system

Abstract

Provide a system. [Solution] A means for collecting personal data input by a user; means for storing said personal data in a database; means for analyzing the personal data and identifying user behavior patterns; A means for generating future action plans based on the action patterns using a generation AI; means for providing the activity schedule to a user; A system including:

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] Conventional activity schedule generation systems have difficulty reflecting users' hobbies, preferences, and activity history, resulting in often inaccurate suggestions. Furthermore, the technological means for generating personalized activity schedules are underdeveloped, making it difficult to provide information that is useful to users. This has led to the issue of users finding it difficult to create activity plans based on their own interests. [Means for solving the problem]

[0005] To solve this problem, the present invention employs the following configuration: A system is provided that includes means for collecting personal data input by a user, means for saving the personal data in a database, means for analyzing the personal data and identifying the user's behavioral patterns, means for generating a future activity schedule based on the behavioral patterns using a generation AI, and means for providing the activity schedule to the user. According to the present invention, a personalized activity schedule based on the user's hobbies, preferences, and behavioral history can be generated, and useful information for the user can be provided.

[0006] "User" refers to an individual or organization that uses the System.

[0007] "Personal data" refers to individual information such as a user's hobbies, preferences, behavioral history, purchasing history, and family composition.

[0008] A "database" refers to a collection of information that systematically stores personal data and allows it to be later searched and analyzed.

[0009] "Analysis" refers to the process of breaking down data to make it easier to handle and extracting patterns and trends.

[0010] "Behavioral patterns" refer to specific behavioral tendencies based on a user's past behavioral data.

[0011] "Generative AI" refers to an algorithm or system that uses artificial intelligence techniques to process data and generate a specific output (in this case, a course of action).

[0012] "Big data" refers to a large, diverse, and rapidly generated data set, and refers to the entire group of data that can be analyzed to gain advanced insights.

[0013] "Planned actions" refers to a future action plan recommended based on the user's hobbies, tastes, and behavioral patterns.

[0014] "Providing" refers to the process of showing, notifying, or sharing the generated action plan with the user. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system that uses AI to generate future schedules based on a user's personal data and provides them to the user. Specifically, the system collects data from the user's device, analyzes the data and generates schedules on a server, and provides the generated schedules to the user.

[0037] System configuration

[0038] This system consists of the following elements:

[0039] 1. Collection of personal data

[0040] Users enter personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application.

[0041] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[0042] 2. Data storage

[0043] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[0044] 3. Data Analysis

[0045] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[0046] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[0047] 4. Generate action schedule

[0048] The server uses a generation AI based on the analysis results to generate a future schedule of activities while referencing Big Data. The generation AI performs statistical analysis and proposes the optimal schedule for the user.

[0049] For example, if a user is interested in sports, the AI ​​will look up sporting events taking place next Monday and create an action plan to watch that event.

[0050] 5. Providing a timeline of actions

[0051] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[0052] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[0053] Specific examples

[0054] For example, suppose user A inputs data that "watching sports is a hobby, and in the past, he has purchased tickets to baseball and soccer games."

[0055] 1. User data collection

[0056] The user inputs into the application, "Watching sports is my hobby" and "I purchase tickets for baseball games and soccer games."

[0057] The device sends this data to the server in JSON format: { "hobbies": ["Sports Games"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"]}

[0058] 2. Data storage

[0059] The server stores the received data in the database, for example, in the format INSERT INTO users (hobbies, purchase_history) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets').

[0060] 3. Data Analysis

[0061] The server analyzes the data through daily batch processing, and uses Python scripts to analyze user behavior patterns and determine whether users are interested in "watching sports."

[0062] 4. Generate action schedule

[0063] The server inputs the data into the generation AI based on the analysis results, and generates a future schedule by referencing Big Data. For example, suppose there is a professional baseball game taking place next Monday, and this is used as the schedule.

[0064] 5. Providing a timeline of actions

[0065] The server sends the generated action plan to the user's device in JSON format: { "action": "Watch the game", "date": "Next Monday", "detail": "Professional baseball game"}

[0066] The device displays the received data in a calendar app or notification system, allowing the user to check their schedule for "watching a professional baseball game next Monday."

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] Using a dedicated application, the user inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. After completing the input, the user presses the "Send" button.

[0070] Step 2:

[0071] The device serializes the personal data entered by the user into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0072] Step 3:

[0073] The server decodes the received JSON-formatted personal data and maps it to the appropriate fields in the database, then stores the personal data in storage using a database engine (e.g., MySQL (registered trademark) or MongoDB).

[0074] Step 4:

[0075] The server analyzes the stored personal data through daily batch processing using Python scripts and SQL queries to extract user preferences and behavioral patterns. For example, machine learning clustering and classification algorithms are used to analyze the data and identify preference patterns.

[0076] Step 5:

[0077] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the pre-processed user data with Big Data and performs statistical analysis and pattern matching. The generation AI generates a future action plan based on the user's interests.

[0078] Step 6:

[0079] The server saves the generated future schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[0080] Step 7:

[0081] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[0082] Step 8:

[0083] The device decodes the received JSON data of the planned events and displays it in the calendar app or notification system. Specifically, it renders the planned events information into UI components within the app and displays them visually to the user.

[0084] Step 9:

[0085] Users can review the proposed action plans and accept, modify, or delete them as needed, allowing users to easily manage their personalized future action plans.

[0086] Example 1

[0087] 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."

[0088] In modern society, it is becoming increasingly important to support users' busy lives by efficiently generating personalized itineraries. However, systems that can automatically generate and appropriately provide accurate itineraries based on users' preferences and behavioral history are still insufficient. Furthermore, there is a need for methods to improve user convenience while ensuring data security and privacy.

[0089] 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.

[0090] In this invention, the server includes means for collecting personal data input by the user, means for saving the personal data in a database, means for encrypting and transmitting the personal data, means for inputting the data to the generation AI based on the analysis results, and means for decrypting the action plan and displaying it to the user. This makes it possible to appropriately generate and safely provide a personalized action plan for the user, thereby improving convenience.

[0091] "Personal data" refers to data entered by the user regarding hobbies, preferences, behavioral history, purchasing history, family structure, and the like.

[0092] A "database" is an information management system that allows a server to store personal data.

[0093] "Behavioral patterns" refer to the tendencies of a user's behavior, hobbies, and preferences that the server obtains by analyzing personal data.

[0094] "Generative AI" is a general term for algorithms and models used for prediction and generation, and is used to generate user action plans.

[0095] An "action plan" is a future activity plan suggested by the generation AI based on the user's behavioral patterns.

[0096] "Encryption" is a technique used to securely transmit data by converting the data into a form different from its original form.

[0097] "Decryption" is the process of returning encrypted data to its original form.

[0098] The present invention relates to a system that uses AI to generate future activity plans based on a user's personal data and provides them to the user. The system collects and analyzes personal data entered by the user and proposes an activity plan based on the results. Detailed embodiments are described below.

[0099] First, the user uses a dedicated application to enter personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. The data entered by the user is formatted in JSON format by the device, encrypted using the RSA encryption algorithm, and then sent to the server.

[0100] The server then decrypts the encrypted personal data it receives and stores it in a database using MySQL or PostgreSQL, mapping the personal data to appropriate fields for easy analysis.

[0101] The server then periodically analyzes the personal data in the database using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). The analysis results in identifying user behavior patterns and saving the behavioral model as a behavior pattern in JSON format.

[0102] Based on the analyzed behavioral patterns, the server uses a generation AI (e.g., OpenAI® GPT-3®) to generate a future action plan while referencing Big Data. Specific prompts are provided to the generation AI, allowing it to appropriately generate an action plan for the user.

[0103] As a concrete example, if a user inputs the data that "Watching sports is a hobby and has purchased tickets to baseball and soccer games in the past," the following prompt sentence is input to the generative AI model: "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an action plan."

[0104] The generated schedule is again encrypted in JSON format and sent to the user's device, where it is decrypted and displayed to the user via a calendar app or notification system (e.g., Google® Calendar API, iOS Notification Center).

[0105] This allows the user to check their schedule for watching a professional baseball game next Monday. In this way, a personalized activity schedule for the user is efficiently generated and provided.

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

[0107] Step 1:

[0108] The user enters personal data into a dedicated application. The entered data includes hobbies, preferences, behavioral history, purchasing history, family composition, etc. This data is entered into the application's form and formatted in JSON format. An example of entered data is the following JSON format:

[0109] json

[0110] {

[0111] "hobbies": ["watching sports"],

[0112] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[0113] "family": ["The whole family is a sports fan"]

[0114] }

[0115] The terminal encrypts this JSON data using the RSA encryption algorithm and then sends it to the server.

[0116] Step 2:

[0117] The server receives the encrypted personal data and decrypts it using the RSA algorithm. The decrypted data is then stored in a database, typically using MySQL or PostgreSQL. Specifically, the data is mapped to the appropriate fields and stored using the following SQL statement:

[0118] sql

[0119] INSERT INTO users (hobbies, purchase_history, family)

[0120] VALUES ('Watching sports', 'Baseball game tickets, Football game tickets', 'The whole family is a sports fan');

[0121] The input here is the decoded JSON data, and the output is the person data inserted into the database.

[0122] Step 3:

[0123] The server periodically analyzes the personal data in the database. This analysis is performed using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). As a result of the analysis, behavioral patterns of individual users are identified and a behavioral model is saved as a behavioral pattern in JSON format. Specific operations include reading from the database, analyzing using machine learning algorithms, and saving the analysis results. The input is the personal data read from the database, and the output is a model based on the behavioral patterns.

[0124] Step 4:

[0125] Based on the analysis results, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, which then generates a future action plan. For example, if a user enters data such as "Watching sports is my hobby, and I have purchased tickets to baseball and soccer games in the past," the following prompts are input into the generation AI model:

[0126] "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an activity schedule."

[0127] The generated action schedule is saved in JSON format. The input is the result of the action pattern analysis, and the output is the generated action schedule.

[0128] Step 5:

[0129] The server encrypts the generated schedule in JSON format and sends it to the user's device. An example of a generated schedule is the following JSON output:

[0130] json

[0131] {

[0132] "action": "spectate",

[0133] "date": "next Monday",

[0134] "detail": "Professional baseball game"

[0135] }

[0136] The device receives this encrypted data, decrypts it using the RSA algorithm, and displays the decrypted event to the user through a calendar app or notification system. The input is the encrypted event data, and the output is the decrypted event.

[0137] This allows the user to check their plans to watch a professional baseball game next Monday.

[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 conventional logistics centers, robot operations require time-consuming setup of individual schedules by managers, making it difficult to allocate work efficiently. Additionally, there was a lack of data analysis and automatic generation mechanisms required to maximize the robot's performance, making it difficult to improve overall operational efficiency.

[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 collecting personal data input by users, means for saving the personal data in a database, means for analyzing the personal data and identifying the user's behavioral patterns, means for generating future action plans using a generation AI, and means for providing the action plans to robots in the logistics center. This makes it possible to improve the work efficiency of the robots in the logistics center, reduce the burden on managers, and optimize overall work efficiency.

[0143] "User" refers to the entity that uses the system and is the person to whom personal data is provided.

[0144] "Personal data" refers to information such as a user's behavioral history, hobbies and preferences, and purchasing history.

[0145] "Database" means a data management system that stores collected personal data and makes it accessible when needed.

[0146] "Behavioral patterns" refer to a tendency for a user to take certain actions based on analyzed personal data.

[0147] "Generative AI" refers to technology that uses artificial intelligence to generate new information and predictions based on input data.

[0148] A "future action plan" is an action plan for a specific date and time in the future that is created by the generation AI based on the user's behavior patterns.

[0149] A "logistics center" is a facility where goods and materials are managed, picked, packed, and shipped.

[0150] A "robot" is a piece of equipment that performs work automatically within a logistics center and operates based on a schedule.

[0151] A "machine learning algorithm" is an algorithm used in data analysis, a method for automatically learning from empirical data and identifying patterns.

[0152] "Big data" refers to a large and diverse set of data, a collection of data that can be used for analysis.

[0153] This invention relates to a system that uses AI to generate future action plans based on a user's personal data and provides them to a robot at a logistics center. Specifically, the system collects data from the user's terminal, analyzes the data and generates an action plan on the server, and then provides the generated action plan to the robot.

[0154] System configuration

[0155] This system consists of the following elements:

[0156] 1. Collection of personal data

[0157] Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application.

[0158] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[0159] 2. Data storage

[0160] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[0161] 3. Data Analysis

[0162] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[0163] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[0164] 4. Generate action schedule

[0165] The server uses a generation AI based on the analysis results to generate a future action plan while referencing big data. The generation AI performs statistical analysis and proposes the optimal action plan for the user.

[0166] For example, when generating a robot's activity schedule for the next week at a logistics center, if past data shows that it will be performing picking, packing, and shipping assistance, the system will create an activity schedule that takes into account the priority of those tasks.

[0167] 5. Providing a timeline of actions

[0168] The server provides the robot's terminal with the generated action plan in JSON format, which contains the information necessary for a specific robot in the logistics center to operate efficiently.

[0169] The terminal receives the action plan and instructs the robot on its actions based on the action plan, allowing the robot to perform its work efficiently on the specified date.

[0170] For example, if a manager predicts that "the volume of picking work will be high this week," the system will automatically adjust the robot's schedule for the next week based on past data and big data, generating a detailed schedule such as "8 hours of picking on Monday," "6 hours of picking and 2 hours of packing on Tuesday," etc. During this process, the following prompt sentences are input into the generative AI model.

[0171] Example prompt sentence:

[0172] "Please generate a schedule for the robot's activities in the distribution center for the next week. According to past data, it is currently performing the tasks of picking, packing, and shipping assistance. The priority of each task is as follows: picking: high, packing: medium, shipping assistance: low. Please generate the most efficient schedule based on this."

[0173] This enables the system to achieve efficient operation of robots in logistics centers, reduce the burden on managers, and optimize work efficiency.

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

[0175] Step 1:

[0176] Users enter personal data such as their hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application. The data entered here specifically includes "type of work," "frequency of work," and "work evaluation score." This data is formatted in JSON format.

[0177] Step 2:

[0178] The terminal sends the data entered by the user in JSON format to the server. At this time, the data is encrypted using an encryption algorithm such as AES. For example, if the input data is {"tasks": ["Picking"], "frequency": [5], "score": [4.5]}, it will be sent to the server in encrypted form.

[0179] Step 3:

[0180] The server stores the received personal data in a database. Here, it parses the JSON format data and maps it appropriately to each field. For example, the database stores "picking" in the tasks field, "5" in the frequency field, and "4.5" in the score field.

[0181] Step 4:

[0182] The server periodically analyzes the personal data in the database. This analysis is performed using scripts such as Python and machine learning algorithms (e.g., KMeans clustering). The input data is all the robot data in the database, and the output is clusters that represent the robot's behavioral patterns.

[0183] Step 5:

[0184] The server inputs data into a generative AI model based on the analysis results, and generates future action plans while referencing big data. At this time, a specific prompt is input into the generative AI. For example, the prompt might be, "Please generate an action plan for the robots at the logistics center for the next week. According to past data, they are performing picking, packing, and shipping assistance." The output of this process is a detailed action plan for the next week.

[0185] Step 6:

[0186] The server provides the generated action schedule to the robot terminal in JSON format. Here, the action schedule is sent in the format {"date": "2023-10-01", "task": "picking", "duration": "8 hours"}, for example.

[0187] Step 7:

[0188] The terminal receives the action plan and instructs the robot on its actions based on that plan. The robot then follows this plan and performs specific actions, such as "picking" for "8 hours" on the specified date.

[0189] 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.

[0190] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[0191] System configuration

[0192] This system consists of the following elements:

[0193] 1. Collection of personal and emotional data

[0194] Users input personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application. In addition, the user's emotional data is acquired through the device's built-in camera and microphone.

[0195] The device sends the personal data and emotion data entered by the user to the server in JSON format, encrypted before transmission.

[0196] 2. Data storage

[0197] The server stores the received personal and emotional data in a database, where it is mapped to appropriate fields for easy later analysis.

[0198] 3. Data and Sentiment Analysis

[0199] The server periodically analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using machine learning algorithms, such as clustering and classification algorithms.

[0200] The emotion engine analyzes the user's emotional data in real time to identify their current emotional state, which is also used for behavioral pattern analysis.

[0201] 4. Generate action schedule

[0202] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and current emotional state.

[0203] For example, if a user is tired and in need of relaxation, the AI ​​will suggest relaxing events and activities as part of their agenda.

[0204] 5. Providing a timeline of actions

[0205] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[0206] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[0207] Specific examples

[0208] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is acquired, the flow is as follows.

[0209] 1. User data collection

[0210] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[0211] The device sends this data to the server in JSON format: { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"}

[0212] 2. Data storage

[0213] The server stores the received data in a database, for example, in the format INSERT INTO users (hobbies, purchase_history, emotion) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[0214] 3. Data and Sentiment Analysis

[0215] The server analyzes the data through daily batch processing. Using Python scripts, it analyzes the user's behavioral patterns and determines whether they are interested in "watching sports." At the same time, the emotion engine detects "stress" and reports their current emotional state.

[0216] 4. Generate action schedule

[0217] The server inputs the data into the generation AI based on the analysis results, which then suggests relaxing events (such as relaxation spots or concerts) based on the emotional data.

[0218] 5. Providing a timeline of actions

[0219] The server sends the generated action plan in JSON format to the user's device: { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}

[0220] The device displays the received data in its calendar app or notification system, allowing the user to see their "Spa & Relax This Weekend" appointments.

[0221] In this way, the system can provide a personalized future itinerary that takes into account the user's emotional state.

[0222] The processing flow will be explained below.

[0223] Step 1:

[0224] Using a dedicated application, users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected through the device's built-in camera and microphone.

[0225] Step 2:

[0226] The device serializes the personal data entered by the user and the collected emotional data into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0227] Step 3:

[0228] The server decodes the received JSON-formatted personal data and emotion data and maps them to appropriate fields in a database. For example, personal data is stored in a user table, and emotion data is stored in an emotion table.

[0229] Step 4:

[0230] The server analyzes the stored personal data and emotional data through daily batch processing to identify users' behavioral patterns and emotional states. Machine learning algorithms, especially clustering and classification algorithms, are used to classify the data and extract patterns.

[0231] Step 5:

[0232] The emotion engine analyzes the acquired emotion data to identify the user's current emotional state, identifying emotion categories (e.g., stress, joy, sadness, etc.), and integrating this information into behavioral pattern analysis.

[0233] Step 6:

[0234] The server inputs data into the generation AI based on the analysis results. The generation AI integrates preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and emotional state.

[0235] Step 7:

[0236] The server saves the generated schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[0237] Step 8:

[0238] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[0239] Step 9:

[0240] The device decodes the received JSON data of the scheduled events and displays the scheduled events in the calendar app or notification system. Specifically, the scheduled events information is rendered in the UI components within the app and displayed visually to the user.

[0241] Step 10:

[0242] Users can review the proposed action plan and accept, modify, or delete it as needed, allowing them to easily manage a personalized future action plan that takes their emotional state into account.

[0243] Example 2

[0244] 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."

[0245] Conventional systems can generate activity plans based on a user's personal data, but they have limitations in providing activity plans that reflect the user's real-time emotional state. Furthermore, it is difficult to provide personalized suggestions that effectively utilize external big data. This makes it impossible to propose optimal activity plans that reflect the user's emotional state, which poses a challenge in sufficiently improving user satisfaction.

[0246] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting personal data and emotional data input by the user; means for saving the personal data and emotional data in a database; means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state; means including an emotion engine for analyzing the emotional data in real time; means for generating a future action plan using a generation AI based on the behavioral patterns and emotional state; means for the generation AI to integrate the preprocessed personal data, emotional data, and external data and perform statistical analysis and pattern matching; means for providing the action plan to the user's terminal; and means for displaying the action plan on the user's terminal. This makes it possible to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on the analysis.

[0247] "Personal data entered by the user" refers to information such as hobbies, preferences, behavioral history, purchasing history, and family composition that the user himself / herself enters through a dedicated application.

[0248] "Emotional data" refers to information about a user's emotional state acquired through a camera or microphone built into the user's device.

[0249] "Database" refers to an information system for storing and managing collected and saved personal data and emotional data.

[0250] "Behavioral patterns" refer to unique behavioral tendencies and patterns that are analyzed based on a user's past behavioral history and hobbies and preferences.

[0251] "Emotion engine" refers to software or a system that analyzes a user's emotional data in real time to identify the user's current emotional state.

[0252] "Generative AI" refers to an artificial intelligence model that takes a user's personal data and emotional data as input and generates future action plans based on that data.

[0253] "Preprocessing" refers to a series of operations that format and convert input data so that it can be easily processed by analytical or generative AI.

[0254] "Statistical analysis" refers to a set of techniques for analyzing data using statistical methods to understand the characteristics and patterns of the data.

[0255] "Pattern matching" refers to algorithms and techniques for detecting and identifying specific patterns or templates within data.

[0256] "Action Plan" refers to future action plans or events suggested by the generative AI, taking into account the user's hobbies, preferences, and emotional state.

[0257] "Terminal" refers to a device used by a user (such as a smartphone or tablet) that is a computer system used to input personal data and emotional data, display planned activities, etc.

[0258] "External data" refers to big data and reference data provided by third parties other than users' personal data and emotional data.

[0259] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[0260] System configuration

[0261] The system consists of the following elements:

[0262] 1. Collection of personal and emotional data

[0263] Users enter personal data (hobbies, preferences, behavioral history, purchasing history, family composition, etc.) through a dedicated application, and emotional data is recorded using the device's camera and microphone.

[0264] The terminal converts this data into JSON format, encrypts it, and sends it to the server.

[0265] 2. Data storage

[0266] The server receives the encrypted JSON data, decrypts it, and stores it in a database, where it is properly mapped to personal data and emotional data.

[0267] 3. Data and Sentiment Analysis

[0268] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[0269] The emotion engine analyzes the user's emotion data in real time to identify their current emotional state.

[0270] 4. Generate action schedule

[0271] The server inputs data into the generative AI model based on the pre-processed personal data and emotion data, which then performs statistical analysis and pattern matching to generate an optimal action plan.

[0272] 5. Providing a timeline of actions

[0273] The server sends the generated action plan in JSON format to the user's device.

[0274] The device displays the received schedule to the user through a calendar app or notification system.

[0275] Specific examples

[0276] For example, consider a case where user A inputs data that "watching sports is a hobby, and has purchased tickets to baseball and soccer games in the past," and is currently feeling stressed.

[0277] 1. User data collection

[0278] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[0279] The device converts this data into JSON format, encrypts it, and sends it to the server:

[0280] json

[0281] {

[0282] "user_id": "12345",

[0283] "hobbies": ["watching sports"],

[0284] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[0285] "emotion": "stress"

[0286] }

[0287] 2. Data storage

[0288] The server interprets the data and stores it in the database, for example, by executing the following SQL statement: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[0289] 3. Data and Sentiment Analysis

[0290] The server analyzes the data in the database and identifies the user's behavior pattern of "watching sports." At the same time, the emotion engine detects stress and notifies the server of the results.

[0291] 4. Generate action schedule

[0292] The server inputs data into the generation AI based on the analysis results, and the generation AI suggests relaxation events (e.g., spa & relaxation).

[0293] 5. Providing a timeline of actions

[0294] The server sends the generated schedule to the user's device in JSON format:

[0295] json

[0296] {

[0297] "action": "relaxation",

[0298] "date": "this weekend",

[0299] "detail": "Spa & Relax"

[0300] }

[0301] The device displays the received data in its calendar app or notification system, allowing the user to check their "Spa & Relax This Weekend" schedule.

[0302] Prompt Sentence Examples

[0303] "If User A enjoys watching sports and has been feeling stressed lately, please suggest some relaxing activities."

[0304] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0305] Step 1: Data collection

[0306] The user opens a dedicated application and inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. Emotional data is also recorded using the device's camera and microphone.

[0307] Input: User input of personal and emotional data.

[0308] Output: Personal data and emotion data converted by the device into JSON format.

[0309] Specific operation: The user enters information such as "watching sports," "baseball game tickets, soccer game tickets," and "stress," and the device compiles this in JSON format.

[0310] Step 2: Send data

[0311] The device converts the personal data and emotional data entered into JSON format, encrypts it, and sends it to the server.

[0312] Input: Personal and sentiment data in JSON format.

[0313] Output: Encrypted JSON data.

[0314] Specific operation: The device uses the RSA encryption algorithm to encrypt the JSON data { "user_id": "12345", "hobbies": ["Watching Sports"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"], "emotion": "Stress"} and sends it to the server.

[0315] Step 3: Save your data

[0316] The server decodes the received JSON data and stores it in the database.

[0317] Input: Encrypted JSON data.

[0318] Output: Personal and emotional data stored in a database.

[0319] What happens: The server performs RSA decryption and stores the decrypted data in the database using an SQL query, e.g.: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Tickets', 'Baseball Tickets, Football Tickets', 'Stress').

[0320] Step 4: Analyzing the data and sentiment data

[0321] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[0322] Input: Personal and emotional data stored in a database.

[0323] Output: Analysis of the user's behavioral patterns and emotional state.

[0324] Specific operation: A Python script is used to apply a clustering algorithm to the acquired data to identify the behavioral pattern of "interested in watching sports." The emotion engine detects "stress" and reports it to the server.

[0325] Step 5: Generate an action plan

[0326] Based on the analysis results, the server inputs the data into a generated AI model, performs statistical analysis and pattern matching, and generates an optimal action plan.

[0327] Input: Analysis results of behavioral patterns and emotional states.

[0328] Output: Action plan generated by the generation AI.

[0329] Specific operation: The generating AI is input with data on "hobby of watching sports" and "stress level," and while referring to external data, suggests relaxation activities (e.g., spa and relaxation events).

[0330] Step 6: Provide an action plan

[0331] The server sends the generated action plan in JSON format to the user's device.

[0332] Input: The generated event schedule data.

[0333] Output: JSON formatted event schedule sent to the user's device.

[0334] Specific operation: The server converts the generated action plan into JSON format, encrypts the data { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}, and sends it to the device.

[0335] Step 7: View upcoming events

[0336] The device decodes the scheduled events it receives and displays them to the user through a calendar app or notification system.

[0337] Input: JSON formatted event schedule sent from the server.

[0338] Output: The upcoming event displayed in the user's calendar app or notification system.

[0339] Specific behavior: The device decodes and interprets the received JSON data, adds an event for "Spa & Relax This Weekend" to the calendar app, and notifies the user via the notification system.

[0340] This allows the system to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on that.

[0341] (Application example 2)

[0342] 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."

[0343] In recent years, there has been a growing demand for individually customized services that take into account users' behavioral patterns and emotional states. However, existing systems are unable to fully utilize users' emotional data, making it difficult to provide appropriate security advice based on the user's current emotions and future plans. This has prevented efficient security management from being realized to enhance user safety. This issue is particularly pronounced in real-time security management using wearable devices such as smart glasses.

[0344] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data and emotional data input by the user, means for saving the personal data and emotional data in a database, means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state, means for generating a future action plan and security advice using a generative AI model based on the behavioral patterns and emotional state, and means for providing the action plan and security advice to the user. This enables real-time security management that reflects the user's emotional state.

[0345] "Personal data" refers to personal information such as a user's hobbies, preferences, behavioral history, purchasing history, and family composition.

[0346] "Emotional data" refers to information that indicates the user's current emotional state and is collected via a camera or microphone.

[0347] "Database" refers to a system for storing collected personal and emotional data.

[0348] "Behavioral patterns" refer to certain regularities or tendencies that are found as a result of analyzing a user's past behavioral history.

[0349] "Emotional state" refers to a user's current emotional or psychological state.

[0350] A "generative AI model" refers to an artificial intelligence model that generates optimal action plans and security advice for users based on the results of data analysis.

[0351] "Future action plan" refers to an action plan for a future date that is generated based on the user's current emotional state and behavioral patterns.

[0352] "Security advice" refers to suggestions for avoiding potential future risks and dangers based on the user's emotional state and behavioral patterns.

[0353] "Collection means" refers to a device or method for collecting personal data and emotional data of a user.

[0354] "Storage means" refers to the device or method for recording collected data in a database.

[0355] "Analysis means" refers to devices and methods for analyzing collected data and identifying user behavioral patterns and emotional states.

[0356] "Providing means" refers to a device or method for notifying the user of the generated action plan and security advice.

[0357] 1. System Program

[0358] This invention provides a system that collects personal data and emotional data of users, stores them in a database, and analyzes the data to identify the user's behavioral patterns and emotional state. Based on the identified behavioral patterns and emotional state, the system uses a generative AI model to generate future action plans and security advice, which are then provided to the user.

[0359] 2. Hardware and software used

[0360] The system is implemented using the following hardware and software:

[0361] Hardware: Smart glasses (with built-in camera and microphone)

[0362] Software: Python, REST API, JSON, Server

[0363] The server provides a dedicated application to collect personal and emotional data from each user. Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through this dedicated application. Furthermore, emotional data is collected using the camera and microphone in the smart glasses.

[0364] The device then converts the collected personal and emotional data into JSON format and sends it to the server, which stores it in a database.

[0365] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. This analysis is performed using machine learning algorithms, such as clustering and classification algorithms. The emotion engine analyzes the emotional data in real time to identify the user's current emotional state. This information is also used for behavioral pattern analysis.

[0366] Based on the analysis results, the server inputs the data into a generative AI model, which performs statistical analysis and pattern matching using preprocessed personal data, emotional data, and Big Data. The generative AI model generates optimal action plans and security advice taking into account the user's preferences and current emotional state.

[0367] Finally, the server provides the generated schedule and security advice to the user's device, which displays them in a JSON format via a calendar app or notification system.

[0368] 3. Specific Examples

[0369] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is obtained, the generative AI model will generate an itinerary for relaxing events (e.g., relaxation spots and concerts) and security advice.

[0370] An example prompt is:

[0371] Based on the user's hobbies, past behavioral history, and current emotional data, we suggest risks and avoidance actions for the next day. The current emotion is "anxiety." The user frequently visits "parks" and "libraries." What avoidance actions should be suggested?

[0372] In this way, the system can provide personalized future itineraries and security advice in real time that take into account the user's emotional state.

[0373] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0374] Step 1:

[0375] The user inputs personal data and emotional data. Using a dedicated application, the user inputs personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected using the camera and microphone of the smart glasses. The input data is converted into JSON format.

[0376] Input: User's personal and emotional data

[0377] Output: JSON format data (e.g., { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"})

[0378] Step 2:

[0379] The device sends the collected personal and emotional data to a server in JSON format over an encrypted connection.

[0380] Input: Personal data and emotion data in JSON format

[0381] Output: A request to send data to the server

[0382] Step 3:

[0383] The server stores the received personal data and emotion data in a database, which maps the data to appropriate fields for efficient analysis.

[0384] Input: Personal data and emotion data in JSON format

[0385] Output: Data stored in the database

[0386] Step 4:

[0387] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. The analysis uses machine learning algorithms, such as clustering and classification algorithms, to analyze the data. The emotion engine analyzes emotions in real time.

[0388] Input: Personal data and emotional data stored in a database

[0389] Output: Identified behavioral patterns and emotional states

[0390] Step 5:

[0391] The server inputs the analysis results into a generative AI model, which combines preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching to generate optimal future action plans and security advice for the user.

[0392] Input: Identified behavioral patterns and emotional states

[0393] Output: Generated itinerary and security advice (e.g., { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"})

[0394] Step 6:

[0395] The server then provides the generated schedule and security advice to the user's device. The schedule and security advice are sent in JSON format, and the device displays the received data in a calendar app or notification system.

[0396] Input: Generated action plan and security advice

[0397] Output: Agenda and security advice displayed on the user's device

[0398] 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.

[0399] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0400] 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.

[0401] [Second embodiment]

[0402] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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).

[0408] 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. 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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."

[0414] This invention relates to a system that uses AI to generate future schedules based on a user's personal data and provides them to the user. Specifically, the system collects data from the user's device, analyzes the data and generates schedules on a server, and provides the generated schedules to the user.

[0415] System configuration

[0416] This system consists of the following elements:

[0417] 1. Collection of personal data

[0418] Users enter personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application.

[0419] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[0420] 2. Data storage

[0421] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[0422] 3. Data Analysis

[0423] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[0424] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[0425] 4. Generate action schedule

[0426] The server uses a generation AI based on the analysis results to generate a future schedule of activities while referencing Big Data. The generation AI performs statistical analysis and proposes the optimal schedule for the user.

[0427] For example, if a user is interested in sports, the AI ​​will look up sporting events taking place next Monday and create an action plan to watch that event.

[0428] 5. Providing a timeline of actions

[0429] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[0430] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[0431] Specific examples

[0432] For example, suppose user A inputs data that "watching sports is a hobby, and in the past, he has purchased tickets to baseball and soccer games."

[0433] 1. User data collection

[0434] The user inputs into the application, "Watching sports is my hobby" and "I purchase tickets for baseball games and soccer games."

[0435] The device sends this data to the server in JSON format: { "hobbies": ["Sports Games"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"]}

[0436] 2. Data storage

[0437] The server stores the received data in the database, for example, in the format INSERT INTO users (hobbies, purchase_history) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets').

[0438] 3. Data Analysis

[0439] The server analyzes the data through daily batch processing, and uses Python scripts to analyze user behavior patterns and determine whether users are interested in "watching sports."

[0440] 4. Generate action schedule

[0441] The server inputs the data into the generation AI based on the analysis results, and generates a future schedule by referencing Big Data. For example, suppose there is a professional baseball game taking place next Monday, and this is used as the schedule.

[0442] 5. Providing a timeline of actions

[0443] The server sends the generated action plan to the user's device in JSON format: { "action": "Watch the game", "date": "Next Monday", "detail": "Professional baseball game"}

[0444] The device displays the received data in a calendar app or notification system, allowing the user to check their schedule for "watching a professional baseball game next Monday."

[0445] The processing flow will be explained below.

[0446] Step 1:

[0447] Using a dedicated application, the user inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. After completing the input, the user presses the "Send" button.

[0448] Step 2:

[0449] The device serializes the personal data entered by the user into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0450] Step 3:

[0451] The server decodes the received JSON-formatted personal data, maps it to the appropriate fields in the database, and then stores the personal data in a database engine (e.g., MySQL or MongoDB).

[0452] Step 4:

[0453] The server analyzes the stored personal data through daily batch processing using Python scripts and SQL queries to extract user preferences and behavioral patterns. For example, machine learning clustering and classification algorithms are used to analyze the data and identify preference patterns.

[0454] Step 5:

[0455] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the pre-processed user data with Big Data and performs statistical analysis and pattern matching. The generation AI generates a future action plan based on the user's interests.

[0456] Step 6:

[0457] The server saves the generated future schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[0458] Step 7:

[0459] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[0460] Step 8:

[0461] The device decodes the received JSON data of the planned events and displays it in the calendar app or notification system. Specifically, it renders the planned events information into UI components within the app and displays them visually to the user.

[0462] Step 9:

[0463] Users can review the proposed action plans and accept, modify, or delete them as needed, allowing users to easily manage their personalized future action plans.

[0464] Example 1

[0465] 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."

[0466] In modern society, it is becoming increasingly important to support users' busy lives by efficiently generating personalized itineraries. However, systems that can automatically generate and appropriately provide accurate itineraries based on users' preferences and behavioral history are still insufficient. Furthermore, there is a need for methods to improve user convenience while ensuring data security and privacy.

[0467] 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.

[0468] In this invention, the server includes means for collecting personal data input by the user, means for saving the personal data in a database, means for encrypting and transmitting the personal data, means for inputting the data to the generation AI based on the analysis results, and means for decrypting the action plan and displaying it to the user. This makes it possible to appropriately generate and safely provide a personalized action plan for the user, thereby improving convenience.

[0469] "Personal data" refers to data entered by the user regarding hobbies, preferences, behavioral history, purchasing history, family structure, and the like.

[0470] A "database" is an information management system that allows a server to store personal data.

[0471] "Behavioral patterns" refer to the tendencies of a user's behavior, hobbies, and preferences that the server obtains by analyzing personal data.

[0472] "Generative AI" is a general term for algorithms and models used for prediction and generation, and is used to generate user action plans.

[0473] An "action plan" is a future activity plan suggested by the generation AI based on the user's behavioral patterns.

[0474] "Encryption" is a technique used to securely transmit data by converting the data into a form different from its original form.

[0475] "Decryption" is the process of returning encrypted data to its original form.

[0476] The present invention relates to a system that uses AI to generate future activity plans based on a user's personal data and provides them to the user. The system collects and analyzes personal data entered by the user and proposes an activity plan based on the results. Detailed embodiments are described below.

[0477] First, the user uses a dedicated application to enter personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. The data entered by the user is formatted in JSON format by the device, encrypted using the RSA encryption algorithm, and then sent to the server.

[0478] The server then decrypts the encrypted personal data it receives and stores it in a database using MySQL or PostgreSQL, mapping the personal data to appropriate fields for easy analysis.

[0479] The server then periodically analyzes the personal data in the database using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). The analysis results in identifying user behavior patterns and saving the behavioral model as a behavior pattern in JSON format.

[0480] Based on the analyzed behavioral patterns, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, allowing it to appropriately generate the user's action plan.

[0481] As a concrete example, if a user inputs the data that "Watching sports is a hobby and has purchased tickets to baseball and soccer games in the past," the following prompt sentence is input to the generative AI model: "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an action plan."

[0482] The generated schedule is then encrypted again in JSON format and sent to the user's device, where it is decrypted and displayed to the user via a calendar app or notification system (e.g., Google Calendar API, iOS Notification Center).

[0483] This allows the user to check their schedule for watching a professional baseball game next Monday. In this way, a personalized activity schedule for the user is efficiently generated and provided.

[0484] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0485] Step 1:

[0486] The user enters personal data into a dedicated application. The entered data includes hobbies, preferences, behavioral history, purchasing history, family composition, etc. This data is entered into the application's form and formatted in JSON format. An example of entered data is the following JSON format:

[0487] json

[0488] {

[0489] "hobbies": ["watching sports"],

[0490] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[0491] "family": ["The whole family is a sports fan"]

[0492] }

[0493] The terminal encrypts this JSON data using the RSA encryption algorithm and then sends it to the server.

[0494] Step 2:

[0495] The server receives the encrypted personal data and decrypts it using the RSA algorithm. The decrypted data is then stored in a database, typically using MySQL or PostgreSQL. Specifically, the data is mapped to the appropriate fields and stored using the following SQL statement:

[0496] sql

[0497] INSERT INTO users (hobbies, purchase_history, family)

[0498] VALUES ('Watching sports', 'Baseball game tickets, Football game tickets', 'The whole family is a sports fan');

[0499] The input here is the decoded JSON data, and the output is the person data inserted into the database.

[0500] Step 3:

[0501] The server periodically analyzes the personal data in the database. This analysis is performed using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). As a result of the analysis, behavioral patterns of individual users are identified and a behavioral model is saved as a behavioral pattern in JSON format. Specific operations include reading from the database, analyzing using machine learning algorithms, and saving the analysis results. The input is the personal data read from the database, and the output is a model based on the behavioral patterns.

[0502] Step 4:

[0503] Based on the analysis results, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, which then generates a future action plan. For example, if a user enters data such as "Watching sports is my hobby, and I have purchased tickets to baseball and soccer games in the past," the following prompts are input into the generation AI model:

[0504] "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an activity schedule."

[0505] The generated action schedule is saved in JSON format. The input is the result of the action pattern analysis, and the output is the generated action schedule.

[0506] Step 5:

[0507] The server encrypts the generated schedule in JSON format and sends it to the user's device. An example of a generated schedule is the following JSON output:

[0508] json

[0509] {

[0510] "action": "spectate",

[0511] "date": "next Monday",

[0512] "detail": "Professional baseball game"

[0513] }

[0514] The device receives this encrypted data, decrypts it using the RSA algorithm, and displays the decrypted event to the user through a calendar app or notification system. The input is the encrypted event data, and the output is the decrypted event.

[0515] This allows the user to check their plans to watch a professional baseball game next Monday.

[0516] (Application example 1)

[0517] 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."

[0518] In conventional logistics centers, robot operations require time-consuming setup of individual schedules by managers, making it difficult to allocate work efficiently. Additionally, there was a lack of data analysis and automatic generation mechanisms required to maximize the robot's performance, making it difficult to improve overall operational efficiency.

[0519] 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.

[0520] In this invention, the server includes means for collecting personal data input by users, means for saving the personal data in a database, means for analyzing the personal data and identifying the user's behavioral patterns, means for generating future action plans using a generation AI, and means for providing the action plans to robots in the logistics center. This makes it possible to improve the work efficiency of the robots in the logistics center, reduce the burden on managers, and optimize overall work efficiency.

[0521] "User" refers to the entity that uses the system and is the person to whom personal data is provided.

[0522] "Personal data" refers to information such as a user's behavioral history, hobbies and preferences, and purchasing history.

[0523] "Database" means a data management system that stores collected personal data and makes it accessible when needed.

[0524] "Behavioral patterns" refer to a tendency for a user to take certain actions based on analyzed personal data.

[0525] "Generative AI" refers to technology that uses artificial intelligence to generate new information and predictions based on input data.

[0526] A "future action plan" is an action plan for a specific date and time in the future that is created by the generation AI based on the user's behavior patterns.

[0527] A "logistics center" is a facility where goods and materials are managed, picked, packed, and shipped.

[0528] A "robot" is a piece of equipment that performs work automatically within a logistics center and operates based on a schedule.

[0529] A "machine learning algorithm" is an algorithm used in data analysis, a method for automatically learning from empirical data and identifying patterns.

[0530] "Big data" refers to a large and diverse set of data, a collection of data that can be used for analysis.

[0531] This invention relates to a system that uses AI to generate future action plans based on a user's personal data and provides them to a robot at a logistics center. Specifically, the system collects data from the user's terminal, analyzes the data and generates an action plan on the server, and then provides the generated action plan to the robot.

[0532] System configuration

[0533] This system consists of the following elements:

[0534] 1. Collection of personal data

[0535] Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application.

[0536] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[0537] 2. Data storage

[0538] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[0539] 3. Data Analysis

[0540] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[0541] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[0542] 4. Generate action schedule

[0543] The server uses a generation AI based on the analysis results to generate a future action plan while referencing big data. The generation AI performs statistical analysis and proposes the optimal action plan for the user.

[0544] For example, when generating a robot's activity schedule for the next week at a logistics center, if past data shows that it will be performing picking, packing, and shipping assistance, the system will create an activity schedule that takes into account the priority of those tasks.

[0545] 5. Providing a timeline of actions

[0546] The server provides the robot's terminal with the generated action plan in JSON format, which contains the information necessary for a specific robot in the logistics center to operate efficiently.

[0547] The terminal receives the action plan and instructs the robot on its actions based on the action plan, allowing the robot to perform its work efficiently on the specified date.

[0548] For example, if a manager predicts that "the volume of picking work will be high this week," the system will automatically adjust the robot's schedule for the next week based on past data and big data, generating a detailed schedule such as "8 hours of picking on Monday," "6 hours of picking and 2 hours of packing on Tuesday," etc. During this process, the following prompt sentences are input into the generative AI model.

[0549] Example prompt sentence:

[0550] "Please generate a schedule for the robot's activities in the distribution center for the next week. According to past data, it is currently performing the tasks of picking, packing, and shipping assistance. The priority of each task is as follows: picking: high, packing: medium, shipping assistance: low. Please generate the most efficient schedule based on this."

[0551] This enables the system to achieve efficient operation of robots in logistics centers, reduce the burden on managers, and optimize work efficiency.

[0552] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0553] Step 1:

[0554] Users enter personal data such as their hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application. The data entered here specifically includes "type of work," "frequency of work," and "work evaluation score." This data is formatted in JSON format.

[0555] Step 2:

[0556] The terminal sends the data entered by the user in JSON format to the server. At this time, the data is encrypted using an encryption algorithm such as AES. For example, if the input data is {"tasks": ["Picking"], "frequency": [5], "score": [4.5]}, it will be sent to the server in encrypted form.

[0557] Step 3:

[0558] The server stores the received personal data in a database. Here, it parses the JSON format data and maps it appropriately to each field. For example, the database stores "picking" in the tasks field, "5" in the frequency field, and "4.5" in the score field.

[0559] Step 4:

[0560] The server periodically analyzes the personal data in the database. This analysis is performed using scripts such as Python and machine learning algorithms (e.g., KMeans clustering). The input data is all the robot data in the database, and the output is clusters that represent the robot's behavioral patterns.

[0561] Step 5:

[0562] The server inputs data into a generative AI model based on the analysis results, and generates future action plans while referencing big data. At this time, a specific prompt is input into the generative AI. For example, the prompt might be, "Please generate an action plan for the robots at the logistics center for the next week. According to past data, they are performing picking, packing, and shipping assistance." The output of this process is a detailed action plan for the next week.

[0563] Step 6:

[0564] The server provides the generated action schedule to the robot terminal in JSON format. Here, the action schedule is sent in the format {"date": "2023-10-01", "task": "picking", "duration": "8 hours"}, for example.

[0565] Step 7:

[0566] The terminal receives the action plan and instructs the robot on its actions based on that plan. The robot then follows this plan and performs specific actions, such as "picking" for "8 hours" on the specified date.

[0567] 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.

[0568] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[0569] System configuration

[0570] This system consists of the following elements:

[0571] 1. Collection of personal and emotional data

[0572] Users input personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application. In addition, the user's emotional data is acquired through the device's built-in camera and microphone.

[0573] The device sends the personal data and emotion data entered by the user to the server in JSON format, encrypted before transmission.

[0574] 2. Data storage

[0575] The server stores the received personal and emotional data in a database, where it is mapped to appropriate fields for easy later analysis.

[0576] 3. Data and Sentiment Analysis

[0577] The server periodically analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using machine learning algorithms, such as clustering and classification algorithms.

[0578] The emotion engine analyzes the user's emotional data in real time to identify their current emotional state, which is also used for behavioral pattern analysis.

[0579] 4. Generate action schedule

[0580] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and current emotional state.

[0581] For example, if a user is tired and in need of relaxation, the AI ​​will suggest relaxing events and activities as part of their agenda.

[0582] 5. Providing a timeline of actions

[0583] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[0584] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[0585] Specific examples

[0586] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is acquired, the flow is as follows.

[0587] 1. User data collection

[0588] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[0589] The device sends this data to the server in JSON format: { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"}

[0590] 2. Data storage

[0591] The server stores the received data in a database, for example, in the format INSERT INTO users (hobbies, purchase_history, emotion) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[0592] 3. Data and Sentiment Analysis

[0593] The server analyzes the data through daily batch processing. Using Python scripts, it analyzes the user's behavioral patterns and determines whether they are interested in "watching sports." At the same time, the emotion engine detects "stress" and reports their current emotional state.

[0594] 4. Generate action schedule

[0595] The server inputs the data into the generation AI based on the analysis results, which then suggests relaxing events (such as relaxation spots or concerts) based on the emotional data.

[0596] 5. Providing a timeline of actions

[0597] The server sends the generated action plan in JSON format to the user's device: { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}

[0598] The device displays the received data in its calendar app or notification system, allowing the user to see their "Spa & Relax This Weekend" appointments.

[0599] In this way, the system can provide a personalized future itinerary that takes into account the user's emotional state.

[0600] The processing flow will be explained below.

[0601] Step 1:

[0602] Using a dedicated application, users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected through the device's built-in camera and microphone.

[0603] Step 2:

[0604] The device serializes the personal data entered by the user and the collected emotional data into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0605] Step 3:

[0606] The server decodes the received JSON-formatted personal data and emotion data and maps them to appropriate fields in a database. For example, personal data is stored in a user table, and emotion data is stored in an emotion table.

[0607] Step 4:

[0608] The server analyzes the stored personal data and emotional data through daily batch processing to identify users' behavioral patterns and emotional states. Machine learning algorithms, especially clustering and classification algorithms, are used to classify the data and extract patterns.

[0609] Step 5:

[0610] The emotion engine analyzes the acquired emotion data to identify the user's current emotional state, identifying emotion categories (e.g., stress, joy, sadness, etc.), and integrating this information into behavioral pattern analysis.

[0611] Step 6:

[0612] The server inputs data into the generation AI based on the analysis results. The generation AI integrates preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and emotional state.

[0613] Step 7:

[0614] The server saves the generated schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[0615] Step 8:

[0616] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[0617] Step 9:

[0618] The device decodes the received JSON data of the scheduled events and displays the scheduled events in the calendar app or notification system. Specifically, the scheduled events information is rendered in the UI components within the app and displayed visually to the user.

[0619] Step 10:

[0620] Users can review the proposed action plan and accept, modify, or delete it as needed, allowing them to easily manage a personalized future action plan that takes their emotional state into account.

[0621] Example 2

[0622] 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."

[0623] Conventional systems can generate activity plans based on a user's personal data, but they have limitations in providing activity plans that reflect the user's real-time emotional state. Furthermore, it is difficult to provide personalized suggestions that effectively utilize external big data. This makes it impossible to propose optimal activity plans that reflect the user's emotional state, which poses a challenge in sufficiently improving user satisfaction.

[0624] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting personal data and emotional data input by the user; means for saving the personal data and emotional data in a database; means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state; means including an emotion engine for analyzing the emotional data in real time; means for generating a future action plan using a generation AI based on the behavioral patterns and emotional state; means for the generation AI to integrate the preprocessed personal data, emotional data, and external data and perform statistical analysis and pattern matching; means for providing the action plan to the user's terminal; and means for displaying the action plan on the user's terminal. This makes it possible to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on the analysis.

[0625] "Personal data entered by the user" refers to information such as hobbies, preferences, behavioral history, purchasing history, and family composition that the user himself / herself enters through a dedicated application.

[0626] "Emotional data" refers to information about a user's emotional state acquired through a camera or microphone built into the user's device.

[0627] "Database" refers to an information system for storing and managing collected and saved personal data and emotional data.

[0628] "Behavioral patterns" refer to unique behavioral tendencies and patterns that are analyzed based on a user's past behavioral history and hobbies and preferences.

[0629] "Emotion engine" refers to software or a system that analyzes a user's emotional data in real time to identify the user's current emotional state.

[0630] "Generative AI" refers to an artificial intelligence model that takes a user's personal data and emotional data as input and generates future action plans based on that data.

[0631] "Preprocessing" refers to a series of operations that format and convert input data so that it can be easily processed by analytical or generative AI.

[0632] "Statistical analysis" refers to a set of techniques for analyzing data using statistical methods to understand the characteristics and patterns of the data.

[0633] "Pattern matching" refers to algorithms and techniques for detecting and identifying specific patterns or templates within data.

[0634] "Action Plan" refers to future action plans or events suggested by the generative AI, taking into account the user's hobbies, preferences, and emotional state.

[0635] "Terminal" refers to a device used by a user (such as a smartphone or tablet) that is a computer system used to input personal data and emotional data, display planned activities, etc.

[0636] "External data" refers to big data and reference data provided by third parties other than users' personal data and emotional data.

[0637] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[0638] System configuration

[0639] The system consists of the following elements:

[0640] 1. Collection of personal and emotional data

[0641] Users enter personal data (hobbies, preferences, behavioral history, purchasing history, family composition, etc.) through a dedicated application, and emotional data is recorded using the device's camera and microphone.

[0642] The terminal converts this data into JSON format, encrypts it, and sends it to the server.

[0643] 2. Data storage

[0644] The server receives the encrypted JSON data, decrypts it, and stores it in a database, where it is properly mapped to personal data and emotional data.

[0645] 3. Data and Sentiment Analysis

[0646] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[0647] The emotion engine analyzes the user's emotion data in real time to identify their current emotional state.

[0648] 4. Generate action schedule

[0649] The server inputs data into the generative AI model based on the pre-processed personal data and emotion data, which then performs statistical analysis and pattern matching to generate an optimal action plan.

[0650] 5. Providing a timeline of actions

[0651] The server sends the generated action plan in JSON format to the user's device.

[0652] The device displays the received schedule to the user through a calendar app or notification system.

[0653] Specific examples

[0654] For example, consider a case where user A inputs data that "watching sports is a hobby, and has purchased tickets to baseball and soccer games in the past," and is currently feeling stressed.

[0655] 1. User data collection

[0656] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[0657] The device converts this data into JSON format, encrypts it, and sends it to the server:

[0658] json

[0659] {

[0660] "user_id": "12345",

[0661] "hobbies": ["watching sports"],

[0662] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[0663] "emotion": "stress"

[0664] }

[0665] 2. Data storage

[0666] The server interprets the data and stores it in the database, for example, by executing the following SQL statement: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[0667] 3. Data and Sentiment Analysis

[0668] The server analyzes the data in the database and identifies the user's behavior pattern of "watching sports." At the same time, the emotion engine detects stress and notifies the server of the results.

[0669] 4. Generate action schedule

[0670] The server inputs data into the generation AI based on the analysis results, and the generation AI suggests relaxation events (e.g., spa & relaxation).

[0671] 5. Providing a timeline of actions

[0672] The server sends the generated schedule to the user's device in JSON format:

[0673] json

[0674] {

[0675] "action": "relaxation",

[0676] "date": "this weekend",

[0677] "detail": "Spa & Relax"

[0678] }

[0679] The device displays the received data in its calendar app or notification system, allowing the user to check their "Spa & Relax This Weekend" schedule.

[0680] Prompt Sentence Examples

[0681] "If User A enjoys watching sports and has been feeling stressed lately, please suggest some relaxing activities."

[0682] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0683] Step 1: Data collection

[0684] The user opens a dedicated application and inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. Emotional data is also recorded using the device's camera and microphone.

[0685] Input: User input of personal and emotional data.

[0686] Output: Personal data and emotion data converted by the device into JSON format.

[0687] Specific operation: The user enters information such as "watching sports," "baseball game tickets, soccer game tickets," and "stress," and the device compiles this in JSON format.

[0688] Step 2: Send data

[0689] The device converts the personal data and emotional data entered into JSON format, encrypts it, and sends it to the server.

[0690] Input: Personal and sentiment data in JSON format.

[0691] Output: Encrypted JSON data.

[0692] Specific operation: The device uses the RSA encryption algorithm to encrypt the JSON data { "user_id": "12345", "hobbies": ["Watching Sports"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"], "emotion": "Stress"} and sends it to the server.

[0693] Step 3: Save your data

[0694] The server decodes the received JSON data and stores it in the database.

[0695] Input: Encrypted JSON data.

[0696] Output: Personal and emotional data stored in a database.

[0697] What happens: The server performs RSA decryption and stores the decrypted data in the database using an SQL query, e.g.: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Tickets', 'Baseball Tickets, Football Tickets', 'Stress').

[0698] Step 4: Analyzing the data and sentiment data

[0699] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[0700] Input: Personal and emotional data stored in a database.

[0701] Output: Analysis of the user's behavioral patterns and emotional state.

[0702] Specific operation: A Python script is used to apply a clustering algorithm to the acquired data to identify the behavioral pattern of "interested in watching sports." The emotion engine detects "stress" and reports it to the server.

[0703] Step 5: Generate an action plan

[0704] Based on the analysis results, the server inputs the data into a generated AI model, performs statistical analysis and pattern matching, and generates an optimal action plan.

[0705] Input: Analysis results of behavioral patterns and emotional states.

[0706] Output: Action plan generated by the generation AI.

[0707] Specific operation: The generating AI is input with data on "hobby of watching sports" and "stress level," and while referring to external data, suggests relaxation activities (e.g., spa and relaxation events).

[0708] Step 6: Provide an action plan

[0709] The server sends the generated action plan in JSON format to the user's device.

[0710] Input: The generated event schedule data.

[0711] Output: JSON formatted event schedule sent to the user's device.

[0712] Specific operation: The server converts the generated action plan into JSON format, encrypts the data { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}, and sends it to the device.

[0713] Step 7: View upcoming events

[0714] The device decodes the scheduled events it receives and displays them to the user through a calendar app or notification system.

[0715] Input: JSON formatted event schedule sent from the server.

[0716] Output: The upcoming event displayed in the user's calendar app or notification system.

[0717] Specific behavior: The device decodes and interprets the received JSON data, adds an event for "Spa & Relax This Weekend" to the calendar app, and notifies the user via the notification system.

[0718] This allows the system to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on that.

[0719] (Application example 2)

[0720] 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."

[0721] In recent years, there has been a growing demand for individually customized services that take into account users' behavioral patterns and emotional states. However, existing systems are unable to fully utilize users' emotional data, making it difficult to provide appropriate security advice based on the user's current emotions and future plans. This has prevented efficient security management from being realized to enhance user safety. This issue is particularly pronounced in real-time security management using wearable devices such as smart glasses.

[0722] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data and emotional data input by the user, means for saving the personal data and emotional data in a database, means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state, means for generating a future action plan and security advice using a generative AI model based on the behavioral patterns and emotional state, and means for providing the action plan and security advice to the user. This enables real-time security management that reflects the user's emotional state.

[0723] "Personal data" refers to personal information such as a user's hobbies, preferences, behavioral history, purchasing history, and family composition.

[0724] "Emotional data" refers to information that indicates the user's current emotional state and is collected via a camera or microphone.

[0725] "Database" refers to a system for storing collected personal and emotional data.

[0726] "Behavioral patterns" refer to certain regularities or tendencies that are found as a result of analyzing a user's past behavioral history.

[0727] "Emotional state" refers to a user's current emotional or psychological state.

[0728] A "generative AI model" refers to an artificial intelligence model that generates optimal action plans and security advice for users based on the results of data analysis.

[0729] "Future action plan" refers to an action plan for a future date that is generated based on the user's current emotional state and behavioral patterns.

[0730] "Security advice" refers to suggestions for avoiding potential future risks and dangers based on the user's emotional state and behavioral patterns.

[0731] "Collection means" refers to a device or method for collecting personal data and emotional data of a user.

[0732] "Storage means" refers to the device or method for recording collected data in a database.

[0733] "Analysis means" refers to devices and methods for analyzing collected data and identifying user behavioral patterns and emotional states.

[0734] "Providing means" refers to a device or method for notifying the user of the generated action plan and security advice.

[0735] 1. System Program

[0736] This invention provides a system that collects personal data and emotional data of users, stores them in a database, and analyzes the data to identify the user's behavioral patterns and emotional state. Based on the identified behavioral patterns and emotional state, the system uses a generative AI model to generate future action plans and security advice, which are then provided to the user.

[0737] 2. Hardware and software used

[0738] The system is implemented using the following hardware and software:

[0739] Hardware: Smart glasses (with built-in camera and microphone)

[0740] Software: Python, REST API, JSON, Server

[0741] The server provides a dedicated application to collect personal and emotional data from each user. Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through this dedicated application. Furthermore, emotional data is collected using the camera and microphone in the smart glasses.

[0742] The device then converts the collected personal and emotional data into JSON format and sends it to the server, which stores it in a database.

[0743] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. This analysis is performed using machine learning algorithms, such as clustering and classification algorithms. The emotion engine analyzes the emotional data in real time to identify the user's current emotional state. This information is also used for behavioral pattern analysis.

[0744] Based on the analysis results, the server inputs the data into a generative AI model, which performs statistical analysis and pattern matching using preprocessed personal data, emotional data, and Big Data. The generative AI model generates optimal action plans and security advice taking into account the user's preferences and current emotional state.

[0745] Finally, the server provides the generated schedule and security advice to the user's device, which displays them in a JSON format via a calendar app or notification system.

[0746] 3. Specific Examples

[0747] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is obtained, the generative AI model will generate an itinerary for relaxing events (e.g., relaxation spots and concerts) and security advice.

[0748] An example prompt is:

[0749] Based on the user's hobbies, past behavioral history, and current emotional data, we suggest risks and avoidance actions for the next day. The current emotion is "anxiety." The user frequently visits "parks" and "libraries." What avoidance actions should be suggested?

[0750] In this way, the system can provide personalized future itineraries and security advice in real time that take into account the user's emotional state.

[0751] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0752] Step 1:

[0753] The user inputs personal data and emotional data. Using a dedicated application, the user inputs personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected using the camera and microphone of the smart glasses. The input data is converted into JSON format.

[0754] Input: User's personal and emotional data

[0755] Output: JSON format data (e.g., { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"})

[0756] Step 2:

[0757] The device sends the collected personal and emotional data to a server in JSON format over an encrypted connection.

[0758] Input: Personal data and emotion data in JSON format

[0759] Output: A request to send data to the server

[0760] Step 3:

[0761] The server stores the received personal data and emotion data in a database, which maps the data to appropriate fields for efficient analysis.

[0762] Input: Personal data and emotion data in JSON format

[0763] Output: Data stored in the database

[0764] Step 4:

[0765] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. The analysis uses machine learning algorithms, such as clustering and classification algorithms, to analyze the data. The emotion engine analyzes emotions in real time.

[0766] Input: Personal data and emotional data stored in a database

[0767] Output: Identified behavioral patterns and emotional states

[0768] Step 5:

[0769] The server inputs the analysis results into a generative AI model, which combines preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching to generate optimal future action plans and security advice for the user.

[0770] Input: Identified behavioral patterns and emotional states

[0771] Output: Generated itinerary and security advice (e.g., { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"})

[0772] Step 6:

[0773] The server then provides the generated schedule and security advice to the user's device. The schedule and security advice are sent in JSON format, and the device displays the received data in a calendar app or notification system.

[0774] Input: Generated action plan and security advice

[0775] Output: Agenda and security advice displayed on the user's device

[0776] 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.

[0777] 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.

[0778] 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.

[0779] [Third embodiment]

[0780] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0781] 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.

[0782] 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).

[0783] 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.

[0784] 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.

[0785] 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).

[0786] 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. 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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."

[0792] This invention relates to a system that uses AI to generate future schedules based on a user's personal data and provides them to the user. Specifically, the system collects data from the user's device, analyzes the data and generates schedules on a server, and provides the generated schedules to the user.

[0793] System configuration

[0794] This system consists of the following elements:

[0795] 1. Collection of personal data

[0796] Users enter personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application.

[0797] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[0798] 2. Data storage

[0799] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[0800] 3. Data Analysis

[0801] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[0802] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[0803] 4. Generate action schedule

[0804] The server uses a generation AI based on the analysis results to generate a future schedule of activities while referencing Big Data. The generation AI performs statistical analysis and proposes the optimal schedule for the user.

[0805] For example, if a user is interested in sports, the AI ​​will look up sporting events taking place next Monday and create an action plan to watch that event.

[0806] 5. Providing a timeline of actions

[0807] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[0808] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[0809] Specific examples

[0810] For example, suppose user A inputs data that "watching sports is a hobby, and in the past, he has purchased tickets to baseball and soccer games."

[0811] 1. User data collection

[0812] The user inputs into the application, "Watching sports is my hobby" and "I purchase tickets for baseball games and soccer games."

[0813] The device sends this data to the server in JSON format: { "hobbies": ["Sports Games"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"]}

[0814] 2. Data storage

[0815] The server stores the received data in the database, for example, in the format INSERT INTO users (hobbies, purchase_history) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets').

[0816] 3. Data Analysis

[0817] The server analyzes the data through daily batch processing, and uses Python scripts to analyze user behavior patterns and determine whether users are interested in "watching sports."

[0818] 4. Generate action schedule

[0819] The server inputs the data into the generation AI based on the analysis results, and generates a future schedule by referencing Big Data. For example, suppose there is a professional baseball game taking place next Monday, and this is used as the schedule.

[0820] 5. Providing a timeline of actions

[0821] The server sends the generated action plan to the user's device in JSON format: { "action": "Watch the game", "date": "Next Monday", "detail": "Professional baseball game"}

[0822] The device displays the received data in a calendar app or notification system, allowing the user to check their schedule for "watching a professional baseball game next Monday."

[0823] The processing flow will be explained below.

[0824] Step 1:

[0825] Using a dedicated application, the user inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. After completing the input, the user presses the "Send" button.

[0826] Step 2:

[0827] The device serializes the personal data entered by the user into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0828] Step 3:

[0829] The server decodes the received JSON-formatted personal data, maps it to the appropriate fields in the database, and then stores the personal data in a database engine (e.g., MySQL or MongoDB).

[0830] Step 4:

[0831] The server analyzes the stored personal data through daily batch processing using Python scripts and SQL queries to extract user preferences and behavioral patterns. For example, machine learning clustering and classification algorithms are used to analyze the data and identify preference patterns.

[0832] Step 5:

[0833] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the pre-processed user data with Big Data and performs statistical analysis and pattern matching. The generation AI generates a future action plan based on the user's interests.

[0834] Step 6:

[0835] The server saves the generated future schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[0836] Step 7:

[0837] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[0838] Step 8:

[0839] The device decodes the received JSON data of the planned events and displays it in the calendar app or notification system. Specifically, it renders the planned events information into UI components within the app and displays them visually to the user.

[0840] Step 9:

[0841] Users can review the proposed action plans and accept, modify, or delete them as needed, allowing users to easily manage their personalized future action plans.

[0842] Example 1

[0843] 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."

[0844] In modern society, it is becoming increasingly important to support users' busy lives by efficiently generating personalized itineraries. However, systems that can automatically generate and appropriately provide accurate itineraries based on users' preferences and behavioral history are still insufficient. Furthermore, there is a need for methods to improve user convenience while ensuring data security and privacy.

[0845] 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.

[0846] In this invention, the server includes means for collecting personal data input by the user, means for saving the personal data in a database, means for encrypting and transmitting the personal data, means for inputting the data to the generation AI based on the analysis results, and means for decrypting the action plan and displaying it to the user. This makes it possible to appropriately generate and safely provide a personalized action plan for the user, thereby improving convenience.

[0847] "Personal data" refers to data entered by the user regarding hobbies, preferences, behavioral history, purchasing history, family structure, and the like.

[0848] A "database" is an information management system that allows a server to store personal data.

[0849] "Behavioral patterns" refer to the tendencies of a user's behavior, hobbies, and preferences that the server obtains by analyzing personal data.

[0850] "Generative AI" is a general term for algorithms and models used for prediction and generation, and is used to generate user action plans.

[0851] An "action plan" is a future activity plan suggested by the generation AI based on the user's behavioral patterns.

[0852] "Encryption" is a technique used to securely transmit data by converting the data into a form different from its original form.

[0853] "Decryption" is the process of returning encrypted data to its original form.

[0854] The present invention relates to a system that uses AI to generate future activity plans based on a user's personal data and provides them to the user. The system collects and analyzes personal data entered by the user and proposes an activity plan based on the results. Detailed embodiments are described below.

[0855] First, the user uses a dedicated application to enter personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. The data entered by the user is formatted in JSON format by the device, encrypted using the RSA encryption algorithm, and then sent to the server.

[0856] The server then decrypts the encrypted personal data it receives and stores it in a database using MySQL or PostgreSQL, mapping the personal data to appropriate fields for easy analysis.

[0857] The server then periodically analyzes the personal data in the database using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). The analysis results in identifying user behavior patterns and saving the behavioral model as a behavior pattern in JSON format.

[0858] Based on the analyzed behavioral patterns, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, allowing it to appropriately generate the user's action plan.

[0859] As a concrete example, if a user inputs the data that "Watching sports is a hobby and has purchased tickets to baseball and soccer games in the past," the following prompt sentence is input to the generative AI model: "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an action plan."

[0860] The generated schedule is then encrypted again in JSON format and sent to the user's device, where it is decrypted and displayed to the user via a calendar app or notification system (e.g., Google Calendar API, iOS Notification Center).

[0861] This allows the user to check their schedule for watching a professional baseball game next Monday. In this way, a personalized activity schedule for the user is efficiently generated and provided.

[0862] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0863] Step 1:

[0864] The user enters personal data into a dedicated application. The entered data includes hobbies, preferences, behavioral history, purchasing history, family composition, etc. This data is entered into the application's form and formatted in JSON format. An example of entered data is the following JSON format:

[0865] json

[0866] {

[0867] "hobbies": ["watching sports"],

[0868] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[0869] "family": ["The whole family is a sports fan"]

[0870] }

[0871] The terminal encrypts this JSON data using the RSA encryption algorithm and then sends it to the server.

[0872] Step 2:

[0873] The server receives the encrypted personal data and decrypts it using the RSA algorithm. The decrypted data is then stored in a database, typically using MySQL or PostgreSQL. Specifically, the data is mapped to the appropriate fields and stored using the following SQL statement:

[0874] sql

[0875] INSERT INTO users (hobbies, purchase_history, family)

[0876] VALUES ('Watching sports', 'Baseball game tickets, Football game tickets', 'The whole family is a sports fan');

[0877] The input here is the decoded JSON data, and the output is the person data inserted into the database.

[0878] Step 3:

[0879] The server periodically analyzes the personal data in the database. This analysis is performed using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). As a result of the analysis, behavioral patterns of individual users are identified and a behavioral model is saved as a behavioral pattern in JSON format. Specific operations include reading from the database, analyzing using machine learning algorithms, and saving the analysis results. The input is the personal data read from the database, and the output is a model based on the behavioral patterns.

[0880] Step 4:

[0881] Based on the analysis results, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, which then generates a future action plan. For example, if a user enters data such as "Watching sports is my hobby, and I have purchased tickets to baseball and soccer games in the past," the following prompts are input into the generation AI model:

[0882] "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an activity schedule."

[0883] The generated action schedule is saved in JSON format. The input is the result of the action pattern analysis, and the output is the generated action schedule.

[0884] Step 5:

[0885] The server encrypts the generated schedule in JSON format and sends it to the user's device. An example of a generated schedule is the following JSON output:

[0886] json

[0887] {

[0888] "action": "spectate",

[0889] "date": "next Monday",

[0890] "detail": "Professional baseball game"

[0891] }

[0892] The device receives this encrypted data, decrypts it using the RSA algorithm, and displays the decrypted event to the user through a calendar app or notification system. The input is the encrypted event data, and the output is the decrypted event.

[0893] This allows the user to check their plans to watch a professional baseball game next Monday.

[0894] (Application example 1)

[0895] 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."

[0896] In conventional logistics centers, robot operations require time-consuming setup of individual schedules by managers, making it difficult to allocate work efficiently. Additionally, there was a lack of data analysis and automatic generation mechanisms required to maximize the robot's performance, making it difficult to improve overall operational efficiency.

[0897] 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.

[0898] In this invention, the server includes means for collecting personal data input by users, means for saving the personal data in a database, means for analyzing the personal data and identifying the user's behavioral patterns, means for generating future action plans using a generation AI, and means for providing the action plans to robots in the logistics center. This makes it possible to improve the work efficiency of the robots in the logistics center, reduce the burden on managers, and optimize overall work efficiency.

[0899] "User" refers to the entity that uses the system and is the person to whom personal data is provided.

[0900] "Personal data" refers to information such as a user's behavioral history, hobbies and preferences, and purchasing history.

[0901] "Database" means a data management system that stores collected personal data and makes it accessible when needed.

[0902] "Behavioral patterns" refer to a tendency for a user to take certain actions based on analyzed personal data.

[0903] "Generative AI" refers to technology that uses artificial intelligence to generate new information and predictions based on input data.

[0904] A "future action plan" is an action plan for a specific date and time in the future that is created by the generation AI based on the user's behavior patterns.

[0905] A "logistics center" is a facility where goods and materials are managed, picked, packed, and shipped.

[0906] A "robot" is a piece of equipment that performs work automatically within a logistics center and operates based on a schedule.

[0907] A "machine learning algorithm" is an algorithm used in data analysis, a method for automatically learning from empirical data and identifying patterns.

[0908] "Big data" refers to a large and diverse set of data, a collection of data that can be used for analysis.

[0909] This invention relates to a system that uses AI to generate future action plans based on a user's personal data and provides them to a robot at a logistics center. Specifically, the system collects data from the user's terminal, analyzes the data and generates an action plan on the server, and then provides the generated action plan to the robot.

[0910] System configuration

[0911] This system consists of the following elements:

[0912] 1. Collection of personal data

[0913] Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application.

[0914] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[0915] 2. Data storage

[0916] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[0917] 3. Data Analysis

[0918] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[0919] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[0920] 4. Generate action schedule

[0921] The server uses a generation AI based on the analysis results to generate a future action plan while referencing big data. The generation AI performs statistical analysis and proposes the optimal action plan for the user.

[0922] For example, when generating a robot's activity schedule for the next week at a logistics center, if past data shows that it will be performing picking, packing, and shipping assistance, the system will create an activity schedule that takes into account the priority of those tasks.

[0923] 5. Providing a timeline of actions

[0924] The server provides the robot's terminal with the generated action plan in JSON format, which contains the information necessary for a specific robot in the logistics center to operate efficiently.

[0925] The terminal receives the action plan and instructs the robot on its actions based on the action plan, allowing the robot to perform its work efficiently on the specified date.

[0926] For example, if a manager predicts that "the volume of picking work will be high this week," the system will automatically adjust the robot's schedule for the next week based on past data and big data, generating a detailed schedule such as "8 hours of picking on Monday," "6 hours of picking and 2 hours of packing on Tuesday," etc. During this process, the following prompt sentences are input into the generative AI model.

[0927] Example prompt sentence:

[0928] "Please generate a schedule for the robot's activities in the distribution center for the next week. According to past data, it is currently performing the tasks of picking, packing, and shipping assistance. The priority of each task is as follows: picking: high, packing: medium, shipping assistance: low. Please generate the most efficient schedule based on this."

[0929] This enables the system to achieve efficient operation of robots in logistics centers, reduce the burden on managers, and optimize work efficiency.

[0930] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0931] Step 1:

[0932] Users enter personal data such as their hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application. The data entered here specifically includes "type of work," "frequency of work," and "work evaluation score." This data is formatted in JSON format.

[0933] Step 2:

[0934] The terminal sends the data entered by the user in JSON format to the server. At this time, the data is encrypted using an encryption algorithm such as AES. For example, if the input data is {"tasks": ["Picking"], "frequency": [5], "score": [4.5]}, it will be sent to the server in encrypted form.

[0935] Step 3:

[0936] The server stores the received personal data in a database. Here, it parses the JSON format data and maps it appropriately to each field. For example, the database stores "picking" in the tasks field, "5" in the frequency field, and "4.5" in the score field.

[0937] Step 4:

[0938] The server periodically analyzes the personal data in the database. This analysis is performed using scripts such as Python and machine learning algorithms (e.g., KMeans clustering). The input data is all the robot data in the database, and the output is clusters that represent the robot's behavioral patterns.

[0939] Step 5:

[0940] The server inputs data into a generative AI model based on the analysis results, and generates future action plans while referencing big data. At this time, a specific prompt is input into the generative AI. For example, the prompt might be, "Please generate an action plan for the robots at the logistics center for the next week. According to past data, they are performing picking, packing, and shipping assistance." The output of this process is a detailed action plan for the next week.

[0941] Step 6:

[0942] The server provides the generated action schedule to the robot terminal in JSON format. Here, the action schedule is sent in the format {"date": "2023-10-01", "task": "picking", "duration": "8 hours"}, for example.

[0943] Step 7:

[0944] The terminal receives the action plan and instructs the robot on its actions based on that plan. The robot then follows this plan and performs specific actions, such as "picking" for "8 hours" on the specified date.

[0945] 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.

[0946] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[0947] System configuration

[0948] This system consists of the following elements:

[0949] 1. Collection of personal and emotional data

[0950] Users input personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application. In addition, the user's emotional data is acquired through the device's built-in camera and microphone.

[0951] The device sends the personal data and emotion data entered by the user to the server in JSON format, encrypted before transmission.

[0952] 2. Data storage

[0953] The server stores the received personal and emotional data in a database, where it is mapped to appropriate fields for easy later analysis.

[0954] 3. Data and Sentiment Analysis

[0955] The server periodically analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using machine learning algorithms, such as clustering and classification algorithms.

[0956] The emotion engine analyzes the user's emotional data in real time to identify their current emotional state, which is also used for behavioral pattern analysis.

[0957] 4. Generate action schedule

[0958] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and current emotional state.

[0959] For example, if a user is tired and in need of relaxation, the AI ​​will suggest relaxing events and activities as part of their agenda.

[0960] 5. Providing a timeline of actions

[0961] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[0962] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[0963] Specific examples

[0964] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is acquired, the flow is as follows.

[0965] 1. User data collection

[0966] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[0967] The device sends this data to the server in JSON format: { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"}

[0968] 2. Data storage

[0969] The server stores the received data in a database, for example, in the format INSERT INTO users (hobbies, purchase_history, emotion) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[0970] 3. Data and Sentiment Analysis

[0971] The server analyzes the data through daily batch processing. Using Python scripts, it analyzes the user's behavioral patterns and determines whether they are interested in "watching sports." At the same time, the emotion engine detects "stress" and reports their current emotional state.

[0972] 4. Generate action schedule

[0973] The server inputs the data into the generation AI based on the analysis results, which then suggests relaxing events (such as relaxation spots or concerts) based on the emotional data.

[0974] 5. Providing a timeline of actions

[0975] The server sends the generated action plan in JSON format to the user's device: { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}

[0976] The device displays the received data in its calendar app or notification system, allowing the user to see their "Spa & Relax This Weekend" appointments.

[0977] In this way, the system can provide a personalized future itinerary that takes into account the user's emotional state.

[0978] The processing flow will be explained below.

[0979] Step 1:

[0980] Using a dedicated application, users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected through the device's built-in camera and microphone.

[0981] Step 2:

[0982] The device serializes the personal data entered by the user and the collected emotional data into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0983] Step 3:

[0984] The server decodes the received JSON-formatted personal data and emotion data and maps them to appropriate fields in a database. For example, personal data is stored in a user table, and emotion data is stored in an emotion table.

[0985] Step 4:

[0986] The server analyzes the stored personal data and emotional data through daily batch processing to identify users' behavioral patterns and emotional states. Machine learning algorithms, especially clustering and classification algorithms, are used to classify the data and extract patterns.

[0987] Step 5:

[0988] The emotion engine analyzes the acquired emotion data to identify the user's current emotional state, identifying emotion categories (e.g., stress, joy, sadness, etc.), and integrating this information into behavioral pattern analysis.

[0989] Step 6:

[0990] The server inputs data into the generation AI based on the analysis results. The generation AI integrates preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and emotional state.

[0991] Step 7:

[0992] The server saves the generated schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[0993] Step 8:

[0994] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[0995] Step 9:

[0996] The device decodes the received JSON data of the scheduled events and displays the scheduled events in the calendar app or notification system. Specifically, the scheduled events information is rendered in the UI components within the app and displayed visually to the user.

[0997] Step 10:

[0998] Users can review the proposed action plan and accept, modify, or delete it as needed, allowing them to easily manage a personalized future action plan that takes their emotional state into account.

[0999] Example 2

[1000] 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."

[1001] Conventional systems can generate activity plans based on a user's personal data, but they have limitations in providing activity plans that reflect the user's real-time emotional state. Furthermore, it is difficult to provide personalized suggestions that effectively utilize external big data. This makes it impossible to propose optimal activity plans that reflect the user's emotional state, which poses a challenge in sufficiently improving user satisfaction.

[1002] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting personal data and emotional data input by the user; means for saving the personal data and emotional data in a database; means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state; means including an emotion engine for analyzing the emotional data in real time; means for generating a future action plan using a generation AI based on the behavioral patterns and emotional state; means for the generation AI to integrate the preprocessed personal data, emotional data, and external data and perform statistical analysis and pattern matching; means for providing the action plan to the user's terminal; and means for displaying the action plan on the user's terminal. This makes it possible to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on the analysis.

[1003] "Personal data entered by the user" refers to information such as hobbies, preferences, behavioral history, purchasing history, and family composition that the user himself / herself enters through a dedicated application.

[1004] "Emotional data" refers to information about a user's emotional state acquired through a camera or microphone built into the user's device.

[1005] "Database" refers to an information system for storing and managing collected and saved personal data and emotional data.

[1006] "Behavioral patterns" refer to unique behavioral tendencies and patterns that are analyzed based on a user's past behavioral history and hobbies and preferences.

[1007] "Emotion engine" refers to software or a system that analyzes a user's emotional data in real time to identify the user's current emotional state.

[1008] "Generative AI" refers to an artificial intelligence model that takes a user's personal data and emotional data as input and generates future action plans based on that data.

[1009] "Preprocessing" refers to a series of operations that format and convert input data so that it can be easily processed by analytical or generative AI.

[1010] "Statistical analysis" refers to a set of techniques for analyzing data using statistical methods to understand the characteristics and patterns of the data.

[1011] "Pattern matching" refers to algorithms and techniques for detecting and identifying specific patterns or templates within data.

[1012] "Action Plan" refers to future action plans or events suggested by the generative AI, taking into account the user's hobbies, preferences, and emotional state.

[1013] "Terminal" refers to a device used by a user (such as a smartphone or tablet) that is a computer system used to input personal data and emotional data, display planned activities, etc.

[1014] "External data" refers to big data and reference data provided by third parties other than users' personal data and emotional data.

[1015] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[1016] System configuration

[1017] The system consists of the following elements:

[1018] 1. Collection of personal and emotional data

[1019] Users enter personal data (hobbies, preferences, behavioral history, purchasing history, family composition, etc.) through a dedicated application, and emotional data is recorded using the device's camera and microphone.

[1020] The terminal converts this data into JSON format, encrypts it, and sends it to the server.

[1021] 2. Data storage

[1022] The server receives the encrypted JSON data, decrypts it, and stores it in a database, where it is properly mapped to personal data and emotional data.

[1023] 3. Data and Sentiment Analysis

[1024] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[1025] The emotion engine analyzes the user's emotion data in real time to identify their current emotional state.

[1026] 4. Generate action schedule

[1027] The server inputs data into the generative AI model based on the pre-processed personal data and emotion data, which then performs statistical analysis and pattern matching to generate an optimal action plan.

[1028] 5. Providing a timeline of actions

[1029] The server sends the generated action plan in JSON format to the user's device.

[1030] The device displays the received schedule to the user through a calendar app or notification system.

[1031] Specific examples

[1032] For example, consider a case where user A inputs data that "watching sports is a hobby, and has purchased tickets to baseball and soccer games in the past," and is currently feeling stressed.

[1033] 1. User data collection

[1034] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[1035] The device converts this data into JSON format, encrypts it, and sends it to the server:

[1036] json

[1037] {

[1038] "user_id": "12345",

[1039] "hobbies": ["watching sports"],

[1040] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[1041] "emotion": "stress"

[1042] }

[1043] 2. Data storage

[1044] The server interprets the data and stores it in the database, for example, by executing the following SQL statement: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[1045] 3. Data and Sentiment Analysis

[1046] The server analyzes the data in the database and identifies the user's behavior pattern of "watching sports." At the same time, the emotion engine detects stress and notifies the server of the results.

[1047] 4. Generate action schedule

[1048] The server inputs data into the generation AI based on the analysis results, and the generation AI suggests relaxation events (e.g., spa & relaxation).

[1049] 5. Providing a timeline of actions

[1050] The server sends the generated schedule to the user's device in JSON format:

[1051] json

[1052] {

[1053] "action": "relaxation",

[1054] "date": "this weekend",

[1055] "detail": "Spa & Relax"

[1056] }

[1057] The device displays the received data in its calendar app or notification system, allowing the user to check their "Spa & Relax This Weekend" schedule.

[1058] Prompt Sentence Examples

[1059] "If User A enjoys watching sports and has been feeling stressed lately, please suggest some relaxing activities."

[1060] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1061] Step 1: Data collection

[1062] The user opens a dedicated application and inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. Emotional data is also recorded using the device's camera and microphone.

[1063] Input: User input of personal and emotional data.

[1064] Output: Personal data and emotion data converted by the device into JSON format.

[1065] Specific operation: The user enters information such as "watching sports," "baseball game tickets, soccer game tickets," and "stress," and the device compiles this in JSON format.

[1066] Step 2: Send data

[1067] The device converts the personal data and emotional data entered into JSON format, encrypts it, and sends it to the server.

[1068] Input: Personal and sentiment data in JSON format.

[1069] Output: Encrypted JSON data.

[1070] Specific operation: The device uses the RSA encryption algorithm to encrypt the JSON data { "user_id": "12345", "hobbies": ["Watching Sports"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"], "emotion": "Stress"} and sends it to the server.

[1071] Step 3: Save your data

[1072] The server decodes the received JSON data and stores it in the database.

[1073] Input: Encrypted JSON data.

[1074] Output: Personal and emotional data stored in a database.

[1075] What happens: The server performs RSA decryption and stores the decrypted data in the database using an SQL query, e.g.: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Tickets', 'Baseball Tickets, Football Tickets', 'Stress').

[1076] Step 4: Analyzing the data and sentiment data

[1077] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[1078] Input: Personal and emotional data stored in a database.

[1079] Output: Analysis of the user's behavioral patterns and emotional state.

[1080] Specific operation: A Python script is used to apply a clustering algorithm to the acquired data to identify the behavioral pattern of "interested in watching sports." The emotion engine detects "stress" and reports it to the server.

[1081] Step 5: Generate an action plan

[1082] Based on the analysis results, the server inputs the data into a generated AI model, performs statistical analysis and pattern matching, and generates an optimal action plan.

[1083] Input: Analysis results of behavioral patterns and emotional states.

[1084] Output: Action plan generated by the generation AI.

[1085] Specific operation: The generating AI is input with data on "hobby of watching sports" and "stress level," and while referring to external data, suggests relaxation activities (e.g., spa and relaxation events).

[1086] Step 6: Provide an action plan

[1087] The server sends the generated action plan in JSON format to the user's device.

[1088] Input: The generated event schedule data.

[1089] Output: JSON formatted event schedule sent to the user's device.

[1090] Specific operation: The server converts the generated action plan into JSON format, encrypts the data { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}, and sends it to the device.

[1091] Step 7: View upcoming events

[1092] The device decodes the scheduled events it receives and displays them to the user through a calendar app or notification system.

[1093] Input: JSON formatted event schedule sent from the server.

[1094] Output: The upcoming event displayed in the user's calendar app or notification system.

[1095] Specific behavior: The device decodes and interprets the received JSON data, adds an event for "Spa & Relax This Weekend" to the calendar app, and notifies the user via the notification system.

[1096] This allows the system to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on that.

[1097] (Application example 2)

[1098] 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."

[1099] In recent years, there has been a growing demand for individually customized services that take into account users' behavioral patterns and emotional states. However, existing systems are unable to fully utilize users' emotional data, making it difficult to provide appropriate security advice based on the user's current emotions and future plans. This has prevented efficient security management from being realized to enhance user safety. This issue is particularly pronounced in real-time security management using wearable devices such as smart glasses.

[1100] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data and emotional data input by the user, means for saving the personal data and emotional data in a database, means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state, means for generating a future action plan and security advice using a generative AI model based on the behavioral patterns and emotional state, and means for providing the action plan and security advice to the user. This enables real-time security management that reflects the user's emotional state.

[1101] "Personal data" refers to personal information such as a user's hobbies, preferences, behavioral history, purchasing history, and family composition.

[1102] "Emotional data" refers to information that indicates the user's current emotional state and is collected via a camera or microphone.

[1103] "Database" refers to a system for storing collected personal and emotional data.

[1104] "Behavioral patterns" refer to certain regularities or tendencies that are found as a result of analyzing a user's past behavioral history.

[1105] "Emotional state" refers to a user's current emotional or psychological state.

[1106] A "generative AI model" refers to an artificial intelligence model that generates optimal action plans and security advice for users based on the results of data analysis.

[1107] "Future action plan" refers to an action plan for a future date that is generated based on the user's current emotional state and behavioral patterns.

[1108] "Security advice" refers to suggestions for avoiding potential future risks and dangers based on the user's emotional state and behavioral patterns.

[1109] "Collection means" refers to a device or method for collecting personal data and emotional data of a user.

[1110] "Storage means" refers to the device or method for recording collected data in a database.

[1111] "Analysis means" refers to devices and methods for analyzing collected data and identifying user behavioral patterns and emotional states.

[1112] "Providing means" refers to a device or method for notifying the user of the generated action plan and security advice.

[1113] 1. System Program

[1114] This invention provides a system that collects personal data and emotional data of users, stores them in a database, and analyzes the data to identify the user's behavioral patterns and emotional state. Based on the identified behavioral patterns and emotional state, the system uses a generative AI model to generate future action plans and security advice, which are then provided to the user.

[1115] 2. Hardware and software used

[1116] The system is implemented using the following hardware and software:

[1117] Hardware: Smart glasses (with built-in camera and microphone)

[1118] Software: Python, REST API, JSON, Server

[1119] The server provides a dedicated application to collect personal and emotional data from each user. Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through this dedicated application. Furthermore, emotional data is collected using the camera and microphone in the smart glasses.

[1120] The device then converts the collected personal and emotional data into JSON format and sends it to the server, which stores it in a database.

[1121] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. This analysis is performed using machine learning algorithms, such as clustering and classification algorithms. The emotion engine analyzes the emotional data in real time to identify the user's current emotional state. This information is also used for behavioral pattern analysis.

[1122] Based on the analysis results, the server inputs the data into a generative AI model, which performs statistical analysis and pattern matching using preprocessed personal data, emotional data, and Big Data. The generative AI model generates optimal action plans and security advice taking into account the user's preferences and current emotional state.

[1123] Finally, the server provides the generated schedule and security advice to the user's device, which displays them in a JSON format via a calendar app or notification system.

[1124] 3. Specific Examples

[1125] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is obtained, the generative AI model will generate an itinerary for relaxing events (e.g., relaxation spots and concerts) and security advice.

[1126] An example prompt is:

[1127] Based on the user's hobbies, past behavioral history, and current emotional data, we suggest risks and avoidance actions for the next day. The current emotion is "anxiety." The user frequently visits "parks" and "libraries." What avoidance actions should be suggested?

[1128] In this way, the system can provide personalized future itineraries and security advice in real time that take into account the user's emotional state.

[1129] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1130] Step 1:

[1131] The user inputs personal data and emotional data. Using a dedicated application, the user inputs personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected using the camera and microphone of the smart glasses. The input data is converted into JSON format.

[1132] Input: User's personal and emotional data

[1133] Output: JSON format data (e.g., { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"})

[1134] Step 2:

[1135] The device sends the collected personal and emotional data to a server in JSON format over an encrypted connection.

[1136] Input: Personal data and emotion data in JSON format

[1137] Output: A request to send data to the server

[1138] Step 3:

[1139] The server stores the received personal data and emotion data in a database, which maps the data to appropriate fields for efficient analysis.

[1140] Input: Personal data and emotion data in JSON format

[1141] Output: Data stored in the database

[1142] Step 4:

[1143] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. The analysis uses machine learning algorithms, such as clustering and classification algorithms, to analyze the data. The emotion engine analyzes emotions in real time.

[1144] Input: Personal data and emotional data stored in a database

[1145] Output: Identified behavioral patterns and emotional states

[1146] Step 5:

[1147] The server inputs the analysis results into a generative AI model, which combines preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching to generate optimal future action plans and security advice for the user.

[1148] Input: Identified behavioral patterns and emotional states

[1149] Output: Generated itinerary and security advice (e.g., { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"})

[1150] Step 6:

[1151] The server then provides the generated schedule and security advice to the user's device. The schedule and security advice are sent in JSON format, and the device displays the received data in a calendar app or notification system.

[1152] Input: Generated action plan and security advice

[1153] Output: Agenda and security advice displayed on the user's device

[1154] 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.

[1155] 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.

[1156] 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.

[1157] [Fourth embodiment]

[1158] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1159] 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.

[1160] 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).

[1161] 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.

[1162] 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.

[1163] 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).

[1164] 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. 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.

[1165] 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.

[1166] 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.

[1167] 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.

[1168] 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.

[1169] 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.

[1170] 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."

[1171] This invention relates to a system that uses AI to generate future schedules based on a user's personal data and provides them to the user. Specifically, the system collects data from the user's device, analyzes the data and generates schedules on a server, and provides the generated schedules to the user.

[1172] System configuration

[1173] This system consists of the following elements:

[1174] 1. Collection of personal data

[1175] Users enter personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application.

[1176] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[1177] 2. Data storage

[1178] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[1179] 3. Data Analysis

[1180] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[1181] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[1182] 4. Generate action schedule

[1183] The server uses a generation AI based on the analysis results to generate a future schedule of activities while referencing Big Data. The generation AI performs statistical analysis and proposes the optimal schedule for the user.

[1184] For example, if a user is interested in sports, the AI ​​will look up sporting events taking place next Monday and create an action plan to watch that event.

[1185] 5. Providing a timeline of actions

[1186] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[1187] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[1188] Specific examples

[1189] For example, suppose user A inputs data that "watching sports is a hobby, and in the past, he has purchased tickets to baseball and soccer games."

[1190] 1. User data collection

[1191] The user inputs into the application, "Watching sports is my hobby" and "I purchase tickets for baseball games and soccer games."

[1192] The device sends this data to the server in JSON format: { "hobbies": ["Sports Games"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"]}

[1193] 2. Data storage

[1194] The server stores the received data in the database, for example, in the format INSERT INTO users (hobbies, purchase_history) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets').

[1195] 3. Data Analysis

[1196] The server analyzes the data through daily batch processing, and uses Python scripts to analyze user behavior patterns and determine whether users are interested in "watching sports."

[1197] 4. Generate action schedule

[1198] The server inputs the data into the generation AI based on the analysis results, and generates a future schedule by referencing Big Data. For example, suppose there is a professional baseball game taking place next Monday, and this is used as the schedule.

[1199] 5. Providing a timeline of actions

[1200] The server sends the generated action plan to the user's device in JSON format: { "action": "Watch the game", "date": "Next Monday", "detail": "Professional baseball game"}

[1201] The device displays the received data in a calendar app or notification system, allowing the user to check their schedule for "watching a professional baseball game next Monday."

[1202] The processing flow will be explained below.

[1203] Step 1:

[1204] Using a dedicated application, the user inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. After completing the input, the user presses the "Send" button.

[1205] Step 2:

[1206] The device serializes the personal data entered by the user into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[1207] Step 3:

[1208] The server decodes the received JSON-formatted personal data, maps it to the appropriate fields in the database, and then stores the personal data in a database engine (e.g., MySQL or MongoDB).

[1209] Step 4:

[1210] The server analyzes the stored personal data through daily batch processing using Python scripts and SQL queries to extract user preferences and behavioral patterns. For example, machine learning clustering and classification algorithms are used to analyze the data and identify preference patterns.

[1211] Step 5:

[1212] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the pre-processed user data with Big Data and performs statistical analysis and pattern matching. The generation AI generates a future action plan based on the user's interests.

[1213] Step 6:

[1214] The server saves the generated future schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[1215] Step 7:

[1216] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[1217] Step 8:

[1218] The device decodes the received JSON data of the planned events and displays it in the calendar app or notification system. Specifically, it renders the planned events information into UI components within the app and displays them visually to the user.

[1219] Step 9:

[1220] Users can review the proposed action plans and accept, modify, or delete them as needed, allowing users to easily manage their personalized future action plans.

[1221] Example 1

[1222] 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."

[1223] In modern society, it is becoming increasingly important to support users' busy lives by efficiently generating personalized itineraries. However, systems that can automatically generate and appropriately provide accurate itineraries based on users' preferences and behavioral history are still insufficient. Furthermore, there is a need for methods to improve user convenience while ensuring data security and privacy.

[1224] 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.

[1225] In this invention, the server includes means for collecting personal data input by the user, means for saving the personal data in a database, means for encrypting and transmitting the personal data, means for inputting the data to the generation AI based on the analysis results, and means for decrypting the action plan and displaying it to the user. This makes it possible to appropriately generate and safely provide a personalized action plan for the user, thereby improving convenience.

[1226] "Personal data" refers to data entered by the user regarding hobbies, preferences, behavioral history, purchasing history, family structure, and the like.

[1227] A "database" is an information management system that allows a server to store personal data.

[1228] "Behavioral patterns" refer to the tendencies of a user's behavior, hobbies, and preferences that the server obtains by analyzing personal data.

[1229] "Generative AI" is a general term for algorithms and models used for prediction and generation, and is used to generate user action plans.

[1230] An "action plan" is a future activity plan suggested by the generation AI based on the user's behavioral patterns.

[1231] "Encryption" is a technique used to securely transmit data by converting the data into a form different from its original form.

[1232] "Decryption" is the process of returning encrypted data to its original form.

[1233] The present invention relates to a system that uses AI to generate future activity plans based on a user's personal data and provides them to the user. The system collects and analyzes personal data entered by the user and proposes an activity plan based on the results. Detailed embodiments are described below.

[1234] First, the user uses a dedicated application to enter personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. The data entered by the user is formatted in JSON format by the device, encrypted using the RSA encryption algorithm, and then sent to the server.

[1235] The server then decrypts the encrypted personal data it receives and stores it in a database using MySQL or PostgreSQL, mapping the personal data to appropriate fields for easy analysis.

[1236] The server then periodically analyzes the personal data in the database using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). The analysis results in identifying user behavior patterns and saving the behavioral model as a behavior pattern in JSON format.

[1237] Based on the analyzed behavioral patterns, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, allowing it to appropriately generate the user's action plan.

[1238] As a concrete example, if a user inputs the data that "Watching sports is a hobby and has purchased tickets to baseball and soccer games in the past," the following prompt sentence is input to the generative AI model: "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an action plan."

[1239] The generated schedule is then encrypted again in JSON format and sent to the user's device, where it is decrypted and displayed to the user via a calendar app or notification system (e.g., Google Calendar API, iOS Notification Center).

[1240] This allows the user to check their schedule for watching a professional baseball game next Monday. In this way, a personalized activity schedule for the user is efficiently generated and provided.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] The user enters personal data into a dedicated application. The entered data includes hobbies, preferences, behavioral history, purchasing history, family composition, etc. This data is entered into the application's form and formatted in JSON format. An example of entered data is the following JSON format:

[1244] json

[1245] {

[1246] "hobbies": ["watching sports"],

[1247] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[1248] "family": ["The whole family is a sports fan"]

[1249] }

[1250] The terminal encrypts this JSON data using the RSA encryption algorithm and then sends it to the server.

[1251] Step 2:

[1252] The server receives the encrypted personal data and decrypts it using the RSA algorithm. The decrypted data is then stored in a database, typically using MySQL or PostgreSQL. Specifically, the data is mapped to the appropriate fields and stored using the following SQL statement:

[1253] sql

[1254] INSERT INTO users (hobbies, purchase_history, family)

[1255] VALUES ('Watching sports', 'Baseball game tickets, Football game tickets', 'The whole family is a sports fan');

[1256] The input here is the decoded JSON data, and the output is the person data inserted into the database.

[1257] Step 3:

[1258] The server periodically analyzes the personal data in the database. This analysis is performed using Python scripts and machine learning algorithms (e.g., K-Means clustering and Random Forest classifiers). As a result of the analysis, behavioral patterns of individual users are identified and a behavioral model is saved as a behavioral pattern in JSON format. Specific operations include reading from the database, analyzing using machine learning algorithms, and saving the analysis results. The input is the personal data read from the database, and the output is a model based on the behavioral patterns.

[1259] Step 4:

[1260] Based on the analysis results, the server uses a generation AI (e.g., OpenAI GPT-3) to generate a future action plan while referencing big data. Specific prompts are provided to the generation AI, which then generates a future action plan. For example, if a user enters data such as "Watching sports is my hobby, and I have purchased tickets to baseball and soccer games in the past," the following prompts are input into the generation AI model:

[1261] "The user enjoys watching sports, and there is a professional baseball game next Monday. Please generate an activity schedule."

[1262] The generated action schedule is saved in JSON format. The input is the result of the action pattern analysis, and the output is the generated action schedule.

[1263] Step 5:

[1264] The server encrypts the generated schedule in JSON format and sends it to the user's device. An example of a generated schedule is the following JSON output:

[1265] json

[1266] {

[1267] "action": "spectate",

[1268] "date": "next Monday",

[1269] "detail": "Professional baseball game"

[1270] }

[1271] The device receives this encrypted data, decrypts it using the RSA algorithm, and displays the decrypted event to the user through a calendar app or notification system. The input is the encrypted event data, and the output is the decrypted event.

[1272] This allows the user to check their plans to watch a professional baseball game next Monday.

[1273] (Application example 1)

[1274] 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."

[1275] In conventional logistics centers, robot operations require time-consuming setup of individual schedules by managers, making it difficult to allocate work efficiently. Additionally, there was a lack of data analysis and automatic generation mechanisms required to maximize the robot's performance, making it difficult to improve overall operational efficiency.

[1276] 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.

[1277] In this invention, the server includes means for collecting personal data input by users, means for saving the personal data in a database, means for analyzing the personal data and identifying the user's behavioral patterns, means for generating future action plans using a generation AI, and means for providing the action plans to robots in the logistics center. This makes it possible to improve the work efficiency of the robots in the logistics center, reduce the burden on managers, and optimize overall work efficiency.

[1278] "User" refers to the entity that uses the system and is the person to whom personal data is provided.

[1279] "Personal data" refers to information such as a user's behavioral history, hobbies and preferences, and purchasing history.

[1280] "Database" means a data management system that stores collected personal data and makes it accessible when needed.

[1281] "Behavioral patterns" refer to a tendency for a user to take certain actions based on analyzed personal data.

[1282] "Generative AI" refers to technology that uses artificial intelligence to generate new information and predictions based on input data.

[1283] A "future action plan" is an action plan for a specific date and time in the future that is created by the generation AI based on the user's behavior patterns.

[1284] A "logistics center" is a facility where goods and materials are managed, picked, packed, and shipped.

[1285] A "robot" is a piece of equipment that performs work automatically within a logistics center and operates based on a schedule.

[1286] A "machine learning algorithm" is an algorithm used in data analysis, a method for automatically learning from empirical data and identifying patterns.

[1287] "Big data" refers to a large and diverse set of data, a collection of data that can be used for analysis.

[1288] This invention relates to a system that uses AI to generate future action plans based on a user's personal data and provides them to a robot at a logistics center. Specifically, the system collects data from the user's terminal, analyzes the data and generates an action plan on the server, and then provides the generated action plan to the robot.

[1289] System configuration

[1290] This system consists of the following elements:

[1291] 1. Collection of personal data

[1292] Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application.

[1293] The terminal sends the data entered by the user to the server in JSON format, and the data is encrypted before being sent.

[1294] 2. Data storage

[1295] The server stores the received personal data in a database, where it is mapped to appropriate fields for easy later analysis.

[1296] 3. Data Analysis

[1297] The server periodically analyzes the personal data in the database to identify user behavior patterns using machine learning algorithms, such as clustering and classification algorithms.

[1298] The analysis results are saved as a behavioral model that reflects the user's hobbies, preferences, and behavioral patterns.

[1299] 4. Generate action schedule

[1300] The server uses a generation AI based on the analysis results to generate a future action plan while referencing big data. The generation AI performs statistical analysis and proposes the optimal action plan for the user.

[1301] For example, when generating a robot's activity schedule for the next week at a logistics center, if past data shows that it will be performing picking, packing, and shipping assistance, the system will create an activity schedule that takes into account the priority of those tasks.

[1302] 5. Providing a timeline of actions

[1303] The server provides the robot's terminal with the generated action plan in JSON format, which contains the information necessary for a specific robot in the logistics center to operate efficiently.

[1304] The terminal receives the action plan and instructs the robot on its actions based on the action plan, allowing the robot to perform its work efficiently on the specified date.

[1305] For example, if a manager predicts that "the volume of picking work will be high this week," the system will automatically adjust the robot's schedule for the next week based on past data and big data, generating a detailed schedule such as "8 hours of picking on Monday," "6 hours of picking and 2 hours of packing on Tuesday," etc. During this process, the following prompt sentences are input into the generative AI model.

[1306] Example prompt sentence:

[1307] "Please generate a schedule for the robot's activities in the distribution center for the next week. According to past data, it is currently performing the tasks of picking, packing, and shipping assistance. The priority of each task is as follows: picking: high, packing: medium, shipping assistance: low. Please generate the most efficient schedule based on this."

[1308] This enables the system to achieve efficient operation of robots in logistics centers, reduce the burden on managers, and optimize work efficiency.

[1309] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1310] Step 1:

[1311] Users enter personal data such as their hobbies, preferences, behavioral history, purchasing history, and work history through a dedicated application. The data entered here specifically includes "type of work," "frequency of work," and "work evaluation score." This data is formatted in JSON format.

[1312] Step 2:

[1313] The terminal sends the data entered by the user in JSON format to the server. At this time, the data is encrypted using an encryption algorithm such as AES. For example, if the input data is {"tasks": ["Picking"], "frequency": [5], "score": [4.5]}, it will be sent to the server in encrypted form.

[1314] Step 3:

[1315] The server stores the received personal data in a database. Here, it parses the JSON format data and maps it appropriately to each field. For example, the database stores "picking" in the tasks field, "5" in the frequency field, and "4.5" in the score field.

[1316] Step 4:

[1317] The server periodically analyzes the personal data in the database. This analysis is performed using scripts such as Python and machine learning algorithms (e.g., KMeans clustering). The input data is all the robot data in the database, and the output is clusters that represent the robot's behavioral patterns.

[1318] Step 5:

[1319] The server inputs data into a generative AI model based on the analysis results, and generates future action plans while referencing big data. At this time, a specific prompt is input into the generative AI. For example, the prompt might be, "Please generate an action plan for the robots at the logistics center for the next week. According to past data, they are performing picking, packing, and shipping assistance." The output of this process is a detailed action plan for the next week.

[1320] Step 6:

[1321] The server provides the generated action schedule to the robot terminal in JSON format. Here, the action schedule is sent in the format {"date": "2023-10-01", "task": "picking", "duration": "8 hours"}, for example.

[1322] Step 7:

[1323] The terminal receives the action plan and instructs the robot on its actions based on that plan. The robot then follows this plan and performs specific actions, such as "picking" for "8 hours" on the specified date.

[1324] 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.

[1325] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[1326] System configuration

[1327] This system consists of the following elements:

[1328] 1. Collection of personal and emotional data

[1329] Users input personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition through a dedicated application. In addition, the user's emotional data is acquired through the device's built-in camera and microphone.

[1330] The device sends the personal data and emotion data entered by the user to the server in JSON format, encrypted before transmission.

[1331] 2. Data storage

[1332] The server stores the received personal and emotional data in a database, where it is mapped to appropriate fields for easy later analysis.

[1333] 3. Data and Sentiment Analysis

[1334] The server periodically analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using machine learning algorithms, such as clustering and classification algorithms.

[1335] The emotion engine analyzes the user's emotional data in real time to identify their current emotional state, which is also used for behavioral pattern analysis.

[1336] 4. Generate action schedule

[1337] The server inputs data into the generation AI based on the analysis results. The generation AI integrates the preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and current emotional state.

[1338] For example, if a user is tired and in need of relaxation, the AI ​​will suggest relaxing events and activities as part of their agenda.

[1339] 5. Providing a timeline of actions

[1340] The server provides the generated schedule to the user's device. The schedule is sent in JSON format.

[1341] The device receives the planned activities and displays them to the user through a calendar app or notification system, allowing the user to review the proposed planned activities.

[1342] Specific examples

[1343] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is acquired, the flow is as follows.

[1344] 1. User data collection

[1345] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[1346] The device sends this data to the server in JSON format: { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"}

[1347] 2. Data storage

[1348] The server stores the received data in a database, for example, in the format INSERT INTO users (hobbies, purchase_history, emotion) VALUES ('Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[1349] 3. Data and Sentiment Analysis

[1350] The server analyzes the data through daily batch processing. Using Python scripts, it analyzes the user's behavioral patterns and determines whether they are interested in "watching sports." At the same time, the emotion engine detects "stress" and reports their current emotional state.

[1351] 4. Generate action schedule

[1352] The server inputs the data into the generation AI based on the analysis results, which then suggests relaxing events (such as relaxation spots or concerts) based on the emotional data.

[1353] 5. Providing a timeline of actions

[1354] The server sends the generated action plan in JSON format to the user's device: { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}

[1355] The device displays the received data in its calendar app or notification system, allowing the user to see their "Spa & Relax This Weekend" appointments.

[1356] In this way, the system can provide a personalized future itinerary that takes into account the user's emotional state.

[1357] The processing flow will be explained below.

[1358] Step 1:

[1359] Using a dedicated application, users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected through the device's built-in camera and microphone.

[1360] Step 2:

[1361] The device serializes the personal data entered by the user and the collected emotional data into JSON format, which is then encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[1362] Step 3:

[1363] The server decodes the received JSON-formatted personal data and emotion data and maps them to appropriate fields in a database. For example, personal data is stored in a user table, and emotion data is stored in an emotion table.

[1364] Step 4:

[1365] The server analyzes the stored personal data and emotional data through daily batch processing to identify users' behavioral patterns and emotional states. Machine learning algorithms, especially clustering and classification algorithms, are used to classify the data and extract patterns.

[1366] Step 5:

[1367] The emotion engine analyzes the acquired emotion data to identify the user's current emotional state, identifying emotion categories (e.g., stress, joy, sadness, etc.), and integrating this information into behavioral pattern analysis.

[1368] Step 6:

[1369] The server inputs data into the generation AI based on the analysis results. The generation AI integrates preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching. The generation AI generates an optimal action plan taking into account the user's hobbies, preferences, and emotional state.

[1370] Step 7:

[1371] The server saves the generated schedule to a database. This data includes the schedule contents, date and time, related event information, etc. Saving is done using INSERT statements.

[1372] Step 8:

[1373] The server periodically sends the generated schedule to the user's device as a batch process. The schedule is again serialized in JSON format and transmitted via a secure communication protocol.

[1374] Step 9:

[1375] The device decodes the received JSON data of the scheduled events and displays the scheduled events in the calendar app or notification system. Specifically, the scheduled events information is rendered in the UI components within the app and displayed visually to the user.

[1376] Step 10:

[1377] Users can review the proposed action plan and accept, modify, or delete it as needed, allowing them to easily manage a personalized future action plan that takes their emotional state into account.

[1378] Example 2

[1379] 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."

[1380] Conventional systems can generate activity plans based on a user's personal data, but they have limitations in providing activity plans that reflect the user's real-time emotional state. Furthermore, it is difficult to provide personalized suggestions that effectively utilize external big data. This makes it impossible to propose optimal activity plans that reflect the user's emotional state, which poses a challenge in sufficiently improving user satisfaction.

[1381] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting personal data and emotional data input by the user; means for saving the personal data and emotional data in a database; means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state; means including an emotion engine for analyzing the emotional data in real time; means for generating a future action plan using a generation AI based on the behavioral patterns and emotional state; means for the generation AI to integrate the preprocessed personal data, emotional data, and external data and perform statistical analysis and pattern matching; means for providing the action plan to the user's terminal; and means for displaying the action plan on the user's terminal. This makes it possible to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on the analysis.

[1382] "Personal data entered by the user" refers to information such as hobbies, preferences, behavioral history, purchasing history, and family composition that the user himself / herself enters through a dedicated application.

[1383] "Emotional data" refers to information about a user's emotional state acquired through a camera or microphone built into the user's device.

[1384] "Database" refers to an information system for storing and managing collected and saved personal data and emotional data.

[1385] "Behavioral patterns" refer to unique behavioral tendencies and patterns that are analyzed based on a user's past behavioral history and hobbies and preferences.

[1386] "Emotion engine" refers to software or a system that analyzes a user's emotional data in real time to identify the user's current emotional state.

[1387] "Generative AI" refers to an artificial intelligence model that takes a user's personal data and emotional data as input and generates future action plans based on that data.

[1388] "Preprocessing" refers to a series of operations that format and convert input data so that it can be easily processed by analytical or generative AI.

[1389] "Statistical analysis" refers to a set of techniques for analyzing data using statistical methods to understand the characteristics and patterns of the data.

[1390] "Pattern matching" refers to algorithms and techniques for detecting and identifying specific patterns or templates within data.

[1391] "Action Plan" refers to future action plans or events suggested by the generative AI, taking into account the user's hobbies, preferences, and emotional state.

[1392] "Terminal" refers to a device used by a user (such as a smartphone or tablet) that is a computer system used to input personal data and emotional data, display planned activities, etc.

[1393] "External data" refers to big data and reference data provided by third parties other than users' personal data and emotional data.

[1394] This invention relates to a system that uses a generation AI to generate a future action plan based on a user's personal data and emotion data, and provides it to the user. Specifically, the system collects data on the user's device, analyzes and generates an action plan on the server, analyzes emotions using an emotion engine, and provides the generated action plan to the user.

[1395] System configuration

[1396] The system consists of the following elements:

[1397] 1. Collection of personal and emotional data

[1398] Users enter personal data (hobbies, preferences, behavioral history, purchasing history, family composition, etc.) through a dedicated application, and emotional data is recorded using the device's camera and microphone.

[1399] The terminal converts this data into JSON format, encrypts it, and sends it to the server.

[1400] 2. Data storage

[1401] The server receives the encrypted JSON data, decrypts it, and stores it in a database, where it is properly mapped to personal data and emotional data.

[1402] 3. Data and Sentiment Analysis

[1403] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[1404] The emotion engine analyzes the user's emotion data in real time to identify their current emotional state.

[1405] 4. Generate action schedule

[1406] The server inputs data into the generative AI model based on the pre-processed personal data and emotion data, which then performs statistical analysis and pattern matching to generate an optimal action plan.

[1407] 5. Providing a timeline of actions

[1408] The server sends the generated action plan in JSON format to the user's device.

[1409] The device displays the received schedule to the user through a calendar app or notification system.

[1410] Specific examples

[1411] For example, consider a case where user A inputs data that "watching sports is a hobby, and has purchased tickets to baseball and soccer games in the past," and is currently feeling stressed.

[1412] 1. User data collection

[1413] The user enters "Watching sports is my hobby" and "I have purchased tickets for baseball and soccer games" into the application, and the current emotion of "stress" is recorded via the camera and microphone.

[1414] The device converts this data into JSON format, encrypts it, and sends it to the server:

[1415] json

[1416] {

[1417] "user_id": "12345",

[1418] "hobbies": ["watching sports"],

[1419] "purchase_history": ["Baseball game tickets", "Football game tickets"],

[1420] "emotion": "stress"

[1421] }

[1422] 2. Data storage

[1423] The server interprets the data and stores it in the database, for example, by executing the following SQL statement: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Games', 'Baseball Game Tickets, Football Game Tickets', 'Stress').

[1424] 3. Data and Sentiment Analysis

[1425] The server analyzes the data in the database and identifies the user's behavior pattern of "watching sports." At the same time, the emotion engine detects stress and notifies the server of the results.

[1426] 4. Generate action schedule

[1427] The server inputs data into the generation AI based on the analysis results, and the generation AI suggests relaxation events (e.g., spa & relaxation).

[1428] 5. Providing a timeline of actions

[1429] The server sends the generated schedule to the user's device in JSON format:

[1430] json

[1431] {

[1432] "action": "relaxation",

[1433] "date": "this weekend",

[1434] "detail": "Spa & Relax"

[1435] }

[1436] The device displays the received data in its calendar app or notification system, allowing the user to check their "Spa & Relax This Weekend" schedule.

[1437] Prompt Sentence Examples

[1438] "If User A enjoys watching sports and has been feeling stressed lately, please suggest some relaxing activities."

[1439] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1440] Step 1: Data collection

[1441] The user opens a dedicated application and inputs personal data such as hobbies, preferences, behavioral history, purchasing history, family composition, etc. Emotional data is also recorded using the device's camera and microphone.

[1442] Input: User input of personal and emotional data.

[1443] Output: Personal data and emotion data converted by the device into JSON format.

[1444] Specific operation: The user enters information such as "watching sports," "baseball game tickets, soccer game tickets," and "stress," and the device compiles this in JSON format.

[1445] Step 2: Send data

[1446] The device converts the personal data and emotional data entered into JSON format, encrypts it, and sends it to the server.

[1447] Input: Personal and sentiment data in JSON format.

[1448] Output: Encrypted JSON data.

[1449] Specific operation: The device uses the RSA encryption algorithm to encrypt the JSON data { "user_id": "12345", "hobbies": ["Watching Sports"], "purchase_history": ["Baseball Game Tickets", "Football Game Tickets"], "emotion": "Stress"} and sends it to the server.

[1450] Step 3: Save your data

[1451] The server decodes the received JSON data and stores it in the database.

[1452] Input: Encrypted JSON data.

[1453] Output: Personal and emotional data stored in a database.

[1454] What happens: The server performs RSA decryption and stores the decrypted data in the database using an SQL query, e.g.: INSERT INTO users (user_id, hobbies, purchase_history, emotion) VALUES ('12345', 'Sports Tickets', 'Baseball Tickets, Football Tickets', 'Stress').

[1455] Step 4: Analyzing the data and sentiment data

[1456] The server analyzes the personal and emotional data in the database to identify the user's behavioral patterns and emotional state using clustering and classification algorithms.

[1457] Input: Personal and emotional data stored in a database.

[1458] Output: Analysis of the user's behavioral patterns and emotional state.

[1459] Specific operation: A Python script is used to apply a clustering algorithm to the acquired data to identify the behavioral pattern of "interested in watching sports." The emotion engine detects "stress" and reports it to the server.

[1460] Step 5: Generate an action plan

[1461] Based on the analysis results, the server inputs the data into a generated AI model, performs statistical analysis and pattern matching, and generates an optimal action plan.

[1462] Input: Analysis results of behavioral patterns and emotional states.

[1463] Output: Action plan generated by the generation AI.

[1464] Specific operation: The generating AI is input with data on "hobby of watching sports" and "stress level," and while referring to external data, suggests relaxation activities (e.g., spa and relaxation events).

[1465] Step 6: Provide an action plan

[1466] The server sends the generated action plan in JSON format to the user's device.

[1467] Input: The generated event schedule data.

[1468] Output: JSON formatted event schedule sent to the user's device.

[1469] Specific operation: The server converts the generated action plan into JSON format, encrypts the data { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"}, and sends it to the device.

[1470] Step 7: View upcoming events

[1471] The device decodes the scheduled events it receives and displays them to the user through a calendar app or notification system.

[1472] Input: JSON formatted event schedule sent from the server.

[1473] Output: The upcoming event displayed in the user's calendar app or notification system.

[1474] Specific behavior: The device decodes and interprets the received JSON data, adds an event for "Spa & Relax This Weekend" to the calendar app, and notifies the user via the notification system.

[1475] This allows the system to analyze the user's current emotional state in real time and generate and provide an optimal action plan based on that.

[1476] (Application example 2)

[1477] 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."

[1478] In recent years, there has been a growing demand for individually customized services that take into account users' behavioral patterns and emotional states. However, existing systems are unable to fully utilize users' emotional data, making it difficult to provide appropriate security advice based on the user's current emotions and future plans. This has prevented efficient security management from being realized to enhance user safety. This issue is particularly pronounced in real-time security management using wearable devices such as smart glasses.

[1479] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data and emotional data input by the user, means for saving the personal data and emotional data in a database, means for analyzing the personal data and emotional data and identifying the user's behavioral patterns and emotional state, means for generating a future action plan and security advice using a generative AI model based on the behavioral patterns and emotional state, and means for providing the action plan and security advice to the user. This enables real-time security management that reflects the user's emotional state.

[1480] "Personal data" refers to personal information such as a user's hobbies, preferences, behavioral history, purchasing history, and family composition.

[1481] "Emotional data" refers to information that indicates the user's current emotional state and is collected via a camera or microphone.

[1482] "Database" refers to a system for storing collected personal and emotional data.

[1483] "Behavioral patterns" refer to certain regularities or tendencies that are found as a result of analyzing a user's past behavioral history.

[1484] "Emotional state" refers to a user's current emotional or psychological state.

[1485] A "generative AI model" refers to an artificial intelligence model that generates optimal action plans and security advice for users based on the results of data analysis.

[1486] "Future action plan" refers to an action plan for a future date that is generated based on the user's current emotional state and behavioral patterns.

[1487] "Security advice" refers to suggestions for avoiding potential future risks and dangers based on the user's emotional state and behavioral patterns.

[1488] "Collection means" refers to a device or method for collecting personal data and emotional data of a user.

[1489] "Storage means" refers to the device or method for recording collected data in a database.

[1490] "Analysis means" refers to devices and methods for analyzing collected data and identifying user behavioral patterns and emotional states.

[1491] "Providing means" refers to a device or method for notifying the user of the generated action plan and security advice.

[1492] 1. System Program

[1493] This invention provides a system that collects personal data and emotional data of users, stores them in a database, and analyzes the data to identify the user's behavioral patterns and emotional state. Based on the identified behavioral patterns and emotional state, the system uses a generative AI model to generate future action plans and security advice, which are then provided to the user.

[1494] 2. Hardware and software used

[1495] The system is implemented using the following hardware and software:

[1496] Hardware: Smart glasses (with built-in camera and microphone)

[1497] Software: Python, REST API, JSON, Server

[1498] The server provides a dedicated application to collect personal and emotional data from each user. Users input personal data such as hobbies, preferences, behavioral history, purchasing history, and family composition through this dedicated application. Furthermore, emotional data is collected using the camera and microphone in the smart glasses.

[1499] The device then converts the collected personal and emotional data into JSON format and sends it to the server, which stores it in a database.

[1500] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. This analysis is performed using machine learning algorithms, such as clustering and classification algorithms. The emotion engine analyzes the emotional data in real time to identify the user's current emotional state. This information is also used for behavioral pattern analysis.

[1501] Based on the analysis results, the server inputs the data into a generative AI model, which performs statistical analysis and pattern matching using preprocessed personal data, emotional data, and Big Data. The generative AI model generates optimal action plans and security advice taking into account the user's preferences and current emotional state.

[1502] Finally, the server provides the generated schedule and security advice to the user's device, which displays them in a JSON format via a calendar app or notification system.

[1503] 3. Specific Examples

[1504] For example, if user A inputs data that "watching sports is a hobby and he has purchased tickets to baseball and soccer games in the past," and emotional data indicating that he is currently feeling stressed is obtained, the generative AI model will generate an itinerary for relaxing events (e.g., relaxation spots and concerts) and security advice.

[1505] An example prompt is:

[1506] Based on the user's hobbies, past behavioral history, and current emotional data, we suggest risks and avoidance actions for the next day. The current emotion is "anxiety." The user frequently visits "parks" and "libraries." What avoidance actions should be suggested?

[1507] In this way, the system can provide personalized future itineraries and security advice in real time that take into account the user's emotional state.

[1508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1509] Step 1:

[1510] The user inputs personal data and emotional data. Using a dedicated application, the user inputs personal data such as their hobbies, preferences, behavioral history, purchasing history, and family composition. Emotional data is also collected using the camera and microphone of the smart glasses. The input data is converted into JSON format.

[1511] Input: User's personal and emotional data

[1512] Output: JSON format data (e.g., { "hobbies": ["Watching sports"], "purchase_history": ["Baseball game tickets", "Football game tickets"], "emotion": "Stress"})

[1513] Step 2:

[1514] The device sends the collected personal and emotional data to a server in JSON format over an encrypted connection.

[1515] Input: Personal data and emotion data in JSON format

[1516] Output: A request to send data to the server

[1517] Step 3:

[1518] The server stores the received personal data and emotion data in a database, which maps the data to appropriate fields for efficient analysis.

[1519] Input: Personal data and emotion data in JSON format

[1520] Output: Data stored in the database

[1521] Step 4:

[1522] The server analyzes the stored data to identify the user's behavioral patterns and emotional state. The analysis uses machine learning algorithms, such as clustering and classification algorithms, to analyze the data. The emotion engine analyzes emotions in real time.

[1523] Input: Personal data and emotional data stored in a database

[1524] Output: Identified behavioral patterns and emotional states

[1525] Step 5:

[1526] The server inputs the analysis results into a generative AI model, which combines preprocessed personal data, emotional data, and Big Data, and performs statistical analysis and pattern matching to generate optimal future action plans and security advice for the user.

[1527] Input: Identified behavioral patterns and emotional states

[1528] Output: Generated itinerary and security advice (e.g., { "action": "Relaxation", "date": "This weekend", "detail": "Spa & Relax"})

[1529] Step 6:

[1530] The server then provides the generated schedule and security advice to the user's device. The schedule and security advice are sent in JSON format, and the device displays the received data in a calendar app or notification system.

[1531] Input: Generated action plan and security advice

[1532] Output: Agenda and security advice displayed on the user's device

[1533] 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.

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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).

[1540] 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.

[1541] 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."

[1542] 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.

[1543] 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).

[1544] 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.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] The following is further disclosed regarding the above embodiment.

[1555] (Claim 1)

[1556] A means for collecting personal data input by a user;

[1557] means for storing said personal data in a database;

[1558] means for analyzing the personal data and identifying user behavior patterns;

[1559] A means for generating future action plans based on the action patterns using a generation AI;

[1560] means for providing the activity schedule to a user;

[1561] A system including:

[1562] (Claim 2)

[1563] 10. The system of claim 1, further comprising means for using a machine learning algorithm to identify the behavioral patterns.

[1564] (Claim 3)

[1565] The system according to claim 1, further comprising means for generating the future activity schedule by referring to Big Data.

[1566] "Example 1"

[1567] (Claim 1)

[1568] A means for collecting personal data input by a user;

[1569] means for storing said personal data in a database;

[1570] means for analyzing the personal data and identifying user behavior patterns;

[1571] A means for generating future action plans using the generated AI based on the action patterns;

[1572] means for providing the activity schedule to a user;

[1573] means for encrypting and transmitting said personal data;

[1574] A means for inputting data into a generating AI based on the analysis results;

[1575] means for decoding the action plan and displaying it to a user;

[1576] A system including:

[1577] (Claim 2)

[1578] 10. The system of claim 1, further comprising means for using a machine learning algorithm to identify the behavioral patterns.

[1579] (Claim 3)

[1580] The system according to claim 1, further comprising means for generating the future activity schedule by referring to Big Data.

[1581] "Application Example 1"

[1582] (Claim 1)

[1583] A means for collecting personal data input by a user;

[1584] means for storing said personal data in a database;

[1585] means for analyzing the personal data and identifying user behavior patterns;

[1586] A means for generating future action plans based on the action patterns using a generation AI;

[1587] a means for providing the action schedule to a robot in a logistics center;

[1588] A system including:

[1589] (Claim 2)

[1590] 10. The system of claim 1, further comprising means for using a machine learning algorithm to identify the behavioral patterns.

[1591] (Claim 3)

[1592] The system according to claim 1, further comprising means for generating the future activity schedule by referring to big data.

[1593] "Example 2: Combining Emotion Engines"

[1594] (Claim 1)

[1595] means for collecting personal data and emotional data input from a user;

[1596] means for storing the personal data and emotion data in a database;

[1597] means for analyzing the personal data and emotional data to identify the user's behavioral patterns and emotional state;

[1598] means including an emotion engine for analyzing emotion data in real time;

[1599] A means for generating future action plans using a generation AI based on the action patterns and emotional states;

[1600] A means for the generation AI to integrate the preprocessed personal data, emotional data, and external data, and perform statistical analysis and pattern matching;

[1601] means for providing the activity schedule to a user's terminal;

[1602] means for displaying the activity schedule on a user's terminal;

[1603] A system including:

[1604] (Claim 2)

[1605] 10. The system of claim 1, further comprising means for using clustering and classification algorithms to identify said behavioral patterns.

[1606] (Claim 3)

[1607] 2. The system according to claim 1, further comprising means for generating the future activity schedule by referring to external data.

[1608] "Application example 2 when combining emotion engines"

[1609] (Claim 1)

[1610] means for collecting personal data and emotional data input from a user;

[1611] means for storing the personal data and emotion data in a database;

[1612] means for analyzing the personal data and emotional data to identify the user's behavioral patterns and emotional state;

[1613] means for generating future action plans and security advice using a generative AI model based on the behavioral patterns and emotional states;

[1614] means for providing said plan of action and security advice to a user;

[1615] A system including:

[1616] (Claim 2)

[1617] 10. The system of claim 1, further comprising means for using machine learning algorithms to identify said behavioral patterns and emotional states.

[1618] (Claim 3)

[1619] The system according to claim 1, further comprising means for generating the future action plan and security advice by referring to Big Data. [Explanation of symbols]

[1620] 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. A means for collecting personal data input by a user; means for storing said personal data in a database; means for analyzing the personal data and identifying user behavior patterns; A means for generating future action plans based on the action patterns using a generation AI; means for providing the activity schedule to a user; A system including:

2. The system of claim 1 , further comprising means for using a machine learning algorithm to identify the behavioral patterns.

3. The system according to claim 1 , further comprising: means for generating the future activity schedule by referring to Big Data.

Images