system

Abstract

To provide a system.SOLUTION: A system includes: means for incorporating diary data of a user; means for analyzing the incorporated diary data by using a natural language processing technique; means for extracting an emotional state of the user from the diary data by using an emotion engine, and analyzing an intensity and a frequency of the extracted emotional state; and means for providing feedback to the user based on an analysis result of the diary data and the emotional state of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] For users to deepen their self-understanding, it is important to objectively understand their own behavioral patterns, mood fluctuations, lifestyle trends, etc. However, it is difficult to understand this information through self-observation alone and use it for self-improvement and mental health management. [Means for solving the problem]

[0005] This invention takes diary data from users and analyzes it using generative AI. Based on the analysis results, it provides feedback and insights to users, providing information that helps users deepen their self-understanding. It also provides information that can be used for self-improvement and mental health management. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention uses a web-based interface or dedicated application to collect diary data from users. Users enter their daily events, feelings, and thoughts as a diary, which is then collected by the system.

[0029] "Example 2"

[0030] The captured diary data is analyzed by generative AI, which uses natural language processing (NLP) techniques to extract user behavioral patterns, mood swings, and lifestyle trends. For example, if a user writes in their diary, "I've been staying up late lately," the AI ​​will interpret this as part of their "irregular lifestyle."

[0031] "Example 3"

[0032] Based on the analysis results, the system provides feedback and insights to the user, either in the form of a webpage or app dashboard, or via email or notification. For example, it may provide specific advice such as, "You've been staying up late lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user enters diary data through a web-based interface or a dedicated application. This data includes the user's daily events, emotions, thoughts, etc.

[0036] Step 2: The system captures the diary data from the user. This capture occurs automatically immediately after the user enters the data.

[0037] "Example 2"

[0038] Step 1: The system sends the diary data it has captured to the generative AI.

[0039] Step 2: Generative AI analyzes the diary data using natural language processing (NLP) techniques to extract user behavioral patterns, mood swings, and lifestyle trends.

[0040] "Example 3"

[0041] Step 1: The generative AI sends the analysis results to the system.

[0042] Step 2: The system generates feedback and insights based on the analysis results.

[0043] Step 3: Provide the system-generated feedback and insights to the user, either via a web page, a dashboard in the application, or via email or notification.

[0044] Example 1

[0045] Next, a description will be given of Example 1 of Form 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."

[0046] Conventional systems have struggled to effectively utilize users' diary data to provide useful feedback and insights to users. Furthermore, they lacked a means to analyze users' behavioral patterns, mood swings, and lifestyle trends to provide information useful for self-understanding, self-improvement, and mental health management.

[0047] 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.

[0048] In this invention, the server includes means for importing diary data from a user, means for storing the imported diary data in a database, means for inputting the stored diary data into a generative AI model, means for the generative AI model to analyze the diary data and generate a prompt sentence, and means for providing the generated prompt sentence to the user. This makes it possible to effectively utilize the user's diary data and provide the user with useful feedback and insights.

[0049] "User" refers to an individual who uses the system to enter diary data.

[0050] "Diary data" refers to text data in which users describe their daily events, feelings, and thoughts.

[0051] "Means of importing" refers to the interface or application for receiving diary data from the user.

[0052] "Database" refers to a relational database or other data storage system for storing captured diary data.

[0053] A "generative AI model" refers to an artificial intelligence model that analyzes diary data and generates appropriate prompts for the user.

[0054] "Prompt sentence" refers to text containing questions or instructions for the user that is generated by the generative AI model based on diary data.

[0055] "Means to provide" refers to an interface or application for displaying the generated prompt text to the user.

[0056] "Analyzing" refers to the process by which the generative AI model analyzes diary data to understand the user's behavioral patterns and emotional fluctuations.

[0057] This invention is a system that takes diary data from users, analyzes it using a generative AI model, and provides useful feedback and insights to the users. A specific embodiment of this system is described below.

[0058] Users enter diary data using a web-based interface or a dedicated application. For example, they open a dedicated application on their smartphone and enter daily events, feelings, and thoughts into text boxes. The hardware used can be a PC or smartphone, and the software can be a web browser (such as GOOGLE CHROME®) or a dedicated application (for iOS or ANDROID®).

[0059] The device sends the diary data entered by the user to the server. The HTTPS protocol is used for transmission to ensure data security. For example, when the user presses the "Send" button, the device sends the diary data to the server.

[0060] The server stores the received diary data in a database. A relational database such as MySQL (registered trademark) or PostgreSQL is used as the database. For example, the server executes the SQL query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (?, ?, ?)" to store the data.

[0061] The server retrieves the diary data stored in the database and inputs it into the generative AI model. For example, the server executes the SQL query "SELECT entry_text FROM diary_entries WHERE user_id = ?" to retrieve the data and pass it to the generative AI model.

[0062] The generative AI model analyzes the input diary data and generates an appropriate prompt for the user. For example, if the diary data says, "Today I went to a cafe with my friends and had a great time," the generative AI model generates a prompt such as, "Tell me a specific story about when you went to a cafe with your friends."

[0063] The server provides the prompts received from the generative AI model to the user, for example, by displaying the prompts to the user through a dedicated application or web interface.

[0064] As a concrete example, consider a scenario in which a user uses a dedicated application to enter a diary entry. The user opens the dedicated application on their smartphone and enters, "Today I went to a cafe with a friend and had a great time. The new coffee tasted really good." This diary entry data is sent to a server through the application and saved in a database. The saved data is then input into a generative AI model, which generates a prompt sentence like the following:

[0065] "Tell me a specific story about when you went to a cafe with a friend."

[0066] This prompt is used as a guide for the user to enter further information.

[0067] In this way, users can input diary data and receive prompts from the generative AI model, which can help them understand themselves better and provide information useful for self-improvement and mental health management.

[0068] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0069] Step 1:

[0070] The user enters diary data.

[0071] Using a web-based interface or a dedicated application, users enter their daily events, feelings, and thoughts into a text box. The entered diary data is saved in text format on the device. A specific example is when a user opens the dedicated application on their smartphone and enters, "Today, I went to a cafe with a friend and had a great time. The new coffee tasted great."

[0072] Step 2:

[0073] The device transmits the diary data to the server.

[0074] When the user presses the "Send" button, the device sends the entered diary data to the server using the HTTPS protocol. The input is text diary data, and the output is data sent to the server. Specifically, the device sends the following text data to the server: "Today I went to a cafe with my friends and had a great time. The new coffee tasted great."

[0075] Step 3:

[0076] The server stores the diary data in a database.

[0077] The server saves the received diary data in a database. The input is the text diary data sent from the device, and the output is the data saved in the database. Specifically, the server executes the SQL query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (?, ?, ?)" to save the data.

[0078] Step 4:

[0079] The server inputs the saved diary data into the generative AI model.

[0080] The server retrieves diary data stored in the database and inputs it into the generative AI model. The input is text diary data retrieved from the database, and the output is data input to the generative AI model. Specifically, the server executes the SQL query "SELECT entry_text FROM diary_entries WHERE user_id = ?" to retrieve the data and pass it to the generative AI model.

[0081] Step 5:

[0082] A generative AI model generates prompts.

[0083] The generative AI model analyzes the input diary data and generates an appropriate prompt for the user. The input is text diary data passed from the server, and the output is the generated prompt. In concrete terms, if the diary data says, "Today I went to a cafe with my friends and had a great time," the generative AI model generates a prompt saying, "Tell me a specific story about when you went to a cafe with your friends."

[0084] Step 6:

[0085] The server generates a prompt and provides it to the user.

[0086] The server provides the user with the prompt received from the generative AI model. The input is the prompt received from the generative AI model, and the output is the display of the prompt to the user. Specifically, the server displays the prompt to the user through a dedicated application or web interface.

[0087] (Application example 1)

[0088] Next, a description will be given of Application Example 1 of Embodiment 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."

[0089] Previous systems simply imported users' diary data, but had limited means of effectively utilizing that data. It was also difficult for users to deepen their self-understanding through their diary entries or provide specific feedback and insights to help them manage their mental health. Furthermore, creative content based on diary data was not generated or distributed, making it difficult to attract users' interest.

[0090] 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.

[0091] In this invention, the server includes means for importing diary data from users, generative AI means for analyzing the imported diary data, means for providing feedback and insights to users based on the analysis results, means for automatically generating stories and essays based on the diary data, and means for delivering the generated stories and essays to users. This makes it possible to utilize users' diary data in a variety of ways to support self-understanding and mental health management, as well as to provide creative content.

[0092] "User" refers to an individual who uses the system to enter diary data.

[0093] "Diary data" refers to information recorded by users about their daily events, feelings, and thoughts.

[0094] "Capturing means" refers to a method or device for collecting diary data from users and storing it in the system.

[0095] "Generative AI means" refers to artificial intelligence technology that analyzes imported diary data and generates information tailored to specific purposes.

[0096] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analytical results obtained by generative AI means.

[0097] "Means for automatically generating stories and essays" refers to methods and devices for generating creative writing based on diary data.

[0098] "Delivery means" refers to the method or device by which the generated story or essay is delivered to the user.

[0099] A system for implementing this invention includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for automatically generating stories and essays based on the diary data, and means for delivering the generated stories and essays to the user.

[0100] Hardware and Software Configuration

[0101] Hardware: Smartphone (iOS or Android), server

[0102] Software: Python (registered trademark), OpenAI (registered trademark) API

[0103] Data processing and calculation

[0104] 1. Importing diary data:

[0105] Users enter diary data using a smartphone application, which is then sent to a server and stored in a database.

[0106] 2. Analysis of diary data:

[0107] The server analyzes the captured diary data using generative AI tools (e.g., OpenAI's GPT-3 (registered trademark)). This analysis extracts the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0108] 3. Providing feedback and insights:

[0109] Based on the analysis, the server provides users with feedback and insights, including information to deepen self-understanding and helpful advice for self-improvement and mental health management.

[0110] 4. Automatic generation of stories and essays:

[0111] The server generates prompts based on the diary data and inputs them into a generative AI system to automatically generate stories or essays. For example, the following prompts can be used:

[0112] Please generate a moving story based on the diary data below.

[0113] Date: 2023-10-01

[0114] Content: I went to a cafe with a friend today. It was fun.

[0115] Date: 2023-10-02

[0116] Content: Work was busy, but fulfilling.

[0117] 5. Distribution of generated content:

[0118] The generated stories and essays are delivered from the server to the user's smartphone, where they can view the content through an application.

[0119] Specific examples

[0120] Suppose a user enters the following diary entry using a smartphone application.

[0121] 2023-10-01: I went to a cafe with a friend today. It was fun.

[0122] 2023-10-02: Work was busy, but fulfilling.

[0123] The server imports this diary data and analyzes it using generative AI. Based on the analysis results, it provides feedback to the user, such as "Cherishing time with friends helps relieve stress." It also generates the following prompt sentences based on the diary data, automatically generating a story.

[0124] Please generate a moving story based on the diary data below.

[0125] Date: 2023-10-01

[0126] Content: I went to a cafe with a friend today. It was fun.

[0127] Date: 2023-10-02

[0128] Content: Work was busy, but fulfilling.

[0129] The generated story is delivered to the user's smartphone, where they can enjoy it through the application.

[0130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0131] Step 1:

[0132] A user inputs diary data using a smartphone application. The input diary data is sent in text format to a server. The server receives this data and stores it in a database. The input is the user's diary data, and the output is the diary data stored on the server.

[0133] Step 2:

[0134] The server analyzes the saved diary data using generative AI tools (e.g., OpenAI's GPT-3). Specifically, it analyzes the diary data and extracts the user's behavioral patterns, mood fluctuations, and lifestyle trends. The input is the saved diary data, and the output is the analysis results.

[0135] Step 3:

[0136] The server generates feedback and insights for the user based on the analysis results. For example, it generates advice such as "Spending time with friends will help relieve stress." The input is the analysis results, and the output is feedback and insights.

[0137] Step 4:

[0138] The server generates a prompt based on the diary data. For example, it generates the following prompt:

[0139] Please generate a moving story based on the diary data below.

[0140] Date: 2023-10-01

[0141] Content: I went to a cafe with a friend today. It was fun.

[0142] Date: 2023-10-02

[0143] Content: Work was busy, but fulfilling.

[0144] The input is diary data and the output is a prompt sentence.

[0145] Step 5:

[0146] The server inputs the generated prompt sentences into a generative AI means to automatically generate a story or essay. The generative AI means analyzes the prompt sentences and generates creative writing. The input is the prompt sentence, and the output is the generated story or essay.

[0147] Step 6:

[0148] The server delivers the generated stories and essays to the user's smartphone. The user can view these contents through the application. The input is the generated stories and essays, and the output is the content delivered to the user's smartphone.

[0149] Example 2

[0150] Next, a description will be given of Example 2 of Form 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."

[0151] In modern society, it is important for users to understand their own behavioral patterns, mood swings, and lifestyle trends, and deepen their self-understanding. However, there are limited systems that can effectively collect, analyze, and provide feedback on this information. In particular, there is a lack of systems that utilize diary data to provide users with information useful for managing their mental health and self-improvement.

[0152] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting diary data from the user, a means for the terminal to transmit the diary data to the server, a means for the server to receive the diary data and pass it to the generative AI model, a means for the generative AI model to analyze the diary data, and a means for the server to feed back the analysis results to the user. This makes it possible to effectively collect and analyze the user's diary data and provide useful feedback to the user.

[0153] "User" refers to an individual who utilizes the system to enter diary data and receive feedback.

[0154] "Diary data" refers to text data in which users record their daily events, emotions, actions, etc.

[0155] "Device" refers to the electronic device used by the user to input diary data and send it to the server. Examples include smartphones and personal computers.

[0156] "Server" refers to a computer system that receives diary data sent from the device, passes it to the generative AI model, and provides the analysis results as feedback to the user.

[0157] "Generative AI models" refer to artificial intelligence models that analyze diary data to extract user behavioral patterns, mood fluctuations, and lifestyle trends. Examples include natural language processing models such as BERT and GPT-3.

[0158] "Feedback" refers to information or insights provided to users based on the results analyzed by the generative AI model.

[0159] "Behavioral patterns" refer to the user's behavioral tendencies and habits in their daily lives.

[0160] "Mood swings" refers to changes in a user's emotions or moods.

[0161] "Lifestyle trends" refers to the user's lifestyle habits and characteristics.

[0162] This invention is a system in which a user inputs diary data, analyzes the data using a generative AI model, and provides feedback. Specific embodiments of this system are described below.

[0163] First, the user enters diary data using a dedicated application or web interface. For example, the user opens the application on their smartphone and enters, "I'm very tired today. I tend to stay up late late these days." This diary data is then sent by the device to the server. The data is sent using encrypted communication via the HTTPS protocol.

[0164] The server receives the diary data sent from the device. The received data is passed to a generative AI model. This generative AI model analyzes the diary data using natural language processing (NLP) techniques. Specifically, it uses the Python libraries NLTK and spaCy to tokenize the text data, tag parts of speech, and perform sentiment analysis. It also uses advanced generative AI models such as BERT and GPT-3 to extract user behavioral patterns, mood fluctuations, and lifestyle trends.

[0165] For example, if a user writes, "I've been staying up late lately," the generative AI model will recognize this as an "irregular lifestyle." The analysis results are returned to the server, which then provides this result as feedback to the user. The feedback is provided in the form of a notification to the user's application saying, "Your lifestyle has been irregular lately." This process uses WebSocket technology to send notifications in real time.

[0166] Below are some specific examples of prompt sentences to input into the generative AI model.

[0167] Example prompt sentence:

[0168] User diary data:

[0169] "I'm very tired today. I've been staying up late lately."

[0170] Prompt the generative AI model:

[0171] "Extract user behavioral patterns, mood swings, and lifestyle trends from this diary data."

[0172] In this way, it is possible to effectively collect and analyze users' diary data and provide useful feedback to users, which will help them deepen their self-understanding and provide information useful for self-improvement and mental health management.

[0173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0174] Step 1:

[0175] The user inputs diary data.

[0176] Users enter diary data using a dedicated application or web interface. For example, they might open the application on their smartphone and enter something like, "I'm very tired today. I tend to stay up late late these days." The data they enter is saved in text format on their device.

[0177] Step 2:

[0178] The device transmits the diary data to the server.

[0179] The device sends the diary data entered by the user to the server. At this time, the data is encrypted using the HTTPS protocol. The input is the user's diary data, and the output is the encrypted data.

[0180] Step 3:

[0181] The server receives the diary data and passes it to the generative AI model.

[0182] The server receives diary data sent from the device. The received data is passed to the generative AI model. Specifically, an API endpoint is created using Python's Flask framework to receive data. The input is encrypted diary data, and the output is text data passed to the generative AI model.

[0183] Step 4:

[0184] A generative AI model analyzes diary data.

[0185] The generative AI model analyzes the received diary data. For example, it uses natural language processing models such as BERT and GPT-3 to tokenize the text data, tag parts of speech, and perform sentiment analysis. The input is the text data passed to the generative AI model, and the output is an analysis result that shows the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0186] Step 5:

[0187] The server provides the analysis results as feedback to the user.

[0188] The server feeds back the analysis results obtained from the generative AI model to the user. For example, it may notify the user's application that "Your lifestyle has been irregular recently." This process uses WebSocket technology to send notifications in real time. The input is the analysis results from the generative AI model, and the output is a feedback message to the user.

[0189] (Application example 2)

[0190] Next, a description will be given of Application Example 2 of Form 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."

[0191] Conventional systems that analyze user diary data focus on analyzing users' behavioral patterns, mood fluctuations, and lifestyle trends, but lack the functionality to evaluate and warn about security risks. This makes it difficult to understand how changes in a user's lifestyle affect security risks. The present invention aims to solve this problem by providing a system that evaluates security risks based on a user's diary data and issues appropriate warnings.

[0192] The identification process 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 importing diary data from the user, generative AI means for analyzing the imported diary data, means for providing feedback and insight to the user based on the analysis results, means for evaluating security risks, and means for issuing warnings based on the security risks. This makes it possible to evaluate security risks based on the user's diary data and issue appropriate warnings.

[0193] "User" refers to any individual or entity that uses the System.

[0194] "Diary data" refers to text data in which users record their daily events, emotions, actions, etc.

[0195] "Capturing means" refers to a method or device for collecting diary data from users and inputting it into the system.

[0196] "Generative AI methods" refers to artificial intelligence technologies for analyzing imported diary data, particularly those that use natural language processing (NLP) technology.

[0197] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analysis results of generative AI means.

[0198] "Means for assessing security risks" refers to methods or devices that evaluate the impact of user behavior and lifestyle on security based on the analysis results of generative AI means.

[0199] "Means for issuing a warning" refers to a method or device for notifying a user of a warning when a security risk increases.

[0200] The system for implementing this invention imports a user's diary data, analyzes it using generative AI, evaluates security risks, and issues appropriate warnings. Specific embodiments are described below.

[0201] System Configuration

[0202] The system consists of the following main components:

[0203] 1. User device: The device on which the user enters diary data. This includes smartphones and PCs.

[0204] 2. Server: A central processing unit that ingests diary data, analyzes it using generative AI, provides feedback and insights, assesses security risks, and issues alerts.

[0205] 3. Generative AI model: An AI model for analyzing diary data using natural language processing (NLP) techniques. Specifically, it uses the spaCy and transformers libraries.

[0206] Data capture and analysis

[0207] Diary data is sent from the user's device to the server. The server receives the data using a means to import diary data and analyzes it using generative AI means. Specifically, the following process is performed:

[0208] 1. Data import: The diary data entered by the user is sent to the server in text format.

[0209] 2. Data analysis: The server analyzes the diary data using generative AI models (e.g., spaCy or the transformers library) to extract user behavioral patterns, mood fluctuations, and lifestyle trends.

[0210] Security risk assessment and warning

[0211] The server evaluates security risks based on the analysis results of the generative AI method. Specifically, the following processes are performed:

[0212] 1. Risk assessment: Evaluate security risks based on extracted behavioral patterns and lifestyle trends. For example, if the behavior of "staying up late" is frequently observed, it is determined that this is an irregular lifestyle and poses a high risk.

[0213] 2. Warning: Based on the assessed security risk, a warning is issued to the user. The warning is sent to the user's device.

[0214] Specific examples

[0215] For example, if a user writes in their diary, "I've been staying up late lately," the server will recognize this as an "irregular lifestyle" and determine that it may pose a security risk. Based on this, the server will issue a warning to the user, such as, "If you continue to stay up late, your security risk will increase. Try to lead a more regular life."

[0216] Prompt Sentence Examples

[0217] An example of a prompt to input to a generative AI model is as follows:

[0218] Analyze the user's diary data to extract behavioral patterns, mood swings, and lifestyle trends. For example, if a user writes, "I've been staying up late lately," recognize this as an "irregular lifestyle."

[0219] In this way, a system can be realized that evaluates security risks based on a user's diary data and issues appropriate warnings.

[0220] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0221] Step 1:

[0222] The user inputs diary data. The diary data is entered in text format using the user's device (smartphone or PC) and sent to the server. The input data includes the user's daily events, emotions, actions, etc.

[0223] Step 2:

[0224] The server receives the diary data. The server receives the diary data sent from the user terminal using a means for importing it and stores it in a database. The input is the user's diary data, and the output is the stored text data.

[0225] Step 3:

[0226] The server analyzes the diary data using a generative AI model. The server uses the spaCy and transformers libraries to analyze the diary data using natural language processing (NLP) techniques. The input is stored text data, and the output is an analysis showing the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0227] Step 4:

[0228] The server evaluates security risks based on the analysis results. Based on the analysis results from generative AI means, the server evaluates the impact of specific behaviors and lifestyles on security risks. For example, if the behavior of "staying up late" is frequently observed, it will determine that this irregular lifestyle poses a high risk. The input is the analysis results, and the output is the security risk assessment results.

[0229] Step 5:

[0230] The server issues a warning based on the security risk. The server notifies the user of the warning based on the assessed security risk. The warning is notified to the user's terminal. The input is the security risk assessment result, and the output is a warning message for the user.

[0231] Step 6:

[0232] The user receives a warning. The user checks the warning message sent to the user's device and takes necessary measures. The input is the warning message sent from the server, and the output is the user's behavior change or implementation of measures.

[0233] In this way, a system can be realized that evaluates security risks based on a user's diary data and issues appropriate warnings.

[0234] Example 3

[0235] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0236] Conventional systems have struggled to effectively collect and analyze user behavioral data and provide appropriate feedback and insights. They also lacked the means to accurately grasp changes in users' behavioral patterns and lifestyles and provide specific advice based on that information. This has prevented them from fully contributing to users' self-understanding, self-improvement, and mental health management.

[0237] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0238] In this invention, the server includes means for capturing behavioral data from users, means for preprocessing the captured behavioral data, generative AI means for analyzing the preprocessed data, means for generating feedback and insights for users based on the analysis results, and means for providing the generated feedback and insights to users, thereby enabling effective collection and analysis of user behavioral data and provision of appropriate feedback and insights.

[0239] "Behavioral Data" refers to information about a user's behavior, such as their web page browsing history, application usage history, or sleep patterns.

[0240] "Preprocessing" refers to the process of improving the quality of collected data by performing operations such as filling in missing values, normalizing the data, and detecting outliers.

[0241] "Generative AI methods" refer to methods that use machine learning or generative AI models to analyze data and generate feedback and insights in natural language.

[0242] "Feedback" refers to specific advice or insights provided to users based on the analysis results.

[0243] "Delivery Vehicle" refers to the means by which generated feedback and insights are communicated to users, including web pages, application dashboards, emails, notifications, etc.

[0244] This invention relates to a system that collects and analyzes user behavior data and provides appropriate feedback and insights. Specific embodiments of this system are described below.

[0245] Data collection

[0246] The server collects user behavior data, such as web page browsing history, application usage history, sleep patterns, etc. This data is stored in a database (e.g., MySQL, PostgreSQL).

[0247] Data Preprocessing

[0248] The server preprocesses the collected data, specifically by imputing missing values, normalizing the data, and detecting outliers. This improves the quality of the data. For example, missing values ​​are imputed with the mean or median. Data normalization involves scaling each data point to a range from 0 to 1. Outlier detection involves using statistical methods to identify and remove abnormal data points.

[0249] Data analysis

[0250] The server uses the preprocessed data to train a machine learning model. For example, to analyze the user's sleep patterns, it uses a Long Short-Term Memory (LSTM) model using time-series data. The model predicts future sleep patterns based on the user's past sleep data. Machine learning libraries such as TENSORFLOW (registered trademark) and scikit-learn are used for the analysis.

[0251] Feedback Generation

[0252] The server generates feedback based on the analysis results. A prompt sentence is input into a generative AI model (e.g., OpenAI GPT-3), and feedback is generated in natural language. For example, a prompt sentence might be input, "After analyzing the user's recent sleep patterns, we have found that they tend to stay up late. Please generate feedback encouraging the user to go to bed early and get up early." The generated feedback would be, "You've been staying up late late recently. Making an effort to go to bed early and get up early may have a positive effect on your health."

[0253] Providing Feedback

[0254] The server provides the generated feedback to the user. This can be provided via a web page, a dashboard on the application, email, or notification. For example, when the user opens the application, the feedback is displayed on the dashboard. Feedback can also be sent via email or push notification. The user receives this feedback and uses it as a reference for improving their behavior.

[0255] Specific examples

[0256] Example 1: Sleep pattern feedback

[0257] If the user has been staying up late recently, the server might generate feedback like this:

[0258] "You've been staying up late lately. Trying to go to bed earlier and get up earlier might have a positive effect on your overall health."

[0259] Example 2: Feedback based on web page browsing history

[0260] If a user frequently views web pages on a particular topic, the server generates feedback like this:

[0261] "You've been browsing a lot of health-related web pages lately. Would you like me to email you the latest health news?"

[0262] Prompt Sentence Examples

[0263] Below is an example of a prompt sentence to input to the generative AI model.

[0264] Prompt 1: Sleep pattern feedback

[0265] Your analysis of the user's recent sleep patterns indicates that they tend to stay up late. Generate feedback to encourage the user to go to bed earlier and get up earlier.

[0266] Prompt 2: Feedback based on web page browsing history

[0267] A user has recently been browsing health web pages frequently. Generate feedback to provide the user with the latest health information.

[0268] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0269] Step 1:

[0270] The server collects user behavior data. Specifically, it records the URL and the time spent viewing each web page. It also collects operation logs when users use applications. This data is stored in a database.

[0271] Input: User behavior data (webpage browsing history, application usage history)

[0272] Output: Behavioral data stored in a database

[0273] Step 2:

[0274] The server preprocesses the collected data by imputing missing values ​​with the mean or median, normalizing the data by scaling each data point to a range between 0 and 1, and detecting outliers by using statistical methods to identify and remove anomalous data points.

[0275] Input: Behavioral data stored in a database

[0276] Output: Preprocessed data

[0277] Step 3:

[0278] The server uses the preprocessed data to train a machine learning model. For example, it uses a Long Short-Term Memory (LSTM) model with time-series data to analyze the user's sleep patterns. The model predicts future sleep patterns based on the user's past sleep data.

[0279] Input: Preprocessed data

[0280] Output: A trained machine learning model

[0281] Step 4:

[0282] The server generates feedback based on the analysis results. A prompt sentence is input into the generative AI model, and feedback is generated in natural language. For example, a prompt sentence might be input as follows: "After analyzing the user's recent sleep patterns, we have noticed a tendency for them to stay up late. Please generate feedback encouraging the user to go to bed early and get up early." The generated feedback would be, "You've been staying up late late recently. Making an effort to go to bed early and get up early may have a positive effect on your health."

[0283] Input: Trained machine learning model, prompt

[0284] Output: Generated feedback

[0285] Step 5:

[0286] The server provides the generated feedback to the user via a web page, an application dashboard, email, or notification. For example, when the user opens the application, the feedback is displayed on the dashboard. Feedback can also be sent via email or push notification.

[0287] Input: Generated feedback

[0288] Output: Feedback provided to the user

[0289] The above are the specific processing steps of the program of this system.

[0290] (Application example 3)

[0291] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0292] In modern society, managing users' physical and mental health is an important issue. However, conventional systems have had difficulty comprehensively analyzing users' behavioral patterns and lifestyles and providing specific feedback. In addition, there are limited ways for users to accurately understand their own physical and mental health conditions and obtain information to take appropriate measures to improve them. This has led to the problem of users being unable to fully understand and improve themselves.

[0293] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0294] In this invention, the server includes a means for importing diary data and biometric data from the user, a generative AI means for analyzing the imported diary data and biometric data, a means for providing feedback and insights to the user based on the analysis results, and a means for providing the feedback and insights via notifications or a dashboard. This enables the server to comprehensively analyze the user's behavioral patterns, mood fluctuations, lifestyle trends, and sleep patterns and provide specific feedback. This allows the user to deepen their self-understanding and obtain information useful for self-improvement and health management.

[0295] "Diary data" is information recorded by users about their daily events, emotions, actions, etc.

[0296] "Biometric data" refers to data that indicates the user's physical condition, such as sleep patterns and exercise levels.

[0297] "Generative AI methods" are artificial intelligence techniques that analyze users' behavioral patterns and lifestyles based on collected data, and generate feedback and insights.

[0298] "Feedback" is specific advice or information provided to users based on the analysis results.

[0299] "Insights" are deep understandings and insights gained through data analysis, containing important information about user behavior and status.

[0300] "Notifications" are a means of providing information to users in real time, including push notifications on smartphones.

[0301] A "dashboard" is a user-accessible interface that visually displays analysis results and feedback.

[0302] "Behavioral patterns" refer to the user's daily behavioral tendencies and habits.

[0303] "Mood swings" refer to changes in a user's emotional or mental state.

[0304] "Lifestyle trends" refers to a user's lifestyle habits and daily behavior patterns.

[0305] "Sleep patterns" refers to data about a user's sleep duration and quality.

[0306] "Self-understanding" means that users gain a deep understanding of their own behavior, emotions, and state.

[0307] "Self-improvement" is the effort by users to improve their own behavior or state.

[0308] "Health management" refers to activities and efforts that users make to maintain and improve their health.

[0309] "Mental health management" refers to activities and efforts that users make to maintain and improve their mental health.

[0310] A system for implementing this invention includes means for capturing diary data and biometric data from a user, generative AI means for analyzing the captured data, means for providing feedback and insights to the user based on the analysis results, and means for providing the feedback and insights via notifications or a dashboard.

[0311] 1. Data Collection

[0312] The server collects users' diary data and biometric data from their smartphones and wearable devices. The diary data includes information on users' daily events, emotions, and behaviors. The biometric data includes users' sleep patterns and exercise levels.

[0313] 2. Data analysis

[0314] The server analyzes the collected diary and biometric data using a generative AI model (e.g., OpenAI GPT-3), which evaluates the user's behavioral patterns, mood swings, lifestyle trends, and sleep patterns.

[0315] 3. Feedback Generation

[0316] The server uses a generative AI model to generate specific feedback and insights based on the analysis results. For example, analyzing a user's sleep data may generate the following feedback:

[0317] "You haven't been getting enough sleep lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[0318] 4. Providing Feedback

[0319] The server then provides the generated feedback and insights to the user via smartphone notifications and an in-app dashboard, providing real-time information about their physical and mental health status.

[0320] Hardware and software used

[0321] Hardware: Smartphones, wearable devices (e.g., smartwatches)

[0322] Software: Python, data analysis libraries (e.g., Pandas, NumPy), generative AI models (e.g., OpenAI GPT-3)

[0323] Specific examples

[0324] If the user enters their sleep data from the past 30 days into the app, the server will provide feedback like this:

[0325] "You haven't been getting enough sleep lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[0326] Prompt Sentence Examples

[0327] Analyze the user's sleep data from the past 30 days and generate feedback such as:

[0328] Data: [5.5, 6.0, 7.0, 4.5, 8.0, 6.5, 7.5, 5.0, 6.0, 7.0, 8.5, 6.0, 7.5, 5.5, 6.0, 7.0, 4.5, 8.0, 6.5, 7.5, 5.0, 6.0, 7.0, 8.5, 6.0, 7.5, 5.5, 6.0, 7.0, 4.5]

[0329] In this way, a system can be realized that provides specific feedback to support the user in managing their health.

[0330] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0331] Step 1:

[0332] Users input diary data and biometric data using smartphones or wearable devices. The diary data includes information recorded by the user about daily events, emotions, and behaviors, while the biometric data includes the user's sleep patterns and amount of exercise. The input data is then sent to a server.

[0333] Step 2:

[0334] The server stores the received diary data and biometric data in a database. The stored data is used for subsequent analysis. Specifically, the data is efficiently managed using a database management system (e.g., MySQL, PostgreSQL).

[0335] Step 3:

[0336] The server inputs the saved diary data and biometric data into a generative AI model (e.g., OpenAI GPT-3). The generative AI model uses this data to analyze the user's behavioral patterns, mood fluctuations, lifestyle trends, and sleep patterns. Based on the input data, the AI ​​model performs data preprocessing (e.g., normalization, missing value imputation) and generates analysis results.

[0337] Step 4:

[0338] The server generates specific feedback and insights for the user based on the analysis results obtained from the generative AI model. For example, after analyzing the user's sleep data, the following feedback may be generated: "You've been sleeping less recently. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[0339] Step 5:

[0340] The server provides the generated feedback and insights to the user through the smartphone notification function and the in-application dashboard. Specifically, the server provides information in real time using push notifications, and the in-application dashboard visually displays the feedback and insights.

[0341] Step 6:

[0342] Based on the feedback and insights provided, users can take concrete actions to improve their behavior and lifestyle, such as going to bed earlier and getting up earlier to get more sleep.

[0343] In this way, a system is realized that provides specific feedback to support the user in managing their health.

[0344] 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.

[0345] "Example 1"

[0346] In one embodiment of the present invention, a system is provided that includes a means for capturing diary data from a user, a generative AI means for analyzing the captured diary data, and a means for providing feedback and insights to the user based on the analysis results. The system analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0347] "Example 2"

[0348] The generative AI means includes an emotion engine that recognizes the user's emotions. This emotion engine extracts the user's emotional state from the diary data and reflects that emotional state in the analysis results. Specifically, it extracts emotional expressions such as "fun" or "sad" that the user wrote in the diary and analyzes the intensity and frequency of those emotions.

[0349] "Example 3"

[0350] Feedback and insights are provided based on the user's emotional state. This allows users to objectively understand their own emotional fluctuations and use them to manage their emotions and improve their mental health. For example, users can reflect on the number of times they felt "sad" over the course of a week and the events that caused that feeling. They can also understand what emotions specific events trigger and consider countermeasures.

[0351] The processing flow of each embodiment will be described below.

[0352] "Example 1"

[0353] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[0354] Step 2: Analyze the captured diary data using generative AI. In this step, the AI ​​extracts and analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0355] Step 3: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results.

[0356] "Example 2"

[0357] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[0358] Step 2: Extract emotional states from the imported diary data using the emotion engine. In this step, the emotion engine extracts emotional expressions from the user's diary data and analyzes the intensity and frequency of those emotions.

[0359] Step 3: Analyze the extracted emotional state using generative AI. In this step, the AI ​​analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the emotional state obtained from the emotion engine.

[0360] Step 4: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results.

[0361] "Example 3"

[0362] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[0363] Step 2: Extract emotional states from the imported diary data using the emotion engine. In this step, the emotion engine extracts emotional expressions from the user's diary data and analyzes the intensity and frequency of those emotions.

[0364] Step 3: Analyze the extracted emotional state using generative AI. In this step, the AI ​​analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the emotional state obtained from the emotion engine.

[0365] Step 4: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results. The feedback and insights are based on the user's emotional state and can be used to manage their emotions and improve their mental health.

[0366] Example 1

[0367] Next, a description will be given of Example 1 of Form 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."

[0368] Conventional systems have struggled to effectively analyze users' diary data and provide useful feedback and insights to users. They also lacked the means to accurately grasp users' behavioral patterns, mood fluctuations, and lifestyle trends, and provide appropriate advice based on those findings. This has resulted in insufficient support for users' self-understanding, self-improvement, and mental health management.

[0369] 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.

[0370] In this invention, the server includes means for importing diary data from a user, means for storing the imported diary data in a database, means for analyzing the stored diary data using a generative AI model, means for generating feedback and insights for the user based on the analysis results, and means for providing the generated feedback to the user. This makes it possible to effectively analyze the user's diary data, understand the user's behavioral patterns, mood fluctuations, and lifestyle trends, and provide appropriate feedback and insights based on them.

[0371] "User" refers to an individual who utilizes the system to enter diary data and receive feedback and insights.

[0372] "Diary data" refers to text data in which users record their daily events, feelings, and thoughts.

[0373] "Means of import" refers to the interface or application that allows users to input diary data into the system.

[0374] "Database" refers to an information system for storing and managing imported diary data.

[0375] A "generative AI model" refers to an artificial intelligence model that analyzes saved diary data and extracts users' behavioral patterns, mood fluctuations, and lifestyle trends.

[0376] "Means of analysis" refers to the process of using a generative AI model to analyze diary data and understand users' behavioral patterns, mood fluctuations, and lifestyle trends.

[0377] "Feedback" refers to advice or insights provided to users based on the analysis results of the generative AI model.

[0378] "Means for providing" refers to the method or system for notifying and displaying the generated feedback to the user.

[0379] The present invention relates to a system for capturing and analyzing a user's diary data and providing feedback. A specific embodiment of this system will be described below.

[0380] System configuration

[0381] Hardware and Software

[0382] Users enter diary data using a web-based interface or dedicated application. For example, they can use a smartphone app or website. The device then sends the entered diary data to a server. The server then stores the received diary data in a database and analyzes it using a generative AI model. The generative AI model used is a natural language processing model such as GPT-4 (registered trademark).

[0383] Data capture and storage

[0384] Users enter diary data through a smartphone app or website. For example, a user might enter, "Today was a tough day at work. My boss scolded me and I'm feeling down." The device then sends this data to a server using the HTTPS protocol. The server then stores the received diary data in a relational database such as MySQL or PostgreSQL. The stored data is organized for later analysis.

[0385] Analyzing the data

[0386] The server analyzes the saved diary data using a generative AI model. GPT-4 is used as the generative AI model. The server inputs the diary data into the AI ​​model and extracts behavioral patterns, mood fluctuations, and lifestyle trends. For example, it sends a prompt message to the AI ​​model saying, "Analyze the user's diary data and extract emotional fluctuations."

[0387] Generating and Providing Feedback

[0388] The server generates feedback and insights for the user based on the analysis results of the AI ​​model. For example, if the AI ​​model analyzes that "the user is feeling stressed at work," the server generates feedback such as "It seems that you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The server sends this feedback to the user's device, and the user can check the feedback through the app.

[0389] Examples of specific examples and prompts

[0390] Specific examples

[0391] A user enters into their diary, "Today was tough at work. My boss got mad at me and I'm feeling down." The device sends this data to the server. The server stores this data in a database and analyzes it using a generative AI model (GPT-4). The AI ​​model analyzes that "The user is feeling stressed at work," and the server generates feedback such as "It seems like you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The server sends this feedback to the user's device, and the user checks it through the app.

[0392] Prompt Sentence Examples

[0393] "Analyze the user's diary data and extract behavioral patterns and mood fluctuations. For example, if a user writes, 'Today was a tough day at work. My boss got mad at me, and I'm feeling down,' generate the type of feedback we should provide."

[0394] In this way, the system goes through a series of processes to capture the user's diary data, analyze it, and provide feedback.

[0395] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0396] Step 1:

[0397] Users enter diary data using a web-based interface or a dedicated application. For example, a user might enter, "Today was a tough day at work. My boss scolded me, and I'm feeling down." The data is then stored on the device.

[0398] Step 2:

[0399] The device sends the entered diary data to the server. The HTTPS protocol is used for transmission to ensure data security. Specifically, the device sends a "POST" request to "https: / / api.example.com / submit." The input is the user's diary data, and the output is the data sent to the server.

[0400] Step 3:

[0401] The server saves the received diary data in a database. MySQL is used as the database. The server executes an "INSERT" query on the database to save the diary data. For example, it executes the query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (1, 'Work was tough today. My boss got mad at me and I'm feeling down.', '2023-10-01');". The input is the received diary data, and the output is saving it to the database.

[0402] Step 4:

[0403] The server analyzes the saved diary data using a generative AI model. GPT-4 is used as the generative AI model. The server inputs the diary data into the AI ​​model and extracts behavioral patterns, mood fluctuations, and lifestyle trends. For example, the server sends a prompt to the AI ​​model saying, "Analyze the user's diary data and extract emotional fluctuations." The input is the saved diary data, and the output is the analysis results.

[0404] Step 5:

[0405] The server generates feedback and insights for the user based on the analysis results of the AI ​​model. For example, if the AI ​​model analyzes that "the user is feeling stressed at work," the server generates feedback such as "It seems that you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The input is the analysis results of the AI ​​model, and the output is the generated feedback.

[0406] Step 6:

[0407] The server provides the generated feedback to the user, who can check the feedback through a dedicated application or web interface. For example, the server sends a notification to the device saying "There is new feedback," and the user opens the app to check the feedback. The input is the generated feedback, and the output is the notification to the user and the display of the feedback.

[0408] (Application example 1)

[0409] Next, a description will be given of Application Example 1 of Embodiment 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."

[0410] Conventional systems that analyze users' diary data analyze users' behavioral patterns, mood fluctuations, and lifestyle trends to provide information useful for self-understanding and mental health management. However, these systems do not support security risk prediction or countermeasure proposals, which means users are unable to effectively manage the security risks they face in their daily lives.

[0411] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for importing diary data from the user, a generative AI means for analyzing the imported diary data, a means for providing feedback and insight to the user based on the analysis results, and a means for predicting security risks and proposing appropriate countermeasures. This makes it possible to evaluate security risks based on the user's diary data and propose specific countermeasures.

[0412] A "user" is an individual who utilizes the system to enter diary data and receive feedback and insights.

[0413] "Diary data" is information in which users record their daily events, feelings, and thoughts.

[0414] "Means of import" refers to the interface or application used to collect diary data from users and input it into the system.

[0415] "Generative AI methods" are artificial intelligence technologies that analyze imported diary data and generate feedback and insights for users.

[0416] "Means for providing feedback and insights" are methods and tools for communicating the analytical results generated by generative AI means to users.

[0417] "Security risks" are dangers or threats that may occur in a user's daily life.

[0418] "Means for proposing appropriate countermeasures" are methods and tools that evaluate security risks and suggest specific preventative or avoidance measures to users.

[0419] "Behavioral patterns" refer to the user's tendencies and habits in daily life.

[0420] "Mood swings" are changes in a user's emotional or mental state.

[0421] "Lifestyle trends" refer to the user's lifestyle habits and characteristics.

[0422] "Self-understanding" refers to users gaining a deep understanding of their own behavior, emotions, and thoughts.

[0423] "Mental health management" refers to methods and activities for maintaining and improving a user's mental health.

[0424] As an embodiment of the present invention, the following system can be constructed.

[0425] System configuration

[0426] The system includes a terminal for capturing the user's diary data, a server for analyzing the data, and an interface for providing the analysis results to the user.

[0427] 1. User Device

[0428] The user terminals are devices such as smartphones and smart glasses. An application is installed on these terminals, allowing users to enter diary data. This application provides an interface for users to enter their daily events, feelings, and thoughts.

[0429] 2. Server

[0430] The server receives the diary data sent by the user and analyzes the data using a generative AI model. Specifically, it performs the following processes:

[0431] Data import: Receives diary data sent from the user's device.

[0432] Prompt generation: Based on the received diary data, a prompt sentence is generated to be passed to the generative AI model.

[0433] Analysis using generative AI models: Using OpenAI's API, security risks are analyzed based on prompt text.

[0434] Feedback generation: Converting the generated feedback into a format for delivery to the user.

[0435] 3. Feedback Providing Interface

[0436] The feedback interface is the part of the application displayed on the user's device that displays feedback and insights sent from the server to the user, such as specific countermeasures for security risks, as well as information about the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0437] Hardware and software used

[0438] Hardware: Smartphones, smart glasses, servers

[0439] Software: Python, OpenAI API

[0440] Data processing and calculation

[0441] The server receives the diary data sent by the user and analyzes it using a generative AI model. Specifically, it processes and calculates the data as follows:

[0442] 1. Data import: Receives diary data sent from the user's device.

[0443] 2. Prompt generation: Based on the received diary data, a prompt sentence is generated to be passed to the generative AI model.

[0444] 3. Analysis using generative AI models: Using OpenAI's API, security risks are analyzed based on prompt text.

[0445] 4. Feedback generation: Converting the generated feedback into a format for delivery to the user.

[0446] Specific examples

[0447] For example, if a user writes in their diary, "I came home late tonight, but the road from the station to my house was dark and I felt uneasy," the system will use that information to analyze the security risks of returning home late at night and suggest taking a well-lit route or taking a taxi.

[0448] Prompt Sentence Examples

[0449] User diary data: I got home late today, but the road from the station to my house was dark and I felt uneasy.

[0450] Based on this data, analyze security risks and propose appropriate countermeasures.

[0451] In this way, it becomes possible to evaluate security risks based on users' diary data and propose specific countermeasures.

[0452] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0453] Step 1:

[0454] The user enters diary data. Using an application installed on a smartphone or smart glasses, the user enters daily events, emotions, and thoughts. The entered diary data is temporarily stored on the device.

[0455] Step 2:

[0456] The device sends the diary data to the server. When the user instructs the device to send the diary data, the device sends the data to the server via the Internet. The input data is sent in text format.

[0457] Step 3:

[0458] The server receives the diary data. The server receives the diary data sent from the device and stores it in a database. The received data is stored in its original format.

[0459] Step 4:

[0460] The server generates a prompt sentence based on the received diary data, which is then passed to the generative AI model. Specifically, the server performs text analysis on the diary data and converts it into a question format for assessing security risks.

[0461] Step 5:

[0462] The server analyzes the diary data using a generative AI model. The server then sends the generated prompts to the OpenAI API to analyze security risks. The input is the prompts, and the output is feedback on security risks.

[0463] Step 6:

[0464] The server generates the feedback. The server converts the feedback obtained from the generative AI model into a format for providing to the user. Specifically, the server formats the feedback into text so that it is easy for the user to understand.

[0465] Step 7:

[0466] The server sends the feedback to the user terminal. The server sends the formatted feedback to the user terminal. The transmitted data is in text format.

[0467] Step 8:

[0468] The user terminal displays the feedback. The user terminal displays the feedback received from the server within the application. The user can check the feedback and obtain specific measures to address security risks.

[0469] In this way, it becomes possible to evaluate security risks based on users' diary data and propose specific countermeasures.

[0470] Example 2

[0471] Next, a description will be given of Example 2 of Form 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."

[0472] Conventional systems simply store users' diary data, making it difficult to extract useful information from that data and provide feedback to users. Furthermore, they lacked the means to perform detailed analysis of users' emotional states and behavioral patterns, making it impossible to provide information useful for self-understanding and mental health management. This made it difficult for users to understand fluctuations in their lifestyles and emotions and gain specific insights for improvement.

[0473] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0474] In this invention, the server includes a means for importing diary data from a user, a generative AI means for analyzing the imported diary data using natural language processing technology, a means for extracting the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the analysis results, a means for providing feedback and insights to the user based on the extracted information, and an emotion engine for extracting emotional states from the user's diary data and analyzing the intensity and frequency of those emotions. This makes it possible to analyze detailed behavioral patterns and emotional fluctuations from the user's diary data and provide specific feedback useful for self-understanding and mental health management.

[0475] "User" refers to an individual who uses the system to enter diary data and receive analysis results.

[0476] "Diary data" refers to text data in which users describe their daily events and feelings.

[0477] "Means of importing" refers to the interface and functions for importing diary data entered by users into the system.

[0478] "Generative AI means" refers to the function of artificial intelligence that uses natural language processing technology to analyze diary data and extract users' behavioral patterns and emotional states.

[0479] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0480] "Analysis results" refers to information such as behavioral patterns, mood fluctuations, and lifestyle trends extracted from diary data by generative AI means.

[0481] "Behavioral patterns" refer to a user's behavioral tendencies and habits extracted from the user's diary data.

[0482] "Mood fluctuations" refers to changes in a user's emotions extracted from the user's diary data.

[0483] "Lifestyle trends" refers to a user's habits and lifestyle patterns extracted from the user's diary data.

[0484] "Means of providing feedback and insights" refers to functions that provide useful information and advice to users based on the analysis results.

[0485] The "emotion engine" refers to a function that extracts the user's emotional state from their diary data and analyzes the intensity and frequency of those emotions.

[0486] "Emotional state" refers to the emotional state of a user based on the emotional expressions described in the user's diary data.

[0487] "Intensity" refers to the strength of the emotion extracted by the emotion engine.

[0488] "Frequency" refers to the frequency with which the emotion extracted by the emotion engine appears in the diary data.

[0489] This invention is a system that analyzes a user's diary data, extracts behavioral patterns, emotional fluctuations, and lifestyle trends, and provides useful feedback and insights to the user. A specific embodiment of this system is described below.

[0490] Hardware and software used

[0491] Hardware: Servers, devices (smartphones, PCs, etc.)

[0492] Software: Generative AI, Natural Language Processing (NLP) engine, Emotion engine

[0493] System configuration

[0494] 1. Importing diary data from users

[0495] Users can input diary data using a terminal, either by text input or voice input.

[0496] The device sends the diary data entered to the server, where encryption technology is used to ensure the security of the data.

[0497] 2. Analysis of diary data

[0498] The server passes the received diary data to the generative AI, which then uses natural language processing (NLP) technology to analyze the text of the diary data.

[0499] The purpose of the analysis is to extract user behavioral patterns, mood swings, and lifestyle trends. Specifically, it identifies patterns of behavior and emotions based on the content written by the user in their diary.

[0500] 3. Emotional Recognition

[0501] The server uses a generative AI emotion engine to extract emotional states from users' diary data. The emotion engine identifies emotional expressions such as "happy" or "sad" and analyzes the intensity and frequency of those emotions.

[0502] 4. Generating analysis results

[0503] The server compiles the analysis results obtained from the generative AI, which include behavioral patterns, emotional states, and lifestyle trends.

[0504] For example, if a user writes, "I've been staying up late lately," the server will classify this as an "irregular lifestyle."

[0505] 5. Providing results

[0506] The server sends the analysis results to the terminal, where the user can check the results.

[0507] Feedback and insights are information that helps users better understand themselves and can be used for self-improvement and mental health management.

[0508] Specific examples

[0509] Diary data entered: "Today was so much fun. I went to the movies with my friends."

[0510] Generative AI analysis results:

[0511] Activity Pattern: Leisure Activities

[0512] Emotional state: High joy

[0513] Lifestyle: Regular

[0514] Prompt Sentence Examples

[0515] "Analyze users' diary data to extract behavioral patterns, mood swings, and lifestyle trends."

[0516] "Extract emotional expressions from diary data and analyze the intensity and frequency of those emotions."

[0517] In this way, the system can analyze the user's diary data in detail and understand changes in lifestyle and emotions.

[0518] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] A user inputs diary data using a terminal.

[0521] Specifically, users open an application on their smartphone or computer and enter the contents of their diary in text format.

[0522] Input: User's diary text

[0523] Output: Diary data saved on the device

[0524] Step 2:

[0525] The terminal transmits the input diary data to the server.

[0526] Specifically, the device uploads diary data to a server via the Internet, and encryption technology is used during data transmission to ensure data security.

[0527] Input: Diary data saved on the device

[0528] Output: Diary data sent to the server

[0529] Step 3:

[0530] The server passes the received diary data to the generative AI.

[0531] Specifically, the server uses an NLP engine to analyze the text of the diary data and extract the user's behavioral patterns and lifestyle trends.

[0532] Input: Diary data sent to the server

[0533] Output: Analysis results by the NLP engine

[0534] Step 4:

[0535] The server uses a generative AI emotion engine to extract the user's emotional state from their diary data.

[0536] Specifically, the emotion engine identifies emotional expressions such as "happy" or "sad" and analyzes the intensity and frequency of those emotions.

[0537] Input: Diary data sent to the server

[0538] Output: Sentiment analysis results by the emotion engine

[0539] Step 5:

[0540] The server compiles the analysis results obtained from the generative AI.

[0541] Specifically, the server generates a report of behavioral patterns, emotional states, and lifestyle trends.

[0542] Input: Analysis results by the NLP engine, emotion analysis results by the emotion engine

[0543] Output: Analysis result report

[0544] Step 6:

[0545] The server sends the analysis results to the terminal.

[0546] Specifically, the server sends the generated report to the user's terminal, and the user checks the analysis results through the terminal.

[0547] Input: Analysis result report

[0548] Output: Analysis results report sent to your device

[0549] Step 7:

[0550] The user checks the analysis results through the terminal.

[0551] Specifically, the user opens the application and views the report sent from the server.

[0552] Input: Analysis result report sent to the terminal

[0553] Output: Analysis results confirmed by the user

[0554] (Application example 2)

[0555] Next, a description will be given of Application Example 2 of Form 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."

[0556] Conventional systems simply record users' diary data, making it difficult to deeply understand their behavioral patterns and emotional states and provide appropriate feedback and insights. Furthermore, they lacked the ability to predict and warn of security risks based on users' emotional states and behavioral patterns, making it difficult to ensure user safety. This created challenges in users' self-understanding, mental health management, and even security risk prediction.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0558] In this invention, the server includes means for importing diary data from users, generative AI means for analyzing the imported diary data, means for providing feedback and insights to users based on the analysis results, an emotion engine for extracting emotional states from the user's diary data and reflecting the emotional states in the analysis results, and means for predicting and warning about security risks based on the emotional states and behavioral patterns. This allows for a deep understanding of the user's behavioral patterns and emotional states, and not only can it provide appropriate feedback and insights, but it can also predict and warn about security risks.

[0559] "User" means any individual or entity that uses the System.

[0560] "Diary data" is text data in which a user records daily events and emotions.

[0561] "Capturing means" refers to a method or device for collecting diary data from users and inputting it into the system.

[0562] "Generative AI means" is an artificial intelligence technology that analyzes imported diary data and extracts the user's behavioral patterns and emotional state.

[0563] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analysis results of generative AI means.

[0564] The "emotion engine" is a technology that extracts a user's emotional state from their diary data and reflects that emotional state in the analysis results.

[0565] "Means for predicting and warning about security risks" refers to methods or devices that predict potential security risks to users and issue warnings based on their emotional state and behavioral patterns.

[0566] The following system configuration will be described as an embodiment of the present invention.

[0567] The server includes a means for importing diary data from users, a generative AI means for analyzing the imported diary data, a means for providing feedback and insights to users based on the analysis results, an emotion engine for extracting emotional states from users' diary data and reflecting the emotional states in the analysis results, and a means for predicting and warning about security risks based on emotional states and behavioral patterns.

[0568] Hardware and software used

[0569] Hardware: Smartphones, servers

[0570] Software: Python, NLTK library, sentiment analysis tool

[0571] Details of data processing and calculation

[0572] 1. Importing diary data: The user inputs diary data using a smartphone and sends it to the server, which receives and stores the data.

[0573] 2. Initialize the sentiment engine: The server initializes the sentiment analysis tool using the NLTK library, which is used to calculate sentiment scores from text data.

[0574] 3. Diary data analysis: The server divides the diary data into sentences and calculates the emotion score for each sentence, thereby extracting the user's emotional state and behavioral patterns.

[0575] 4. Security risk prediction: Based on the emotion score, the server determines that the security risk is high if there are a lot of negative emotions and issues a warning to the user.

[0576] Specific examples

[0577] For example, if a user writes in their diary, "I've been staying up late lately and feeling depressed," the server receives this data and uses the emotion engine to recognize it as a negative emotion, determining that the security risk is high and issuing a warning to the user.

[0578] Prompt Sentence Examples

[0579] Develop an application that analyzes a user's diary data, understands their emotional state and behavioral patterns, and predicts and warns about security risks. The diary data includes a comment such as, "I've been staying up late lately and I'm feeling depressed." Based on this data, create a program that uses an emotion engine to recognize negative emotions and determine whether a security risk is high.

[0580] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0581] Step 1:

[0582] Users input diary data using their smartphones. The data is sent in text format to the server, which then receives it and stores it in a database.

[0583] Input: Diary data entered by the user

[0584] Output: Diary data saved on the server

[0585] Step 2:

[0586] The server initializes a sentiment analysis tool using the NLTK library, which is used to calculate sentiment scores from text data.

[0587] Input: None (initialization process)

[0588] Output: Initialized sentiment analysis tool

[0589] Step 3:

[0590] The server divides the stored diary data into sentences. Each sentence is input into the emotion engine, which calculates an emotion score. The emotion score is output as a positive, negative, or neutral score.

[0591] Input: Saved diary data

[0592] Output: Sentiment score for each sentence (positive, negative, neutral)

[0593] Step 4:

[0594] The server extracts the user's emotional state and behavioral patterns based on the calculated emotion score. If the emotion score is above a certain level, the server determines that the security risk is high.

[0595] Input: Sentiment score for each sentence

[0596] Output: User's emotional state, behavioral patterns, and security risk assessment

[0597] Step 5:

[0598] If the server determines that the security risk is high, it will issue a warning to the user. The warning will be sent to the user using the notification function of the smartphone.

[0599] Input: Security Risk Assessment

[0600] Output: A warning notice to the user

[0601] Step 6:

[0602] The server provides feedback and insights to the user based on the analysis results, including detailed information about the user's behavioral patterns and emotional state. The feedback is displayed to the user through a smartphone application.

[0603] Input: User's emotional state, behavioral patterns

[0604] Output: User feedback and insights

[0605] Example 3

[0606] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0607] Conventional emotion management systems have struggled to effectively collect and analyze users' emotional data and provide appropriate feedback and insights. Furthermore, they lacked the means to analyze users' emotional states and behavioral patterns in detail and provide information useful for self-understanding and mental health management. This left users unable to fully understand their own emotional fluctuations and their causes, making it difficult to take appropriate measures.

[0608] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0609] In this invention, the server includes means for capturing emotional data from a user, means for saving the captured emotional data in a database, means for periodically acquiring the saved emotional data, means for inputting the acquired emotional data into a generative AI model, means for the generative AI model to analyze the emotional data and generate feedback and insights, and means for providing the generated feedback and insights to the user. This makes it possible to analyze the user's emotional state and behavioral patterns in detail and provide information useful for self-understanding and mental health management.

[0610] "User" refers to an individual who utilizes the system to input emotional data and receive feedback and insights.

[0611] "Emotional data" refers to information entered by a user about their emotional state and its causes.

[0612] "Database" refers to an information management system for storing emotion data and retrieving it as needed.

[0613] "Generative AI models" refer to artificial intelligence algorithms that analyze emotional data and generate feedback and insights.

[0614] "Feedback" refers to advice or information provided to users by a generative AI model based on the results of analyzing emotional data.

[0615] "Insights" refers to the deep understanding and insights that a generative AI model gains from analyzing emotion data.

[0616] "Server" refers to a computer system for capturing, storing, retrieving, analyzing, generating and providing feedback on emotion data.

[0617] "Capturing means" refers to a method or device for collecting emotional data from a user.

[0618] "Means for storing" refers to a method or device for storing captured emotion data in a database.

[0619] "Means for obtaining" refers to a method or device for periodically retrieving emotion data from the database.

[0620] "Means for input" refers to a method or device for providing acquired emotion data to a generative AI model.

[0621] "Means for analyzing" refers to the methods and devices by which the generative AI model analyzes the emotional data and generates feedback and insights.

[0622] "Means for providing" refers to the method or device for communicating the generated feedback or insights to the user.

[0623] The present invention relates to a system for collecting and analyzing user emotion data and providing feedback and insights. Specific embodiments of this system are described below.

[0624] Hardware and software used

[0625] Hardware: Servers, user devices (PCs, smartphones, etc.)

[0626] Software: Generative AI models, database management systems (e.g., MySQL), web servers (e.g., Apache), notification systems (e.g., Firebase)

[0627] Data collection

[0628] The user opens the smartphone app and accesses the emotion input screen.

[0629] The user inputs their emotional state (e.g., "sad") and its cause (e.g., "stress from work") and presses the send button.

[0630] The terminal converts the input data into JSON format and sends an HTTP POST request to the server.

[0631] Data storage

[0632] The server parses the received JSON data and stores it in a database.

[0633] The server executes an INSERT statement on the MySQL database and stores the data in the "emotion data" table.

[0634] Data Acquisition

[0635] The server runs a regular job every night to obtain emotion data from the past week.

[0636] The server executes an SQL query to retrieve the required data from the database. For example, it executes the query "SELECT FROM emotion data WHERE date >= DATE_SUB(CURDATE(), INTERVAL 7 DAY)".

[0637] Data analysis

[0638] The server converts the acquired emotional data into a prompt sentence, for example, "Analyze the user's emotional data and generate feedback based on the following data:..."

[0639] The server sends the generated prompt sentence to the generative AI model, for example, by using an API request.

[0640] Feedback Generation

[0641] The generative AI model analyzes the emotional data based on the prompt and generates feedback and insights, such as, "You felt sad three times this week. This may be due to work stress. We recommend you spend more time relaxing."

[0642] The server receives the feedback from the generative AI model and formats it for delivery to the user, for example, generating an HTML dashboard or email body.

[0643] Providing Feedback

[0644] The server provides the generated feedback to the user, for example by generating HTML for display on a web page dashboard and sending it to the user's browser.

[0645] The user opens the application and sees the feedback provided, such as a dashboard message saying, "You felt sad three times this week. This may be due to work stress. We recommend that you spend more time relaxing."

[0646] Specific examples

[0647] For example, if a user records the number of times they felt "sad" over the course of a week, the server can analyze this data and generate feedback such as, "You felt sad three times this week. This may be due to work stress. We recommend that you spend more time relaxing."

[0648] Prompt Sentence Examples

[0649] An example of a prompt to be input to the generative AI model is as follows:

[0650] Analyze user sentiment data and generate feedback based on the following data:

[0651] Date: 2023-10-01, Emotion: Sad, Cause: Work stress

[0652] Date: 2023-10-02, Emotion: Sad, Cause: Relationship

[0653] Date: 2023-10-03, Emotion: Sad, Cause: Work stress

[0654] In this way, the system analyzes the user's emotional state and provides appropriate feedback and insight. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0655] Step 1:

[0656] The user opens the smartphone app and accesses the emotion input screen. The user inputs their emotional state (e.g., "sad") and its cause (e.g., "work stress") and presses the submit button. The input data is generated as JSON-formatted data containing the emotional state and its cause.

[0657] Step 2:

[0658] The device sends the emotion data entered by the user to the server. Specifically, it uses an HTTP POST request to send JSON formatted data to the server. The input is the user's emotion data, and the output is the data sent to the server.

[0659] Step 3:

[0660] The server parses the received JSON data and stores it in a database. Specifically, it parses the JSON data, extracts the emotional state and its cause, and executes an INSERT statement into a MySQL database. The input is the parsed emotional data, and the output is data stored in the database.

[0661] Step 4:

[0662] The server runs a regular job every night at midnight to retrieve emotion data for the past week. Specifically, it executes an SQL query to retrieve emotion data for the past week from the database. For example, it executes the query "SELECT FROM emotion data WHERE date >= DATE_SUB(CURDATE(), INTERVAL 7 DAY)". The input is the SQL query, and the output is the retrieved emotion data.

[0663] Step 5:

[0664] The server converts the acquired emotional data into a prompt. Specifically, it formats the emotional data into a text prompt. For example, it generates a prompt in the format "Analyze the user's emotional data and generate feedback based on the following data:...". The input is the acquired emotional data, and the output is the generated prompt.

[0665] Step 6:

[0666] The server sends the generated prompt sentence to the generative AI model. Specifically, it sends the prompt sentence to the generative AI model using an API request. The input is the generated prompt sentence, and the output is the data sent to the generative AI model.

[0667] Step 7:

[0668] The generative AI model analyzes emotional data based on prompts and generates feedback and insights. For example, it generates feedback such as, "You felt 'sad' three times this week. This may be due to work stress. I recommend you spend more time relaxing." The input is the prompt, and the output is the generated feedback and insights.

[0669] Step 8:

[0670] The server receives the feedback returned by the generative AI model and formats it for delivery to the user, specifically generating an HTML dashboard or email body. The input is the generated feedback or insights, and the output is the formatted feedback.

[0671] Step 9:

[0672] The server provides the generated feedback to the user, for example by generating HTML to display on a web page dashboard and sending it to the user's browser. The input is the formatted feedback, and the output is the feedback provided to the user.

[0673] Step 10:

[0674] The user opens the application and sees the feedback provided, for example, a message on a dashboard saying "You felt sad three times this week. This may be due to work stress. We recommend that you spend more time relaxing." The input is the feedback provided, and the output is the user's confirmation of the feedback.

[0675] (Application example 3)

[0676] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0677] In modern society, managing users' emotional states and mental health is an important issue. However, conventional systems have had difficulty monitoring users' emotional states in real time and providing appropriate feedback and security measures when abnormalities are detected. It has also been difficult to provide information to deepen users' self-understanding or specific advice to help them improve themselves in real time. This has led to problems with users' mental health and security not being adequately maintained.

[0678] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0679] In this invention, the server includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for monitoring the user's emotional state in real time, means for detecting abnormal emotional fluctuations and sending an alert to the user, and means for proposing security measures when an abnormality is detected. This makes it possible to monitor the user's emotional state in real time and provide appropriate feedback and security measures when an abnormality is detected.

[0680] "User" means any individual or entity that uses the System.

[0681] "Diary data" is information in which a user records daily events and emotions.

[0682] "Generative AI methods" are artificial intelligence techniques that analyze input data and generate results.

[0683] "Feedback" refers to the evaluation and advice the system provides to the user.

[0684] "Insights" are deep understandings and perspectives gained from data analysis.

[0685] "Emotional state" refers to the user's current feelings or mood.

[0686] "Real-time" refers to processing and reactions occurring almost simultaneously.

[0687] "Abnormal emotional fluctuations" are sudden changes in emotions that go beyond the normal range.

[0688] An "alert" is a warning that notifies the user when an abnormality is detected.

[0689] "Security measures" are specific means and methods for ensuring user safety.

[0690] A system for implementing this invention includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for monitoring the user's emotional state in real time, means for detecting abnormal emotional fluctuations and sending an alert to the user, and means for suggesting security measures when an abnormality is detected.

[0691] Hardware and Software Configuration

[0692] Hardware:

[0693] It uses the camera and microphone of a smartphone or smart glasses, which allows it to capture the user's facial expressions and tone of voice in real time.

[0694] software:

[0695] OpenCV: A library for image processing. It is used to convert the image acquired from the camera to grayscale and extract the face area.

[0696] Keras: A deep learning framework for implementing emotion recognition models. It is used to predict emotions from extracted face regions.

[0697] smtplib: A library for sending emails. Used to alert users when abnormal emotions are detected.

[0698] Data processing and calculation

[0699] Data processing:

[0700] The image acquired from the camera is converted to grayscale and the facial region is extracted, which is then preprocessed for input into the emotion recognition model.

[0701] Data Calculation:

[0702] Using an emotion recognition model, we predict emotions from the extracted facial regions, allowing us to assess the user's emotional state in real time.

[0703] Specific examples

[0704] For example, if a user is feeling stressed late at night, the system uses a camera and microphone to monitor the user's facial expressions and tone of voice in real time. If the emotion recognition model determines the user's emotional state as "stressed," the system uses smtplib to send the user an alert saying, "It looks like you're feeling stressed late at night. Try taking a deep breath to relax."

[0705] Prompt Sentence Examples

[0706] "Write a Python program that monitors a user's emotional state in real time and sends an alert if an anomaly is detected."

[0707] In this way, it is possible to monitor the user's emotional state in real time and provide appropriate feedback and security measures if anomalies are detected.

[0708] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0709] Step 1:

[0710] The device uses a camera and microphone to capture the user's facial expressions and tone of voice in real time.

[0711] Input: User's facial image and voice data.

[0712] Data processing: Convert images to grayscale and extract facial regions. Convert audio data into audio features.

[0713] Output: Grayscale face region and audio features.

[0714] Step 2:

[0715] The device uses OpenCV to convert the acquired facial image to grayscale and extract the facial area.

[0716] Input: A face image of the user taken from the camera.

[0717] Data processing: Convert the image to grayscale and extract the face area using a face detection algorithm.

[0718] Output: Grayscale image of extracted face region.

[0719] Step 3:

[0720] The device uses Keras to predict emotions from the extracted face regions.

[0721] Input: A grayscale image of the extracted face region.

[0722] Data calculation: Input an image into the emotion recognition model to predict the emotion.

[0723] Output: Emotion prediction (e.g. anger, fear, sadness, etc.).

[0724] Step 4:

[0725] The device analyzes the emotion prediction results and determines whether there are any abnormal emotional fluctuations.

[0726] Input: Emotion prediction results.

[0727] Data calculations: Compare forecast results with historical data to determine if there are any unusual fluctuations.

[0728] Output: Presence or absence of abnormal emotional fluctuations.

[0729] Step 5:

[0730] If the device detects abnormal emotional fluctuations, it will send an alert to the user.

[0731] Input: Presence or absence of abnormal emotional fluctuations.

[0732] Data processing: Generate alert messages.

[0733] Output: An alert notification to the user.

[0734] Step 6:

[0735] If an abnormality is detected on the device, the system will suggest security measures to the user.

[0736] Input: Presence or absence of abnormal emotional fluctuations.

[0737] Data processing: Generate a message proposing security measures.

[0738] Output: Notification of suggested security measures to the user.

[0739] In this way, it is possible to monitor the user's emotional state in real time and provide appropriate feedback and security measures if anomalies are detected.

[0740] 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.

[0741] 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> ) 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.

[0742] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0743] 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.

[0744] [Second embodiment]

[0745] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0746] 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.

[0747] 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).

[0748] 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.

[0749] 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.

[0750] 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).

[0751] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0757] "Example 1"

[0758] The system of the present invention uses a web-based interface or dedicated application to collect diary data from users. Users enter their daily events, feelings, and thoughts as a diary, which is then collected by the system.

[0759] "Example 2"

[0760] The captured diary data is analyzed by generative AI, which uses natural language processing (NLP) techniques to extract user behavioral patterns, mood swings, and lifestyle trends. For example, if a user writes in their diary, "I've been staying up late lately," the AI ​​will interpret this as part of their "irregular lifestyle."

[0761] "Example 3"

[0762] Based on the analysis results, the system provides feedback and insights to the user, either in the form of a webpage or app dashboard, or via email or notification. For example, it may provide specific advice such as, "You've been staying up late lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[0763] The processing flow of each embodiment will be described below.

[0764] "Example 1"

[0765] Step 1: The user enters diary data through a web-based interface or a dedicated application. This data includes the user's daily events, emotions, thoughts, etc.

[0766] Step 2: The system captures the diary data from the user. This capture occurs automatically immediately after the user enters the data.

[0767] "Example 2"

[0768] Step 1: The system sends the diary data it has captured to the generative AI.

[0769] Step 2: Generative AI analyzes the diary data using natural language processing (NLP) techniques to extract user behavioral patterns, mood swings, and lifestyle trends.

[0770] "Example 3"

[0771] Step 1: The generative AI sends the analysis results to the system.

[0772] Step 2: The system generates feedback and insights based on the analysis results.

[0773] Step 3: Provide the system-generated feedback and insights to the user, either via a web page, a dashboard in the application, or via email or notification.

[0774] Example 1

[0775] Next, a description will be given of Example 1 of Form 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."

[0776] Conventional systems have struggled to effectively utilize users' diary data to provide useful feedback and insights to users. Furthermore, they lacked a means to analyze users' behavioral patterns, mood swings, and lifestyle trends to provide information useful for self-understanding, self-improvement, and mental health management.

[0777] 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.

[0778] In this invention, the server includes means for importing diary data from a user, means for storing the imported diary data in a database, means for inputting the stored diary data into a generative AI model, means for the generative AI model to analyze the diary data and generate a prompt sentence, and means for providing the generated prompt sentence to the user. This makes it possible to effectively utilize the user's diary data and provide the user with useful feedback and insights.

[0779] "User" refers to an individual who uses the system to enter diary data.

[0780] "Diary data" refers to text data in which users describe their daily events, feelings, and thoughts.

[0781] "Means of importing" refers to the interface or application for receiving diary data from the user.

[0782] "Database" refers to a relational database or other data storage system for storing captured diary data.

[0783] A "generative AI model" refers to an artificial intelligence model that analyzes diary data and generates appropriate prompts for the user.

[0784] "Prompt sentence" refers to text containing questions or instructions for the user that is generated by the generative AI model based on diary data.

[0785] "Means to provide" refers to an interface or application for displaying the generated prompt text to the user.

[0786] "Analyzing" refers to the process by which the generative AI model analyzes diary data to understand the user's behavioral patterns and emotional fluctuations.

[0787] This invention is a system that takes diary data from users, analyzes it using a generative AI model, and provides useful feedback and insights to the users. A specific embodiment of this system is described below.

[0788] Users enter diary data using a web-based interface or a dedicated application. For example, they open a dedicated application on their smartphone and enter daily events, feelings, and thoughts into text boxes. The hardware used can be a PC or smartphone, and the software can be a web browser (such as Google® Chrome) or a dedicated application (for iOS or Android).

[0789] The device sends the diary data entered by the user to the server. The HTTPS protocol is used for transmission to ensure data security. For example, when the user presses the "Send" button, the device sends the diary data to the server.

[0790] The server stores the received diary data in a database, typically a relational database such as MySQL or PostgreSQL. For example, the server executes the SQL query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (?, ?, ?)" to store the data.

[0791] The server retrieves the diary data stored in the database and inputs it into the generative AI model. For example, the server executes the SQL query "SELECT entry_text FROM diary_entries WHERE user_id = ?" to retrieve the data and pass it to the generative AI model.

[0792] The generative AI model analyzes the input diary data and generates an appropriate prompt for the user. For example, if the diary data says, "Today I went to a cafe with my friends and had a great time," the generative AI model generates a prompt such as, "Tell me a specific story about when you went to a cafe with your friends."

[0793] The server provides the prompts received from the generative AI model to the user, for example, by displaying the prompts to the user through a dedicated application or web interface.

[0794] As a concrete example, consider a scenario in which a user uses a dedicated application to enter a diary entry. The user opens the dedicated application on their smartphone and enters, "Today I went to a cafe with a friend and had a great time. The new coffee tasted really good." This diary entry data is sent to a server through the application and saved in a database. The saved data is then input into a generative AI model, which generates a prompt sentence like the following:

[0795] "Tell me a specific story about when you went to a cafe with a friend."

[0796] This prompt is used as a guide for the user to enter further information.

[0797] In this way, users can input diary data and receive prompts from the generative AI model, which can help them understand themselves better and provide information useful for self-improvement and mental health management.

[0798] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0799] Step 1:

[0800] The user enters diary data.

[0801] Using a web-based interface or a dedicated application, users enter their daily events, feelings, and thoughts into a text box. The entered diary data is saved in text format on the device. A specific example is when a user opens the dedicated application on their smartphone and enters, "Today, I went to a cafe with a friend and had a great time. The new coffee tasted great."

[0802] Step 2:

[0803] The device transmits the diary data to the server.

[0804] When the user presses the "Send" button, the device sends the entered diary data to the server using the HTTPS protocol. The input is text diary data, and the output is data sent to the server. Specifically, the device sends the following text data to the server: "Today I went to a cafe with my friends and had a great time. The new coffee tasted great."

[0805] Step 3:

[0806] The server stores the diary data in a database.

[0807] The server saves the received diary data in a database. The input is the text diary data sent from the device, and the output is the data saved in the database. Specifically, the server executes the SQL query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (?, ?, ?)" to save the data.

[0808] Step 4:

[0809] The server inputs the saved diary data into the generative AI model.

[0810] The server retrieves diary data stored in the database and inputs it into the generative AI model. The input is text diary data retrieved from the database, and the output is data input to the generative AI model. Specifically, the server executes the SQL query "SELECT entry_text FROM diary_entries WHERE user_id = ?" to retrieve the data and pass it to the generative AI model.

[0811] Step 5:

[0812] A generative AI model generates prompts.

[0813] The generative AI model analyzes the input diary data and generates an appropriate prompt for the user. The input is text diary data passed from the server, and the output is the generated prompt. In concrete terms, if the diary data says, "Today I went to a cafe with my friends and had a great time," the generative AI model generates a prompt saying, "Tell me a specific story about when you went to a cafe with your friends."

[0814] Step 6:

[0815] The server generates a prompt and provides it to the user.

[0816] The server provides the user with the prompt received from the generative AI model. The input is the prompt received from the generative AI model, and the output is the display of the prompt to the user. Specifically, the server displays the prompt to the user through a dedicated application or web interface.

[0817] (Application example 1)

[0818] Next, a description will be given of Application Example 1 of Form 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."

[0819] Previous systems simply imported users' diary data, but had limited means of effectively utilizing that data. It was also difficult for users to deepen their self-understanding through their diary entries or provide specific feedback and insights to help them manage their mental health. Furthermore, creative content based on diary data was not generated or distributed, making it difficult to attract users' interest.

[0820] 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.

[0821] In this invention, the server includes means for importing diary data from users, generative AI means for analyzing the imported diary data, means for providing feedback and insights to users based on the analysis results, means for automatically generating stories and essays based on the diary data, and means for delivering the generated stories and essays to users. This makes it possible to utilize users' diary data in a variety of ways to support self-understanding and mental health management, as well as to provide creative content.

[0822] "User" refers to an individual who uses the system to enter diary data.

[0823] "Diary data" refers to information recorded by users about their daily events, feelings, and thoughts.

[0824] "Capturing means" refers to a method or device for collecting diary data from users and storing it in the system.

[0825] "Generative AI means" refers to artificial intelligence technology that analyzes imported diary data and generates information tailored to specific purposes.

[0826] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analytical results obtained by generative AI means.

[0827] "Means for automatically generating stories and essays" refers to methods and devices for generating creative writing based on diary data.

[0828] "Delivery means" refers to the method or device by which the generated story or essay is delivered to the user.

[0829] A system for implementing this invention includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for automatically generating stories and essays based on the diary data, and means for delivering the generated stories and essays to the user.

[0830] Hardware and Software Configuration

[0831] Hardware: Smartphone (iOS or Android), server

[0832] Software: Python, OpenAI API

[0833] Data processing and calculation

[0834] 1. Importing diary data:

[0835] Users enter diary data using a smartphone application, which is then sent to a server and stored in a database.

[0836] 2. Analysis of diary data:

[0837] The server analyzes the captured diary data using generative AI tools (e.g., OpenAI's GPT-3), which extracts the user's behavioral patterns, mood swings, and lifestyle trends.

[0838] 3. Providing feedback and insights:

[0839] Based on the analysis, the server provides users with feedback and insights, including information to deepen self-understanding and helpful advice for self-improvement and mental health management.

[0840] 4. Automatic generation of stories and essays:

[0841] The server generates prompts based on the diary data and inputs them into a generative AI system to automatically generate stories or essays. For example, the following prompts can be used:

[0842] Please generate a moving story based on the diary data below.

[0843] Date: 2023-10-01

[0844] Content: I went to a cafe with a friend today. It was fun.

[0845] Date: 2023-10-02

[0846] Content: Work was busy, but fulfilling.

[0847] 5. Distribution of generated content:

[0848] The generated stories and essays are delivered from the server to the user's smartphone, where they can view the content through an application.

[0849] Specific examples

[0850] Suppose a user enters the following diary entry using a smartphone application.

[0851] 2023-10-01: I went to a cafe with a friend today. It was fun.

[0852] 2023-10-02: Work was busy, but fulfilling.

[0853] The server imports this diary data and analyzes it using generative AI. Based on the analysis results, it provides feedback to the user, such as "Cherishing time with friends helps relieve stress." It also generates the following prompt sentences based on the diary data, automatically generating a story.

[0854] Please generate a moving story based on the diary data below.

[0855] Date: 2023-10-01

[0856] Content: I went to a cafe with a friend today. It was fun.

[0857] Date: 2023-10-02

[0858] Content: Work was busy, but fulfilling.

[0859] The generated story is delivered to the user's smartphone, where they can enjoy it through the application.

[0860] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0861] Step 1:

[0862] A user inputs diary data using a smartphone application. The input diary data is sent in text format to a server. The server receives this data and stores it in a database. The input is the user's diary data, and the output is the diary data stored on the server.

[0863] Step 2:

[0864] The server analyzes the saved diary data using generative AI tools (e.g., OpenAI's GPT-3). Specifically, it analyzes the diary data and extracts the user's behavioral patterns, mood fluctuations, and lifestyle trends. The input is the saved diary data, and the output is the analysis results.

[0865] Step 3:

[0866] The server generates feedback and insights for the user based on the analysis results. For example, it generates advice such as "Spending time with friends will help relieve stress." The input is the analysis results, and the output is feedback and insights.

[0867] Step 4:

[0868] The server generates a prompt based on the diary data. For example, it generates the following prompt:

[0869] Please generate a moving story based on the diary data below.

[0870] Date: 2023-10-01

[0871] Content: I went to a cafe with a friend today. It was fun.

[0872] Date: 2023-10-02

[0873] Content: Work was busy, but fulfilling.

[0874] The input is diary data and the output is a prompt sentence.

[0875] Step 5:

[0876] The server inputs the generated prompt sentences into a generative AI means to automatically generate a story or essay. The generative AI means analyzes the prompt sentences and generates creative writing. The input is the prompt sentence, and the output is the generated story or essay.

[0877] Step 6:

[0878] The server delivers the generated stories and essays to the user's smartphone. The user can view these contents through the application. The input is the generated stories and essays, and the output is the content delivered to the user's smartphone.

[0879] Example 2

[0880] Next, a description will be given of Example 2 of Form 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."

[0881] In modern society, it is important for users to understand their own behavioral patterns, mood swings, and lifestyle trends, and deepen their self-understanding. However, there are limited systems that can effectively collect, analyze, and provide feedback on this information. In particular, there is a lack of systems that utilize diary data to provide users with information useful for managing their mental health and self-improvement.

[0882] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting diary data from the user, a means for the terminal to transmit the diary data to the server, a means for the server to receive the diary data and pass it to the generative AI model, a means for the generative AI model to analyze the diary data, and a means for the server to feed back the analysis results to the user. This makes it possible to effectively collect and analyze the user's diary data and provide useful feedback to the user.

[0883] "User" refers to an individual who utilizes the system to enter diary data and receive feedback.

[0884] "Diary data" refers to text data in which users record their daily events, emotions, actions, etc.

[0885] "Device" refers to the electronic device used by the user to input diary data and send it to the server. Examples include smartphones and personal computers.

[0886] "Server" refers to a computer system that receives diary data sent from the device, passes it to the generative AI model, and provides the analysis results as feedback to the user.

[0887] "Generative AI models" refer to artificial intelligence models that analyze diary data to extract user behavioral patterns, mood fluctuations, and lifestyle trends. Examples include natural language processing models such as BERT and GPT-3.

[0888] "Feedback" refers to information or insights provided to users based on the results analyzed by the generative AI model.

[0889] "Behavioral patterns" refer to the user's behavioral tendencies and habits in their daily lives.

[0890] "Mood swings" refers to changes in a user's emotions or moods.

[0891] "Lifestyle trends" refers to the user's lifestyle habits and characteristics.

[0892] This invention is a system in which a user inputs diary data, analyzes the data using a generative AI model, and provides feedback. Specific embodiments of this system are described below.

[0893] First, the user enters diary data using a dedicated application or web interface. For example, the user opens the application on their smartphone and enters, "I'm very tired today. I tend to stay up late late these days." This diary data is then sent by the device to the server. The data is sent using encrypted communication via the HTTPS protocol.

[0894] The server receives the diary data sent from the device. The received data is passed to a generative AI model. This generative AI model analyzes the diary data using natural language processing (NLP) techniques. Specifically, it uses the Python libraries NLTK and spaCy to tokenize the text data, tag parts of speech, and perform sentiment analysis. It also uses advanced generative AI models such as BERT and GPT-3 to extract user behavioral patterns, mood fluctuations, and lifestyle trends.

[0895] For example, if a user writes, "I've been staying up late lately," the generative AI model will recognize this as an "irregular lifestyle." The analysis results are returned to the server, which then provides this result as feedback to the user. The feedback is provided in the form of a notification to the user's application saying, "Your lifestyle has been irregular lately." This process uses WebSocket technology to send notifications in real time.

[0896] Below are some specific examples of prompt sentences to input into the generative AI model.

[0897] Example prompt sentence:

[0898] User diary data:

[0899] "I'm very tired today. I've been staying up late lately."

[0900] Prompt the generative AI model:

[0901] "Extract user behavioral patterns, mood swings, and lifestyle trends from this diary data."

[0902] In this way, it is possible to effectively collect and analyze users' diary data and provide useful feedback to users, which will help them deepen their self-understanding and provide information useful for self-improvement and mental health management.

[0903] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0904] Step 1:

[0905] The user inputs diary data.

[0906] Users enter diary data using a dedicated application or web interface. For example, they might open the application on their smartphone and enter something like, "I'm very tired today. I tend to stay up late late these days." The data they enter is saved in text format on their device.

[0907] Step 2:

[0908] The device transmits the diary data to the server.

[0909] The device sends the diary data entered by the user to the server. At this time, the data is encrypted using the HTTPS protocol. The input is the user's diary data, and the output is the encrypted data.

[0910] Step 3:

[0911] The server receives the diary data and passes it to the generative AI model.

[0912] The server receives diary data sent from the device. The received data is passed to the generative AI model. Specifically, an API endpoint is created using Python's Flask framework to receive data. The input is encrypted diary data, and the output is text data passed to the generative AI model.

[0913] Step 4:

[0914] A generative AI model analyzes diary data.

[0915] The generative AI model analyzes the received diary data. For example, it uses natural language processing models such as BERT and GPT-3 to tokenize the text data, tag parts of speech, and perform sentiment analysis. The input is the text data passed to the generative AI model, and the output is an analysis result that shows the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0916] Step 5:

[0917] The server provides the analysis results as feedback to the user.

[0918] The server feeds back the analysis results obtained from the generative AI model to the user. For example, it may notify the user's application that "Your lifestyle has been irregular recently." This process uses WebSocket technology to send notifications in real time. The input is the analysis results from the generative AI model, and the output is a feedback message to the user.

[0919] (Application example 2)

[0920] Next, a description will be given of Application Example 2 of Form 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."

[0921] Conventional systems that analyze user diary data focus on analyzing users' behavioral patterns, mood fluctuations, and lifestyle trends, but lack the functionality to evaluate and warn about security risks. This makes it difficult to understand how changes in a user's lifestyle affect security risks. The present invention aims to solve this problem by providing a system that evaluates security risks based on a user's diary data and issues appropriate warnings.

[0922] The identification process 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 importing diary data from the user, generative AI means for analyzing the imported diary data, means for providing feedback and insight to the user based on the analysis results, means for evaluating security risks, and means for issuing warnings based on the security risks. This makes it possible to evaluate security risks based on the user's diary data and issue appropriate warnings.

[0923] "User" refers to any individual or entity that uses the System.

[0924] "Diary data" refers to text data in which users record their daily events, emotions, actions, etc.

[0925] "Capturing means" refers to a method or device for collecting diary data from users and inputting it into the system.

[0926] "Generative AI methods" refers to artificial intelligence technologies for analyzing imported diary data, particularly those that use natural language processing (NLP) technology.

[0927] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analysis results of generative AI means.

[0928] "Means for assessing security risks" refers to methods or devices that evaluate the impact of user behavior and lifestyle on security based on the analysis results of generative AI means.

[0929] "Means for issuing a warning" refers to a method or device for notifying a user of a warning when a security risk increases.

[0930] The system for implementing this invention imports a user's diary data, analyzes it using generative AI, evaluates security risks, and issues appropriate warnings. Specific embodiments are described below.

[0931] System Configuration

[0932] The system consists of the following main components:

[0933] 1. User device: The device on which the user enters diary data. This includes smartphones and PCs.

[0934] 2. Server: A central processing unit that ingests diary data, analyzes it using generative AI, provides feedback and insights, assesses security risks, and issues alerts.

[0935] 3. Generative AI model: An AI model for analyzing diary data using natural language processing (NLP) techniques. Specifically, it uses the spaCy and transformers libraries.

[0936] Data capture and analysis

[0937] Diary data is sent from the user's device to the server. The server receives the data using a means to import diary data and analyzes it using generative AI means. Specifically, the following process is performed:

[0938] 1. Data import: The diary data entered by the user is sent to the server in text format.

[0939] 2. Data analysis: The server analyzes the diary data using generative AI models (e.g., spaCy or the transformers library) to extract user behavioral patterns, mood fluctuations, and lifestyle trends.

[0940] Security risk assessment and warning

[0941] The server evaluates security risks based on the analysis results of the generative AI method. Specifically, the following processes are performed:

[0942] 1. Risk assessment: Evaluate security risks based on extracted behavioral patterns and lifestyle trends. For example, if the behavior of "staying up late" is frequently observed, it is determined that this is an irregular lifestyle and poses a high risk.

[0943] 2. Warning: Based on the assessed security risk, a warning is issued to the user. The warning is sent to the user's device.

[0944] Specific examples

[0945] For example, if a user writes in their diary, "I've been staying up late lately," the server will recognize this as an "irregular lifestyle" and determine that it may pose a security risk. Based on this, the server will issue a warning to the user, such as, "If you continue to stay up late, your security risk will increase. Try to lead a more regular life."

[0946] Prompt Sentence Examples

[0947] An example of a prompt to input to a generative AI model is as follows:

[0948] Analyze the user's diary data to extract behavioral patterns, mood swings, and lifestyle trends. For example, if a user writes, "I've been staying up late lately," recognize this as an "irregular lifestyle."

[0949] In this way, a system can be realized that evaluates security risks based on a user's diary data and issues appropriate warnings.

[0950] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0951] Step 1:

[0952] The user inputs diary data. The diary data is entered in text format using the user's device (smartphone or PC) and sent to the server. The input data includes the user's daily events, emotions, actions, etc.

[0953] Step 2:

[0954] The server receives the diary data. The server receives the diary data sent from the user terminal using a means for importing it and stores it in a database. The input is the user's diary data, and the output is the stored text data.

[0955] Step 3:

[0956] The server analyzes the diary data using a generative AI model. The server uses the spaCy and transformers libraries to analyze the diary data using natural language processing (NLP) techniques. The input is stored text data, and the output is an analysis showing the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[0957] Step 4:

[0958] The server evaluates security risks based on the analysis results. Based on the analysis results from generative AI means, the server evaluates the impact of specific behaviors and lifestyles on security risks. For example, if the behavior of "staying up late" is frequently observed, it will determine that this irregular lifestyle poses a high risk. The input is the analysis results, and the output is the security risk assessment results.

[0959] Step 5:

[0960] The server issues a warning based on the security risk. The server notifies the user of the warning based on the assessed security risk. The warning is notified to the user's terminal. The input is the security risk assessment result, and the output is a warning message for the user.

[0961] Step 6:

[0962] The user receives a warning. The user checks the warning message sent to the user's device and takes necessary measures. The input is the warning message sent from the server, and the output is the user's behavior change or implementation of measures.

[0963] In this way, a system can be realized that evaluates security risks based on a user's diary data and issues appropriate warnings.

[0964] Example 3

[0965] Next, a description will be given of Example 3 of Form Example 3. 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."

[0966] Conventional systems have struggled to effectively collect and analyze user behavioral data and provide appropriate feedback and insights. They also lacked the means to accurately grasp changes in users' behavioral patterns and lifestyles and provide specific advice based on that information. This has prevented them from fully contributing to users' self-understanding, self-improvement, and mental health management.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0968] In this invention, the server includes means for capturing behavioral data from users, means for preprocessing the captured behavioral data, generative AI means for analyzing the preprocessed data, means for generating feedback and insights for users based on the analysis results, and means for providing the generated feedback and insights to users, thereby enabling effective collection and analysis of user behavioral data and provision of appropriate feedback and insights.

[0969] "Behavioral Data" refers to information about a user's behavior, such as their web page browsing history, application usage history, or sleep patterns.

[0970] "Preprocessing" refers to the process of improving the quality of collected data by performing operations such as filling in missing values, normalizing the data, and detecting outliers.

[0971] "Generative AI methods" refer to methods that use machine learning or generative AI models to analyze data and generate feedback and insights in natural language.

[0972] "Feedback" refers to specific advice or insights provided to users based on the analysis results.

[0973] "Delivery Vehicle" refers to the means by which generated feedback and insights are communicated to users, including web pages, application dashboards, emails, notifications, etc.

[0974] This invention relates to a system that collects and analyzes user behavior data and provides appropriate feedback and insights. Specific embodiments of this system are described below.

[0975] Data collection

[0976] The server collects user behavior data, such as web page browsing history, application usage history, sleep patterns, etc. This data is stored in a database (e.g., MySQL, PostgreSQL).

[0977] Data Preprocessing

[0978] The server preprocesses the collected data, specifically by imputing missing values, normalizing the data, and detecting outliers. This improves the quality of the data. For example, missing values ​​are imputed with the mean or median. Data normalization involves scaling each data point to a range from 0 to 1. Outlier detection involves using statistical methods to identify and remove abnormal data points.

[0979] Data analysis

[0980] The server uses the preprocessed data to train a machine learning model. For example, to analyze the user's sleep patterns, it uses a Long Short-Term Memory (LSTM) model using time-series data. The model predicts future sleep patterns based on the user's past sleep data. Machine learning libraries such as TensorFlow and scikit-learn are used for the analysis.

[0981] Feedback Generation

[0982] The server generates feedback based on the analysis results. A prompt sentence is input into a generative AI model (e.g., OpenAI GPT-3), and feedback is generated in natural language. For example, a prompt sentence might be input, "After analyzing the user's recent sleep patterns, we have found that they tend to stay up late. Please generate feedback encouraging the user to go to bed early and get up early." The generated feedback would be, "You've been staying up late late recently. Making an effort to go to bed early and get up early may have a positive effect on your health."

[0983] Providing Feedback

[0984] The server provides the generated feedback to the user. This can be provided via a web page, a dashboard on the application, email, or notification. For example, when the user opens the application, the feedback is displayed on the dashboard. Feedback can also be sent via email or push notification. The user receives this feedback and uses it as a reference for improving their behavior.

[0985] Specific examples

[0986] Example 1: Sleep pattern feedback

[0987] If the user has been staying up late recently, the server might generate feedback like this:

[0988] "You've been staying up late lately. Trying to go to bed earlier and get up earlier might have a positive effect on your overall health."

[0989] Example 2: Feedback based on web page browsing history

[0990] If a user frequently views web pages on a particular topic, the server generates feedback like this:

[0991] "You've been browsing a lot of health-related web pages lately. Would you like me to email you the latest health news?"

[0992] Prompt Sentence Examples

[0993] Below is an example of a prompt sentence to input to the generative AI model.

[0994] Prompt 1: Sleep pattern feedback

[0995] Your analysis of the user's recent sleep patterns indicates that they tend to stay up late. Generate feedback to encourage the user to go to bed earlier and get up earlier.

[0996] Prompt 2: Feedback based on web page browsing history

[0997] A user has recently been browsing health web pages frequently. Generate feedback to provide the user with the latest health information.

[0998] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0999] Step 1:

[1000] The server collects user behavior data. Specifically, it records the URL and the time spent viewing each web page. It also collects operation logs when users use applications. This data is stored in a database.

[1001] Input: User behavior data (webpage browsing history, application usage history)

[1002] Output: Behavioral data stored in a database

[1003] Step 2:

[1004] The server preprocesses the collected data by imputing missing values ​​with the mean or median, normalizing the data by scaling each data point to a range between 0 and 1, and detecting outliers by using statistical methods to identify and remove anomalous data points.

[1005] Input: Behavioral data stored in a database

[1006] Output: Preprocessed data

[1007] Step 3:

[1008] The server uses the preprocessed data to train a machine learning model. For example, it uses a Long Short-Term Memory (LSTM) model with time-series data to analyze the user's sleep patterns. The model predicts future sleep patterns based on the user's past sleep data.

[1009] Input: Preprocessed data

[1010] Output: A trained machine learning model

[1011] Step 4:

[1012] The server generates feedback based on the analysis results. A prompt sentence is input into the generative AI model, and feedback is generated in natural language. For example, a prompt sentence might be input as follows: "After analyzing the user's recent sleep patterns, we have noticed a tendency for them to stay up late. Please generate feedback encouraging the user to go to bed early and get up early." The generated feedback would be, "You've been staying up late late recently. Making an effort to go to bed early and get up early may have a positive effect on your health."

[1013] Input: Trained machine learning model, prompt

[1014] Output: Generated feedback

[1015] Step 5:

[1016] The server provides the generated feedback to the user via a web page, an application dashboard, email, or notification. For example, when the user opens the application, the feedback is displayed on the dashboard. Feedback can also be sent via email or push notification.

[1017] Input: Generated feedback

[1018] Output: Feedback provided to the user

[1019] The above are the specific processing steps of the program of this system.

[1020] (Application example 3)

[1021] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1022] In modern society, managing users' physical and mental health is an important issue. However, conventional systems have had difficulty comprehensively analyzing users' behavioral patterns and lifestyles and providing specific feedback. In addition, there are limited ways for users to accurately understand their own physical and mental health conditions and obtain information to take appropriate measures to improve them. This has led to the problem of users being unable to fully understand and improve themselves.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1024] In this invention, the server includes a means for importing diary data and biometric data from the user, a generative AI means for analyzing the imported diary data and biometric data, a means for providing feedback and insights to the user based on the analysis results, and a means for providing the feedback and insights via notifications or a dashboard. This enables the server to comprehensively analyze the user's behavioral patterns, mood fluctuations, lifestyle trends, and sleep patterns and provide specific feedback. This allows the user to deepen their self-understanding and obtain information useful for self-improvement and health management.

[1025] "Diary data" is information recorded by users about their daily events, emotions, actions, etc.

[1026] "Biometric data" refers to data that indicates the user's physical condition, such as sleep patterns and exercise levels.

[1027] "Generative AI methods" are artificial intelligence techniques that analyze users' behavioral patterns and lifestyles based on collected data, and generate feedback and insights.

[1028] "Feedback" is specific advice or information provided to users based on the analysis results.

[1029] "Insights" are deep understandings and insights gained through data analysis, containing important information about user behavior and status.

[1030] "Notifications" are a means of providing information to users in real time, including push notifications on smartphones.

[1031] A "dashboard" is a user-accessible interface that visually displays analysis results and feedback.

[1032] "Behavioral patterns" refer to the user's daily behavioral tendencies and habits.

[1033] "Mood swings" refer to changes in a user's emotional or mental state.

[1034] "Lifestyle trends" refers to a user's lifestyle habits and daily behavior patterns.

[1035] "Sleep patterns" refers to data about a user's sleep duration and quality.

[1036] "Self-understanding" means that users gain a deep understanding of their own behavior, emotions, and state.

[1037] "Self-improvement" is the effort by users to improve their own behavior or state.

[1038] "Health management" refers to activities and efforts that users make to maintain and improve their health.

[1039] "Mental health management" refers to activities and efforts that users make to maintain and improve their mental health.

[1040] A system for implementing this invention includes means for capturing diary data and biometric data from a user, generative AI means for analyzing the captured data, means for providing feedback and insights to the user based on the analysis results, and means for providing the feedback and insights via notifications or a dashboard.

[1041] 1. Data Collection

[1042] The server collects users' diary data and biometric data from their smartphones and wearable devices. The diary data includes information on users' daily events, emotions, and behaviors. The biometric data includes users' sleep patterns and exercise levels.

[1043] 2. Data analysis

[1044] The server analyzes the collected diary and biometric data using a generative AI model (e.g., OpenAI GPT-3), which evaluates the user's behavioral patterns, mood swings, lifestyle trends, and sleep patterns.

[1045] 3. Feedback Generation

[1046] The server uses a generative AI model to generate specific feedback and insights based on the analysis results. For example, analyzing a user's sleep data may generate the following feedback:

[1047] "You haven't been getting enough sleep lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1048] 4. Providing Feedback

[1049] The server then provides the generated feedback and insights to the user via smartphone notifications and an in-app dashboard, providing real-time information about their physical and mental health status.

[1050] Hardware and software used

[1051] Hardware: Smartphones, wearable devices (e.g., smartwatches)

[1052] Software: Python, data analysis libraries (e.g., Pandas, NumPy), generative AI models (e.g., OpenAI GPT-3)

[1053] Specific examples

[1054] If the user enters their sleep data from the past 30 days into the app, the server will provide feedback like this:

[1055] "You haven't been getting enough sleep lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1056] Prompt Sentence Examples

[1057] Analyze the user's sleep data from the past 30 days and generate feedback such as:

[1058] Data: [5.5, 6.0, 7.0, 4.5, 8.0, 6.5, 7.5, 5.0, 6.0, 7.0, 8.5, 6.0, 7.5, 5.5, 6.0, 7.0, 4.5, 8.0, 6.5, 7.5, 5.0, 6.0, 7.0, 8.5, 6.0, 7.5, 5.5, 6.0, 7.0, 4.5]

[1059] In this way, a system can be realized that provides specific feedback to support the user in managing their health.

[1060] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1061] Step 1:

[1062] Users input diary data and biometric data using smartphones or wearable devices. The diary data includes information recorded by the user about daily events, emotions, and behaviors, while the biometric data includes the user's sleep patterns and amount of exercise. The input data is then sent to a server.

[1063] Step 2:

[1064] The server stores the received diary data and biometric data in a database. The stored data is used for subsequent analysis. Specifically, the data is efficiently managed using a database management system (e.g., MySQL, PostgreSQL).

[1065] Step 3:

[1066] The server inputs the saved diary data and biometric data into a generative AI model (e.g., OpenAI GPT-3). The generative AI model uses this data to analyze the user's behavioral patterns, mood fluctuations, lifestyle trends, and sleep patterns. Based on the input data, the AI ​​model performs data preprocessing (e.g., normalization, missing value imputation) and generates analysis results.

[1067] Step 4:

[1068] The server generates specific feedback and insights for the user based on the analysis results obtained from the generative AI model. For example, after analyzing the user's sleep data, the following feedback may be generated: "You've been sleeping less recently. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1069] Step 5:

[1070] The server provides the generated feedback and insights to the user through the smartphone notification function and the in-application dashboard. Specifically, the server provides information in real time using push notifications, and the in-application dashboard visually displays the feedback and insights.

[1071] Step 6:

[1072] Based on the feedback and insights provided, users can take concrete actions to improve their behavior and lifestyle, such as going to bed earlier and getting up earlier to get more sleep.

[1073] In this way, a system is realized that provides specific feedback to support the user in managing their health.

[1074] 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.

[1075] "Example 1"

[1076] In one embodiment of the present invention, a system is provided that includes a means for capturing diary data from a user, a generative AI means for analyzing the captured diary data, and a means for providing feedback and insights to the user based on the analysis results. The system analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1077] "Example 2"

[1078] The generative AI means includes an emotion engine that recognizes the user's emotions. This emotion engine extracts the user's emotional state from the diary data and reflects that emotional state in the analysis results. Specifically, it extracts emotional expressions such as "fun" or "sad" that the user wrote in the diary and analyzes the intensity and frequency of those emotions.

[1079] "Example 3"

[1080] Feedback and insights are provided based on the user's emotional state. This allows users to objectively understand their own emotional fluctuations and use them to manage their emotions and improve their mental health. For example, users can reflect on the number of times they felt "sad" over the course of a week and the events that caused that feeling. They can also understand what emotions specific events trigger and consider countermeasures.

[1081] The processing flow of each embodiment will be described below.

[1082] "Example 1"

[1083] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[1084] Step 2: Analyze the captured diary data using generative AI. In this step, the AI ​​extracts and analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1085] Step 3: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results.

[1086] "Example 2"

[1087] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[1088] Step 2: Extract emotional states from the imported diary data using the emotion engine. In this step, the emotion engine extracts emotional expressions from the user's diary data and analyzes the intensity and frequency of those emotions.

[1089] Step 3: Analyze the extracted emotional state using generative AI. In this step, the AI ​​analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the emotional state obtained from the emotion engine.

[1090] Step 4: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results.

[1091] "Example 3"

[1092] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[1093] Step 2: Extract emotional states from the imported diary data using the emotion engine. In this step, the emotion engine extracts emotional expressions from the user's diary data and analyzes the intensity and frequency of those emotions.

[1094] Step 3: Analyze the extracted emotional state using generative AI. In this step, the AI ​​analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the emotional state obtained from the emotion engine.

[1095] Step 4: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results. The feedback and insights are based on the user's emotional state and can be used to manage their emotions and improve their mental health.

[1096] Example 1

[1097] Next, a description will be given of Example 1 of Form 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."

[1098] Conventional systems have struggled to effectively analyze users' diary data and provide useful feedback and insights to users. They also lacked the means to accurately grasp users' behavioral patterns, mood fluctuations, and lifestyle trends, and provide appropriate advice based on those findings. This has resulted in insufficient support for users' self-understanding, self-improvement, and mental health management.

[1099] 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.

[1100] In this invention, the server includes means for importing diary data from a user, means for storing the imported diary data in a database, means for analyzing the stored diary data using a generative AI model, means for generating feedback and insights for the user based on the analysis results, and means for providing the generated feedback to the user. This makes it possible to effectively analyze the user's diary data, understand the user's behavioral patterns, mood fluctuations, and lifestyle trends, and provide appropriate feedback and insights based on them.

[1101] "User" refers to an individual who utilizes the system to enter diary data and receive feedback and insights.

[1102] "Diary data" refers to text data in which users record their daily events, feelings, and thoughts.

[1103] "Means of import" refers to the interface or application that allows users to input diary data into the system.

[1104] "Database" refers to an information system for storing and managing imported diary data.

[1105] A "generative AI model" refers to an artificial intelligence model that analyzes saved diary data and extracts users' behavioral patterns, mood fluctuations, and lifestyle trends.

[1106] "Means of analysis" refers to the process of using a generative AI model to analyze diary data and understand users' behavioral patterns, mood fluctuations, and lifestyle trends.

[1107] "Feedback" refers to advice or insights provided to users based on the analysis results of the generative AI model.

[1108] "Means for providing" refers to the method or system for notifying and displaying the generated feedback to the user.

[1109] The present invention relates to a system for capturing and analyzing a user's diary data and providing feedback. A specific embodiment of this system will be described below.

[1110] System configuration

[1111] Hardware and Software

[1112] Users enter diary data using a web-based interface or dedicated application. For example, they can use a smartphone app or website. The device then sends the entered diary data to a server. The server then stores the received diary data in a database and analyzes it using a generative AI model. The generative AI model used is a natural language processing model such as GPT-4.

[1113] Data capture and storage

[1114] Users enter diary data through a smartphone app or website. For example, a user might enter, "Today was a tough day at work. My boss scolded me and I'm feeling down." The device then sends this data to a server using the HTTPS protocol. The server then stores the received diary data in a relational database such as MySQL or PostgreSQL. The stored data is organized for later analysis.

[1115] Analyzing the data

[1116] The server analyzes the saved diary data using a generative AI model. GPT-4 is used as the generative AI model. The server inputs the diary data into the AI ​​model and extracts behavioral patterns, mood fluctuations, and lifestyle trends. For example, it sends a prompt message to the AI ​​model saying, "Analyze the user's diary data and extract emotional fluctuations."

[1117] Generating and Providing Feedback

[1118] The server generates feedback and insights for the user based on the analysis results of the AI ​​model. For example, if the AI ​​model analyzes that "the user is feeling stressed at work," the server generates feedback such as "It seems that you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The server sends this feedback to the user's device, and the user can check the feedback through the app.

[1119] Examples of specific examples and prompts

[1120] Specific examples

[1121] A user enters into their diary, "Today was tough at work. My boss got mad at me and I'm feeling down." The device sends this data to the server. The server stores this data in a database and analyzes it using a generative AI model (GPT-4). The AI ​​model analyzes that "The user is feeling stressed at work," and the server generates feedback such as "It seems like you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The server sends this feedback to the user's device, and the user checks it through the app.

[1122] Prompt Sentence Examples

[1123] "Analyze the user's diary data and extract behavioral patterns and mood fluctuations. For example, if a user writes, 'Today was a tough day at work. My boss got mad at me, and I'm feeling down,' generate the type of feedback we should provide."

[1124] In this way, the system goes through a series of processes to capture the user's diary data, analyze it, and provide feedback.

[1125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1126] Step 1:

[1127] Users enter diary data using a web-based interface or a dedicated application. For example, a user might enter, "Today was a tough day at work. My boss scolded me, and I'm feeling down." The data is then stored on the device.

[1128] Step 2:

[1129] The device sends the entered diary data to the server. The HTTPS protocol is used for transmission to ensure data security. Specifically, the device sends a "POST" request to "https: / / api.example.com / submit." The input is the user's diary data, and the output is the data sent to the server.

[1130] Step 3:

[1131] The server saves the received diary data in a database. MySQL is used as the database. The server executes an "INSERT" query on the database to save the diary data. For example, it executes the query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (1, 'Work was tough today. My boss got mad at me and I'm feeling down.', '2023-10-01');". The input is the received diary data, and the output is saving it to the database.

[1132] Step 4:

[1133] The server analyzes the saved diary data using a generative AI model. GPT-4 is used as the generative AI model. The server inputs the diary data into the AI ​​model and extracts behavioral patterns, mood fluctuations, and lifestyle trends. For example, the server sends a prompt to the AI ​​model saying, "Analyze the user's diary data and extract emotional fluctuations." The input is the saved diary data, and the output is the analysis results.

[1134] Step 5:

[1135] The server generates feedback and insights for the user based on the analysis results of the AI ​​model. For example, if the AI ​​model analyzes that "the user is feeling stressed at work," the server generates feedback such as "It seems that you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The input is the analysis results of the AI ​​model, and the output is the generated feedback.

[1136] Step 6:

[1137] The server provides the generated feedback to the user, who can check the feedback through a dedicated application or web interface. For example, the server sends a notification to the device saying "There is new feedback," and the user opens the app to check the feedback. The input is the generated feedback, and the output is the notification to the user and the display of the feedback.

[1138] (Application example 1)

[1139] Next, a description will be given of Application Example 1 of Form 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."

[1140] Conventional systems that analyze users' diary data analyze users' behavioral patterns, mood fluctuations, and lifestyle trends to provide information useful for self-understanding and mental health management. However, these systems do not support security risk prediction or countermeasure proposals, which means users are unable to effectively manage the security risks they face in their daily lives.

[1141] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for importing diary data from the user, a generative AI means for analyzing the imported diary data, a means for providing feedback and insight to the user based on the analysis results, and a means for predicting security risks and proposing appropriate countermeasures. This makes it possible to evaluate security risks based on the user's diary data and propose specific countermeasures.

[1142] A "user" is an individual who utilizes the system to enter diary data and receive feedback and insights.

[1143] "Diary data" is information in which users record their daily events, feelings, and thoughts.

[1144] "Means of import" refers to the interface or application used to collect diary data from users and input it into the system.

[1145] "Generative AI methods" are artificial intelligence technologies that analyze imported diary data and generate feedback and insights for users.

[1146] "Means for providing feedback and insights" are methods and tools for communicating the analytical results generated by generative AI means to users.

[1147] "Security risks" are dangers or threats that may occur in a user's daily life.

[1148] "Means for proposing appropriate countermeasures" are methods and tools that evaluate security risks and suggest specific preventative or avoidance measures to users.

[1149] "Behavioral patterns" refer to the user's tendencies and habits in daily life.

[1150] "Mood swings" are changes in a user's emotional or mental state.

[1151] "Lifestyle trends" refer to the user's lifestyle habits and characteristics.

[1152] "Self-understanding" refers to users gaining a deep understanding of their own behavior, emotions, and thoughts.

[1153] "Mental health management" refers to methods and activities for maintaining and improving a user's mental health.

[1154] As an embodiment of the present invention, the following system can be constructed.

[1155] System configuration

[1156] The system includes a terminal for capturing the user's diary data, a server for analyzing the data, and an interface for providing the analysis results to the user.

[1157] 1. User Device

[1158] The user terminals are devices such as smartphones and smart glasses. An application is installed on these terminals, allowing users to enter diary data. This application provides an interface for users to enter their daily events, feelings, and thoughts.

[1159] 2. Server

[1160] The server receives the diary data sent by the user and analyzes the data using a generative AI model. Specifically, it performs the following processes:

[1161] Data import: Receives diary data sent from the user's device.

[1162] Prompt generation: Based on the received diary data, a prompt sentence is generated to be passed to the generative AI model.

[1163] Analysis using generative AI models: Using OpenAI's API, security risks are analyzed based on prompt text.

[1164] Feedback generation: Converting the generated feedback into a format for delivery to the user.

[1165] 3. Feedback Providing Interface

[1166] The feedback interface is the part of the application displayed on the user's device that displays feedback and insights sent from the server to the user, such as specific countermeasures for security risks, as well as information about the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1167] Hardware and software used

[1168] Hardware: Smartphones, smart glasses, servers

[1169] Software: Python, OpenAI API

[1170] Data processing and calculation

[1171] The server receives the diary data sent by the user and analyzes it using a generative AI model. Specifically, it processes and calculates the data as follows:

[1172] 1. Data import: Receives diary data sent from the user's device.

[1173] 2. Prompt generation: Based on the received diary data, a prompt sentence is generated to be passed to the generative AI model.

[1174] 3. Analysis using generative AI models: Using OpenAI's API, security risks are analyzed based on prompt text.

[1175] 4. Feedback generation: Converting the generated feedback into a format for delivery to the user.

[1176] Specific examples

[1177] For example, if a user writes in their diary, "I came home late tonight, but the road from the station to my house was dark and I felt uneasy," the system will use that information to analyze the security risks of returning home late at night and suggest taking a well-lit route or taking a taxi.

[1178] Prompt Sentence Examples

[1179] User diary data: I got home late today, but the road from the station to my house was dark and I felt uneasy.

[1180] Based on this data, analyze security risks and propose appropriate countermeasures.

[1181] In this way, it becomes possible to evaluate security risks based on users' diary data and propose specific countermeasures.

[1182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1183] Step 1:

[1184] The user enters diary data. Using an application installed on a smartphone or smart glasses, the user enters daily events, emotions, and thoughts. The entered diary data is temporarily stored on the device.

[1185] Step 2:

[1186] The device sends the diary data to the server. When the user instructs the device to send the diary data, the device sends the data to the server via the Internet. The input data is sent in text format.

[1187] Step 3:

[1188] The server receives the diary data. The server receives the diary data sent from the device and stores it in a database. The received data is stored in its original format.

[1189] Step 4:

[1190] The server generates a prompt sentence based on the received diary data, which is then passed to the generative AI model. Specifically, the server performs text analysis on the diary data and converts it into a question format for assessing security risks.

[1191] Step 5:

[1192] The server analyzes the diary data using a generative AI model. The server then sends the generated prompts to the OpenAI API to analyze security risks. The input is the prompts, and the output is feedback on security risks.

[1193] Step 6:

[1194] The server generates the feedback. The server converts the feedback obtained from the generative AI model into a format for providing to the user. Specifically, the server formats the feedback into text so that it is easy for the user to understand.

[1195] Step 7:

[1196] The server sends the feedback to the user terminal. The server sends the formatted feedback to the user terminal. The transmitted data is in text format.

[1197] Step 8:

[1198] The user terminal displays the feedback. The user terminal displays the feedback received from the server within the application. The user can check the feedback and obtain specific measures to address security risks.

[1199] In this way, it becomes possible to evaluate security risks based on users' diary data and propose specific countermeasures.

[1200] Example 2

[1201] Next, a description will be given of Example 2 of Form 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."

[1202] Conventional systems simply store users' diary data, making it difficult to extract useful information from that data and provide feedback to users. Furthermore, they lacked the means to perform detailed analysis of users' emotional states and behavioral patterns, making it impossible to provide information useful for self-understanding and mental health management. This made it difficult for users to understand fluctuations in their lifestyles and emotions and gain specific insights for improvement.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1204] In this invention, the server includes a means for importing diary data from a user, a generative AI means for analyzing the imported diary data using natural language processing technology, a means for extracting the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the analysis results, a means for providing feedback and insights to the user based on the extracted information, and an emotion engine for extracting emotional states from the user's diary data and analyzing the intensity and frequency of those emotions. This makes it possible to analyze detailed behavioral patterns and emotional fluctuations from the user's diary data and provide specific feedback useful for self-understanding and mental health management.

[1205] "User" refers to an individual who uses the system to enter diary data and receive analysis results.

[1206] "Diary data" refers to text data in which users describe their daily events and feelings.

[1207] "Means of importing" refers to the interface and functions for importing diary data entered by users into the system.

[1208] "Generative AI means" refers to the function of artificial intelligence that uses natural language processing technology to analyze diary data and extract users' behavioral patterns and emotional states.

[1209] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[1210] "Analysis results" refers to information such as behavioral patterns, mood fluctuations, and lifestyle trends extracted from diary data by generative AI means.

[1211] "Behavioral patterns" refer to a user's behavioral tendencies and habits extracted from the user's diary data.

[1212] "Mood fluctuations" refers to changes in a user's emotions extracted from the user's diary data.

[1213] "Lifestyle trends" refers to a user's habits and lifestyle patterns extracted from the user's diary data.

[1214] "Means of providing feedback and insights" refers to functions that provide useful information and advice to users based on the analysis results.

[1215] The "emotion engine" refers to a function that extracts the user's emotional state from their diary data and analyzes the intensity and frequency of those emotions.

[1216] "Emotional state" refers to the emotional state of a user based on the emotional expressions described in the user's diary data.

[1217] "Intensity" refers to the strength of the emotion extracted by the emotion engine.

[1218] "Frequency" refers to the frequency with which the emotion extracted by the emotion engine appears in the diary data.

[1219] This invention is a system that analyzes a user's diary data, extracts behavioral patterns, emotional fluctuations, and lifestyle trends, and provides useful feedback and insights to the user. A specific embodiment of this system is described below.

[1220] Hardware and software used

[1221] Hardware: Servers, devices (smartphones, PCs, etc.)

[1222] Software: Generative AI, Natural Language Processing (NLP) engine, Emotion engine

[1223] System configuration

[1224] 1. Importing diary data from users

[1225] Users can input diary data using a terminal, either by text input or voice input.

[1226] The device sends the diary data entered to the server, where encryption technology is used to ensure the security of the data.

[1227] 2. Analysis of diary data

[1228] The server passes the received diary data to the generative AI, which then uses natural language processing (NLP) technology to analyze the text of the diary data.

[1229] The purpose of the analysis is to extract user behavioral patterns, mood swings, and lifestyle trends. Specifically, it identifies patterns of behavior and emotions based on the content written by the user in their diary.

[1230] 3. Emotional Recognition

[1231] The server uses a generative AI emotion engine to extract emotional states from users' diary data. The emotion engine identifies emotional expressions such as "happy" or "sad" and analyzes the intensity and frequency of those emotions.

[1232] 4. Generating analysis results

[1233] The server compiles the analysis results obtained from the generative AI, which include behavioral patterns, emotional states, and lifestyle trends.

[1234] For example, if a user writes, "I've been staying up late lately," the server will classify this as an "irregular lifestyle."

[1235] 5. Providing results

[1236] The server sends the analysis results to the terminal, where the user can check the results.

[1237] Feedback and insights are information that helps users better understand themselves and can be used for self-improvement and mental health management.

[1238] Specific examples

[1239] Diary data entered: "Today was so much fun. I went to the movies with my friends."

[1240] Generative AI analysis results:

[1241] Activity Pattern: Leisure Activities

[1242] Emotional state: High joy

[1243] Lifestyle: Regular

[1244] Prompt Sentence Examples

[1245] "Analyze users' diary data to extract behavioral patterns, mood swings, and lifestyle trends."

[1246] "Extract emotional expressions from diary data and analyze the intensity and frequency of those emotions."

[1247] In this way, the system can analyze the user's diary data in detail and understand changes in lifestyle and emotions.

[1248] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1249] Step 1:

[1250] A user inputs diary data using a terminal.

[1251] Specifically, users open an application on their smartphone or computer and enter the contents of their diary in text format.

[1252] Input: User's diary text

[1253] Output: Diary data saved on the device

[1254] Step 2:

[1255] The terminal transmits the input diary data to the server.

[1256] Specifically, the device uploads diary data to a server via the Internet, and encryption technology is used during data transmission to ensure data security.

[1257] Input: Diary data saved on the device

[1258] Output: Diary data sent to the server

[1259] Step 3:

[1260] The server passes the received diary data to the generative AI.

[1261] Specifically, the server uses an NLP engine to analyze the text of the diary data and extract the user's behavioral patterns and lifestyle trends.

[1262] Input: Diary data sent to the server

[1263] Output: Analysis results by the NLP engine

[1264] Step 4:

[1265] The server uses a generative AI emotion engine to extract the user's emotional state from their diary data.

[1266] Specifically, the emotion engine identifies emotional expressions such as "happy" or "sad" and analyzes the intensity and frequency of those emotions.

[1267] Input: Diary data sent to the server

[1268] Output: Sentiment analysis results by the emotion engine

[1269] Step 5:

[1270] The server compiles the analysis results obtained from the generative AI.

[1271] Specifically, the server generates a report of behavioral patterns, emotional states, and lifestyle trends.

[1272] Input: Analysis results by the NLP engine, emotion analysis results by the emotion engine

[1273] Output: Analysis result report

[1274] Step 6:

[1275] The server sends the analysis results to the terminal.

[1276] Specifically, the server sends the generated report to the user's terminal, and the user checks the analysis results through the terminal.

[1277] Input: Analysis result report

[1278] Output: Analysis results report sent to your device

[1279] Step 7:

[1280] The user checks the analysis results through the terminal.

[1281] Specifically, the user opens the application and views the report sent from the server.

[1282] Input: Analysis result report sent to the terminal

[1283] Output: Analysis results confirmed by the user

[1284] (Application example 2)

[1285] Next, a description will be given of Application Example 2 of Form 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."

[1286] Conventional systems simply record users' diary data, making it difficult to deeply understand their behavioral patterns and emotional states and provide appropriate feedback and insights. Furthermore, they lacked the ability to predict and warn of security risks based on users' emotional states and behavioral patterns, making it difficult to ensure user safety. This created challenges in users' self-understanding, mental health management, and even security risk prediction.

[1287] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1288] In this invention, the server includes means for importing diary data from users, generative AI means for analyzing the imported diary data, means for providing feedback and insights to users based on the analysis results, an emotion engine for extracting emotional states from the user's diary data and reflecting the emotional states in the analysis results, and means for predicting and warning about security risks based on the emotional states and behavioral patterns. This allows for a deep understanding of the user's behavioral patterns and emotional states, and not only can it provide appropriate feedback and insights, but it can also predict and warn about security risks.

[1289] "User" means any individual or entity that uses the System.

[1290] "Diary data" is text data in which a user records daily events and emotions.

[1291] "Capturing means" refers to a method or device for collecting diary data from users and inputting it into the system.

[1292] "Generative AI means" is an artificial intelligence technology that analyzes imported diary data and extracts the user's behavioral patterns and emotional state.

[1293] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analysis results of generative AI means.

[1294] The "emotion engine" is a technology that extracts a user's emotional state from their diary data and reflects that emotional state in the analysis results.

[1295] "Means for predicting and warning about security risks" refers to methods or devices that predict potential security risks to users and issue warnings based on their emotional state and behavioral patterns.

[1296] The following system configuration will be described as an embodiment of the present invention.

[1297] The server includes a means for importing diary data from users, a generative AI means for analyzing the imported diary data, a means for providing feedback and insights to users based on the analysis results, an emotion engine for extracting emotional states from users' diary data and reflecting the emotional states in the analysis results, and a means for predicting and warning about security risks based on emotional states and behavioral patterns.

[1298] Hardware and software used

[1299] Hardware: Smartphones, servers

[1300] Software: Python, NLTK library, sentiment analysis tool

[1301] Details of data processing and calculation

[1302] 1. Importing diary data: The user inputs diary data using a smartphone and sends it to the server, which receives and stores the data.

[1303] 2. Initialize the sentiment engine: The server initializes the sentiment analysis tool using the NLTK library, which is used to calculate sentiment scores from text data.

[1304] 3. Diary data analysis: The server divides the diary data into sentences and calculates the emotion score for each sentence, thereby extracting the user's emotional state and behavioral patterns.

[1305] 4. Security risk prediction: Based on the emotion score, the server determines that the security risk is high if there are a lot of negative emotions and issues a warning to the user.

[1306] Specific examples

[1307] For example, if a user writes in their diary, "I've been staying up late lately and feeling depressed," the server receives this data and uses the emotion engine to recognize it as a negative emotion, determining that the security risk is high and issuing a warning to the user.

[1308] Prompt Sentence Examples

[1309] Develop an application that analyzes a user's diary data, understands their emotional state and behavioral patterns, and predicts and warns about security risks. The diary data includes a comment such as, "I've been staying up late lately and I'm feeling depressed." Based on this data, create a program that uses an emotion engine to recognize negative emotions and determine whether a security risk is high.

[1310] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1311] Step 1:

[1312] Users input diary data using their smartphones. The data is sent in text format to the server, which then receives it and stores it in a database.

[1313] Input: Diary data entered by the user

[1314] Output: Diary data saved on the server

[1315] Step 2:

[1316] The server initializes a sentiment analysis tool using the NLTK library, which is used to calculate sentiment scores from text data.

[1317] Input: None (initialization process)

[1318] Output: Initialized sentiment analysis tool

[1319] Step 3:

[1320] The server divides the stored diary data into sentences. Each sentence is input into the emotion engine, which calculates an emotion score. The emotion score is output as a positive, negative, or neutral score.

[1321] Input: Saved diary data

[1322] Output: Sentiment score for each sentence (positive, negative, neutral)

[1323] Step 4:

[1324] The server extracts the user's emotional state and behavioral patterns based on the calculated emotion score. If the emotion score is above a certain level, the server determines that the security risk is high.

[1325] Input: Sentiment score for each sentence

[1326] Output: User's emotional state, behavioral patterns, and security risk assessment

[1327] Step 5:

[1328] If the server determines that the security risk is high, it will issue a warning to the user. The warning will be sent to the user using the notification function of the smartphone.

[1329] Input: Security Risk Assessment

[1330] Output: A warning notice to the user

[1331] Step 6:

[1332] The server provides feedback and insights to the user based on the analysis results, including detailed information about the user's behavioral patterns and emotional state. The feedback is displayed to the user through a smartphone application.

[1333] Input: User's emotional state, behavioral patterns

[1334] Output: User feedback and insights

[1335] Example 3

[1336] Next, a description will be given of Example 3 of Form Example 3. 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."

[1337] Conventional emotion management systems have struggled to effectively collect and analyze users' emotional data and provide appropriate feedback and insights. Furthermore, they lacked the means to analyze users' emotional states and behavioral patterns in detail and provide information useful for self-understanding and mental health management. This left users unable to fully understand their own emotional fluctuations and their causes, making it difficult to take appropriate measures.

[1338] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1339] In this invention, the server includes means for capturing emotional data from a user, means for saving the captured emotional data in a database, means for periodically acquiring the saved emotional data, means for inputting the acquired emotional data into a generative AI model, means for the generative AI model to analyze the emotional data and generate feedback and insights, and means for providing the generated feedback and insights to the user. This makes it possible to analyze the user's emotional state and behavioral patterns in detail and provide information useful for self-understanding and mental health management.

[1340] "User" refers to an individual who utilizes the system to input emotional data and receive feedback and insights.

[1341] "Emotional data" refers to information entered by a user about their emotional state and its causes.

[1342] "Database" refers to an information management system for storing emotion data and retrieving it as needed.

[1343] "Generative AI models" refer to artificial intelligence algorithms that analyze emotional data and generate feedback and insights.

[1344] "Feedback" refers to advice or information provided to users by a generative AI model based on the results of analyzing emotional data.

[1345] "Insights" refers to the deep understanding and insights that a generative AI model gains from analyzing emotion data.

[1346] "Server" refers to a computer system for capturing, storing, retrieving, analyzing, generating and providing feedback on emotion data.

[1347] "Capturing means" refers to a method or device for collecting emotional data from a user.

[1348] "Means for storing" refers to a method or device for storing captured emotion data in a database.

[1349] "Means for obtaining" refers to a method or device for periodically retrieving emotion data from the database.

[1350] "Means for input" refers to a method or device for providing acquired emotion data to a generative AI model.

[1351] "Means for analyzing" refers to the methods and devices by which the generative AI model analyzes the emotional data and generates feedback and insights.

[1352] "Means for providing" refers to the method or device for communicating the generated feedback or insights to the user.

[1353] The present invention relates to a system for collecting and analyzing user emotion data and providing feedback and insights. Specific embodiments of this system are described below.

[1354] Hardware and software used

[1355] Hardware: Servers, user devices (PCs, smartphones, etc.)

[1356] Software: Generative AI models, database management systems (e.g., MySQL), web servers (e.g., Apache), notification systems (e.g., Firebase)

[1357] Data collection

[1358] The user opens the smartphone app and accesses the emotion input screen.

[1359] The user inputs their emotional state (e.g., "sad") and its cause (e.g., "stress from work") and presses the send button.

[1360] The terminal converts the input data into JSON format and sends an HTTP POST request to the server.

[1361] Data storage

[1362] The server parses the received JSON data and stores it in a database.

[1363] The server executes an INSERT statement on the MySQL database and stores the data in the "emotion data" table.

[1364] Data Acquisition

[1365] The server runs a regular job every night to obtain emotion data from the past week.

[1366] The server executes an SQL query to retrieve the required data from the database. For example, it executes the query "SELECT FROM emotion data WHERE date >= DATE_SUB(CURDATE(), INTERVAL 7 DAY)".

[1367] Data analysis

[1368] The server converts the acquired emotional data into a prompt sentence, for example, "Analyze the user's emotional data and generate feedback based on the following data:..."

[1369] The server sends the generated prompt sentence to the generative AI model, for example, by using an API request.

[1370] Feedback Generation

[1371] The generative AI model analyzes the emotional data based on the prompt and generates feedback and insights, such as, "You felt sad three times this week. This may be due to work stress. We recommend you spend more time relaxing."

[1372] The server receives the feedback from the generative AI model and formats it for delivery to the user, for example, generating an HTML dashboard or email body.

[1373] Providing Feedback

[1374] The server provides the generated feedback to the user, for example by generating HTML for display on a web page dashboard and sending it to the user's browser.

[1375] The user opens the application and sees the feedback provided, such as a dashboard message saying, "You felt sad three times this week. This may be due to work stress. We recommend that you spend more time relaxing."

[1376] Specific examples

[1377] For example, if a user records the number of times they felt "sad" over the course of a week, the server can analyze this data and generate feedback such as, "You felt sad three times this week. This may be due to work stress. We recommend that you spend more time relaxing."

[1378] Prompt Sentence Examples

[1379] An example of a prompt to be input to the generative AI model is as follows:

[1380] Analyze user sentiment data and generate feedback based on the following data:

[1381] Date: 2023-10-01, Emotion: Sad, Cause: Work stress

[1382] Date: 2023-10-02, Emotion: Sad, Cause: Relationship

[1383] Date: 2023-10-03, Emotion: Sad, Cause: Work stress

[1384] In this way, the system analyzes the user's emotional state and provides appropriate feedback and insight. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1385] Step 1:

[1386] The user opens the smartphone app and accesses the emotion input screen. The user inputs their emotional state (e.g., "sad") and its cause (e.g., "work stress") and presses the submit button. The input data is generated as JSON-formatted data containing the emotional state and its cause.

[1387] Step 2:

[1388] The device sends the emotion data entered by the user to the server. Specifically, it uses an HTTP POST request to send JSON formatted data to the server. The input is the user's emotion data, and the output is the data sent to the server.

[1389] Step 3:

[1390] The server parses the received JSON data and stores it in a database. Specifically, it parses the JSON data, extracts the emotional state and its cause, and executes an INSERT statement into a MySQL database. The input is the parsed emotional data, and the output is data stored in the database.

[1391] Step 4:

[1392] The server runs a regular job every night at midnight to retrieve emotion data for the past week. Specifically, it executes an SQL query to retrieve emotion data for the past week from the database. For example, it executes the query "SELECT FROM emotion data WHERE date >= DATE_SUB(CURDATE(), INTERVAL 7 DAY)". The input is the SQL query, and the output is the retrieved emotion data.

[1393] Step 5:

[1394] The server converts the acquired emotional data into a prompt. Specifically, it formats the emotional data into a text prompt. For example, it generates a prompt in the format "Analyze the user's emotional data and generate feedback based on the following data:...". The input is the acquired emotional data, and the output is the generated prompt.

[1395] Step 6:

[1396] The server sends the generated prompt sentence to the generative AI model. Specifically, it sends the prompt sentence to the generative AI model using an API request. The input is the generated prompt sentence, and the output is the data sent to the generative AI model.

[1397] Step 7:

[1398] The generative AI model analyzes emotional data based on prompts and generates feedback and insights. For example, it generates feedback such as, "You felt 'sad' three times this week. This may be due to work stress. I recommend you spend more time relaxing." The input is the prompt, and the output is the generated feedback and insights.

[1399] Step 8:

[1400] The server receives the feedback returned by the generative AI model and formats it for delivery to the user, specifically generating an HTML dashboard or email body. The input is the generated feedback or insights, and the output is the formatted feedback.

[1401] Step 9:

[1402] The server provides the generated feedback to the user, for example by generating HTML to display on a web page dashboard and sending it to the user's browser. The input is the formatted feedback, and the output is the feedback provided to the user.

[1403] Step 10:

[1404] The user opens the application and sees the feedback provided, for example, a message on a dashboard saying "You felt sad three times this week. This may be due to work stress. We recommend that you spend more time relaxing." The input is the feedback provided, and the output is the user's confirmation of the feedback.

[1405] (Application example 3)

[1406] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1407] In modern society, managing users' emotional states and mental health is an important issue. However, conventional systems have had difficulty monitoring users' emotional states in real time and providing appropriate feedback and security measures when abnormalities are detected. It has also been difficult to provide information to deepen users' self-understanding or specific advice to help them improve themselves in real time. This has led to problems with users' mental health and security not being adequately maintained.

[1408] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1409] In this invention, the server includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for monitoring the user's emotional state in real time, means for detecting abnormal emotional fluctuations and sending an alert to the user, and means for proposing security measures when an abnormality is detected. This makes it possible to monitor the user's emotional state in real time and provide appropriate feedback and security measures when an abnormality is detected.

[1410] "User" means any individual or entity that uses the System.

[1411] "Diary data" is information in which a user records daily events and emotions.

[1412] "Generative AI methods" are artificial intelligence techniques that analyze input data and generate results.

[1413] "Feedback" refers to the evaluation and advice the system provides to the user.

[1414] "Insights" are deep understandings and perspectives gained from data analysis.

[1415] "Emotional state" refers to the user's current feelings or mood.

[1416] "Real-time" refers to processing and reactions occurring almost simultaneously.

[1417] "Abnormal emotional fluctuations" are sudden changes in emotions that go beyond the normal range.

[1418] An "alert" is a warning that notifies the user when an abnormality is detected.

[1419] "Security measures" are specific means and methods for ensuring user safety.

[1420] A system for implementing this invention includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for monitoring the user's emotional state in real time, means for detecting abnormal emotional fluctuations and sending an alert to the user, and means for suggesting security measures when an abnormality is detected.

[1421] Hardware and Software Configuration

[1422] Hardware:

[1423] It uses the camera and microphone of a smartphone or smart glasses, which allows it to capture the user's facial expressions and tone of voice in real time.

[1424] software:

[1425] OpenCV: A library for image processing. It is used to convert the image acquired from the camera to grayscale and extract the face area.

[1426] Keras: A deep learning framework for implementing emotion recognition models. It is used to predict emotions from extracted face regions.

[1427] smtplib: A library for sending emails. Used to alert users when abnormal emotions are detected.

[1428] Data processing and calculation

[1429] Data processing:

[1430] The image acquired from the camera is converted to grayscale and the facial region is extracted, which is then preprocessed for input into the emotion recognition model.

[1431] Data Calculation:

[1432] Using an emotion recognition model, we predict emotions from the extracted facial regions, allowing us to assess the user's emotional state in real time.

[1433] Specific examples

[1434] For example, if a user is feeling stressed late at night, the system uses a camera and microphone to monitor the user's facial expressions and tone of voice in real time. If the emotion recognition model determines the user's emotional state as "stressed," the system uses smtplib to send the user an alert saying, "It looks like you're feeling stressed late at night. Try taking a deep breath to relax."

[1435] Prompt Sentence Examples

[1436] "Write a Python program that monitors a user's emotional state in real time and sends an alert if an anomaly is detected."

[1437] In this way, it is possible to monitor the user's emotional state in real time and provide appropriate feedback and security measures if anomalies are detected.

[1438] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1439] Step 1:

[1440] The device uses a camera and microphone to capture the user's facial expressions and tone of voice in real time.

[1441] Input: User's facial image and voice data.

[1442] Data processing: Convert images to grayscale and extract facial regions. Convert audio data into audio features.

[1443] Output: Grayscale face region and audio features.

[1444] Step 2:

[1445] The device uses OpenCV to convert the acquired facial image to grayscale and extract the facial area.

[1446] Input: A face image of the user taken from the camera.

[1447] Data processing: Convert the image to grayscale and extract the face area using a face detection algorithm.

[1448] Output: Grayscale image of extracted face region.

[1449] Step 3:

[1450] The device uses Keras to predict emotions from the extracted face regions.

[1451] Input: A grayscale image of the extracted face region.

[1452] Data calculation: Input an image into the emotion recognition model to predict the emotion.

[1453] Output: Emotion prediction (e.g. anger, fear, sadness, etc.).

[1454] Step 4:

[1455] The device analyzes the emotion prediction results and determines whether there are any abnormal emotional fluctuations.

[1456] Input: Emotion prediction results.

[1457] Data calculations: Compare forecast results with historical data to determine if there are any unusual fluctuations.

[1458] Output: Presence or absence of abnormal emotional fluctuations.

[1459] Step 5:

[1460] If the device detects abnormal emotional fluctuations, it will send an alert to the user.

[1461] Input: Presence or absence of abnormal emotional fluctuations.

[1462] Data processing: Generate alert messages.

[1463] Output: An alert notification to the user.

[1464] Step 6:

[1465] If an abnormality is detected on the device, the system will suggest security measures to the user.

[1466] Input: Presence or absence of abnormal emotional fluctuations.

[1467] Data processing: Generate a message proposing security measures.

[1468] Output: Notification of suggested security measures to the user.

[1469] In this way, it is possible to monitor the user's emotional state in real time and provide appropriate feedback and security measures if anomalies are detected.

[1470] 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.

[1471] 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> ) 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.

[1472] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1473] 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.

[1474] [Third embodiment]

[1475] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1476] 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.

[1477] 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).

[1478] 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.

[1479] 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.

[1480] 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).

[1481] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1487] "Example 1"

[1488] The system of the present invention uses a web-based interface or dedicated application to collect diary data from users. Users enter their daily events, feelings, and thoughts as a diary, which is then collected by the system.

[1489] "Example 2"

[1490] The captured diary data is analyzed by generative AI, which uses natural language processing (NLP) techniques to extract user behavioral patterns, mood swings, and lifestyle trends. For example, if a user writes in their diary, "I've been staying up late lately," the AI ​​will interpret this as part of their "irregular lifestyle."

[1491] "Example 3"

[1492] Based on the analysis results, the system provides feedback and insights to the user, either in the form of a webpage or app dashboard, or via email or notification. For example, it may provide specific advice such as, "You've been staying up late lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1493] The processing flow of each embodiment will be described below.

[1494] "Example 1"

[1495] Step 1: The user enters diary data through a web-based interface or a dedicated application. This data includes the user's daily events, emotions, thoughts, etc.

[1496] Step 2: The system captures the diary data from the user. This capture occurs automatically immediately after the user enters the data.

[1497] "Example 2"

[1498] Step 1: The system sends the diary data it has captured to the generative AI.

[1499] Step 2: Generative AI analyzes the diary data using natural language processing (NLP) techniques to extract user behavioral patterns, mood swings, and lifestyle trends.

[1500] "Example 3"

[1501] Step 1: The generative AI sends the analysis results to the system.

[1502] Step 2: The system generates feedback and insights based on the analysis results.

[1503] Step 3: Provide the system-generated feedback and insights to the user, either via a web page, a dashboard in the application, or via email or notification.

[1504] Example 1

[1505] Next, a description will be given of Example 1 of Form 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."

[1506] Conventional systems have struggled to effectively utilize users' diary data to provide useful feedback and insights to users. Furthermore, they lacked a means to analyze users' behavioral patterns, mood swings, and lifestyle trends to provide information useful for self-understanding, self-improvement, and mental health management.

[1507] 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.

[1508] In this invention, the server includes means for importing diary data from a user, means for storing the imported diary data in a database, means for inputting the stored diary data into a generative AI model, means for the generative AI model to analyze the diary data and generate a prompt sentence, and means for providing the generated prompt sentence to the user. This makes it possible to effectively utilize the user's diary data and provide the user with useful feedback and insights.

[1509] "User" refers to an individual who uses the system to enter diary data.

[1510] "Diary data" refers to text data in which users describe their daily events, feelings, and thoughts.

[1511] "Means of importing" refers to the interface or application for receiving diary data from the user.

[1512] "Database" refers to a relational database or other data storage system for storing captured diary data.

[1513] A "generative AI model" refers to an artificial intelligence model that analyzes diary data and generates appropriate prompts for the user.

[1514] "Prompt sentence" refers to text containing questions or instructions for the user that is generated by the generative AI model based on diary data.

[1515] "Means to provide" refers to an interface or application for displaying the generated prompt text to the user.

[1516] "Analyzing" refers to the process by which the generative AI model analyzes diary data to understand the user's behavioral patterns and emotional fluctuations.

[1517] This invention is a system that takes diary data from users, analyzes it using a generative AI model, and provides useful feedback and insights to the users. A specific embodiment of this system is described below.

[1518] Users enter diary data using a web-based interface or a dedicated application. For example, they open a dedicated application on their smartphone and enter daily events, feelings, and thoughts into text boxes. The hardware used can be a PC or smartphone, and the software can be a web browser (such as Google Chrome) or a dedicated application (for iOS or Android).

[1519] The device sends the diary data entered by the user to the server. The HTTPS protocol is used for transmission to ensure data security. For example, when the user presses the "Send" button, the device sends the diary data to the server.

[1520] The server stores the received diary data in a database, typically a relational database such as MySQL or PostgreSQL. For example, the server executes the SQL query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (?, ?, ?)" to store the data.

[1521] The server retrieves the diary data stored in the database and inputs it into the generative AI model. For example, the server executes the SQL query "SELECT entry_text FROM diary_entries WHERE user_id = ?" to retrieve the data and pass it to the generative AI model.

[1522] The generative AI model analyzes the input diary data and generates an appropriate prompt for the user. For example, if the diary data says, "Today I went to a cafe with my friends and had a great time," the generative AI model generates a prompt such as, "Tell me a specific story about when you went to a cafe with your friends."

[1523] The server provides the prompts received from the generative AI model to the user, for example, by displaying the prompts to the user through a dedicated application or web interface.

[1524] As a concrete example, consider a scenario in which a user uses a dedicated application to enter a diary entry. The user opens the dedicated application on their smartphone and enters, "Today I went to a cafe with a friend and had a great time. The new coffee tasted really good." This diary entry data is sent to a server through the application and saved in a database. The saved data is then input into a generative AI model, which generates a prompt sentence like the following:

[1525] "Tell me a specific story about when you went to a cafe with a friend."

[1526] This prompt is used as a guide for the user to enter further information.

[1527] In this way, users can input diary data and receive prompts from the generative AI model, which can help them understand themselves better and provide information useful for self-improvement and mental health management.

[1528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1529] Step 1:

[1530] The user enters diary data.

[1531] Using a web-based interface or a dedicated application, users enter their daily events, feelings, and thoughts into a text box. The entered diary data is saved in text format on the device. A specific example is when a user opens the dedicated application on their smartphone and enters, "Today, I went to a cafe with a friend and had a great time. The new coffee tasted great."

[1532] Step 2:

[1533] The device transmits the diary data to the server.

[1534] When the user presses the "Send" button, the device sends the entered diary data to the server using the HTTPS protocol. The input is text diary data, and the output is data sent to the server. Specifically, the device sends the following text data to the server: "Today I went to a cafe with my friends and had a great time. The new coffee tasted great."

[1535] Step 3:

[1536] The server stores the diary data in a database.

[1537] The server saves the received diary data in a database. The input is the text diary data sent from the device, and the output is the data saved in the database. Specifically, the server executes the SQL query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (?, ?, ?)" to save the data.

[1538] Step 4:

[1539] The server inputs the saved diary data into the generative AI model.

[1540] The server retrieves diary data stored in the database and inputs it into the generative AI model. The input is text diary data retrieved from the database, and the output is data input to the generative AI model. Specifically, the server executes the SQL query "SELECT entry_text FROM diary_entries WHERE user_id = ?" to retrieve the data and pass it to the generative AI model.

[1541] Step 5:

[1542] A generative AI model generates prompts.

[1543] The generative AI model analyzes the input diary data and generates an appropriate prompt for the user. The input is text diary data passed from the server, and the output is the generated prompt. In concrete terms, if the diary data says, "Today I went to a cafe with my friends and had a great time," the generative AI model generates a prompt saying, "Tell me a specific story about when you went to a cafe with your friends."

[1544] Step 6:

[1545] The server generates a prompt and provides it to the user.

[1546] The server provides the user with the prompt received from the generative AI model. The input is the prompt received from the generative AI model, and the output is the display of the prompt to the user. Specifically, the server displays the prompt to the user through a dedicated application or web interface.

[1547] (Application example 1)

[1548] Next, a description will be given of Application Example 1 of Form 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."

[1549] Previous systems simply imported users' diary data, but had limited means of effectively utilizing that data. It was also difficult for users to deepen their self-understanding through their diary entries or provide specific feedback and insights to help them manage their mental health. Furthermore, creative content based on diary data was not generated or distributed, making it difficult to attract users' interest.

[1550] 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.

[1551] In this invention, the server includes means for importing diary data from users, generative AI means for analyzing the imported diary data, means for providing feedback and insights to users based on the analysis results, means for automatically generating stories and essays based on the diary data, and means for delivering the generated stories and essays to users. This makes it possible to utilize users' diary data in a variety of ways to support self-understanding and mental health management, as well as to provide creative content.

[1552] "User" refers to an individual who uses the system to enter diary data.

[1553] "Diary data" refers to information recorded by users about their daily events, feelings, and thoughts.

[1554] "Capturing means" refers to a method or device for collecting diary data from users and storing it in the system.

[1555] "Generative AI means" refers to artificial intelligence technology that analyzes imported diary data and generates information tailored to specific purposes.

[1556] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analytical results obtained by generative AI means.

[1557] "Means for automatically generating stories and essays" refers to methods and devices for generating creative writing based on diary data.

[1558] "Delivery means" refers to the method or device by which the generated story or essay is delivered to the user.

[1559] A system for implementing this invention includes means for importing diary data from a user, generative AI means for analyzing the imported diary data, means for providing feedback and insights to the user based on the analysis results, means for automatically generating stories and essays based on the diary data, and means for delivering the generated stories and essays to the user.

[1560] Hardware and Software Configuration

[1561] Hardware: Smartphone (iOS or Android), server

[1562] Software: Python, OpenAI API

[1563] Data processing and calculation

[1564] 1. Importing diary data:

[1565] Users enter diary data using a smartphone application, which is then sent to a server and stored in a database.

[1566] 2. Analysis of diary data:

[1567] The server analyzes the captured diary data using generative AI tools (e.g., OpenAI's GPT-3), which extracts the user's behavioral patterns, mood swings, and lifestyle trends.

[1568] 3. Providing feedback and insights:

[1569] Based on the analysis, the server provides users with feedback and insights, including information to deepen self-understanding and helpful advice for self-improvement and mental health management.

[1570] 4. Automatic generation of stories and essays:

[1571] The server generates prompts based on the diary data and inputs them into a generative AI system to automatically generate stories or essays. For example, the following prompts can be used:

[1572] Please generate a moving story based on the diary data below.

[1573] Date: 2023-10-01

[1574] Content: I went to a cafe with a friend today. It was fun.

[1575] Date: 2023-10-02

[1576] Content: Work was busy, but fulfilling.

[1577] 5. Distribution of generated content:

[1578] The generated stories and essays are delivered from the server to the user's smartphone, where they can view the content through an application.

[1579] Specific examples

[1580] Suppose a user enters the following diary entry using a smartphone application.

[1581] 2023-10-01: I went to a cafe with a friend today. It was fun.

[1582] 2023-10-02: Work was busy, but fulfilling.

[1583] The server imports this diary data and analyzes it using generative AI. Based on the analysis results, it provides feedback to the user, such as "Cherishing time with friends helps relieve stress." It also generates the following prompt sentences based on the diary data, automatically generating a story.

[1584] Please generate a moving story based on the diary data below.

[1585] Date: 2023-10-01

[1586] Content: I went to a cafe with a friend today. It was fun.

[1587] Date: 2023-10-02

[1588] Content: Work was busy, but fulfilling.

[1589] The generated story is delivered to the user's smartphone, where they can enjoy it through the application.

[1590] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1591] Step 1:

[1592] A user inputs diary data using a smartphone application. The input diary data is sent in text format to a server. The server receives this data and stores it in a database. The input is the user's diary data, and the output is the diary data stored on the server.

[1593] Step 2:

[1594] The server analyzes the saved diary data using generative AI tools (e.g., OpenAI's GPT-3). Specifically, it analyzes the diary data and extracts the user's behavioral patterns, mood fluctuations, and lifestyle trends. The input is the saved diary data, and the output is the analysis results.

[1595] Step 3:

[1596] The server generates feedback and insights for the user based on the analysis results. For example, it generates advice such as "Spending time with friends will help relieve stress." The input is the analysis results, and the output is feedback and insights.

[1597] Step 4:

[1598] The server generates a prompt based on the diary data. For example, it generates the following prompt:

[1599] Please generate a moving story based on the diary data below.

[1600] Date: 2023-10-01

[1601] Content: I went to a cafe with a friend today. It was fun.

[1602] Date: 2023-10-02

[1603] Content: Work was busy, but fulfilling.

[1604] The input is diary data and the output is a prompt sentence.

[1605] Step 5:

[1606] The server inputs the generated prompt sentences into a generative AI means to automatically generate a story or essay. The generative AI means analyzes the prompt sentences and generates creative writing. The input is the prompt sentence, and the output is the generated story or essay.

[1607] Step 6:

[1608] The server delivers the generated stories and essays to the user's smartphone. The user can view these contents through the application. The input is the generated stories and essays, and the output is the content delivered to the user's smartphone.

[1609] Example 2

[1610] Next, a description will be given of Example 2 of Form 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."

[1611] In modern society, it is important for users to understand their own behavioral patterns, mood swings, and lifestyle trends, and deepen their self-understanding. However, there are limited systems that can effectively collect, analyze, and provide feedback on this information. In particular, there is a lack of systems that utilize diary data to provide users with information useful for managing their mental health and self-improvement.

[1612] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting diary data from the user, a means for the terminal to transmit the diary data to the server, a means for the server to receive the diary data and pass it to the generative AI model, a means for the generative AI model to analyze the diary data, and a means for the server to feed back the analysis results to the user. This makes it possible to effectively collect and analyze the user's diary data and provide useful feedback to the user.

[1613] "User" refers to an individual who utilizes the system to enter diary data and receive feedback.

[1614] "Diary data" refers to text data in which users record their daily events, emotions, actions, etc.

[1615] "Device" refers to the electronic device used by the user to input diary data and send it to the server. Examples include smartphones and personal computers.

[1616] "Server" refers to a computer system that receives diary data sent from the device, passes it to the generative AI model, and provides the analysis results as feedback to the user.

[1617] "Generative AI models" refer to artificial intelligence models that analyze diary data to extract user behavioral patterns, mood fluctuations, and lifestyle trends. Examples include natural language processing models such as BERT and GPT-3.

[1618] "Feedback" refers to information or insights provided to users based on the results analyzed by the generative AI model.

[1619] "Behavioral patterns" refer to the user's behavioral tendencies and habits in their daily lives.

[1620] "Mood swings" refers to changes in a user's emotions or moods.

[1621] "Lifestyle trends" refers to the user's lifestyle habits and characteristics.

[1622] This invention is a system in which a user inputs diary data, analyzes the data using a generative AI model, and provides feedback. Specific embodiments of this system are described below.

[1623] First, the user enters diary data using a dedicated application or web interface. For example, the user opens the application on their smartphone and enters, "I'm very tired today. I tend to stay up late late these days." This diary data is then sent by the device to the server. The data is sent using encrypted communication via the HTTPS protocol.

[1624] The server receives the diary data sent from the device. The received data is passed to a generative AI model. This generative AI model analyzes the diary data using natural language processing (NLP) techniques. Specifically, it uses the Python libraries NLTK and spaCy to tokenize the text data, tag parts of speech, and perform sentiment analysis. It also uses advanced generative AI models such as BERT and GPT-3 to extract user behavioral patterns, mood fluctuations, and lifestyle trends.

[1625] For example, if a user writes, "I've been staying up late lately," the generative AI model will recognize this as an "irregular lifestyle." The analysis results are returned to the server, which then provides this result as feedback to the user. The feedback is provided in the form of a notification to the user's application saying, "Your lifestyle has been irregular lately." This process uses WebSocket technology to send notifications in real time.

[1626] Below are some specific examples of prompt sentences to input into the generative AI model.

[1627] Example prompt sentence:

[1628] User diary data:

[1629] "I'm very tired today. I've been staying up late lately."

[1630] Prompt the generative AI model:

[1631] "Extract user behavioral patterns, mood swings, and lifestyle trends from this diary data."

[1632] In this way, it is possible to effectively collect and analyze users' diary data and provide useful feedback to users, which will help them deepen their self-understanding and provide information useful for self-improvement and mental health management.

[1633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1634] Step 1:

[1635] The user inputs diary data.

[1636] Users enter diary data using a dedicated application or web interface. For example, they might open the application on their smartphone and enter something like, "I'm very tired today. I tend to stay up late late these days." The data they enter is saved in text format on their device.

[1637] Step 2:

[1638] The device transmits the diary data to the server.

[1639] The device sends the diary data entered by the user to the server. At this time, the data is encrypted using the HTTPS protocol. The input is the user's diary data, and the output is the encrypted data.

[1640] Step 3:

[1641] The server receives the diary data and passes it to the generative AI model.

[1642] The server receives diary data sent from the device. The received data is passed to the generative AI model. Specifically, an API endpoint is created using Python's Flask framework to receive data. The input is encrypted diary data, and the output is text data passed to the generative AI model.

[1643] Step 4:

[1644] A generative AI model analyzes diary data.

[1645] The generative AI model analyzes the received diary data. For example, it uses natural language processing models such as BERT and GPT-3 to tokenize the text data, tag parts of speech, and perform sentiment analysis. The input is the text data passed to the generative AI model, and the output is an analysis result that shows the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1646] Step 5:

[1647] The server provides the analysis results as feedback to the user.

[1648] The server feeds back the analysis results obtained from the generative AI model to the user. For example, it may notify the user's application that "Your lifestyle has been irregular recently." This process uses WebSocket technology to send notifications in real time. The input is the analysis results from the generative AI model, and the output is a feedback message to the user.

[1649] (Application example 2)

[1650] Next, a description will be given of Application Example 2 of Form 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."

[1651] Conventional systems that analyze user diary data focus on analyzing users' behavioral patterns, mood fluctuations, and lifestyle trends, but lack the functionality to evaluate and warn about security risks. This makes it difficult to understand how changes in a user's lifestyle affect security risks. The present invention aims to solve this problem by providing a system that evaluates security risks based on a user's diary data and issues appropriate warnings.

[1652] The identification process 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 importing diary data from the user, generative AI means for analyzing the imported diary data, means for providing feedback and insight to the user based on the analysis results, means for evaluating security risks, and means for issuing warnings based on the security risks. This makes it possible to evaluate security risks based on the user's diary data and issue appropriate warnings.

[1653] "User" refers to any individual or entity that uses the System.

[1654] "Diary data" refers to text data in which users record their daily events, emotions, actions, etc.

[1655] "Capturing means" refers to a method or device for collecting diary data from users and inputting it into the system.

[1656] "Generative AI methods" refers to artificial intelligence technologies for analyzing imported diary data, particularly those that use natural language processing (NLP) technology.

[1657] "Means for providing feedback and insights" refers to methods or devices that provide useful information or advice to users based on the analysis results of generative AI means.

[1658] "Means for assessing security risks" refers to methods or devices that evaluate the impact of user behavior and lifestyle on security based on the analysis results of generative AI means.

[1659] "Means for issuing a warning" refers to a method or device for notifying a user of a warning when a security risk increases.

[1660] The system for implementing this invention imports a user's diary data, analyzes it using generative AI, evaluates security risks, and issues appropriate warnings. Specific embodiments are described below.

[1661] System Configuration

[1662] The system consists of the following main components:

[1663] 1. User device: The device on which the user enters diary data. This includes smartphones and PCs.

[1664] 2. Server: A central processing unit that ingests diary data, analyzes it using generative AI, provides feedback and insights, assesses security risks, and issues alerts.

[1665] 3. Generative AI model: An AI model for analyzing diary data using natural language processing (NLP) techniques. Specifically, it uses the spaCy and transformers libraries.

[1666] Data capture and analysis

[1667] Diary data is sent from the user's device to the server. The server receives the data using a means to import diary data and analyzes it using generative AI means. Specifically, the following process is performed:

[1668] 1. Data import: The diary data entered by the user is sent to the server in text format.

[1669] 2. Data analysis: The server analyzes the diary data using generative AI models (e.g., spaCy or the transformers library) to extract user behavioral patterns, mood fluctuations, and lifestyle trends.

[1670] Security risk assessment and warning

[1671] The server evaluates security risks based on the analysis results of the generative AI method. Specifically, the following processes are performed:

[1672] 1. Risk assessment: Evaluate security risks based on extracted behavioral patterns and lifestyle trends. For example, if the behavior of "staying up late" is frequently observed, it is determined that this is an irregular lifestyle and poses a high risk.

[1673] 2. Warning: Based on the assessed security risk, a warning is issued to the user. The warning is sent to the user's device.

[1674] Specific examples

[1675] For example, if a user writes in their diary, "I've been staying up late lately," the server will recognize this as an "irregular lifestyle" and determine that it may pose a security risk. Based on this, the server will issue a warning to the user, such as, "If you continue to stay up late, your security risk will increase. Try to lead a more regular life."

[1676] Prompt Sentence Examples

[1677] An example of a prompt to input to a generative AI model is as follows:

[1678] Analyze the user's diary data to extract behavioral patterns, mood swings, and lifestyle trends. For example, if a user writes, "I've been staying up late lately," recognize this as an "irregular lifestyle."

[1679] In this way, a system can be realized that evaluates security risks based on a user's diary data and issues appropriate warnings.

[1680] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1681] Step 1:

[1682] The user inputs diary data. The diary data is entered in text format using the user's device (smartphone or PC) and sent to the server. The input data includes the user's daily events, emotions, actions, etc.

[1683] Step 2:

[1684] The server receives the diary data. The server receives the diary data sent from the user terminal using a means for importing it and stores it in a database. The input is the user's diary data, and the output is the stored text data.

[1685] Step 3:

[1686] The server analyzes the diary data using a generative AI model. The server uses the spaCy and transformers libraries to analyze the diary data using natural language processing (NLP) techniques. The input is stored text data, and the output is an analysis showing the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1687] Step 4:

[1688] The server evaluates security risks based on the analysis results. Based on the analysis results from generative AI means, the server evaluates the impact of specific behaviors and lifestyles on security risks. For example, if the behavior of "staying up late" is frequently observed, it will determine that this irregular lifestyle poses a high risk. The input is the analysis results, and the output is the security risk assessment results.

[1689] Step 5:

[1690] The server issues a warning based on the security risk. The server notifies the user of the warning based on the assessed security risk. The warning is notified to the user's terminal. The input is the security risk assessment result, and the output is a warning message for the user.

[1691] Step 6:

[1692] The user receives a warning. The user checks the warning message sent to the user's device and takes necessary measures. The input is the warning message sent from the server, and the output is the user's behavior change or implementation of measures.

[1693] In this way, a system can be realized that evaluates security risks based on a user's diary data and issues appropriate warnings.

[1694] Example 3

[1695] Next, a third embodiment of the third embodiment will be described. 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."

[1696] Conventional systems have struggled to effectively collect and analyze user behavioral data and provide appropriate feedback and insights. They also lacked the means to accurately grasp changes in users' behavioral patterns and lifestyles and provide specific advice based on that information. This has prevented them from fully contributing to users' self-understanding, self-improvement, and mental health management.

[1697] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1698] In this invention, the server includes means for capturing behavioral data from users, means for preprocessing the captured behavioral data, generative AI means for analyzing the preprocessed data, means for generating feedback and insights for users based on the analysis results, and means for providing the generated feedback and insights to users, thereby enabling effective collection and analysis of user behavioral data and provision of appropriate feedback and insights.

[1699] "Behavioral Data" refers to information about a user's behavior, such as their web page browsing history, application usage history, or sleep patterns.

[1700] "Preprocessing" refers to the process of improving the quality of collected data by performing operations such as filling in missing values, normalizing the data, and detecting outliers.

[1701] "Generative AI methods" refer to methods that use machine learning or generative AI models to analyze data and generate feedback and insights in natural language.

[1702] "Feedback" refers to specific advice or insights provided to users based on the analysis results.

[1703] "Delivery Vehicle" refers to the means by which generated feedback and insights are communicated to users, including web pages, application dashboards, emails, notifications, etc.

[1704] This invention relates to a system that collects and analyzes user behavior data and provides appropriate feedback and insights. Specific embodiments of this system are described below.

[1705] Data collection

[1706] The server collects user behavior data, such as web page browsing history, application usage history, sleep patterns, etc. This data is stored in a database (e.g., MySQL, PostgreSQL).

[1707] Data Preprocessing

[1708] The server preprocesses the collected data, specifically by imputing missing values, normalizing the data, and detecting outliers. This improves the quality of the data. For example, missing values ​​are imputed with the mean or median. Data normalization involves scaling each data point to a range from 0 to 1. Outlier detection involves using statistical methods to identify and remove abnormal data points.

[1709] Data analysis

[1710] The server uses the preprocessed data to train a machine learning model. For example, to analyze the user's sleep patterns, it uses a Long Short-Term Memory (LSTM) model using time-series data. The model predicts future sleep patterns based on the user's past sleep data. Machine learning libraries such as TensorFlow and scikit-learn are used for the analysis.

[1711] Feedback Generation

[1712] The server generates feedback based on the analysis results. A prompt sentence is input into a generative AI model (e.g., OpenAI GPT-3), and feedback is generated in natural language. For example, a prompt sentence might be input, "After analyzing the user's recent sleep patterns, we have found that they tend to stay up late. Please generate feedback encouraging the user to go to bed early and get up early." The generated feedback would be, "You've been staying up late late recently. Making an effort to go to bed early and get up early may have a positive effect on your health."

[1713] Providing Feedback

[1714] The server provides the generated feedback to the user. This can be provided via a web page, a dashboard on the application, email, or notification. For example, when the user opens the application, the feedback is displayed on the dashboard. Feedback can also be sent via email or push notification. The user receives this feedback and uses it as a reference for improving their behavior.

[1715] Specific examples

[1716] Example 1: Sleep pattern feedback

[1717] If the user has been staying up late recently, the server might generate feedback like this:

[1718] "You've been staying up late lately. Trying to go to bed earlier and get up earlier might have a positive effect on your overall health."

[1719] Example 2: Feedback based on web page browsing history

[1720] If a user frequently views web pages on a particular topic, the server generates feedback like this:

[1721] "You've been browsing a lot of health-related web pages lately. Would you like me to email you the latest health news?"

[1722] Prompt Sentence Examples

[1723] Below is an example of a prompt sentence to input to the generative AI model.

[1724] Prompt 1: Sleep pattern feedback

[1725] Your analysis of the user's recent sleep patterns indicates that they tend to stay up late. Generate feedback to encourage the user to go to bed earlier and get up earlier.

[1726] Prompt 2: Feedback based on web page browsing history

[1727] A user has recently been browsing health web pages frequently. Generate feedback to provide the user with the latest health information.

[1728] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1729] Step 1:

[1730] The server collects user behavior data. Specifically, it records the URL and the time spent viewing each web page. It also collects operation logs when users use applications. This data is stored in a database.

[1731] Input: User behavior data (webpage browsing history, application usage history)

[1732] Output: Behavioral data stored in a database

[1733] Step 2:

[1734] The server preprocesses the collected data by imputing missing values ​​with the mean or median, normalizing the data by scaling each data point to a range between 0 and 1, and detecting outliers by using statistical methods to identify and remove anomalous data points.

[1735] Input: Behavioral data stored in a database

[1736] Output: Preprocessed data

[1737] Step 3:

[1738] The server uses the preprocessed data to train a machine learning model. For example, it uses a Long Short-Term Memory (LSTM) model with time-series data to analyze the user's sleep patterns. The model predicts future sleep patterns based on the user's past sleep data.

[1739] Input: Preprocessed data

[1740] Output: A trained machine learning model

[1741] Step 4:

[1742] The server generates feedback based on the analysis results. A prompt sentence is input into the generative AI model, and feedback is generated in natural language. For example, a prompt sentence might be input as follows: "After analyzing the user's recent sleep patterns, we have noticed a tendency for them to stay up late. Please generate feedback encouraging the user to go to bed early and get up early." The generated feedback would be, "You've been staying up late late recently. Making an effort to go to bed early and get up early may have a positive effect on your health."

[1743] Input: Trained machine learning model, prompt

[1744] Output: Generated feedback

[1745] Step 5:

[1746] The server provides the generated feedback to the user via a web page, an application dashboard, email, or notification. For example, when the user opens the application, the feedback is displayed on the dashboard. Feedback can also be sent via email or push notification.

[1747] Input: Generated feedback

[1748] Output: Feedback provided to the user

[1749] The above are the specific processing steps of the program of this system.

[1750] (Application example 3)

[1751] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1752] In modern society, managing users' physical and mental health is an important issue. However, conventional systems have had difficulty comprehensively analyzing users' behavioral patterns and lifestyles and providing specific feedback. In addition, there are limited ways for users to accurately understand their own physical and mental health conditions and obtain information to take appropriate measures to improve them. This has led to the problem of users being unable to fully understand and improve themselves.

[1753] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1754] In this invention, the server includes a means for importing diary data and biometric data from the user, a generative AI means for analyzing the imported diary data and biometric data, a means for providing feedback and insights to the user based on the analysis results, and a means for providing the feedback and insights via notifications or a dashboard. This enables the server to comprehensively analyze the user's behavioral patterns, mood fluctuations, lifestyle trends, and sleep patterns and provide specific feedback. This allows the user to deepen their self-understanding and obtain information useful for self-improvement and health management.

[1755] "Diary data" is information recorded by users about their daily events, emotions, actions, etc.

[1756] "Biometric data" refers to data that indicates the user's physical condition, such as sleep patterns and exercise levels.

[1757] "Generative AI methods" are artificial intelligence techniques that analyze users' behavioral patterns and lifestyles based on collected data, and generate feedback and insights.

[1758] "Feedback" is specific advice or information provided to users based on the analysis results.

[1759] "Insights" are deep understandings and insights gained through data analysis, containing important information about user behavior and status.

[1760] "Notifications" are a means of providing information to users in real time, including push notifications on smartphones.

[1761] A "dashboard" is a user-accessible interface that visually displays analysis results and feedback.

[1762] "Behavioral patterns" refer to the user's daily behavioral tendencies and habits.

[1763] "Mood swings" refer to changes in a user's emotional or mental state.

[1764] "Lifestyle trends" refers to a user's lifestyle habits and daily behavior patterns.

[1765] "Sleep patterns" refers to data about a user's sleep duration and quality.

[1766] "Self-understanding" means that users gain a deep understanding of their own behavior, emotions, and state.

[1767] "Self-improvement" is the effort by users to improve their own behavior or state.

[1768] "Health management" refers to activities and efforts that users make to maintain and improve their health.

[1769] "Mental health management" refers to activities and efforts that users make to maintain and improve their mental health.

[1770] A system for implementing this invention includes means for capturing diary data and biometric data from a user, generative AI means for analyzing the captured data, means for providing feedback and insights to the user based on the analysis results, and means for providing the feedback and insights via notifications or a dashboard.

[1771] 1. Data Collection

[1772] The server collects users' diary data and biometric data from their smartphones and wearable devices. The diary data includes information on users' daily events, emotions, and behaviors. The biometric data includes users' sleep patterns and exercise levels.

[1773] 2. Data analysis

[1774] The server analyzes the collected diary and biometric data using a generative AI model (e.g., OpenAI GPT-3), which evaluates the user's behavioral patterns, mood swings, lifestyle trends, and sleep patterns.

[1775] 3. Feedback Generation

[1776] The server uses a generative AI model to generate specific feedback and insights based on the analysis results. For example, analyzing a user's sleep data may generate the following feedback:

[1777] "You haven't been getting enough sleep lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1778] 4. Providing Feedback

[1779] The server then provides the generated feedback and insights to the user via smartphone notifications and an in-app dashboard, providing real-time information about their physical and mental health status.

[1780] Hardware and software used

[1781] Hardware: Smartphones, wearable devices (e.g., smartwatches)

[1782] Software: Python, data analysis libraries (e.g., Pandas, NumPy), generative AI models (e.g., OpenAI GPT-3)

[1783] Specific examples

[1784] If the user enters their sleep data from the past 30 days into the app, the server will provide feedback like this:

[1785] "You haven't been getting enough sleep lately. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1786] Prompt Sentence Examples

[1787] Analyze the user's sleep data from the past 30 days and generate feedback such as:

[1788] Data: [5.5, 6.0, 7.0, 4.5, 8.0, 6.5, 7.5, 5.0, 6.0, 7.0, 8.5, 6.0, 7.5, 5.5, 6.0, 7.0, 4.5, 8.0, 6.5, 7.5, 5.0, 6.0, 7.0, 8.5, 6.0, 7.5, 5.5, 6.0, 7.0, 4.5]

[1789] In this way, a system can be realized that provides specific feedback to support the user in managing their health.

[1790] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1791] Step 1:

[1792] Users input diary data and biometric data using smartphones or wearable devices. The diary data includes information recorded by the user about daily events, emotions, and behaviors, while the biometric data includes the user's sleep patterns and amount of exercise. The input data is then sent to a server.

[1793] Step 2:

[1794] The server stores the received diary data and biometric data in a database. The stored data is used for subsequent analysis. Specifically, the data is efficiently managed using a database management system (e.g., MySQL, PostgreSQL).

[1795] Step 3:

[1796] The server inputs the saved diary data and biometric data into a generative AI model (e.g., OpenAI GPT-3). The generative AI model uses this data to analyze the user's behavioral patterns, mood fluctuations, lifestyle trends, and sleep patterns. Based on the input data, the AI ​​model performs data preprocessing (e.g., normalization, missing value imputation) and generates analysis results.

[1797] Step 4:

[1798] The server generates specific feedback and insights for the user based on the analysis results obtained from the generative AI model. For example, after analyzing the user's sleep data, the following feedback may be generated: "You've been sleeping less recently. Trying to go to bed earlier and get up earlier may have a positive effect on your health."

[1799] Step 5:

[1800] The server provides the generated feedback and insights to the user through the smartphone notification function and the in-application dashboard. Specifically, the server provides information in real time using push notifications, and the in-application dashboard visually displays the feedback and insights.

[1801] Step 6:

[1802] Based on the feedback and insights provided, users can take concrete actions to improve their behavior and lifestyle, such as going to bed earlier and getting up earlier to get more sleep.

[1803] In this way, a system is realized that provides specific feedback to support the user in managing their health.

[1804] 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.

[1805] "Example 1"

[1806] In one embodiment of the present invention, a system is provided that includes a means for capturing diary data from a user, a generative AI means for analyzing the captured diary data, and a means for providing feedback and insights to the user based on the analysis results. The system analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1807] "Example 2"

[1808] The generative AI means includes an emotion engine that recognizes the user's emotions. This emotion engine extracts the user's emotional state from the diary data and reflects that emotional state in the analysis results. Specifically, it extracts emotional expressions such as "fun" or "sad" that the user wrote in the diary and analyzes the intensity and frequency of those emotions.

[1809] "Example 3"

[1810] Feedback and insights are provided based on the user's emotional state, allowing them to objectively understand their own emotional fluctuations and use them to manage their emotions and improve their mental health. For example, the number of times they felt "sad" in a week and the events that caused them can be displayed.

[1811] It allows you to reflect on events, understand how certain events evoke emotions, and think about how to deal with them.

[1812] The processing flow of each embodiment will be described below.

[1813] "Example 1"

[1814] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[1815] Step 2: Analyze the captured diary data using generative AI. In this step, the AI ​​extracts and analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1816] Step 3: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results.

[1817] "Example 2"

[1818] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[1819] Step 2: Extract emotional states from the imported diary data using the emotion engine. In this step, the emotion engine extracts emotional expressions from the user's diary data and analyzes the intensity and frequency of those emotions.

[1820] Step 3: Analyze the extracted emotional state using generative AI. In this step, the AI ​​analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the emotional state obtained from the emotion engine.

[1821] Step 4: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results.

[1822] "Example 3"

[1823] Step 1: Capture diary data from users. In this step, the system collects text data entered by users into the diary application.

[1824] Step 2: Extract emotional states from the imported diary data using the emotion engine. In this step, the emotion engine extracts emotional expressions from the user's diary data and analyzes the intensity and frequency of those emotions.

[1825] Step 3: Analyze the extracted emotional state using generative AI. In this step, the AI ​​analyzes the user's behavioral patterns, mood fluctuations, and lifestyle trends based on the emotional state obtained from the emotion engine.

[1826] Step 4: Provide feedback and insights to the user based on the analysis results. In this step, the AI ​​provides specific feedback and insights to the user based on the analysis results. The feedback and insights are based on the user's emotional state and can be used to manage their emotions and improve their mental health.

[1827] Example 1

[1828] Next, a description will be given of Example 1 of Form 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."

[1829] Conventional systems have struggled to effectively analyze users' diary data and provide useful feedback and insights to users. They also lacked the means to accurately grasp users' behavioral patterns, mood fluctuations, and lifestyle trends, and provide appropriate advice based on those findings. This has resulted in insufficient support for users' self-understanding, self-improvement, and mental health management.

[1830] 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.

[1831] In this invention, the server includes means for importing diary data from a user, means for storing the imported diary data in a database, means for analyzing the stored diary data using a generative AI model, means for generating feedback and insights for the user based on the analysis results, and means for providing the generated feedback to the user. This makes it possible to effectively analyze the user's diary data, understand the user's behavioral patterns, mood fluctuations, and lifestyle trends, and provide appropriate feedback and insights based on them.

[1832] "User" refers to an individual who utilizes the system to enter diary data and receive feedback and insights.

[1833] "Diary data" refers to text data in which users record their daily events, feelings, and thoughts.

[1834] "Means of import" refers to the interface or application that allows users to input diary data into the system.

[1835] "Database" refers to an information system for storing and managing imported diary data.

[1836] A "generative AI model" refers to an artificial intelligence model that analyzes saved diary data and extracts users' behavioral patterns, mood fluctuations, and lifestyle trends.

[1837] "Means of analysis" refers to the process of using a generative AI model to analyze diary data and understand users' behavioral patterns, mood fluctuations, and lifestyle trends.

[1838] "Feedback" refers to advice or insights provided to users based on the analysis results of the generative AI model.

[1839] "Means for providing" refers to the method or system for notifying and displaying the generated feedback to the user.

[1840] The present invention relates to a system for capturing and analyzing a user's diary data and providing feedback. A specific embodiment of this system will be described below.

[1841] System configuration

[1842] Hardware and Software

[1843] Users enter diary data using a web-based interface or dedicated application. For example, they can use a smartphone app or website. The device then sends the entered diary data to a server. The server then stores the received diary data in a database and analyzes it using a generative AI model. The generative AI model used is a natural language processing model such as GPT-4.

[1844] Data capture and storage

[1845] Users enter diary data through a smartphone app or website. For example, a user might enter, "Today was a tough day at work. My boss scolded me and I'm feeling down." The device then sends this data to a server using the HTTPS protocol. The server then stores the received diary data in a relational database such as MySQL or PostgreSQL. The stored data is organized for later analysis.

[1846] Analyzing the data

[1847] The server analyzes the saved diary data using a generative AI model. GPT-4 is used as the generative AI model. The server inputs the diary data into the AI ​​model and extracts behavioral patterns, mood fluctuations, and lifestyle trends. For example, it sends a prompt message to the AI ​​model saying, "Analyze the user's diary data and extract emotional fluctuations."

[1848] Generating and Providing Feedback

[1849] The server generates feedback and insights for the user based on the analysis results of the AI ​​model. For example, if the AI ​​model analyzes that "the user is feeling stressed at work," the server generates feedback such as "It seems that you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The server sends this feedback to the user's device, and the user can check the feedback through the app.

[1850] Examples of specific examples and prompts

[1851] Specific examples

[1852] A user enters into their diary, "Today was tough at work. My boss got mad at me and I'm feeling down." The device sends this data to the server. The server stores this data in a database and analyzes it using a generative AI model (GPT-4). The AI ​​model analyzes that "The user is feeling stressed at work," and the server generates feedback such as "It seems like you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The server sends this feedback to the user's device, and the user checks it through the app.

[1853] Prompt Sentence Examples

[1854] "Analyze the user's diary data and extract behavioral patterns and mood fluctuations. For example, if a user writes, 'Today was a tough day at work. My boss got mad at me, and I'm feeling down,' generate the type of feedback we should provide."

[1855] In this way, the system goes through a series of processes to capture the user's diary data, analyze it, and provide feedback.

[1856] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1857] Step 1:

[1858] Users enter diary data using a web-based interface or a dedicated application. For example, a user might enter, "Today was a tough day at work. My boss scolded me, and I'm feeling down." The data is then stored on the device.

[1859] Step 2:

[1860] The device sends the entered diary data to the server. The HTTPS protocol is used for transmission to ensure data security. Specifically, the device sends a "POST" request to "https: / / api.example.com / submit." The input is the user's diary data, and the output is the data sent to the server.

[1861] Step 3:

[1862] The server saves the received diary data in a database. MySQL is used as the database. The server executes an "INSERT" query on the database to save the diary data. For example, it executes the query "INSERT INTO diary_entries (user_id, entry_text, entry_date) VALUES (1, 'Work was tough today. My boss got mad at me and I'm feeling down.', '2023-10-01');". The input is the received diary data, and the output is saving it to the database.

[1863] Step 4:

[1864] The server analyzes the saved diary data using a generative AI model. GPT-4 is used as the generative AI model. The server inputs the diary data into the AI ​​model and extracts behavioral patterns, mood fluctuations, and lifestyle trends. For example, the server sends a prompt to the AI ​​model saying, "Analyze the user's diary data and extract emotional fluctuations." The input is the saved diary data, and the output is the analysis results.

[1865] Step 5:

[1866] The server generates feedback and insights for the user based on the analysis results of the AI ​​model. For example, if the AI ​​model analyzes that "the user is feeling stressed at work," the server generates feedback such as "It seems that you've been feeling stressed at work lately. Why don't you try spending more time on your hobbies to relax?" The input is the analysis results of the AI ​​model, and the output is the generated feedback.

[1867] Step 6:

[1868] The server provides the generated feedback to the user, who can check the feedback through a dedicated application or web interface. For example, the server sends a notification to the device saying "There is new feedback," and the user opens the app to check the feedback. The input is the generated feedback, and the output is the notification to the user and the display of the feedback.

[1869] (Application example 1)

[1870] Next, a description will be given of Application Example 1 of Form 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."

[1871] Conventional systems that analyze users' diary data analyze users' behavioral patterns, mood fluctuations, and lifestyle trends to provide information useful for self-understanding and mental health management. However, these systems do not support security risk prediction or countermeasure proposals, which means users are unable to effectively manage the security risks they face in their daily lives.

[1872] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for importing diary data from the user, a generative AI means for analyzing the imported diary data, a means for providing feedback and insight to the user based on the analysis results, and a means for predicting security risks and proposing appropriate countermeasures. This makes it possible to evaluate security risks based on the user's diary data and propose specific countermeasures.

[1873] A "user" is an individual who utilizes the system to enter diary data and receive feedback and insights.

[1874] "Diary data" is information in which users record their daily events, feelings, and thoughts.

[1875] "Means of import" refers to the interface or application used to collect diary data from users and input it into the system.

[1876] "Generative AI methods" are artificial intelligence technologies that analyze imported diary data and generate feedback and insights for users.

[1877] "Means for providing feedback and insights" are methods and tools for communicating the analytical results generated by generative AI means to users.

[1878] "Security risks" are dangers or threats that may occur in a user's daily life.

[1879] "Means for proposing appropriate countermeasures" are methods and tools that evaluate security risks and suggest specific preventative or avoidance measures to users.

[1880] "Behavioral patterns" refer to the user's tendencies and habits in daily life.

[1881] "Mood swings" are changes in a user's emotional or mental state.

[1882] "Lifestyle trends" refer to the user's lifestyle habits and characteristics.

[1883] "Self-understanding" refers to users gaining a deep understanding of their own behavior, emotions, and thoughts.

[1884] "Mental health management" refers to methods and activities for maintaining and improving a user's mental health.

[1885] As an embodiment of the present invention, the following system can be constructed.

[1886] System configuration

[1887] The system includes a terminal for capturing the user's diary data, a server for analyzing the data, and an interface for providing the analysis results to the user.

[1888] 1. User Device

[1889] The user terminals are devices such as smartphones and smart glasses. An application is installed on these terminals, allowing users to enter diary data. This application provides an interface for users to enter their daily events, feelings, and thoughts.

[1890] 2. Server

[1891] The server receives the diary data sent by the user and analyzes the data using a generative AI model. Specifically, it performs the following processes:

[1892] Data import: Receives diary data sent from the user's device.

[1893] Prompt generation: Based on the received diary data, a prompt sentence is generated to be passed to the generative AI model.

[1894] Analysis using generative AI models: Using OpenAI's API, security risks are analyzed based on prompt text.

[1895] Feedback generation: Converting the generated feedback into a format for delivery to the user.

[1896] 3. Feedback Providing Interface

[1897] The feedback interface is the part of the application displayed on the user's device that displays feedback and insights sent from the server to the user, such as specific countermeasures for security risks, as well as information about the user's behavioral patterns, mood fluctuations, and lifestyle trends.

[1898] Hardware and software used

[1899] Hardware: Smartphones, smart glasses, servers

[1900] Software: Python, OpenAI API

[1901] Data processing and calculation

[1902] The server receives the diary data sent by the user and analyzes it using a generative AI model. Specifically, it processes and calculates the data as follows:

[1903] 1. Data import: Receives diary data sent from the user's device.

[1904] 2. Prompt generation: Based on the received diary data, a prompt sentence is generated to be passed to the generative AI model.

[1905] 3. Analysis using generative AI models: Using OpenAI's API, security risks are analyzed based on prompt text.

[1906] 4. Feedback generation: Converting the generated feedback into a format for delivery to the user.

[1907] Specific examples

[1908] For example, if a user writes in their diary, "I came home late tonight, but the road from the station to my house was dark and I felt uneasy," the system will use that information to analyze the security risks of returning home late at night and suggest taking a well-lit route or taking a taxi.

[1909] Prompt Sentence Examples

[1910] User diary data: I got home late today, but the road from the station to my house was dark and I felt uneasy.

[1911] Based on this data, analyze security risks and propose appropriate countermeasures.

[1912] In this way, it becomes possible to evaluate security risks based on users' diary data and propose specific countermeasures.

[1913] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1914] Step 1:

[1915] The user enters diary data. Using an application installed on a smartphone or smart glasses, the user enters daily events, emotions, and thoughts. The entered diary data is temporarily stored on the device.

[1916] Step 2:

[1917] The device sends the diary data to the server. When the user instructs the device to send the diary data, the device sends the data to the server via the Internet. The input data is sent in text format.

[1918] Step 3:

[1919] The server receives the diary data. The server receives the diary data sent from the device and stores it in a database. The received data is stored in its original format.

[1920] Step 4:

[1921] The server generates a prompt sentence based on the received diary data, which is then passed to the generative AI model. Specifically, the server performs text analysis on the diary data and converts it into a question format for assessing security risks.

[1922] Step 5:

[1923] The server analyzes the diary data using a generative AI model. The server then sends the generated prompts to the OpenAI API to analyze security risks. The input is the prompts, and the output is feedback on security risks.

[1924] Step 6:

[1925] The server generates the feedback. The server converts the feedback obtained fr...

Claims

1. means for capturing diary data and biometric data of a user; A generative AI means performs preprocessing including normalization and missing value completion on the imported diary data and biometric data; a means for determining the emotional state of the user from the diary data based on an emotion map in which a plurality of emotions are arranged in concentric circles radiating from a center, with primitive emotions being arranged closer to the center of the concentric circles and emotions representing states and actions arising from mental states being arranged on the outer sides of the concentric circles, and for analyzing the intensity and frequency of the determined emotional state; means for applying natural language processing technology to the pre-processed diary data, and for the generative AI means to analyze the user's behavioral patterns, mood fluctuations, lifestyle tendencies, and sleep patterns based on the pre-processed diary data, the biometric data, and the analyzed emotional state; means for providing feedback to the user based on the analysis result by the generative AI means and the emotional state of the user; A system including:

2. The providing means provides the feedback generated using a generative AI model based on a prompt sentence according to the emotional state of the user. The system of claim 1 .

Images