and displays the suggestions through its user interface.

[0833] Data processing: The terminal converts the received proposals into an appropriate format and presents them to the user in an easy-to-understand form.

[0834] Output: A guide is provided for the user to review and implement the improvement suggestions.

[0835] In this way, a system has been constructed that processes specific input data at each step and ultimately provides appropriate improvement suggestions to the user.

[0836] (Application example 1)

[0837] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0838] In modern factory environments, managing worker stress and proposing efficient work patterns are important. However, current management systems have difficulty fully understanding the individual conditions of workers, making it difficult to make appropriate improvement proposals. Furthermore, while real-time information collection and analysis is essential to improving on-site work efficiency, the tools and systems available to achieve this are limited. As a result, worker stress and inefficient work patterns remain unresolved, preventing the optimization of the work environment.

[0839] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0840] In this invention, the server includes means for acquiring initial user information and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, and means for notifying the user of the improvement suggestions on the user's display device and providing visual guidance. This enables stress management and improved work efficiency tailored to each worker's individual situation. Furthermore, a generative AI model can be used to analyze the user's thought patterns from their body surface signals and behavioral history, and to generate improvement suggestions based on prompts, thereby providing more accurate suggestions in real time.

[0841] "Initial interview information" refers to basic information such as the user's name, age, role at work, stress level, and lifestyle habits.

[0842] A "user profile" is a data set that indicates the user's individual characteristics, generated based on the user's initial hearing information, lifestyle data, and data from wearable devices.

[0843] "Thinking patterns" are an analysis of the tendencies and habits that indicate how a user thinks and behaves in specific situations.

[0844] "Improvement suggestions" are specific advice or guidelines for action that are generated based on the analysis of the user's thought patterns and are intended to help the user manage stress and improve work efficiency.

[0845] "User display device" refers to a device used by a user to display visual information, such as smart glasses.

[0846] A "wearable device" is a device that is worn on the user's body and has the function of collecting data such as activity level and heart rate.

[0847] A "generative AI model" is a machine learning model that learns from large amounts of data and analyzes a user's behavior and body surface signals to infer thought patterns.

[0848] A "prompt" is an instruction given to a generative AI model, which serves as a basis for generating output for a specific purpose.

[0849] The "database" is an information management system for storing the user's initial hearing information and data from the wearable device.

[0850] "Lifestyle data" refers to data related to the user's daily life, including web usage history and app usage history.

[0851] The present invention relates to a system for managing the stress of factory workers and improving their work efficiency. Specific embodiments for carrying out the present invention will be described below.

[0852] Obtaining initial hearing information

[0853] The user logs in to the system through a display device (smart glasses) and inputs initial hearing information (such as name, age, role at work, stress level, current lifestyle habits, etc.). The display device receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0854] Data Collection and Profiling

[0855] With the user's permission, the server collects data such as heart rate, activity level, and working hours from the wearable device (e.g., a helmet-type smart device). This data is received by the server and automatically stored in a database. The server also collects the user's web usage history and app usage history. Based on this data, the server creates a user profile.

[0856] Analyzing your thinking patterns

[0857] The server periodically updates the user's profile based on collected data and analyzes the user's thought patterns using a generative AI model that analyzes, for example, the user's stress level and work efficiency at specific times and in specific situations.

[0858] Generate improvement suggestions

[0859] The server generates optimal improvement proposals for each user based on the analysis of their thought patterns. These improvement proposals aim to help users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet their needs.

[0860] Notification of improvement proposals

[0861] The server notifies the user of the generated improvement proposals on their display device (smart glasses). The display device visually notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily work and life.

[0862] Specific examples

[0863] For example, a factory worker logs into the system and enters the information that "I feel particularly tired in the afternoon." The display device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's helmet-type smart device and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly tired after 2:00 PM. The server then generates improvement suggestions, such as "stretch for 10 minutes at 1:00 PM," and notifies the display device. The display device then displays a pop-up in the user's field of vision guiding them on how to stretch.

[0864] Hardware and software used

[0865] Hardware: Smart glasses, smart helmet devices

[0866] Software: Data extraction tool (Apache Kafka), data analysis tool (Apache Spark), notification system (Firebase Cloud Messaging)

[0867] Prompt Sentence Examples

[0868] Use the data below to generate suggestions to improve stress and efficiency for factory workers.

[0869] Data: Heart rate (1:00 PM - 3:00 PM), work hours (9:00 AM - 5:00 PM), interview information (stress level: high, time of day when you feel unwell: afternoon)

[0870] Goal: Stress management, improved work efficiency

[0871] As described above, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement proposals, thereby improving factory work efficiency and reducing worker stress.

[0872] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0873] Step 1:

[0874] Entering initial hearing information

[0875] Subject: User

[0876] Specific operation: The user puts on the smart glasses and logs in to the system. The system prompts the user to enter initial information such as name, age, role at work, stress level, and lifestyle habits.

[0877] Input: Initial hearing information provided by the user

[0878] Output: The initial hearing information is sent from the display device to the server and stored in a database.

[0879] Step 2:

[0880] Data collection

[0881] Subject: Server

[0882] Specific operation: With the user's permission, the server collects data such as heart rate, activity level, and working time in real time from a wearable device (such as a helmet-type smart device).

[0883] Input: Data such as heart rate, activity level, and working hours from wearable devices

[0884] Output: The collected data is stored in a database on the server.

[0885] Step 3:

[0886] Creating a User Profile

[0887] Subject: Server

[0888] Specific operation: The server combines the collected data with the initial hearing information to create a profile of the user.

[0889] Input: Initial hearing information and lifestyle data stored in a database, data from wearable devices

[0890] Output: A user profile is generated and stored in a database.

[0891] Step 4:

[0892] Analyzing your thinking patterns

[0893] Subject: Server

[0894] How it works: The server uses the generative AI model to analyze the user's profile stored in the database. Specifically, it analyzes the user's stress level and work efficiency based on their heart rate and activity level during specific times and situations.

[0895] Input: User profile

[0896] Output: The analysis results in the user's thought patterns.

[0897] Step 5:

[0898] Generate improvement suggestions

[0899] Subject: Server

[0900] Specific operation: Based on the analysis of thought patterns, the server uses a generative AI model to generate prompt sentences, and then creates improvement suggestions customized for each user.

[0901] Input: Thought pattern analysis results

[0902] Output: User-optimized improvement suggestions

[0903] Step 6:

[0904] Notification of improvement proposals

[0905] Subject: Server and terminal

[0906] Specific operation: The server notifies the device (smart glasses) of the generated improvement proposal. The device displays the improvement proposal in the user's field of vision and provides a visual of the specific implementation method and schedule.

[0907] Input: Improvement suggestion

[0908] Output: The contents of the improvement proposal are notified to the terminal and visually displayed to the user.

[0909] For example, if a user feels particularly tired in the afternoon, the server will analyze the data and generate specific improvement suggestions, such as "stretch for 10 minutes at 1 p.m.", and notify the user through the smart glasses. By using a generative AI model, more accurate suggestions can be provided in real time.

[0910] Example prompt sentence:

[0911] "Based on the following data, please generate a proposal to improve the stress and efficiency of factory workers. Data: Heart rate (1:00 PM - 3:00 PM), working hours (9:00 AM - 5:00 PM), interview information (stress level: high, bad time: afternoon). Goal: Stress management, improving work efficiency."

[0912] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0913] The present invention combines an emotion engine with a system that analyzes a user's thought patterns and makes appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[0914] Obtaining initial hearing information

[0915] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[0916] Data Collection and Profiling

[0917] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smartwatches) (such as activity level, heart rate, and sleep data). The server also runs an emotion engine to analyze the user's emotions based on their facial expressions, voice, and biometric data. This data is used to create a user profile by recording the user's activity, health, and emotional state in detail.

[0918] Analysis of thought patterns and emotions

[0919] The server creates a user profile based on the periodically collected data. The profile includes lifestyle data, data from the wearable device, and emotional data. Based on this profile, an algorithm is run to analyze the user's thought and emotional patterns. For example, the algorithm can analyze stress levels in specific situations, efficient work schedules, rest habits, and emotional fluctuations.

[0920] Generate improvement suggestions

[0921] The server generates optimal improvement suggestions for each user based on the analysis of their thought patterns and emotional patterns. These improvement suggestions are aimed at managing the user's stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication. The generated improvement suggestions are customized for each user and designed to meet their needs.

[0922] Notification of improvement proposals

[0923] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[0924] Specific examples

[0925] For example, a user logs into the system and inputs information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch), as well as web usage history, app usage, and emotional data from the user's facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after afternoon meetings. Furthermore, the emotion engine reveals that emotions tend to become unstable after afternoon meetings. The server then generates improvement suggestions, such as "take a short break to relax before and after afternoon meetings" or "take a walk after lunch," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[0926] In this way, the system based on the present invention analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[0927] The processing flow will be explained below.

[0928] Step 1:

[0929] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[0930] Step 2:

[0931] The terminal receives the input initial hearing information and transmits it to the server.

[0932] Step 3:

[0933] The server stores the received initial hearing information in a database.

[0934] Step 4:

[0935] With the user's permission, the server collects the user's web usage history and app usage history.

[0936] Step 5:

[0937] The server collects physical data (activity level, heart rate, sleep data, etc.) from a wearable device (e.g., a smart watch) worn by the user.

[0938] Step 6:

[0939] The server integrates the collected web usage history, app usage history, and physical data to create a user profile.

[0940] Step 7:

[0941] The server analyzes the user's facial expressions, voice, and biometric data in real time and uses an emotion engine to identify the user's emotional state.

[0942] Step 8:

[0943] The server runs algorithms to analyze the user's thought and emotional patterns based on emotion data from the emotion engine and existing profile data.

[0944] Step 9:

[0945] The server generates an optimal improvement proposal for the user based on the analysis results of the thought patterns and emotion patterns.

[0946] Step 10:

[0947] The server notifies the user's device (smartphone, PC, etc.) of the generated improvement proposals.

[0948] Step 11:

[0949] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods and schedules for implementing the suggestions.

[0950] Step 12:

[0951] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[0952] Example 2

[0953] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0954] In modern society, users lead busy lives and are required to manage stress, improve their lifestyles, and increase work efficiency. However, conventional methods have difficulty effectively providing improvement suggestions tailored to individual users. In particular, there is a lack of means to provide improvement suggestions that take into account the user's thought patterns and emotional patterns, so the suggestions are often general and ineffective.

[0955] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns and emotional patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns and emotional patterns, and means for notifying the user's terminal of the improvement suggestions. This makes it possible to provide improvement suggestions customized to the individual state of the user.

[0956] "Initial hearing information" is information obtained in the initial stage of system use, such as the user's name, age, occupation, stress level, and current lifestyle.

[0957] "Database" means a digital storage system for storing and managing collected user information and profile data.

[0958] A "wearable device" is an electronic device worn on the body that collects activity levels, heart rate, sleep data, and other data.

[0959] A "profile" is detailed information about a user that is created based on collected lifestyle data about the user and data from wearable devices.

[0960] "Thought patterns" refer to the mental and behavioral characteristics of users, such as stress levels in specific situations, efficient work times, and how they take rest.

[0961] An "emotion pattern" represents the fluctuations and tendencies of a user's emotional state, and is analyzed from data such as facial expressions and voice.

[0962] "Improvement suggestions" are suggestions generated based on the user's profile, aimed at managing stress, improving work efficiency, improving lifestyle habits, and the like.

[0963] The "emotion engine" is software that analyzes emotions from a user's facial expressions and voice, and uses machine learning algorithms.

[0964] "Natural language generation technology" is a technology that automatically generates sentences that are easy for humans to understand based on collected data.

[0965] A "machine learning algorithm" is a mathematical model or computational method used to analyze collected data and extract patterns and trends.

[0966] "Notification" refers to a communication method such as email, pop-up, or push notification that notifies the user of the content of the improvement proposal on their device.

[0967] A "terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[0968] The present invention relates to a system for analyzing a user's thought patterns and emotional patterns and providing improvement suggestions suited to the user. Specific embodiments will be described below.

[0969] Obtaining initial hearing information

[0970] The user logs into the system and enters initial interview information such as name, age, occupation, stress level, and current lifestyle habits. The terminal provides this information as an input form and sends it to an API endpoint that sends the entered information to a database. The server receives this information and stores it in the database. At this stage, the data is validated, and only reliable data is saved in the database.

[0971] Data Collection and Profiling

[0972] With your permission, the server collects the following data:

[0973] "Web Usage History": Collects the user's web page browsing history through browser extensions.

[0974] "App usage history": Collects usage history of applications installed on smartphones and PCs.

[0975] "Data from wearable devices": For example, activity, heart rate, and sleep data from a smartwatch can be obtained through an API.

[0976] The server then runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The output of the emotion engine is stored in a database and becomes part of the user's profile.

[0977] Analysis of thought and emotional patterns

[0978] The server creates and updates a user profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server then uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in specific situations, efficient work schedules, how to take breaks, and emotional fluctuations, and finds patterns customized for each user.

[0979] Generate improvement suggestions

[0980] Based on the analysis results, the server generates optimal improvement suggestions for the user. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate optimal sentences for the user. The generated improvement suggestions aim to manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[0981] Notification of improvement proposals

[0982] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. The notification provides the specific content of the suggestion, how to implement it, and a timeline. This allows the user to put the suggestions into practice in their daily lives or work.

[0983] Specific examples

[0984] For example, a user logs into the system and enters, "I've been feeling stressed a lot recently." The device receives this information and sends it to the server. The server stores it in a database. The server then collects heart rate and activity data, web usage history, and app usage from the user's wearable device (smartwatch), as well as emotional data from facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after an afternoon meeting. Furthermore, the emotion engine's results reveal that emotions become unstable after an afternoon meeting. The server then generates improvement suggestions, such as "take a short relaxation break before or after an afternoon meeting" or "take a walk after lunch," and notifies the device. The device displays these suggestions to the user and provides specific guidance for implementing the suggestions.

[0985] Prompt Sentence Examples

[0986] A system description can be generated by inputting the following prompts into the generative AI model:

[0987] "Please explain the system that analyzes the user's thought and emotional patterns and makes appropriate suggestions for improvement."

[0988] "Please tell me more about the system that collects and profiles user data."

[0989] "Give us an example of a system that generates recommendations for users to manage stress or improve their lifestyle habits."

[0990] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0991] Step 1: Obtaining initial hearing information

[0992] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits). The device provides this information as an input form, and the entered data is sent to the server via API. The server receives this information and stores it in a database. Specifically, it validates the data, confirms its accuracy, and then issues an INSERT query to the database. The input data is the initial interview information, and the output is the user information stored in the database.

[0993] Step 2: Data collection and profiling

[0994] With your permission, the server collects the following data:

[0995] Web usage history: Collects user's web page browsing history through browser extensions.

[0996] App usage history: Collects usage history of applications installed on smartphones and PCs.

[0997] Data from wearable devices: Activity, heart rate, and sleep data are obtained from smartwatches via API.

[0998] The server also runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The input data is various user and emotional data, and the output is a detailed user profile. This profile is then stored in a database.

[0999] Step 3: Analyze your thinking and emotional patterns

[1000] The server periodically updates the user's profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in a particular situation, efficient working times, how to take rest, and emotional fluctuations. The input data is the collected user data and profile information, and the output is the analyzed thought and emotional patterns. Specific operations include data cleansing, feature extraction, and application of machine learning models.

[1001] Step 4: Generate improvement suggestions

[1002] The server generates optimal improvement suggestions for the user based on the analysis of thought patterns and emotional patterns. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate specific improvement suggestions in text format. The input data are the analysis results and user profile information, and the output is the optimal improvement suggestions for the user. The generated improvement suggestions are aimed at managing stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication.

[1003] Step 5: Notification of improvement proposals

[1004] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. This notification includes the specific content of the suggestion, how to implement it, and a timeline. The input data is the generated improvement suggestions, and the output is the notification sent to the user's device. This allows the user to follow specific guidance on how to put the suggestions into practice.

[1005] Through these processing steps, the system analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving performance at work and in private life and reducing stress.

[1006] (Application example 2)

[1007] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1008] In modern logistics centers, the working environment is stressful, and employee stress and fatigue are serious issues that reduce work efficiency and safety. However, there is no system that can closely monitor the condition of each employee in real time and make appropriate improvement proposals. New technology is needed to simultaneously manage employee health and optimize work efficiency.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1010] In this invention, the server includes means for acquiring initial hearing information from the user and storing it in a database, means for collecting user lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, means for notifying the user's terminal of the improvement suggestions, and means for monitoring the activity data of workers at the logistics center in real time and recommending optimal work schedules and break timings, thereby optimizing both the health and work efficiency of employees at the logistics center.

[1011] "User" refers to a person who uses this system, and primarily refers to an employee of the logistics center.

[1012] "Initial hearing information" refers to basic information that is entered when a user first logs into the system, such as the user's name, age, occupation, stress level, and current lifestyle.

[1013] "Database" refers to an information management system for storing users' initial hearing information, collected lifestyle data, and data from wearable devices.

[1014] "Lifestyle data" refers to data related to a user's daily life, such as information collected from smartphones and web usage history.

[1015] A "wearable device" refers to a device worn by a user that can collect biometric information such as heart rate and activity level. An example of this is a smartwatch.

[1016] A "profile" refers to a data set that represents a user's behavioral, thought, and emotional patterns, created based on collected lifestyle data and data from wearable devices.

[1017] "Thinking patterns" are data that indicate the user's thinking tendencies and habits, and include stress levels in specific situations and efficient working times.

[1018] "Improvement suggestions" refer to recommendations regarding stress management, improving work efficiency, improving lifestyle habits, etc., that are generated based on the analysis of the user's thought patterns and emotional patterns.

[1019] "Terminal" refers to a device used by a user, such as a computer or smartphone, that can receive notifications of improvement suggestions.

[1020] A "logistics center" refers to a physical facility that manages logistics and products, and is the place where logistics operations are carried out.

[1021] "Activity data" is information about the user's physical activity, including the number of steps, distance traveled, and working hours.

[1022] "Real-time" refers to a state in which data is processed immediately after it is generated and the results are reflected.

[1023] "Work schedule" refers to the timetable and order of work that a user must perform at a logistics center.

[1024] "Rest timing" refers to the time for the user to take an appropriate rest.

[1025] "Server" refers to the central computer that processes and manages data for the entire system.

[1026] This invention is a system that collects activity data and emotion data of employees in a logistics center, monitors them in real time, and notifies them of optimal work schedules and break timings. Specific embodiments will be described below.

[1027] Obtaining initial hearing information

[1028] Employees (users) first log in to the system and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. This information is sent to the server via their device (smartphone or PC) and stored in a database. This initial information becomes the basis for creating the user's profile.

[1029] Data Collection and Profiling

[1030] With the user's permission, the server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). It also collects web usage history and app usage history. Furthermore, the server uses an emotion engine to analyze emotional data from the user's facial expressions and voice. Based on this data, a user profile is created.

[1031] Analysis of thought patterns and emotions

[1032] Using the profile data, the server analyzes the user's thought and emotional patterns. This analysis involves collecting lifestyle data, data from wearable devices, and emotional data. For example, it analyzes stress levels at specific times and in specific situations, and the most efficient working hours.

[1033] Generate improvement suggestions

[1034] The server generates optimal improvement suggestions for users based on the analysis of their thought patterns and emotional patterns. These improvement suggestions include stress management, improving work efficiency, and optimizing break timing. Specific examples of improvement suggestions for a logistics center include "encouraging short breaks every 30 minutes" and "stretching at a specific time in the afternoon."

[1035] Notification of improvement proposals

[1036] The generated improvement suggestions are notified to the user via the device, for example, a notification message is sent to a smartwatch or smartphone, allowing the user to check the suggestions and implement them.

[1037] Specific examples

[1038] Specifically, if a user's stress level is measured as high while working at a logistics center, the server analyzes the situation and generates an improvement suggestion such as "take a short break every 30 minutes." This suggestion is notified to the user via their smartwatch, allowing them to take a break at an appropriate time.

[1039] Example of input prompt for generative AI model

[1040] "Create a notification message that suggests the best time to take a break based on the user's stress level and activity level."

[1041] This will enable the optimization of both the health and work efficiency of employees at logistics centers.

[1042] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1043] Step 1:

[1044] Users log in to the system using a device (smartphone or PC) and enter initial interview information. This information includes name, age, occupation, stress level, current lifestyle habits, etc. The device sends this data to the server, which stores the received information in a database and creates an initial profile for each user.

[1045] Input: Name, age, occupation, stress level, lifestyle

[1046] Output: Initial hearing information and initial profile stored in a database

[1047] Step 2:

[1048] The server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). With the user's permission, it also collects their web and app usage history. This data is used to analyze the user's behavioral patterns and physical condition in detail.

[1049] Input: Activity data from wearable devices, heart rate data, web usage history, app usage history

[1050] Output: User profile update data

[1051] Step 3:

[1052] The server uses an emotion engine to analyze the user's emotions from the collected facial and voice data. The emotion data is used to evaluate the situations in which the user is likely to feel stressed, the time periods in which their emotions become unstable, and so on.

[1053] Input: facial expression data, voice data

[1054] Output: Emotion pattern data

[1055] Step 4:

[1056] The server creates a detailed profile of the user by combining collected lifestyle data, activity data, heart rate data, web usage history, app usage history, emotional patterns, etc. This profile includes the user's behavioral patterns, thought patterns, and emotional patterns. The server uses this data to analyze the user's thought patterns.

[1057] Input: Various collected data

[1058] Output: Detailed user profile

[1059] Step 5:

[1060] The server uses a generative AI model to generate optimal improvement proposals for each user based on a detailed user profile and various data, including specific action plans for improving work efficiency and stress management.

[1061] Input: User profile, thought pattern data, emotion pattern data

[1062] Output: Improvement suggestions

[1063] Step 6:

[1064] Once an improvement suggestion is generated, the server notifies the user's device. For example, a notification such as "Take a break in the next 30 minutes" is sent to a smartwatch. The user can then take appropriate action based on this.

[1065] Input: Improvement suggestion

[1066] Output: Notification message to terminal

[1067] Through the above processing steps, logistics center employees can achieve real-time health management and optimize work efficiency.

[1068] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1069] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1070] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1071] [Fourth embodiment]

[1072] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1073] 7, a 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.

[1074] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1075] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1076] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1077] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1078] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1079] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1080] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1081] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1082] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1083] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1084] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1085] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[1086] Obtaining initial hearing information

[1087] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[1088] Data Collection and Profiling

[1089] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smart watches) (such as activity level, heart rate, and sleep data). This data is used to record the user's activity and health status in detail and create a user profile.

[1090] Analyzing your thinking patterns

[1091] The server creates a user profile based on the data collected periodically, and then runs an algorithm to analyze the user's thought patterns based on the profile, such as stress levels in specific situations, efficient work times, and resting habits.

[1092] Generate improvement suggestions

[1093] The server generates optimal improvement proposals for the user based on the analysis results. These improvement proposals aim to help the user manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet the user's needs.

[1094] Notification of improvement proposals

[1095] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[1096] Specific examples

[1097] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch) and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[1098] In this way, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[1099] The processing flow will be explained below.

[1100] Step 1:

[1101] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[1102] Step 2:

[1103] The terminal receives the input initial hearing information and transmits it to the server.

[1104] Step 3:

[1105] The server stores the received initial hearing information in a database.

[1106] Step 4:

[1107] With the user's permission, the server runs a script to periodically collect web usage history and app usage history.

[1108] Step 5:

[1109] The server collects physical data (activity level, heart rate, sleep data, etc.) from the user's wearable device (e.g., smart watch).

[1110] Step 6:

[1111] The server combines the collected web and app history with wearable data to create a user profile.

[1112] Step 7:

[1113] The server runs an algorithm to analyze the user's thought patterns based on the created profile.

[1114] Step 8:

[1115] The server generates improvement proposals customized for each user based on the analysis results of the thought patterns.

[1116] Step 9:

[1117] The server sends the generated improvement proposals to the user's device (smartphone, PC, etc.).

[1118] Step 10:

[1119] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods for implementing the suggestions.

[1120] Step 11:

[1121] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[1122] Example 1

[1123] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1124] Until now, there has been no system that can accurately grasp a user's thought patterns and daily stress factors and provide optimal individualized improvement suggestions. As a result, many users lack a means to obtain specific advice on improving their lifestyle habits and work performance. The present invention aims to solve this problem and improve the quality of users' lives.

[1125] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1126] In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting lifestyle data of the user and data from the wearable device to create a user profile, and means for analyzing the user's thought patterns based on the profile, thereby making it possible to provide optimal improvement suggestions for each user.

[1127] "User" refers to an individual who uses the system.

[1128] "Terminal" refers to the device operated by the user, such as a smartphone or PC.

[1129] "Server" refers to a computer system that receives, processes, and stores data sent by users.

[1130] "Initial hearing information" refers to basic information that the user initially enters, such as name, age, occupation, stress level, and current lifestyle habits.

[1131] "Database" refers to an electronic information collection system for systematically storing and managing collected information.

[1132] A "profile" refers to information that indicates a user's characteristics and behavioral patterns, generated based on collected data.

[1133] A "wearable device" refers to a device worn by a user, such as a smartwatch, that collects data such as activity levels and heart rate.

[1134] "Thought patterns" refer to the user's daily thought tendencies and patterns, which are analyzed by an algorithm.

[1135] "Generative AI model" refers to an artificial intelligence model that generates improvement suggestions for each user based on collected data.

[1136] "Improvement suggestions" refer to advice aimed at helping users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[1137] "Notification" refers to the act of sending a message to a device to inform the user of improvement suggestions or other important information.

[1138] The present invention relates to a system for analyzing a user's thought patterns and making appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[1139] This system consists of three entities: the user, the terminal, and the server. The user logs in to the system and inputs the necessary information. The terminal is the device operated by the user and communicates with the server. The server processes and stores the data, and generates and provides optimal improvement proposals to the user.

[1140] Obtaining initial hearing information

[1141] Users log in to the system through a web browser or a dedicated application and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. The device receives this information and sends it to the server using an HTTP request. The server stores the received information in a database. This allows the user's basic information to be managed within the system.

[1142] Data Collection and Profiling

[1143] With permission from the user, the server collects the user's web usage history, app usage history, and activity, heart rate, and sleep data from wearable devices (e.g., smart watches). During this collection process, the server obtains permission from the user through OAuth authentication and then calls the APIs of each data source to obtain the data. The server then integrates this data to create a detailed profile of the user's activity and health status.

[1144] Analyzing your thinking patterns

[1145] The server uses an AI model to analyze the user's thought patterns based on the collected data. This analysis tool uses machine learning algorithms to analyze stress levels in specific situations, efficient work times, how to take breaks, etc. The analysis results are stored in a database and used for future analysis and improvement suggestions.

[1146] Generate improvement suggestions

[1147] The server uses a generative AI model to analyze the user's thought patterns and generate optimal improvement suggestions for the user. These suggestions include stress management, improving work efficiency, lifestyle improvements, improving decision-making quality, and improving communication. The generated improvement suggestions are customized to each user's individual needs.

[1148] Notification of improvement proposals

[1149] The server sends the generated improvement proposals to the user's device using a notification API. The device receives the notification and displays specific implementation methods and schedules to the user, allowing the user to receive practical advice that can be applied in their daily lives and work.

[1150] Specific examples

[1151] For example, a user logs into the system and enters information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device and creates a profile based on their web usage history and app usage. After inputting the collected data into an AI model and analyzing it, it is determined that the user feels particularly stressed after an afternoon meeting. The server then generates improvement suggestions, such as "take a short break to relax before and after the afternoon meeting," and notifies the device. The device then notifies the user and displays guidance on how to implement the suggestions.

[1152] Prompt Sentence Examples

[1153] As an example of a prompt sentence, enter "I've been feeling stressed a lot recently." Analysis and notification will then be performed.

[1154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1155] Step 1:

[1156] Obtaining initial hearing information

[1157] Input: The user logs into the system and enters their name, age, occupation, stress level, current lifestyle habits, etc.

[1158] How it works: A user enters information using a web browser or dedicated application and sends it to the device, which then generates an HTTP request and sends this information to the server.

[1159] Data processing: The server accurately analyzes the received information and converts it into a format that can be stored in the database.

[1160] Output: Initial hearing information is stored in a database.

[1161] Step 2:

[1162] Data collection and integration

[1163] Input: User's web usage history, app usage history, activity, heart rate, and sleep data from wearable devices (such as smartwatches).

[1164] How it works: The server obtains permission from the user through OAuth authentication and collects data using the API of each data source.

[1165] Data processing: The collected data is integrated and processed to create a detailed record of the user's activity and health status.

[1166] Output: The consolidated data is stored in a database and the user's profile is completed.

[1167] Step 3:

[1168] Analyzing your thinking patterns

[1169] Input: User's integrated data (web usage history, app usage history, activity level, heart rate, sleep data, etc.).

[1170] How it works: An AI model on the server uses this data to analyze the user's thought patterns.

[1171] Data calculations: Using machine learning algorithms, it analyzes stress levels in specific situations, efficient work times, resting habits, and more.

[1172] Output: Analysis results are generated and stored in a database.

[1173] Step 4:

[1174] Generate improvement suggestions

[1175] Input: Thought pattern analysis results.

[1176] How it works: The server uses a generative AI model to generate customized improvement suggestions for each user.

[1177] Data calculation: Based on the analysis results, the AI ​​model generates suggestions for stress management, efficiency improvement, lifestyle improvements, etc.

[1178] Output: The generated improvement suggestions are stored in a database.

[1179] Step 5:

[1180] Notification of improvement proposals

[1181] Input: Generated improvement suggestions.

[1182] How it works: The server uses the notification API to send improvement suggestions to the user's device, which processes the received notification and displays the suggestions through its user interface.

[1183] Data processing: The terminal converts the received proposals into an appropriate format and presents them to the user in an easy-to-understand form.

[1184] Output: A guide is provided for the user to review and implement the improvement suggestions.

[1185] In this way, a system has been constructed that processes specific input data at each step and ultimately provides appropriate improvement suggestions to the user.

[1186] (Application example 1)

[1187] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1188] In modern factory environments, managing worker stress and proposing efficient work patterns are important. However, current management systems have difficulty fully understanding the individual conditions of workers, making it difficult to make appropriate improvement proposals. Furthermore, while real-time information collection and analysis is essential to improving on-site work efficiency, the tools and systems available to achieve this are limited. As a result, worker stress and inefficient work patterns remain unresolved, preventing the optimization of the work environment.

[1189] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1190] In this invention, the server includes means for acquiring initial user information and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, and means for notifying the user of the improvement suggestions on the user's display device and providing visual guidance. This enables stress management and improved work efficiency tailored to each worker's individual situation. Furthermore, a generative AI model can be used to analyze the user's thought patterns from their body surface signals and behavioral history, and to generate improvement suggestions based on prompts, thereby providing more accurate suggestions in real time.

[1191] "Initial interview information" refers to basic information such as the user's name, age, role at work, stress level, and lifestyle habits.

[1192] A "user profile" is a data set that indicates the user's individual characteristics, generated based on the user's initial hearing information, lifestyle data, and data from wearable devices.

[1193] "Thinking patterns" are an analysis of the tendencies and habits that indicate how a user thinks and behaves in specific situations.

[1194] "Improvement suggestions" are specific advice or guidelines for action that are generated based on the analysis of the user's thought patterns and are intended to help the user manage stress and improve work efficiency.

[1195] "User display device" refers to a device used by a user to display visual information, such as smart glasses.

[1196] A "wearable device" is a device that is worn on the user's body and has the function of collecting data such as activity level and heart rate.

[1197] A "generative AI model" is a machine learning model that learns from large amounts of data and analyzes a user's behavior and body surface signals to infer thought patterns.

[1198] A "prompt" is an instruction given to a generative AI model, which serves as a basis for generating output for a specific purpose.

[1199] The "database" is an information management system for storing the user's initial hearing information and data from the wearable device.

[1200] "Lifestyle data" refers to data related to the user's daily life, including web usage history and app usage history.

[1201] The present invention relates to a system for managing the stress of factory workers and improving their work efficiency. Specific embodiments for carrying out the present invention will be described below.

[1202] Obtaining initial hearing information

[1203] The user logs in to the system through a display device (smart glasses) and inputs initial hearing information (such as name, age, role at work, stress level, current lifestyle habits, etc.). The display device receives this initial hearing information and sends it to the server, which stores the received information in a database.

[1204] Data Collection and Profiling

[1205] With the user's permission, the server collects data such as heart rate, activity level, and working hours from the wearable device (e.g., a helmet-type smart device). This data is received by the server and automatically stored in a database. The server also collects the user's web usage history and app usage history. Based on this data, the server creates a user profile.

[1206] Analyzing your thinking patterns

[1207] The server periodically updates the user's profile based on collected data and analyzes the user's thought patterns using a generative AI model that analyzes, for example, the user's stress level and work efficiency at specific times and in specific situations.

[1208] Generate improvement suggestions

[1209] The server generates optimal improvement proposals for each user based on the analysis of their thought patterns. These improvement proposals aim to help users manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication. The generated improvement proposals are customized for each user and designed to meet their needs.

[1210] Notification of improvement proposals

[1211] The server notifies the user of the generated improvement proposals on their display device (smart glasses). The display device visually notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily work and life.

[1212] Specific examples

[1213] For example, a factory worker logs into the system and enters the information that "I feel particularly tired in the afternoon." The display device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's helmet-type smart device and creates a profile based on their web usage history and app usage. Analysis reveals that the user feels particularly tired after 2:00 PM. The server then generates improvement suggestions, such as "stretch for 10 minutes at 1:00 PM," and notifies the display device. The display device then displays a pop-up in the user's field of vision guiding them on how to stretch.

[1214] Hardware and software used

[1215] Hardware: Smart glasses, smart helmet devices

[1216] Software: Data extraction tool (Apache Kafka), data analysis tool (Apache Spark), notification system (Firebase Cloud Messaging)

[1217] Prompt Sentence Examples

[1218] Use the data below to generate suggestions to improve stress and efficiency for factory workers.

[1219] Data: Heart rate (1:00 PM - 3:00 PM), work hours (9:00 AM - 5:00 PM), interview information (stress level: high, time of day when you feel unwell: afternoon)

[1220] Goal: Stress management, improved work efficiency

[1221] As described above, the system based on the present invention analyzes the user's thought patterns and provides individually tailored improvement proposals, thereby improving factory work efficiency and reducing worker stress.

[1222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1223] Step 1:

[1224] Entering initial hearing information

[1225] Subject: User

[1226] Specific operation: The user puts on the smart glasses and logs in to the system. The system prompts the user to enter initial information such as name, age, role at work, stress level, and lifestyle habits.

[1227] Input: Initial hearing information provided by the user

[1228] Output: The initial hearing information is sent from the display device to the server and stored in a database.

[1229] Step 2:

[1230] Data collection

[1231] Subject: Server

[1232] Specific operation: With the user's permission, the server collects data such as heart rate, activity level, and working time in real time from a wearable device (such as a helmet-type smart device).

[1233] Input: Data such as heart rate, activity level, and working hours from wearable devices

[1234] Output: The collected data is stored in a database on the server.

[1235] Step 3:

[1236] Creating a User Profile

[1237] Subject: Server

[1238] Specific operation: The server combines the collected data with the initial hearing information to create a profile of the user.

[1239] Input: Initial hearing information and lifestyle data stored in a database, data from wearable devices

[1240] Output: A user profile is generated and stored in a database.

[1241] Step 4:

[1242] Analyzing your thinking patterns

[1243] Subject: Server

[1244] How it works: The server uses the generative AI model to analyze the user's profile stored in the database. Specifically, it analyzes the user's stress level and work efficiency based on their heart rate and activity level during specific times and situations.

[1245] Input: User profile

[1246] Output: The analysis results in the user's thought patterns.

[1247] Step 5:

[1248] Generate improvement suggestions

[1249] Subject: Server

[1250] Specific operation: Based on the analysis of thought patterns, the server uses a generative AI model to generate prompt sentences, and then creates improvement suggestions customized for each user.

[1251] Input: Thought pattern analysis results

[1252] Output: User-optimized improvement suggestions

[1253] Step 6:

[1254] Notification of improvement proposals

[1255] Subject: Server and terminal

[1256] Specific operation: The server notifies the device (smart glasses) of the generated improvement proposal. The device displays the improvement proposal in the user's field of vision and provides a visual of the specific implementation method and schedule.

[1257] Input: Improvement suggestion

[1258] Output: The contents of the improvement proposal are notified to the terminal and visually displayed to the user.

[1259] For example, if a user feels particularly tired in the afternoon, the server will analyze the data and generate specific improvement suggestions, such as "stretch for 10 minutes at 1 p.m.", and notify the user through the smart glasses. By using a generative AI model, more accurate suggestions can be provided in real time.

[1260] Example prompt sentence:

[1261] "Based on the following data, please generate a proposal to improve the stress and efficiency of factory workers. Data: Heart rate (1:00 PM - 3:00 PM), working hours (9:00 AM - 5:00 PM), interview information (stress level: high, bad time: afternoon). Goal: Stress management, improving work efficiency."

[1262] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1263] The present invention combines an emotion engine with a system that analyzes a user's thought patterns and makes appropriate suggestions for improvement. Specific embodiments for carrying out the present invention will be described below.

[1264] Obtaining initial hearing information

[1265] The user logs in to the system and inputs initial hearing information (such as name, age, occupation, stress level, and current lifestyle habits). The terminal receives this initial hearing information and sends it to the server, which stores the received information in a database.

[1266] Data Collection and Profiling

[1267] With the user's permission, the server collects data from the user's web usage history, app usage history, and wearable devices (e.g., smartwatches) (such as activity level, heart rate, and sleep data). The server also runs an emotion engine to analyze the user's emotions based on their facial expressions, voice, and biometric data. This data is used to create a user profile by recording the user's activity, health, and emotional state in detail.

[1268] Analysis of thought patterns and emotions

[1269] The server creates a user profile based on the periodically collected data. The profile includes lifestyle data, data from the wearable device, and emotional data. Based on this profile, an algorithm is run to analyze the user's thought and emotional patterns. For example, the algorithm can analyze stress levels in specific situations, efficient work schedules, rest habits, and emotional fluctuations.

[1270] Generate improvement suggestions

[1271] The server generates optimal improvement suggestions for each user based on the analysis of their thought patterns and emotional patterns. These improvement suggestions are aimed at managing the user's stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication. The generated improvement suggestions are customized for each user and designed to meet their needs.

[1272] Notification of improvement proposals

[1273] The server notifies the user's device (such as a smartphone or PC) of the generated improvement proposals. The device then notifies the user of the contents of the improvement proposals and provides specific implementation methods and schedules. This allows the user to put the improvement proposals into practice in their daily lives and work.

[1274] Specific examples

[1275] For example, a user logs into the system and inputs information such as "I've been feeling stressed a lot recently." The device sends this information to the server, which stores it in a database. The server then collects heart rate and activity data from the user's wearable device (smartwatch), as well as web usage history, app usage, and emotional data from the user's facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after afternoon meetings. Furthermore, the emotion engine reveals that emotions tend to become unstable after afternoon meetings. The server then generates improvement suggestions, such as "take a short break to relax before and after afternoon meetings" or "take a walk after lunch," and notifies the device. The device then notifies the user and displays guidance for implementing the suggestions.

[1276] In this way, the system based on the present invention analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving work and personal performance and reducing stress.

[1277] The processing flow will be explained below.

[1278] Step 1:

[1279] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits).

[1280] Step 2:

[1281] The terminal receives the input initial hearing information and transmits it to the server.

[1282] Step 3:

[1283] The server stores the received initial hearing information in a database.

[1284] Step 4:

[1285] With the user's permission, the server collects the user's web usage history and app usage history.

[1286] Step 5:

[1287] The server collects physical data (activity level, heart rate, sleep data, etc.) from a wearable device (e.g., a smart watch) worn by the user.

[1288] Step 6:

[1289] The server integrates the collected web usage history, app usage history, and physical data to create a user profile.

[1290] Step 7:

[1291] The server analyzes the user's facial expressions, voice, and biometric data in real time and uses an emotion engine to identify the user's emotional state.

[1292] Step 8:

[1293] The server runs algorithms to analyze the user's thought and emotional patterns based on emotion data from the emotion engine and existing profile data.

[1294] Step 9:

[1295] The server generates an optimal improvement proposal for the user based on the analysis results of the thought patterns and emotion patterns.

[1296] Step 10:

[1297] The server notifies the user's device (smartphone, PC, etc.) of the generated improvement proposals.

[1298] Step 11:

[1299] The device will report the improvement suggestions it receives to the user via push notification or email, and provide specific methods and schedules for implementing the suggestions.

[1300] Step 12:

[1301] The user receives notifications from the device and implements suggested actions and lifestyle improvements.

[1302] Example 2

[1303] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1304] In modern society, users lead busy lives and are required to manage stress, improve their lifestyles, and increase work efficiency. However, conventional methods have difficulty effectively providing improvement suggestions tailored to individual users. In particular, there is a lack of means to provide improvement suggestions that take into account the user's thought patterns and emotional patterns, so the suggestions are often general and ineffective.

[1305] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring initial hearing information of the user and storing it in a database, means for collecting the user's lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns and emotional patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns and emotional patterns, and means for notifying the user's terminal of the improvement suggestions. This makes it possible to provide improvement suggestions customized to the individual state of the user.

[1306] "Initial hearing information" is information obtained in the initial stage of system use, such as the user's name, age, occupation, stress level, and current lifestyle.

[1307] "Database" means a digital storage system for storing and managing collected user information and profile data.

[1308] A "wearable device" is an electronic device worn on the body that collects activity levels, heart rate, sleep data, and other data.

[1309] A "profile" is detailed information about a user that is created based on collected lifestyle data about the user and data from wearable devices.

[1310] "Thought patterns" refer to the mental and behavioral characteristics of users, such as stress levels in specific situations, efficient work times, and how they take rest.

[1311] An "emotion pattern" represents the fluctuations and tendencies of a user's emotional state, and is analyzed from data such as facial expressions and voice.

[1312] "Improvement suggestions" are suggestions generated based on the user's profile, aimed at managing stress, improving work efficiency, improving lifestyle habits, and the like.

[1313] The "emotion engine" is software that analyzes emotions from a user's facial expressions and voice, and uses machine learning algorithms.

[1314] "Natural language generation technology" is a technology that automatically generates sentences that are easy for humans to understand based on collected data.

[1315] A "machine learning algorithm" is a mathematical model or computational method used to analyze collected data and extract patterns and trends.

[1316] "Notification" refers to a communication method such as email, pop-up, or push notification that notifies the user of the content of the improvement proposal on their device.

[1317] A "terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[1318] The present invention relates to a system for analyzing a user's thought patterns and emotional patterns and providing improvement suggestions suited to the user. Specific embodiments will be described below.

[1319] Obtaining initial hearing information

[1320] The user logs into the system and enters initial interview information such as name, age, occupation, stress level, and current lifestyle habits. The terminal provides this information as an input form and sends it to an API endpoint that sends the entered information to a database. The server receives this information and stores it in the database. At this stage, the data is validated, and only reliable data is saved in the database.

[1321] Data Collection and Profiling

[1322] With your permission, the server collects the following data:

[1323] "Web Usage History": Collects the user's web page browsing history through browser extensions.

[1324] "App usage history": Collects usage history of applications installed on smartphones and PCs.

[1325] "Data from wearable devices": For example, activity, heart rate, and sleep data from a smartwatch can be obtained through an API.

[1326] The server then runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The output of the emotion engine is stored in a database and becomes part of the user's profile.

[1327] Analysis of thought and emotional patterns

[1328] The server creates and updates a user profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server then uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in specific situations, efficient work schedules, how to take breaks, and emotional fluctuations, and finds patterns customized for each user.

[1329] Generate improvement suggestions

[1330] Based on the analysis results, the server generates optimal improvement suggestions for the user. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate optimal sentences for the user. The generated improvement suggestions aim to manage stress, improve work efficiency, improve lifestyle habits, improve the quality of decision-making, and improve communication.

[1331] Notification of improvement proposals

[1332] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. The notification provides the specific content of the suggestion, how to implement it, and a timeline. This allows the user to put the suggestions into practice in their daily lives or work.

[1333] Specific examples

[1334] For example, a user logs into the system and enters, "I've been feeling stressed a lot recently." The device receives this information and sends it to the server. The server stores it in a database. The server then collects heart rate and activity data, web usage history, and app usage from the user's wearable device (smartwatch), as well as emotional data from facial expressions and voice using an emotion engine. A profile is created based on this data, and analysis reveals that the user feels particularly stressed after an afternoon meeting. Furthermore, the emotion engine's results reveal that emotions become unstable after an afternoon meeting. The server then generates improvement suggestions, such as "take a short relaxation break before or after an afternoon meeting" or "take a walk after lunch," and notifies the device. The device displays these suggestions to the user and provides specific guidance for implementing the suggestions.

[1335] Prompt Sentence Examples

[1336] A system description can be generated by inputting the following prompts into the generative AI model:

[1337] "Please explain the system that analyzes the user's thought and emotional patterns and makes appropriate suggestions for improvement."

[1338] "Please tell me more about the system that collects and profiles user data."

[1339] "Give us an example of a system that generates recommendations for users to manage stress or improve their lifestyle habits."

[1340] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1341] Step 1: Obtaining initial hearing information

[1342] The user logs into the system and enters initial interview information (such as name, age, occupation, stress level, and current lifestyle habits). The device provides this information as an input form, and the entered data is sent to the server via API. The server receives this information and stores it in a database. Specifically, it validates the data, confirms its accuracy, and then issues an INSERT query to the database. The input data is the initial interview information, and the output is the user information stored in the database.

[1343] Step 2: Data collection and profiling

[1344] With your permission, the server collects the following data:

[1345] Web usage history: Collects user's web page browsing history through browser extensions.

[1346] App usage history: Collects usage history of applications installed on smartphones and PCs.

[1347] Data from wearable devices: Activity, heart rate, and sleep data are obtained from smartwatches via API.

[1348] The server also runs an emotion engine that analyzes the user's facial expressions, voice, and biometric data in real time to extract emotional patterns. This data is then fed into an emotion recognition model built using Python and TensorFlow. The input data is various user and emotional data, and the output is a detailed user profile. This profile is then stored in a database.

[1349] Step 3: Analyze your thinking and emotional patterns

[1350] The server periodically updates the user's profile based on the collected data. This profile includes lifestyle data, data from wearable devices, and emotional data. The server uses machine learning algorithms to analyze the user's thought and emotional patterns. For example, it analyzes the stress level felt in a particular situation, efficient working times, how to take rest, and emotional fluctuations. The input data is the collected user data and profile information, and the output is the analyzed thought and emotional patterns. Specific operations include data cleansing, feature extraction, and application of machine learning models.

[1351] Step 4: Generate improvement suggestions

[1352] The server generates optimal improvement suggestions for the user based on the analysis of thought patterns and emotional patterns. These suggestions are made using natural language generation (NLG) technology. For example, a Python-based NLG library is used to automatically generate specific improvement suggestions in text format. The input data are the analysis results and user profile information, and the output is the optimal improvement suggestions for the user. The generated improvement suggestions are aimed at managing stress, improving work efficiency, improving lifestyle habits, improving the quality of decision-making, and improving communication.

[1353] Step 5: Notification of improvement proposals

[1354] The server notifies the user's device of the generated improvement suggestions. The device then triggers the notification, displaying a pop-up or push notification to the user. This notification includes the specific content of the suggestion, how to implement it, and a timeline. The input data is the generated improvement suggestions, and the output is the notification sent to the user's device. This allows the user to follow specific guidance on how to put the suggestions into practice.

[1355] Through these processing steps, the system analyzes the user's thought patterns and emotional patterns and provides individually tailored improvement suggestions, thereby improving performance at work and in private life and reducing stress.

[1356] (Application example 2)

[1357] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] In modern logistics centers, the working environment is stressful, and employee stress and fatigue are serious issues that reduce work efficiency and safety. However, there is no system that can closely monitor the condition of each employee in real time and make appropriate improvement proposals. New technology is needed to simultaneously manage employee health and optimize work efficiency.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1360] In this invention, the server includes means for acquiring initial hearing information from the user and storing it in a database, means for collecting user lifestyle data and data from the wearable device and creating a user profile, means for analyzing the user's thought patterns based on the profile, means for generating improvement suggestions for each user based on the analysis results of the thought patterns, means for notifying the user's terminal of the improvement suggestions, and means for monitoring the activity data of workers at the logistics center in real time and recommending optimal work schedules and break timings, thereby optimizing both the health and work efficiency of employees at the logistics center.

[1361] "User" refers to a person who uses this system, and primarily refers to an employee of the logistics center.

[1362] "Initial hearing information" refers to basic information that is entered when a user first logs into the system, such as the user's name, age, occupation, stress level, and current lifestyle.

[1363] "Database" refers to an information management system for storing users' initial hearing information, collected lifestyle data, and data from wearable devices.

[1364] "Lifestyle data" refers to data related to a user's daily life, such as information collected from smartphones and web usage history.

[1365] A "wearable device" refers to a device worn by a user that can collect biometric information such as heart rate and activity level. An example of this is a smartwatch.

[1366] A "profile" refers to a data set that represents a user's behavioral, thought, and emotional patterns, created based on collected lifestyle data and data from wearable devices.

[1367] "Thinking patterns" are data that indicate the user's thinking tendencies and habits, and include stress levels in specific situations and efficient working times.

[1368] "Improvement suggestions" refer to recommendations regarding stress management, improving work efficiency, improving lifestyle habits, etc., that are generated based on the analysis of the user's thought patterns and emotional patterns.

[1369] "Terminal" refers to a device used by a user, such as a computer or smartphone, that can receive notifications of improvement suggestions.

[1370] A "logistics center" refers to a physical facility that manages logistics and products, and is the place where logistics operations are carried out.

[1371] "Activity data" is information about the user's physical activity, including the number of steps, distance traveled, and working hours.

[1372] "Real-time" refers to a state in which data is processed immediately after it is generated and the results are reflected.

[1373] "Work schedule" refers to the timetable and order of work that a user must perform at a logistics center.

[1374] "Rest timing" refers to the time for the user to take an appropriate rest.

[1375] "Server" refers to the central computer that processes and manages data for the entire system.

[1376] This invention is a system that collects activity data and emotion data of employees in a logistics center, monitors them in real time, and notifies them of optimal work schedules and break timings. Specific embodiments will be described below.

[1377] Obtaining initial hearing information

[1378] Employees (users) first log in to the system and enter initial information such as their name, age, occupation, stress level, and current lifestyle habits. This information is sent to the server via their device (smartphone or PC) and stored in a database. This initial information becomes the basis for creating the user's profile.

[1379] Data Collection and Profiling

[1380] With the user's permission, the server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). It also collects web usage history and app usage history. Furthermore, the server uses an emotion engine to analyze emotional data from the user's facial expressions and voice. Based on this data, a user profile is created.

[1381] Analysis of thought patterns and emotions

[1382] Using the profile data, the server analyzes the user's thought and emotional patterns. This analysis involves collecting lifestyle data, data from wearable devices, and emotional data. For example, it analyzes stress levels at specific times and in specific situations, and the most efficient working hours.

[1383] Generate improvement suggestions

[1384] The server generates optimal improvement suggestions for users based on the analysis of their thought patterns and emotional patterns. These improvement suggestions include stress management, improving work efficiency, and optimizing break timing. Specific examples of improvement suggestions for a logistics center include "encouraging short breaks every 30 minutes" and "stretching at a specific time in the afternoon."

[1385] Notification of improvement proposals

[1386] The generated improvement suggestions are notified to the user via the device, for example, a notification message is sent to a smartwatch or smartphone, allowing the user to check the suggestions and implement them.

[1387] Specific examples

[1388] Specifically, if a user's stress level is measured as high while working at a logistics center, the server analyzes the situation and generates an improvement suggestion such as "take a short break every 30 minutes." This suggestion is notified to the user via their smartwatch, allowing them to take a break at an appropriate time.

[1389] Example of input prompt for generative AI model

[1390] "Create a notification message that suggests the best time to take a break based on the user's stress level and activity level."

[1391] This will enable the optimization of both the health and work efficiency of employees at logistics centers.

[1392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1393] Step 1:

[1394] Users log in to the system using a device (smartphone or PC) and enter initial interview information. This information includes name, age, occupation, stress level, current lifestyle habits, etc. The device sends this data to the server, which stores the received information in a database and creates an initial profile for each user.

[1395] Input: Name, age, occupation, stress level, lifestyle

[1396] Output: Initial hearing information and initial profile stored in a database

[1397] Step 2:

[1398] The server collects the user's activity level and heart rate in real time from a wearable device (e.g., a smartwatch). With the user's permission, it also collects their web and app usage history. This data is used to analyze the user's behavioral patterns and physical condition in detail.

[1399] Input: Activity data from wearable devices, heart rate data, web usage history, app usage history

[1400] Output: User profile update data

[1401] Step 3:

[1402] The server uses an emotion engine to analyze the user's emotions from the collected facial and voice data. The emotion data is used to evaluate the situations in which the user is likely to feel stressed, the time periods in which their emotions become unstable, and so on.

[1403] Input: facial expression data, voice data

[1404] Output: Emotion pattern data

[1405] Step 4:

[1406] The server creates a detailed profile of the user by combining collected lifestyle data, activity data, heart rate data, web usage history, app usage history, emotional patterns, etc. This profile includes the user's behavioral patterns, thought patterns, and emotional patterns. The server uses this data to analyze the user's thought patterns.

[1407] Input: Various collected data

[1408] Output: Detailed user profile

[1409] Step 5:

[1410] The server uses a generative AI model to generate optimal improvement proposals for each user based on a detailed user profile and various data, including specific action plans for improving work efficiency and stress management.

[1411] Input: User profile, thought pattern data, emotion pattern data

[1412] Output: Improvement suggestions

[1413] Step 6:

[1414] Once an improvement suggestion is generated, the server notifies the user's device. For example, a notification such as "Take a break in the next 30 minutes" is sent to a smartwatch. The user can then take appropriate action based on this.

[1415] Input: Improvement suggestion

[1416] Output: Notification message to terminal

[1417] Through the above processing steps, logistics center employees can achieve real-time health management and optimize work efficiency.

[1418] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1419] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1420] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1421] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1422] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1423] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1424] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1425] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1426] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1427] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1428] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1429] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1430] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1431] 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.

[1432] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1433] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1434] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1435] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1436] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1437] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1438] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1439] The following is further disclosed regarding the above embodiment.

[1440] (Claim 1)

[1441] means for acquiring and storing initial hearing information of a user in a database;

[1442] A means for collecting user life data and data from a wearable device to create a user profile;

[1443] means for analyzing the user's thought patterns based on the profile;

[1444] means for generating improvement proposals for each user based on the analysis results of the thought patterns;

[1445] means for notifying a user terminal of the improvement proposal;

[1446] A system including:

[1447] (Claim 2)

[1448] 2. The system according to claim 1, wherein the collected data includes the user's web usage history, app usage history, and activity level and heart rate from a wearable device.

[1449] (Claim 3)

[1450] 2. The system of claim 1, wherein the improvement suggestions include stress management, improving work efficiency, improving lifestyle habits, improving decision-making quality, and improving communication.

[1451] "Example 1"

[1452] (Claim 1)

[1453] means for acquiring and storing initial hearing information of a user in a database;

[1454] A means for collecting user life data and data from a wearable device to create a user profile;

[1455] means for analyzing the user's thought patterns based on the profile;

[1456] A means using a generative AI model to generate improvement proposals for each user based on the analysis results of the thought patterns;

[1457] means for notifying a user terminal of the improvement proposal;

[1458] A system including:

[1459] (Claim 2)

[1460] 2. The system according to claim 1, wherein the collected data includes the user's web usage history, app usage history, and activity level and heart rate from a wearable device.

[1461] (Claim 3)

[1462] 2. The system of claim 1, wherein the improvement suggestions include stress management, improving work efficiency, improving lifestyle habits, improving decision-making quality, and improving communication.

[1463] "Application Example 1"

[1464] (Claim 1)

[1465] means for acquiring and storing initial hearing information of a user in a database;

[1466] A means for collecting user life data and data from a wearable device to create a user profile;

[1467] means for analyzing the user's thought patterns based on the profile;

[1468] means for generating improvement proposals for each user based on the analysis results of the thought patterns;

[1469] means for notifying the user of the improvement suggestions on a display device to provide visual guidance;

[1470] A system including:

[1471] (Claim 2)

[1472] 2. The system according to claim 1, wherein the collected data includes the user's web usage history, app usage history, and activity level and heart rate from a wearable device.

[1473] (Claim 3)

[1474] 2. The system of claim 1, wherein the improvement suggestions include stress management, improving work efficiency, improving lifestyle habits, improving decision-making quality, and improving communication.

[1475] (Claim 4)

[1476] 10. The system of claim 1, wherein smart glasses are used as the user's display device.

[1477] (Claim 5)

[1478] The system described in claim 1, characterized in that it uses a generative AI model to analyze the user's thought patterns from their body surface signals and behavioral history, and generates improvement suggestions based on prompt sentences.

[1479] "Example 2: Combining Emotion Engines"

[1480] (Claim 1)

[1481] means for acquiring and storing initial hearing information of a user in a database;

[1482] A means for collecting user life data and data from a wearable device to create a user profile;

[1483] means for analyzing the user's thought patterns and emotion patterns based on the profile;

[1484] means for generating improvement suggestions for each user based on the analysis results of the thought patterns and emotion patterns;

[1485] means for notifying a user terminal of the improvement proposal;

[1486] A system including:

[1487] (Claim 2)

[1488] 2. The system of claim 1, wherein the collected data includes the user's web usage history, app usage history, activity level, heart rate, and sleep data from a wearable device.

[1489] (Claim 3)

[1490] 2. The system of claim 1, wherein the improvement suggestions include stress management, improving work efficiency, improving lifestyle habits, improving decision-making quality, and improving communication.

[1491] (Claim 4)

[1492] 10. The system of claim 1, further comprising an emotion engine for analyzing emotions from the user's facial expressions and voice.

[1493] (Claim 5)

[1494] 2. The system according to claim 1, wherein natural language generation technology is used to generate improvement suggestions.

[1495] (Claim 6)

[1496] 10. The system of claim 1, wherein machine learning algorithms are used to collect and analyze data.

[1497] "Application example 2 when combining emotion engines"

[1498] (Claim 1)

[1499] means for acquiring and storing initial hearing information of a user in a database;

[1500] A means for collecting user life data and data from a wearable device to create a user profile;

[1501] means for analyzing the user's thought patterns based on the profile;

[1502] means for generating improvement proposals for each user based on the analysis results of the thought patterns;

[1503] means for notifying a user terminal of the improvement proposal;

[1504] A method for monitoring worker activity data in logistics centers in real time and recommending optimal work schedules and break timings.

[1505] A system including:

[1506] (Claim 2)

[1507] 2. The system according to claim 1, wherein the collected data includes the user's web usage history, app usage history, and activity level and heart rate from a wearable device.

[1508] (Claim 3)

[1509] 2. The system of claim 1, wherein the improvement suggestions include stress management, improving work efficiency, improving lifestyle habits, improving decision-making quality, and improving communication. [Explanation of symbols]

[1510] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for acquiring and storing initial hearing information of a user in a database; A means for collecting user life data and data from a wearable device to create a user profile; means for analyzing the user's thought patterns based on the profile; means for generating improvement proposals for each user based on the analysis results of the thought patterns; means for notifying a user terminal of the improvement proposal; A system including:

2. The system according to claim 1, wherein the collected data includes the user's web usage history, app usage history, and activity level and heart rate from a wearable device.

3. 2. The system of claim 1, wherein the improvement suggestions include stress management, improving work efficiency, improving lifestyle habits, improving decision-making quality, and improving communication.

Images