System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving diary text data of a user; means for analyzing the received diary text data; means for identifying emotions and behavior patterns based on the analyzed data; means for generating feedback to the user based on the identified data; and means for transmitting the generated feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, many people seek ways to deepen self-understanding and promote personal growth amid their busy daily lives. However, it is difficult to objectively grasp one's emotions and behavioral patterns or receive concrete feedback simply by writing a diary. As a result, there is a problem in that opportunities for self-insight and growth through diary writing are not being fully utilized. [Means for solving the problem]

[0005] The present invention provides a system that receives a user's diary text data, analyzes the data to identify emotions and behavioral patterns, and generates personalized feedback based on the received data. The system of the present invention includes a means for receiving the user's diary text data, a means for analyzing the received diary text data, a means for identifying emotions and behavioral patterns based on the analyzed data, a means for generating feedback to the user based on the identified data, and a means for transmitting the generated feedback. This allows the user to deepen self-understanding through the diary and obtain specific guidelines for action.

[0006] "User" refers to an individual who uses the System.

[0007] "Diary text data" refers to text information entered by the user in diary format.

[0008] "Means for receiving" refers to a function that enables the server to receive diary text data from a user.

[0009] "Means for analyzing" refers to a function for analyzing received diary text data using natural language processing technology.

[0010] "Means for identifying emotion and behavioral patterns" refers to the ability to identify the user's emotional state and behavioral characteristics from the analyzed data.

[0011] "Means for generating feedback" refers to the ability to create recommendations to improve the user's life based on identified emotions and behavioral patterns.

[0012] The "means for transmitting" refers to a function for transmitting the generated feedback to the user's terminal.

[0013] "Means for performing preprocessing" refers to the function of converting received diary text data into a format that is easy to analyze.

[0014] "Means for saving to a database" refers to the function of recording analysis results and identified data in a database so that they can be reused later. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] System Overview

[0037] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[0038] Program processing

[0039] User diary data entry and reception

[0040] First, the user inputs the text of the diary using the terminal. This text describes the user's daily life and emotional movements. The terminal then transmits this text data to the server.

[0041] Receiving diary data and preprocessing it on the server

[0042] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms).

[0043] Emotion and behavioral pattern analysis

[0044] The AI ​​analysis module in the server analyzes the preprocessed text data. The analysis is carried out using natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) in the text. The results of this identification are stored in a database.

[0045] Generate personalized feedback

[0046] The server generates user-specific feedback based on the analysis results. This feedback generation module also takes into account past data and data from similar users to create specific advice to improve the user's daily life.

[0047] Sending and Viewing Feedback

[0048] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0049] Example

[0050] Specific processing example

[0051] 1. User diary entry

[0052] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0053] The terminal transmits this text data to the server.

[0054] 2. Receiving and preprocessing text data on the server

[0055] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0056] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0057] Next, the words are stemmed and converted to their base forms.

[0058] 3. Conducting the analysis

[0059] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[0060] The server stores these identification results in a database.

[0061] 4. Generate feedback

[0062] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[0063] 5. Sending and Viewing Feedback

[0064] The server transmits the generated feedback data to the terminal.

[0065] The terminal displays the received feedback to the user, and the user receives specific advice.

[0066] In this way, we have realized a system that can provide specific and personalized feedback from users' diary entries.

[0067] The processing flow will be explained below.

[0068] Step 1: The user uses the terminal to input the text of the diary. In the input form, the user writes, "I'm tired from meetings all day today, but I'm happy that the project was successful."

[0069] Step 2: The terminal prepares a data format for sending the input text data to the server. The terminal sends the text to the server as an HTTP request.

[0070] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[0071] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[0072] Step 5: The server's AI analysis module analyzes the preprocessed text, using natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") and behavioral patterns (e.g., "meeting," "project") within the text.

[0073] Step 6: The server stores the analysis results in a database, including tagging information for identified emotions and behavioral patterns.

[0074] Step 7: The server's feedback generation module retrieves the analysis results from the database and generates user-specific feedback, such as "You seem tired today, but you seem to be satisfied with your work success. We recommend that you take adequate rest and prepare for tomorrow."

[0075] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[0076] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[0077] Through this series of processes, the user can deepen their self-understanding and obtain specific guidelines for action.

[0078] Example 1

[0079] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0080] Conventional systems have had difficulty efficiently analyzing users' diary text data and providing personalized feedback. Furthermore, due to low accuracy in preprocessing and analysis, they were unable to accurately identify users' emotions and behavioral patterns. Furthermore, there was no established method for utilizing the analysis results to generate appropriate feedback and provide it to users. Therefore, there was a need to build a system that would deepen users' self-understanding and provide them with specific guidelines for action.

[0081] 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.

[0082] In this invention, the server includes means for receiving a user's diary text data, means for preprocessing the received diary text data by cleaning, tokenizing, and stemming, means for analyzing the preprocessed diary text data using natural language processing technology, means for identifying emotions and behavioral patterns based on the analyzed data, means for storing the identified data in a database, means for generating user-specific feedback based on the stored data and past data, means for transmitting the generated feedback to the user's terminal, and means for displaying the transmitted feedback to the user. This makes it possible to provide highly accurate and personalized feedback based on the user's diary content.

[0083] "User" refers to a person who uses the system to enter diary text data.

[0084] "Terminal" refers to a device that allows a user to input diary text data and send it to the server.

[0085] "Server" refers to the computer system that processes, analyzes, and stores received diary text data, and generates and transmits feedback.

[0086] "Diary text data" refers to text information entered by a user about their daily life and emotions.

[0087] "Preprocessing" refers to the process of converting text data into a format that is easy to analyze by performing processes such as cleaning, tokenization, and stemming on the data.

[0088] "Cleaning" refers to the process of removing unnecessary spaces and special characters from diary text data.

[0089] "Tokenization" refers to the process of dividing diary text data into words or phrases.

[0090] "Stemming" refers to the process of converting words into their base forms.

[0091] "Natural language processing technology" refers to technology for analyzing text data and identifying meaning and emotion.

[0092] "Analysis" refers to the process of identifying sentiment and behavioral patterns from preprocessed text data.

[0093] "Emotion" refers to the user's psychological state, such as joy, sadness, or anger, contained in the text data.

[0094] "Behavioral pattern" refers to elements in text data that identify user activities or behaviors (e.g., work, rest).

[0095] "Identification" refers to the process of identifying specific emotions or behavioral patterns from the analysis results.

[0096] "Database" refers to the digital storage for identifying emotions and behavioral patterns and other related data.

[0097] "Feedback" refers to specific advice or guidelines for users that are generated based on the analysis results.

[0098] "Generation" refers to the process of creating feedback based on data stored in a database or past data.

[0099] "Send" refers to the act of transferring the generated feedback from the server to the user's terminal.

[0100] "Display" refers to the act of visually showing the submitted feedback on the user's terminal.

[0101] System Overview

[0102] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[0103] Program processing

[0104] User diary data entry and reception

[0105] The user inputs text for the diary using a terminal. This text includes information about the user's daily life and emotions. The terminal then transmits this text data to a server. Any text input device or smartphone can be used as the hardware.

[0106] Receiving diary data and preprocessing it on the server

[0107] The server receives the diary text data sent from the device. As the received data is not suitable for analysis as is, it undergoes preprocessing. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). Preprocessing prepares the data in a format that is easy to analyze. Specific text processing libraries that are introduced include Python NLP libraries (e.g., NLTK and spaCy).

[0108] Emotion and behavioral pattern analysis

[0109] The AI ​​analysis module in the server analyzes the preprocessed text data. This analysis uses natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) within the text. Generative AI models used include the BERT and GPT series models, for example. The analysis results are stored in a database and accumulated as each user's historical data.

[0110] Generate personalized feedback

[0111] The server generates user-specific feedback based on the analysis results. This feedback generation module references the user's own past data and data from similar users to create specific advice to improve the user's daily life. Advanced natural language generation is made possible by inputting prompt sentences into the generative AI model.

[0112] Sending and Viewing Feedback

[0113] The generated feedback is sent from the server to the device. The device displays this feedback to the user in a format that is intuitively easy to understand. This allows the user to deepen their self-understanding and obtain specific guidelines for action. Notification messages, pop-up windows, and other display formats are used.

[0114] Specific examples

[0115] 1. User diary entry

[0116] The user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0117] The terminal transmits this text data to the server.

[0118] 2. Receiving and preprocessing text data on the server

[0119] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0120] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0121] Next, the words are stemmed and converted to their base forms.

[0122] 3. Conducting the analysis

[0123] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[0124] The server stores these identification results in a database.

[0125] 4. Generate feedback

[0126] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[0127] 5. Sending and Viewing Feedback

[0128] The server transmits the generated feedback data to the terminal.

[0129] The terminal displays the received feedback to the user, and the user receives specific advice.

[0130] In this way, a system is realized that provides specific and personalized feedback based on the contents of a user's diary.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1: Enter and submit user diary data

[0133] A user inputs diary text into a terminal. For example, the user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." The input text data is sent by the terminal to the server. The input here is the user's diary text data, and the output is the text data sent to the server.

[0134] Step 2: Receiving diary data on the server

[0135] The server receives the diary text data sent from the terminal. The received data is temporarily stored in memory. The input here is the diary text data sent from the terminal, and the output is the data stored in memory.

[0136] Step 3: Preprocessing the text data

[0137] The server performs preprocessing on the diary text data it receives. Specifically, it performs text cleaning (removing unnecessary spaces and special characters), tokenization (dividing into words and phrases), and stemming (converting words into their base forms). The input is the diary text data stored in memory, and the output is the preprocessed text data. For example, the input "I was tired from meetings all day today, but I'm happy that the project was successful" is converted into "today," "all day," "meeting," "tiring," "project," "success," and "satisfied."

[0138] Step 4: Emotion and behavioral pattern analysis

[0139] The AI ​​analysis module on the server analyzes the preprocessed text data. It uses natural language processing technology to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The input is the preprocessed text data, and the output is the identified emotion and behavioral pattern data. For example, "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)" are identified.

[0140] Step 5: Save the analysis results to a database

[0141] The server stores the identified emotion and behavior pattern data in a database. It is important to store the data in association with past data. The input is the identified emotion and behavior pattern data, and the output is the data stored in the database.

[0142] Step 6: Generate personalized feedback

[0143] The server generates user-specific feedback based on the analysis results. It is created using a generative AI model based on the prompt text. The input is the analysis results and past user data, and the output is user-specific feedback. Specifically, it might be something like, "You seem tired today, but you seem to be feeling satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow."

[0144] Step 7: Submit your feedback

[0145] The server sends the generated feedback data to the terminal, where the input is the user-specific feedback and the output is the feedback data sent to the terminal.

[0146] Step 8: Viewing feedback

[0147] The feedback received by the device is displayed to the user in a format that allows the user to confirm specific advice. The input is the feedback data sent to the device, and the output is the feedback displayed to the user. For example, it is displayed as a notification message or a pop-up window on the device.

[0148] (Application example 1)

[0149] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0150] While existing systems have the ability to analyze users' diary data to identify their emotions and behavioral patterns, they lack the ability to recommend content appropriate to the user's mood based on the results of this identification. Therefore, there was a need for a system that would not only help users deepen their self-understanding, but also allow them to enjoy appropriate content according to their daily mood.

[0151] 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.

[0152] In this invention, the server

[0153] means for receiving user diary text data;

[0154] means for analyzing the received diary text data;

[0155] means for identifying emotions and behavioral patterns based on the analyzed data;

[0156] means for generating feedback to a user based on the identified data;

[0157] means for transmitting the generated feedback;

[0158] means for recommending appropriate content to a user based on the identified emotion;

[0159] This makes it possible to recommend content that matches the user's daily emotional state.

[0160] The "means for receiving user's diary text data" is a function for transmitting diary text data entered by the user to the server via the network and receiving it.

[0161] The "means for analyzing the received diary text data" is a function for analyzing the received diary text data grammatically and semantically using natural language processing technology.

[0162] The "means for identifying emotions and behavioral patterns based on the analyzed data" is a function for identifying the emotions and behavioral patterns of a user based on information extracted from the analyzed text data.

[0163] The "means for generating feedback to the user based on the identified data" is a function for generating personalized feedback to the user based on the identified emotions and behavioral patterns.

[0164] The "means for transmitting the generated feedback" is a function for transmitting the generated feedback to the user terminal.

[0165] The "means for recommending appropriate content to the user based on the identified emotion" is a function for obtaining content such as videos and music that is appropriate for the identified emotion from an external content providing service and recommending it to the user.

[0166] To implement this invention, a server, a user terminal, and natural language processing technology are used. The following describes specific program processing and how to use it.

[0167] First, a user inputs diary text data using their own device (e.g., a smartphone). This diary text data describes the user's daily life and emotional movements, and the device then transmits this data to a server.

[0168] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes are performed using spaCy and TextBlob, natural language processing libraries specialized for text analysis.

[0169] After preprocessing, the AI ​​analysis module on the server analyzes the text data. A generative AI model is used to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The analysis results are stored in a database.

[0170] The server then generates user-specific feedback based on the identified emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Furthermore, based on the identified emotions, the server retrieves and recommends content appropriate for the user (e.g., relaxing music or mood-boosting videos) from external content providers.

[0171] The generated feedback and recommended content are sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to obtain specific guidelines for action and appropriate content.

[0172] For example, suppose a user writes in their diary, "I'm tired from meetings all day today, but I'm satisfied that the project was a success." From this text, the analysis module reads the emotions of "fatigue" and "success" and identifies that the user is tired from their daytime activities but also feels a sense of accomplishment. Based on this analysis result, the server generates feedback such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow." It also recommends content appropriate to the user's state, such as relaxing music or inspiring movie trailers.

[0173] An example of a prompt sentence input to the generative AI model is as follows:

[0174] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[0175] This invention enables personalized content recommendations that match the user's daily emotional state, thereby improving the user's quality of life.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The user inputs diary text data using a terminal. Specifically, the user starts the application and describes their daily life and emotional movements in the text input box. The input diary text data is encoded on the terminal and sent to the server via the network.

[0179] Input: User's diary text data

[0180] Output: Encoded text data sent to the server

[0181] Step 2:

[0182] The server receives diary text data sent from user devices. Since the received data is not suitable for analysis as is, it undergoes preprocessing. Preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes use natural language processing libraries such as spaCy and TextBlob.

[0183] Input: Encoded diary text data

[0184] Output: Clean text data after preprocessing

[0185] Step 3:

[0186] The AI ​​analysis module in the server analyzes the pre-processed text data and uses a generative AI model to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) in the text. This uses natural language processing techniques, and the analysis results are stored in a database.

[0187] Input: Clean, preprocessed text data

[0188] Output: Emotion and behavior pattern identification results

[0189] Step 4:

[0190] The server generates user-specific feedback based on the results of identifying emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Based on the analysis results, the server also obtains and recommends content (videos, music, etc.) suitable for the user from external content providers.

[0191] Input: Emotion and behavior pattern identification results

[0192] Output: User-specific feedback and recommended content

[0193] Step 5:

[0194] The generated feedback and recommended content are sent from the server to the user's device, which then displays them in an intuitively understandable format. For example, the feedback might say, "You seem tired today, but you seem to be satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow," and provide links to relaxing music or videos that lift your spirits.

[0195] Input: User-specific feedback and suggested content

[0196] Output: Feedback and recommended content displayed on the user's device

[0197] For example, if a user enters "I'm tired from meetings all day today, but I'm happy that the project was a success," the server analyzes the text and generates appropriate feedback and content to provide to the user. An example of a prompt sentence in this case is as follows:

[0198] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[0199] 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.

[0200] System Overview

[0201] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to more accurately identify the user's emotional state and generate personalized feedback.

[0202] Program processing

[0203] User diary data entry and reception

[0204] First, the user inputs the text of the diary using the device. This text describes the user's daily life and emotional movements. The device then transmits the input text data to the server.

[0205] Receiving diary data and preprocessing it on the server

[0206] The server receives the diary text data sent from the device. The received data undergoes preprocessing before analysis. Preprocessing includes text cleaning, tokenization, stemming, etc.

[0207] Analysis by emotion engine

[0208] The emotion engine in the server analyzes the pre-processed text data. Using natural language processing techniques, the emotion engine identifies emotions (e.g., joy, sadness, anger, surprise) in the text. This identifies the user's emotional state based on the diary data.

[0209] Identifying emotions and behavioral patterns

[0210] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meetings" and "projects," from the user's text and stores them in a database.

[0211] Generate personalized feedback

[0212] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. This feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life.

[0213] Sending and Viewing Feedback

[0214] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0215] Example

[0216] Specific processing example

[0217] 1. User diary entry

[0218] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0219] The terminal transmits this text data to the server.

[0220] 2. Receiving and preprocessing text data on the server

[0221] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0222] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0223] Next, the words are stemmed and converted to their base forms.

[0224] 3. Analysis by Emotion Engine

[0225] The server's emotion engine analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "satisfaction (positive emotion)."

[0226] 4. Identifying Behavioral Patterns

[0227] The server identifies the behavioral patterns in the text, such as "meetings (behavioral patterns)" and "projects (behavioral patterns)," and stores them in a database along with the analysis results.

[0228] 5. Generate feedback

[0229] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend that you get some proper rest."

[0230] 6. Sending and Viewing Feedback

[0231] The server transmits the generated feedback data to the terminal.

[0232] The terminal displays the received feedback to the user, and the user receives specific advice.

[0233] In this way, we have realized a system that can provide specific and personalized feedback based on the user's diary entries.By introducing an emotion engine, we can analyze the user's emotional state more accurately and provide more appropriate feedback.

[0234] The processing flow will be explained below.

[0235] Step 1: The user uses the terminal to input the text of the diary. For example, the user might write, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0236] Step 2: The terminal prepares a data format for sending the input text data to the server, and sends the text to the server as an HTTP request.

[0237] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[0238] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[0239] Step 5: The emotion engine in the server analyzes the pre-processed text data. The emotion engine uses natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") from the text. The emotional state is identified.

[0240] Step 6: The server also identifies behavioral patterns (e.g., "meeting" or "project") in the diary text based on the analysis results of the emotion engine. The identified emotion and behavioral pattern information is stored in a database.

[0241] Step 7: The server's feedback generation module retrieves the emotion and behavior pattern identification results from the database and generates user-specific feedback. For example, it could generate feedback such as, "You seem tired today, but you feel satisfied with the success of the project. I recommend you get some proper rest and prepare for tomorrow."

[0242] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[0243] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[0244] Through this series of processes, users can deepen their self-understanding and obtain specific guidelines for action through emotion analysis and behavioral pattern identification using the engine.

[0245] Example 2

[0246] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0247] In systems that analyze users' diary text data, identify their emotions and behavioral patterns, and provide feedback, it is difficult to improve the accuracy of the analysis and provide personalized feedback. There is also a need for the feedback received by users to be displayed in an intuitive and easy-to-understand format.

[0248] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving diary text data of a user, means for pre-processing the received diary text data, means for analyzing the pre-processed diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for generating feedback to the user based on the identified data, means for transmitting the generated feedback, and means for displaying the feedback in a format that is intuitively easy for the user to understand. This enables highly accurate identification of emotions and behavioral patterns and provision of personalized feedback based on past data.

[0249] "User" refers to a person who uses this system to input diary text data and receives feedback on it.

[0250] "Diary text data" refers to text data in which a user describes events, feelings, and actions in their daily life.

[0251] "Means for receiving" refers to a function for transmitting diary text data from a terminal to a server.

[0252] "Preprocessing means" refers to processes such as cleaning, tokenization, and stemming that are carried out to prepare the received diary text data in a form that is easy to analyze.

[0253] "Means for analysis" refers to the function of classifying the contents of preprocessed diary text data into emotions and behavioral patterns using natural language processing technology.

[0254] "Emotion" refers to states such as joy, sadness, anger, surprise, etc. contained in the user's diary text data.

[0255] A "behavioral pattern" refers to the repetition of a specific behavior or event contained in the user's diary text data.

[0256] "Means for identifying" refers to the ability to extract emotion and behavioral patterns based on the analyzed data.

[0257] "Feedback" refers to advice and comments to the user that are generated based on the analysis and identification results.

[0258] "Means of generation" refers to the function of creating feedback for users by referring to past data and data of similar users.

[0259] "Means for sending" refers to the function of sending the generated feedback from the server to the terminal.

[0260] The "means for displaying" refers to a function for displaying the received feedback on the terminal in a format that is intuitively easy for the user to understand.

[0261] The present invention is a system that analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and provides feedback. A specific embodiment of this system will be described below.

[0262] First, a user inputs text data for a diary entry using their own device (e.g., smartphone or PC). For example, a user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." This text data describes the user's daily life and emotional movements. The device then sends the input diary text data to the server.

[0263] The server receives the diary text data sent from the device. The received data is preprocessed before analysis. This preprocessing includes the following steps:

[0264] Text cleaning: Remove unnecessary spaces and special characters from text.

[0265] Tokenization: Breaking text into meaningful units (words and phrases), such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0266] Stemming: Converting words into their base form. For example, converting "tired" into "tired."

[0267] After preprocessing, the text data is passed to the emotion engine on the server. This emotion engine uses natural language processing techniques to analyze the text and identify emotions. For example, the following emotions can be identified:

[0268] "Tired" -> fatigue (negative emotion)

[0269] "Success" -> positive emotions

[0270] "Satisfaction" -> positive emotions

[0271] After identifying emotions, the server then identifies behavioral patterns. This is the process of extracting specific actions or events from the text. For example, behavioral patterns such as "meeting" and "project" are extracted. This identified data is then stored in a database along with the analysis results.

[0272] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. The generated feedback is created by referring to past data and data from similar users. A specific example would be the feedback, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend you get some proper rest."

[0273] The generated feedback is sent from the server to the device, which then displays the received feedback to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0274] Example prompt sentence:

[0275] "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0276] As described above, the present invention is a system that realizes highly accurate identification of emotions and behavioral patterns and provides personalized feedback based on past data.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] The user inputs diary text data.

[0280] Specifically, the user uses the terminal and enters the following into the text input screen: "I'm tired from meetings all day today, but I'm happy that the project was a success." This input text is sent to the server as input data for the terminal.

[0281] Step 2:

[0282] The server receives the diary text data.

[0283] Specifically, the server receives diary text data sent from the device via the network and temporarily stores it in memory. The input data is raw text data, and the output at this point is text data before preprocessing.

[0284] Step 3:

[0285] The server pre-processes the diary text data.

[0286] Specifically, the server performs text cleaning, removing unnecessary spaces and special characters. Next, it performs text tokenization, dividing the sentence into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied." Finally, it performs stemming, converting the words into their base forms. The input is raw text data, and the output is cleaned, tokenized, and stemmed text data.

[0287] Step 4:

[0288] The server analyzes the preprocessed text data using an emotion engine.

[0289] Specifically, the emotion engine uses natural language processing technology to identify emotions from preprocessed text data. For example, emotions are extracted in the form of "tired" -> fatigue (negative emotion), and "success" or "satisfied" -> positive emotion. The input is preprocessed text data, and the output is identified emotion data.

[0290] Step 5:

[0291] The server identifies behavioral patterns based on the analyzed data.

[0292] Specifically, the server extracts behavioral patterns such as "meeting" and "project" from the text. This clarifies the activities the user performed. The input is text data analyzed by the emotion engine, and the output is the identified behavioral pattern data.

[0293] Step 6:

[0294] The server generates feedback to the user.

[0295] Specifically, the server generates personalized feedback based on the analysis and identification results. It also references past data and data from similar users to create specific advice such as, "You seem tired today, but you seem to be satisfied with the success of the project. I recommend you get some proper rest." The input is the identified emotion data and behavioral pattern data, and the output is the generated feedback.

[0296] Step 7:

[0297] The server generates feedback and sends it to the device.

[0298] Specifically, the server sends the generated feedback data to the terminal via the network. The input is the generated feedback, and the output is the feedback data sent to the terminal.

[0299] Step 8:

[0300] The terminal displays the sent feedback to the user.

[0301] Specifically, the device displays the received feedback in an intuitively understandable format to the user, allowing the user to receive specific advice on their own status. The input is the transmitted feedback data, and the output is the feedback displayed to the user.

[0302] (Application example 2)

[0303] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0304] Current security services do not adequately monitor users' emotional changes and behavioral patterns, making it difficult to respond quickly to sudden emotional changes or abnormal behavioral patterns. To solve this problem and ensure users' safety and security, a system is needed that analyzes diary text data, accurately identifies emotional states and behavioral patterns, and provides feedback.

[0305] 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.

[0306] In this invention, the server includes means for receiving diary text data of a user, means for analyzing the received diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for detecting abnormal behavioral patterns or sudden changes in emotions based on the generated feedback, means for sending a notification to the user based on the detected abnormality, and means for sending the generated feedback. This makes it possible to early detect abnormal emotional changes or behavioral patterns of a user and provide appropriate notifications, thereby ensuring the safety and security of the user.

[0307] "Diary text data" refers to text data entered by a user about their daily life or the events of the day.

[0308] The "receiving means" refers to a device or program that has the function of sending the diary text data entered by the user to the server and capturing that data.

[0309] The "analyzing means" refers to a device or program that has the function of analyzing the received diary text data and extracting the emotions and behavioral patterns contained therein.

[0310] "Emotion" indicates the user's inherent psychological state, such as joy, sadness, anger, or surprise.

[0311] A "behavioral pattern" refers to a series of actions or activities that a user performs in daily life or in a specific situation.

[0312] "Feedback" refers to advice or information provided to users based on analyzed emotions and behavioral patterns.

[0313] An "abnormal behavior pattern" is a behavior that is significantly different from the user's normal behavior, and is often linked to a sudden change in emotion.

[0314] A "sudden change in emotion" refers to a large change in the emotional state of a user analyzed from the diary text data in a short period of time.

[0315] The "means for sending a notification" is a device or program that has the function of sending a notification to a user or administrator based on the analysis results.

[0316] System Overview

[0317] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to identify the user's emotional state with greater accuracy, provide personalized feedback, and detect abnormalities.

[0318] Program processing

[0319] User diary data entry and reception

[0320] The user inputs diary text using a smartphone, and the input text data is sent to a server via a dedicated application.

[0321] Receiving diary data and preprocessing it on the server

[0322] The server receives the diary text data sent from the device and performs preprocessing on the received data, which includes text cleaning, tokenization, stemming, etc.

[0323] Analysis by emotion engine

[0324] The emotion engine in the server analyzes the preprocessed text data and uses natural language processing (NLP) techniques to identify emotions (such as joy, sadness, anger, and surprise) in the text. Specifically, it uses the Hugging Face Transformers library to accurately identify emotional states.

[0325] Identifying emotions and behavioral patterns

[0326] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meeting" or "project" in the text, and stores them in a database.

[0327] Generate personalized feedback

[0328] The server generates user-specific feedback based on the emotion engine's analysis results and behavioral pattern identification. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates appropriate notifications. For example, it creates specific advice such as, "You seem to be feeling stressed today. We recommend you take a rest."

[0329] Sending and Viewing Feedback

[0330] The generated feedback is sent from the server to the terminal, which displays the feedback to the user and also sends notifications to the user based on the detected anomalies.

[0331] Specific examples

[0332] 1. User diary entry

[0333] The user types, "I've been feeling very stressed today. Some things haven't gone as planned and I'm frustrated."

[0334] The terminal transmits this text data to the server.

[0335] 2. Receiving and preprocessing text data on the server

[0336] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0337] For example, the text is tokenized and divided into words such as "today," "stress," "work," "not progressing," and "frustrated."

[0338] Next, the words are stemmed and converted to their base forms.

[0339] 3. Analysis by Emotion Engine

[0340] The server's emotion engine analyzes the text and identifies "high stress" and "medium irritation."

[0341] 4. Identifying Behavioral Patterns

[0342] The server identifies the behavioral pattern of the text, "High Work," and stores it in a database along with the analysis results.

[0343] 5. Generate feedback

[0344] Based on the analysis results, the server generates specific advice such as, "You seem to be feeling stressed today, so we recommend that you take a rest."

[0345] If an anomaly is detected, generate a notification saying "An abnormal behavior pattern has been detected. Attention required."

[0346] 6. Sending and Viewing Feedback

[0347] The server sends the generated feedback data and notification to the terminal.

[0348] The device displays the received feedback and notifications to the user.

[0349] Prompt Sentence Examples

[0350] Below are some example prompts for generative AI models:

[0351] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[0352] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[0353] Emotion analysis:

[0354] Stress: High

[0355] Irritation: Medium

[0356] Behavior Pattern:

[0357] Work: High

[0358] Assess the risk level and generate feedback.”

[0359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0360] Step 1:

[0361] User diary data entry

[0362] A user inputs diary text using a smartphone. The input text data is sent to a server via a dedicated application. This text data describes the user's daily life and emotional movements.

[0363] Step 2:

[0364] Receiving diary text data

[0365] The server receives the diary text data sent from the terminal. At this stage, the input data itself is stored in a specified memory area of ​​the server. The input is the diary text data, and the output is the received text data.

[0366] Step 3:

[0367] Preprocessing text data

[0368] The server performs preprocessing on the received text data, including cleaning, tokenization, and stemming. Cleaning removes unnecessary special characters and noise, tokenization divides the data into words, and stemming converts words into their base forms. The input is the received text data, and the output is the preprocessed text data.

[0369] Step 4:

[0370] Analysis by emotion engine

[0371] The emotion engine in the server analyzes the preprocessed text data. It uses natural language processing techniques (e.g., Hugging Face's Transformers library) to identify the emotions contained in the text (e.g., "stress," "joy," etc.). The input is the preprocessed text data, and the output is the emotion analysis results.

[0372] Step 5:

[0373] Identifying behavioral patterns

[0374] In addition to analyzing sentiment, the server also identifies behavioral patterns within the text. This identification is done by the occurrence of specific keywords (e.g., "meeting," "project," etc.). The input is the preprocessed text data, and the output is the behavioral pattern identification results.

[0375] Step 6:

[0376] Data storage

[0377] The server stores the emotion analysis results and behavioral pattern identification results in a database. This storage process accumulates the user's diary data as past data and can be used for future analysis. The input is the emotion analysis results and behavioral pattern identification results, and the output is the data stored in the database.

[0378] Step 7:

[0379] Generate feedback

[0380] The server generates feedback for the user based on the emotion analysis results and behavioral pattern identification results. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates an appropriate notification. The input is the emotion analysis results and behavioral pattern identification results, and the output is the generated feedback message and notification.

[0381] Step 8:

[0382] Sending feedback and notifications

[0383] The server sends the generated feedback and notifications to the user's terminal. The terminal displays the received feedback and notifications to the user. The input is the generated feedback message and notification, and the output is the feedback and notification displayed on the terminal.

[0384] Specifically, the generative AI model is given a prompt like the one below, which is then analyzed and feedback is generated:

[0385] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[0386] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[0387] Emotion analysis:

[0388] Stress: High

[0389] Irritation: Medium

[0390] Behavior Pattern:

[0391] Work: High

[0392] Assess the risk level and generate feedback.”

[0393] 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.

[0394] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0395] 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.

[0396] [Second embodiment]

[0397] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0409] System Overview

[0410] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[0411] Program processing

[0412] User diary data entry and reception

[0413] First, the user inputs the text of the diary using the terminal. This text describes the user's daily life and emotional movements. The terminal then transmits this text data to the server.

[0414] Receiving diary data and preprocessing it on the server

[0415] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms).

[0416] Emotion and behavioral pattern analysis

[0417] The AI ​​analysis module in the server analyzes the preprocessed text data. The analysis is carried out using natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) in the text. The results of this identification are stored in a database.

[0418] Generate personalized feedback

[0419] The server generates user-specific feedback based on the analysis results. This feedback generation module also takes into account past data and data from similar users to create specific advice to improve the user's daily life.

[0420] Sending and Viewing Feedback

[0421] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0422] Example

[0423] Specific processing example

[0424] 1. User diary entry

[0425] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0426] The terminal transmits this text data to the server.

[0427] 2. Receiving and preprocessing text data on the server

[0428] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0429] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0430] Next, the words are stemmed and converted to their base forms.

[0431] 3. Conducting the analysis

[0432] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[0433] The server stores these identification results in a database.

[0434] 4. Generate feedback

[0435] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[0436] 5. Sending and Viewing Feedback

[0437] The server transmits the generated feedback data to the terminal.

[0438] The terminal displays the received feedback to the user, and the user receives specific advice.

[0439] In this way, we have realized a system that can provide specific and personalized feedback from users' diary entries.

[0440] The processing flow will be explained below.

[0441] Step 1: The user uses the terminal to input the text of the diary. In the input form, the user writes, "I'm tired from meetings all day today, but I'm happy that the project was successful."

[0442] Step 2: The terminal prepares a data format for sending the input text data to the server. The terminal sends the text to the server as an HTTP request.

[0443] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[0444] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[0445] Step 5: The server's AI analysis module analyzes the preprocessed text, using natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") and behavioral patterns (e.g., "meeting," "project") within the text.

[0446] Step 6: The server stores the analysis results in a database, including tagging information for identified emotions and behavioral patterns.

[0447] Step 7: The server's feedback generation module retrieves the analysis results from the database and generates user-specific feedback, such as "You seem tired today, but you seem to be satisfied with your work success. We recommend that you take adequate rest and prepare for tomorrow."

[0448] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[0449] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[0450] Through this series of processes, the user can deepen their self-understanding and obtain specific guidelines for action.

[0451] Example 1

[0452] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0453] Conventional systems have had difficulty efficiently analyzing users' diary text data and providing personalized feedback. Furthermore, due to low accuracy in preprocessing and analysis, they were unable to accurately identify users' emotions and behavioral patterns. Furthermore, there was no established method for utilizing the analysis results to generate appropriate feedback and provide it to users. Therefore, there was a need to build a system that would deepen users' self-understanding and provide them with specific guidelines for action.

[0454] 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.

[0455] In this invention, the server includes means for receiving a user's diary text data, means for preprocessing the received diary text data by cleaning, tokenizing, and stemming, means for analyzing the preprocessed diary text data using natural language processing technology, means for identifying emotions and behavioral patterns based on the analyzed data, means for storing the identified data in a database, means for generating user-specific feedback based on the stored data and past data, means for transmitting the generated feedback to the user's terminal, and means for displaying the transmitted feedback to the user. This makes it possible to provide highly accurate and personalized feedback based on the user's diary content.

[0456] "User" refers to a person who uses the system to enter diary text data.

[0457] "Terminal" refers to a device that allows a user to input diary text data and send it to the server.

[0458] "Server" refers to the computer system that processes, analyzes, and stores received diary text data, and generates and transmits feedback.

[0459] "Diary text data" refers to text information entered by a user about their daily life and emotions.

[0460] "Preprocessing" refers to the process of converting text data into a format that is easy to analyze by performing processes such as cleaning, tokenization, and stemming on the data.

[0461] "Cleaning" refers to the process of removing unnecessary spaces and special characters from diary text data.

[0462] "Tokenization" refers to the process of dividing diary text data into words or phrases.

[0463] "Stemming" refers to the process of converting words into their base forms.

[0464] "Natural language processing technology" refers to technology for analyzing text data and identifying meaning and emotion.

[0465] "Analysis" refers to the process of identifying sentiment and behavioral patterns from preprocessed text data.

[0466] "Emotion" refers to the user's psychological state, such as joy, sadness, or anger, contained in the text data.

[0467] "Behavioral pattern" refers to elements in text data that identify user activities or behaviors (e.g., work, rest).

[0468] "Identification" refers to the process of identifying specific emotions or behavioral patterns from the analysis results.

[0469] "Database" refers to the digital storage for identifying emotions and behavioral patterns and other related data.

[0470] "Feedback" refers to specific advice or guidelines for users that are generated based on the analysis results.

[0471] "Generation" refers to the process of creating feedback based on data stored in a database or past data.

[0472] "Send" refers to the act of transferring the generated feedback from the server to the user's terminal.

[0473] "Display" refers to the act of visually showing the submitted feedback on the user's terminal.

[0474] System Overview

[0475] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[0476] Program processing

[0477] User diary data entry and reception

[0478] The user inputs text for the diary using a terminal. This text includes information about the user's daily life and emotions. The terminal then transmits this text data to a server. Any text input device or smartphone can be used as the hardware.

[0479] Receiving diary data and preprocessing it on the server

[0480] The server receives the diary text data sent from the device. As the received data is not suitable for analysis as is, it undergoes preprocessing. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). Preprocessing prepares the data in a format that is easy to analyze. Specific text processing libraries that are introduced include Python NLP libraries (e.g., NLTK and spaCy).

[0481] Emotion and behavioral pattern analysis

[0482] The AI ​​analysis module in the server analyzes the preprocessed text data. This analysis uses natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) within the text. Generative AI models used include the BERT and GPT series models, for example. The analysis results are stored in a database and accumulated as each user's historical data.

[0483] Generate personalized feedback

[0484] The server generates user-specific feedback based on the analysis results. This feedback generation module references the user's own past data and data from similar users to create specific advice to improve the user's daily life. Advanced natural language generation is made possible by inputting prompt sentences into the generative AI model.

[0485] Sending and Viewing Feedback

[0486] The generated feedback is sent from the server to the device. The device displays this feedback to the user in a format that is intuitively easy to understand. This allows the user to deepen their self-understanding and obtain specific guidelines for action. Notification messages, pop-up windows, and other display formats are used.

[0487] Specific examples

[0488] 1. User diary entry

[0489] The user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0490] The terminal transmits this text data to the server.

[0491] 2. Receiving and preprocessing text data on the server

[0492] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0493] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0494] Next, the words are stemmed and converted to their base forms.

[0495] 3. Conducting the analysis

[0496] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[0497] The server stores these identification results in a database.

[0498] 4. Generate feedback

[0499] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[0500] 5. Sending and Viewing Feedback

[0501] The server transmits the generated feedback data to the terminal.

[0502] The terminal displays the received feedback to the user, and the user receives specific advice.

[0503] In this way, a system is realized that provides specific and personalized feedback based on the contents of a user's diary.

[0504] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0505] Step 1: Enter and submit user diary data

[0506] A user inputs diary text into a terminal. For example, the user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." The input text data is sent by the terminal to the server. The input here is the user's diary text data, and the output is the text data sent to the server.

[0507] Step 2: Receiving diary data on the server

[0508] The server receives the diary text data sent from the terminal. The received data is temporarily stored in memory. The input here is the diary text data sent from the terminal, and the output is the data stored in memory.

[0509] Step 3: Preprocessing the text data

[0510] The server performs preprocessing on the diary text data it receives. Specifically, it performs text cleaning (removing unnecessary spaces and special characters), tokenization (dividing into words and phrases), and stemming (converting words into their base forms). The input is the diary text data stored in memory, and the output is the preprocessed text data. For example, the input "I was tired from meetings all day today, but I'm happy that the project was successful" is converted into "today," "all day," "meeting," "tiring," "project," "success," and "satisfied."

[0511] Step 4: Emotion and behavioral pattern analysis

[0512] The AI ​​analysis module on the server analyzes the preprocessed text data. It uses natural language processing technology to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The input is the preprocessed text data, and the output is the identified emotion and behavioral pattern data. For example, "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)" are identified.

[0513] Step 5: Save the analysis results to a database

[0514] The server stores the identified emotion and behavior pattern data in a database. It is important to store the data in association with past data. The input is the identified emotion and behavior pattern data, and the output is the data stored in the database.

[0515] Step 6: Generate personalized feedback

[0516] The server generates user-specific feedback based on the analysis results. It is created using a generative AI model based on the prompt text. The input is the analysis results and past user data, and the output is user-specific feedback. Specifically, it might be something like, "You seem tired today, but you seem to be feeling satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow."

[0517] Step 7: Submit your feedback

[0518] The server sends the generated feedback data to the terminal, where the input is the user-specific feedback and the output is the feedback data sent to the terminal.

[0519] Step 8: Viewing feedback

[0520] The feedback received by the device is displayed to the user in a format that allows the user to confirm specific advice. The input is the feedback data sent to the device, and the output is the feedback displayed to the user. For example, it is displayed as a notification message or a pop-up window on the device.

[0521] (Application example 1)

[0522] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0523] While existing systems have the ability to analyze users' diary data to identify their emotions and behavioral patterns, they lack the ability to recommend content appropriate to the user's mood based on the results of this identification. Therefore, there was a need for a system that would not only help users deepen their self-understanding, but also allow them to enjoy appropriate content according to their daily mood.

[0524] 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.

[0525] In this invention, the server

[0526] means for receiving user diary text data;

[0527] means for analyzing the received diary text data;

[0528] means for identifying emotions and behavioral patterns based on the analyzed data;

[0529] means for generating feedback to a user based on the identified data;

[0530] means for transmitting the generated feedback;

[0531] means for recommending appropriate content to a user based on the identified emotion;

[0532] This makes it possible to recommend content that matches the user's daily emotional state.

[0533] The "means for receiving user's diary text data" is a function for transmitting diary text data entered by the user to the server via the network and receiving it.

[0534] The "means for analyzing the received diary text data" is a function for analyzing the received diary text data grammatically and semantically using natural language processing technology.

[0535] The "means for identifying emotions and behavioral patterns based on the analyzed data" is a function for identifying the emotions and behavioral patterns of a user based on information extracted from the analyzed text data.

[0536] The "means for generating feedback to the user based on the identified data" is a function for generating personalized feedback to the user based on the identified emotions and behavioral patterns.

[0537] The "means for transmitting the generated feedback" is a function for transmitting the generated feedback to the user terminal.

[0538] The "means for recommending appropriate content to the user based on the identified emotion" is a function for obtaining content such as videos and music that is appropriate for the identified emotion from an external content providing service and recommending it to the user.

[0539] To implement this invention, a server, a user terminal, and natural language processing technology are used. The following describes specific program processing and how to use it.

[0540] First, a user inputs diary text data using their own device (e.g., a smartphone). This diary text data describes the user's daily life and emotional movements, and the device then transmits this data to a server.

[0541] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes are performed using spaCy and TextBlob, natural language processing libraries specialized for text analysis.

[0542] After preprocessing, the AI ​​analysis module on the server analyzes the text data. A generative AI model is used to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The analysis results are stored in a database.

[0543] The server then generates user-specific feedback based on the identified emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Furthermore, based on the identified emotions, the server retrieves and recommends content appropriate for the user (e.g., relaxing music or mood-boosting videos) from external content providers.

[0544] The generated feedback and recommended content are sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to obtain specific guidelines for action and appropriate content.

[0545] For example, suppose a user writes in their diary, "I'm tired from meetings all day today, but I'm satisfied that the project was a success." From this text, the analysis module reads the emotions of "fatigue" and "success" and identifies that the user is tired from their daytime activities but also feels a sense of accomplishment. Based on this analysis result, the server generates feedback such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow." It also recommends content appropriate to the user's state, such as relaxing music or inspiring movie trailers.

[0546] An example of a prompt sentence input to the generative AI model is as follows:

[0547] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[0548] This invention enables personalized content recommendations that match the user's daily emotional state, thereby improving the user's quality of life.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] The user inputs diary text data using a terminal. Specifically, the user starts the application and describes their daily life and emotional movements in the text input box. The input diary text data is encoded on the terminal and sent to the server via the network.

[0552] Input: User's diary text data

[0553] Output: Encoded text data sent to the server

[0554] Step 2:

[0555] The server receives diary text data sent from user devices. Since the received data is not suitable for analysis as is, it undergoes preprocessing. Preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes use natural language processing libraries such as spaCy and TextBlob.

[0556] Input: Encoded diary text data

[0557] Output: Clean text data after preprocessing

[0558] Step 3:

[0559] The AI ​​analysis module in the server analyzes the pre-processed text data and uses a generative AI model to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) in the text. This uses natural language processing techniques, and the analysis results are stored in a database.

[0560] Input: Clean, preprocessed text data

[0561] Output: Emotion and behavior pattern identification results

[0562] Step 4:

[0563] The server generates user-specific feedback based on the results of identifying emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Based on the analysis results, the server also obtains and recommends content (videos, music, etc.) suitable for the user from external content providers.

[0564] Input: Emotion and behavior pattern identification results

[0565] Output: User-specific feedback and recommended content

[0566] Step 5:

[0567] The generated feedback and recommended content are sent from the server to the user's device, which then displays them in an intuitively understandable format. For example, the feedback might say, "You seem tired today, but you seem to be satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow," and provide links to relaxing music or videos that lift your spirits.

[0568] Input: User-specific feedback and suggested content

[0569] Output: Feedback and recommended content displayed on the user's device

[0570] For example, if a user enters "I'm tired from meetings all day today, but I'm happy that the project was a success," the server analyzes the text and generates appropriate feedback and content to provide to the user. An example of a prompt sentence in this case is as follows:

[0571] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[0572] 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.

[0573] System Overview

[0574] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to more accurately identify the user's emotional state and generate personalized feedback.

[0575] Program processing

[0576] User diary data entry and reception

[0577] First, the user inputs the text of the diary using the device. This text describes the user's daily life and emotional movements. The device then transmits the input text data to the server.

[0578] Receiving diary data and preprocessing it on the server

[0579] The server receives the diary text data sent from the device. The received data undergoes preprocessing before analysis. Preprocessing includes text cleaning, tokenization, stemming, etc.

[0580] Analysis by emotion engine

[0581] The emotion engine in the server analyzes the pre-processed text data. Using natural language processing techniques, the emotion engine identifies emotions (e.g., joy, sadness, anger, surprise) in the text. This identifies the user's emotional state based on the diary data.

[0582] Identifying emotions and behavioral patterns

[0583] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meetings" and "projects," from the user's text and stores them in a database.

[0584] Generate personalized feedback

[0585] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. This feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life.

[0586] Sending and Viewing Feedback

[0587] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0588] Example

[0589] Specific processing example

[0590] 1. User diary entry

[0591] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0592] The terminal transmits this text data to the server.

[0593] 2. Receiving and preprocessing text data on the server

[0594] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0595] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0596] Next, the words are stemmed and converted to their base forms.

[0597] 3. Analysis by Emotion Engine

[0598] The server's emotion engine analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "satisfaction (positive emotion)."

[0599] 4. Identifying Behavioral Patterns

[0600] The server identifies the behavioral patterns in the text, such as "meetings (behavioral patterns)" and "projects (behavioral patterns)," and stores them in a database along with the analysis results.

[0601] 5. Generate feedback

[0602] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend that you get some proper rest."

[0603] 6. Sending and Viewing Feedback

[0604] The server transmits the generated feedback data to the terminal.

[0605] The terminal displays the received feedback to the user, and the user receives specific advice.

[0606] In this way, we have realized a system that can provide specific and personalized feedback based on the user's diary entries.By introducing an emotion engine, we can analyze the user's emotional state more accurately and provide more appropriate feedback.

[0607] The processing flow will be explained below.

[0608] Step 1: The user uses the terminal to input the text of the diary. For example, the user might write, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0609] Step 2: The terminal prepares a data format for sending the input text data to the server, and sends the text to the server as an HTTP request.

[0610] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[0611] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[0612] Step 5: The emotion engine in the server analyzes the pre-processed text data. The emotion engine uses natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") from the text. The emotional state is identified.

[0613] Step 6: The server also identifies behavioral patterns (e.g., "meeting" or "project") in the diary text based on the analysis results of the emotion engine. The identified emotion and behavioral pattern information is stored in a database.

[0614] Step 7: The server's feedback generation module retrieves the emotion and behavior pattern identification results from the database and generates user-specific feedback. For example, it could generate feedback such as, "You seem tired today, but you feel satisfied with the success of the project. I recommend you get some proper rest and prepare for tomorrow."

[0615] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[0616] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[0617] Through this series of processes, users can deepen their self-understanding and obtain specific guidelines for action through emotion analysis and behavioral pattern identification using the engine.

[0618] Example 2

[0619] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0620] In systems that analyze users' diary text data, identify their emotions and behavioral patterns, and provide feedback, it is difficult to improve the accuracy of the analysis and provide personalized feedback. There is also a need for the feedback received by users to be displayed in an intuitive and easy-to-understand format.

[0621] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving diary text data of a user, means for pre-processing the received diary text data, means for analyzing the pre-processed diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for generating feedback to the user based on the identified data, means for transmitting the generated feedback, and means for displaying the feedback in a format that is intuitively easy for the user to understand. This enables highly accurate identification of emotions and behavioral patterns and provision of personalized feedback based on past data.

[0622] "User" refers to a person who uses this system to input diary text data and receives feedback on it.

[0623] "Diary text data" refers to text data in which a user describes events, feelings, and actions in their daily life.

[0624] "Means for receiving" refers to a function for transmitting diary text data from a terminal to a server.

[0625] "Preprocessing means" refers to processes such as cleaning, tokenization, and stemming that are carried out to prepare the received diary text data in a form that is easy to analyze.

[0626] "Means for analysis" refers to the function of classifying the contents of preprocessed diary text data into emotions and behavioral patterns using natural language processing technology.

[0627] "Emotion" refers to states such as joy, sadness, anger, surprise, etc. contained in the user's diary text data.

[0628] A "behavioral pattern" refers to the repetition of a specific behavior or event contained in the user's diary text data.

[0629] "Means for identifying" refers to the ability to extract emotion and behavioral patterns based on the analyzed data.

[0630] "Feedback" refers to advice and comments to the user that are generated based on the analysis and identification results.

[0631] "Means of generation" refers to the function of creating feedback for users by referring to past data and data of similar users.

[0632] "Means for sending" refers to the function of sending the generated feedback from the server to the terminal.

[0633] The "means for displaying" refers to a function for displaying the received feedback on the terminal in a format that is intuitively easy for the user to understand.

[0634] The present invention is a system that analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and provides feedback. A specific embodiment of this system will be described below.

[0635] First, a user inputs text data for a diary entry using their own device (e.g., smartphone or PC). For example, a user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." This text data describes the user's daily life and emotional movements. The device then sends the input diary text data to the server.

[0636] The server receives the diary text data sent from the device. The received data is preprocessed before analysis. This preprocessing includes the following steps:

[0637] Text cleaning: Remove unnecessary spaces and special characters from text.

[0638] Tokenization: Breaking text into meaningful units (words and phrases), such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0639] Stemming: Converting words into their base form. For example, converting "tired" into "tired."

[0640] After preprocessing, the text data is passed to the emotion engine on the server. This emotion engine uses natural language processing techniques to analyze the text and identify emotions. For example, the following emotions can be identified:

[0641] "Tired" -> fatigue (negative emotion)

[0642] "Success" -> positive emotions

[0643] "Satisfaction" -> positive emotions

[0644] After identifying emotions, the server then identifies behavioral patterns. This is the process of extracting specific actions or events from the text. For example, behavioral patterns such as "meeting" and "project" are extracted. This identified data is then stored in a database along with the analysis results.

[0645] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. The generated feedback is created by referring to past data and data from similar users. A specific example would be the feedback, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend you get some proper rest."

[0646] The generated feedback is sent from the server to the device, which then displays the received feedback to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0647] Example prompt sentence:

[0648] "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0649] As described above, the present invention is a system that realizes highly accurate identification of emotions and behavioral patterns and provides personalized feedback based on past data.

[0650] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0651] Step 1:

[0652] The user inputs diary text data.

[0653] Specifically, the user uses the terminal and enters the following into the text input screen: "I'm tired from meetings all day today, but I'm happy that the project was a success." This input text is sent to the server as input data for the terminal.

[0654] Step 2:

[0655] The server receives the diary text data.

[0656] Specifically, the server receives diary text data sent from the device via the network and temporarily stores it in memory. The input data is raw text data, and the output at this point is text data before preprocessing.

[0657] Step 3:

[0658] The server pre-processes the diary text data.

[0659] Specifically, the server performs text cleaning, removing unnecessary spaces and special characters. Next, it performs text tokenization, dividing the sentence into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied." Finally, it performs stemming, converting the words into their base forms. The input is raw text data, and the output is cleaned, tokenized, and stemmed text data.

[0660] Step 4:

[0661] The server analyzes the preprocessed text data using an emotion engine.

[0662] Specifically, the emotion engine uses natural language processing technology to identify emotions from preprocessed text data. For example, emotions are extracted in the form of "tired" -> fatigue (negative emotion), and "success" or "satisfied" -> positive emotion. The input is preprocessed text data, and the output is identified emotion data.

[0663] Step 5:

[0664] The server identifies behavioral patterns based on the analyzed data.

[0665] Specifically, the server extracts behavioral patterns such as "meeting" and "project" from the text. This clarifies the activities the user performed. The input is text data analyzed by the emotion engine, and the output is the identified behavioral pattern data.

[0666] Step 6:

[0667] The server generates feedback to the user.

[0668] Specifically, the server generates personalized feedback based on the analysis and identification results. It also references past data and data from similar users to create specific advice such as, "You seem tired today, but you seem to be satisfied with the success of the project. I recommend you get some proper rest." The input is the identified emotion data and behavioral pattern data, and the output is the generated feedback.

[0669] Step 7:

[0670] The server generates feedback and sends it to the device.

[0671] Specifically, the server sends the generated feedback data to the terminal via the network. The input is the generated feedback, and the output is the feedback data sent to the terminal.

[0672] Step 8:

[0673] The terminal displays the sent feedback to the user.

[0674] Specifically, the device displays the received feedback in an intuitively understandable format to the user, allowing the user to receive specific advice on their own status. The input is the transmitted feedback data, and the output is the feedback displayed to the user.

[0675] (Application example 2)

[0676] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0677] Current security services do not adequately monitor users' emotional changes and behavioral patterns, making it difficult to respond quickly to sudden emotional changes or abnormal behavioral patterns. To solve this problem and ensure users' safety and security, a system is needed that analyzes diary text data, accurately identifies emotional states and behavioral patterns, and provides feedback.

[0678] 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.

[0679] In this invention, the server includes means for receiving diary text data of a user, means for analyzing the received diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for detecting abnormal behavioral patterns or sudden changes in emotions based on the generated feedback, means for sending a notification to the user based on the detected abnormality, and means for sending the generated feedback. This makes it possible to early detect abnormal emotional changes or behavioral patterns of a user and provide appropriate notifications, thereby ensuring the safety and security of the user.

[0680] "Diary text data" refers to text data entered by a user about their daily life or the events of the day.

[0681] The "receiving means" refers to a device or program that has the function of sending the diary text data entered by the user to the server and capturing that data.

[0682] The "analyzing means" refers to a device or program that has the function of analyzing the received diary text data and extracting the emotions and behavioral patterns contained therein.

[0683] "Emotion" indicates the user's inherent psychological state, such as joy, sadness, anger, or surprise.

[0684] A "behavioral pattern" refers to a series of actions or activities that a user performs in daily life or in a specific situation.

[0685] "Feedback" refers to advice or information provided to users based on analyzed emotions and behavioral patterns.

[0686] An "abnormal behavior pattern" is a behavior that is significantly different from the user's normal behavior, and is often linked to a sudden change in emotion.

[0687] A "sudden change in emotion" refers to a large change in the emotional state of a user analyzed from the diary text data in a short period of time.

[0688] The "means for sending a notification" is a device or program that has the function of sending a notification to a user or administrator based on the analysis results.

[0689] System Overview

[0690] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to identify the user's emotional state with greater accuracy, provide personalized feedback, and detect abnormalities.

[0691] Program processing

[0692] User diary data entry and reception

[0693] The user inputs diary text using a smartphone, and the input text data is sent to a server via a dedicated application.

[0694] Receiving diary data and preprocessing it on the server

[0695] The server receives the diary text data sent from the device and performs preprocessing on the received data, which includes text cleaning, tokenization, stemming, etc.

[0696] Analysis by emotion engine

[0697] The emotion engine in the server analyzes the preprocessed text data and uses natural language processing (NLP) techniques to identify emotions (such as joy, sadness, anger, and surprise) in the text. Specifically, it uses the Hugging Face Transformers library to accurately identify emotional states.

[0698] Identifying emotions and behavioral patterns

[0699] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meeting" or "project" in the text, and stores them in a database.

[0700] Generate personalized feedback

[0701] The server generates user-specific feedback based on the emotion engine's analysis results and behavioral pattern identification. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates appropriate notifications. For example, it creates specific advice such as, "You seem to be feeling stressed today. We recommend you take a rest."

[0702] Sending and Viewing Feedback

[0703] The generated feedback is sent from the server to the terminal, which displays the feedback to the user and also sends notifications to the user based on the detected anomalies.

[0704] Specific examples

[0705] 1. User diary entry

[0706] The user types, "I've been feeling very stressed today. Some things haven't gone as planned and I'm frustrated."

[0707] The terminal transmits this text data to the server.

[0708] 2. Receiving and preprocessing text data on the server

[0709] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0710] For example, the text is tokenized and divided into words such as "today," "stress," "work," "not progressing," and "frustrated."

[0711] Next, the words are stemmed and converted to their base forms.

[0712] 3. Analysis by Emotion Engine

[0713] The server's emotion engine analyzes the text and identifies "high stress" and "medium irritation."

[0714] 4. Identifying Behavioral Patterns

[0715] The server identifies the behavioral pattern of the text, "High Work," and stores it in a database along with the analysis results.

[0716] 5. Generate feedback

[0717] Based on the analysis results, the server generates specific advice such as, "You seem to be feeling stressed today, so we recommend that you take a rest."

[0718] If an anomaly is detected, generate a notification saying "An abnormal behavior pattern has been detected. Attention required."

[0719] 6. Sending and Viewing Feedback

[0720] The server sends the generated feedback data and notification to the terminal.

[0721] The device displays the received feedback and notifications to the user.

[0722] Prompt Sentence Examples

[0723] Below are some example prompts for generative AI models:

[0724] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[0725] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[0726] Emotion analysis:

[0727] Stress: High

[0728] Irritation: Medium

[0729] Behavior Pattern:

[0730] Work: High

[0731] Assess the risk level and generate feedback.”

[0732] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0733] Step 1:

[0734] User diary data entry

[0735] A user inputs diary text using a smartphone. The input text data is sent to a server via a dedicated application. This text data describes the user's daily life and emotional movements.

[0736] Step 2:

[0737] Receiving diary text data

[0738] The server receives the diary text data sent from the terminal. At this stage, the input data itself is stored in a specified memory area of ​​the server. The input is the diary text data, and the output is the received text data.

[0739] Step 3:

[0740] Preprocessing text data

[0741] The server performs preprocessing on the received text data, including cleaning, tokenization, and stemming. Cleaning removes unnecessary special characters and noise, tokenization divides the data into words, and stemming converts words into their base forms. The input is the received text data, and the output is the preprocessed text data.

[0742] Step 4:

[0743] Analysis by emotion engine

[0744] The emotion engine in the server analyzes the preprocessed text data. It uses natural language processing techniques (e.g., Hugging Face's Transformers library) to identify the emotions contained in the text (e.g., "stress," "joy," etc.). The input is the preprocessed text data, and the output is the emotion analysis results.

[0745] Step 5:

[0746] Identifying behavioral patterns

[0747] In addition to analyzing sentiment, the server also identifies behavioral patterns within the text. This identification is done by the occurrence of specific keywords (e.g., "meeting," "project," etc.). The input is the preprocessed text data, and the output is the behavioral pattern identification results.

[0748] Step 6:

[0749] Data storage

[0750] The server stores the emotion analysis results and behavioral pattern identification results in a database. This storage process accumulates the user's diary data as past data and can be used for future analysis. The input is the emotion analysis results and behavioral pattern identification results, and the output is the data stored in the database.

[0751] Step 7:

[0752] Generate feedback

[0753] The server generates feedback for the user based on the emotion analysis results and behavioral pattern identification results. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates an appropriate notification. The input is the emotion analysis results and behavioral pattern identification results, and the output is the generated feedback message and notification.

[0754] Step 8:

[0755] Sending feedback and notifications

[0756] The server sends the generated feedback and notifications to the user's terminal. The terminal displays the received feedback and notifications to the user. The input is the generated feedback message and notification, and the output is the feedback and notification displayed on the terminal.

[0757] Specifically, the generative AI model is given a prompt like the one below, which is then analyzed and feedback is generated:

[0758] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[0759] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[0760] Emotion analysis:

[0761] Stress: High

[0762] Irritation: Medium

[0763] Behavior Pattern:

[0764] Work: High

[0765] Assess the risk level and generate feedback.”

[0766] 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.

[0767] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0768] 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.

[0769] [Third embodiment]

[0770] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0771] 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.

[0772] 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).

[0773] 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.

[0774] 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.

[0775] 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).

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0782] System Overview

[0783] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[0784] Program processing

[0785] User diary data entry and reception

[0786] First, the user inputs the text of the diary using the terminal. This text describes the user's daily life and emotional movements. The terminal then transmits this text data to the server.

[0787] Receiving diary data and preprocessing it on the server

[0788] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms).

[0789] Emotion and behavioral pattern analysis

[0790] The AI ​​analysis module in the server analyzes the preprocessed text data. The analysis is carried out using natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) in the text. The results of this identification are stored in a database.

[0791] Generate personalized feedback

[0792] The server generates user-specific feedback based on the analysis results. This feedback generation module also takes into account past data and data from similar users to create specific advice to improve the user's daily life.

[0793] Sending and Viewing Feedback

[0794] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0795] Example

[0796] Specific processing example

[0797] 1. User diary entry

[0798] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0799] The terminal transmits this text data to the server.

[0800] 2. Receiving and preprocessing text data on the server

[0801] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0802] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0803] Next, the words are stemmed and converted to their base forms.

[0804] 3. Conducting the analysis

[0805] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[0806] The server stores these identification results in a database.

[0807] 4. Generate feedback

[0808] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[0809] 5. Sending and Viewing Feedback

[0810] The server transmits the generated feedback data to the terminal.

[0811] The terminal displays the received feedback to the user, and the user receives specific advice.

[0812] In this way, we have realized a system that can provide specific and personalized feedback from users' diary entries.

[0813] The processing flow will be explained below.

[0814] Step 1: The user uses the terminal to input the text of the diary. In the input form, the user writes, "I'm tired from meetings all day today, but I'm happy that the project was successful."

[0815] Step 2: The terminal prepares a data format for sending the input text data to the server. The terminal sends the text to the server as an HTTP request.

[0816] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[0817] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[0818] Step 5: The server's AI analysis module analyzes the preprocessed text, using natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") and behavioral patterns (e.g., "meeting," "project") within the text.

[0819] Step 6: The server stores the analysis results in a database, including tagging information for identified emotions and behavioral patterns.

[0820] Step 7: The server's feedback generation module retrieves the analysis results from the database and generates user-specific feedback, such as "You seem tired today, but you seem to be satisfied with your work success. We recommend that you take adequate rest and prepare for tomorrow."

[0821] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[0822] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[0823] Through this series of processes, the user can deepen their self-understanding and obtain specific guidelines for action.

[0824] Example 1

[0825] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0826] Conventional systems have had difficulty efficiently analyzing users' diary text data and providing personalized feedback. Furthermore, due to low accuracy in preprocessing and analysis, they were unable to accurately identify users' emotions and behavioral patterns. Furthermore, there was no established method for utilizing the analysis results to generate appropriate feedback and provide it to users. Therefore, there was a need to build a system that would deepen users' self-understanding and provide them with specific guidelines for action.

[0827] 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.

[0828] In this invention, the server includes means for receiving a user's diary text data, means for preprocessing the received diary text data by cleaning, tokenizing, and stemming, means for analyzing the preprocessed diary text data using natural language processing technology, means for identifying emotions and behavioral patterns based on the analyzed data, means for storing the identified data in a database, means for generating user-specific feedback based on the stored data and past data, means for transmitting the generated feedback to the user's terminal, and means for displaying the transmitted feedback to the user. This makes it possible to provide highly accurate and personalized feedback based on the user's diary content.

[0829] "User" refers to a person who uses the system to enter diary text data.

[0830] "Terminal" refers to a device that allows a user to input diary text data and send it to the server.

[0831] "Server" refers to the computer system that processes, analyzes, and stores received diary text data, and generates and transmits feedback.

[0832] "Diary text data" refers to text information entered by a user about their daily life and emotions.

[0833] "Preprocessing" refers to the process of converting text data into a format that is easy to analyze by performing processes such as cleaning, tokenization, and stemming on the data.

[0834] "Cleaning" refers to the process of removing unnecessary spaces and special characters from diary text data.

[0835] "Tokenization" refers to the process of dividing diary text data into words or phrases.

[0836] "Stemming" refers to the process of converting words into their base forms.

[0837] "Natural language processing technology" refers to technology for analyzing text data and identifying meaning and emotion.

[0838] "Analysis" refers to the process of identifying sentiment and behavioral patterns from preprocessed text data.

[0839] "Emotion" refers to the user's psychological state, such as joy, sadness, or anger, contained in the text data.

[0840] "Behavioral pattern" refers to elements in text data that identify user activities or behaviors (e.g., work, rest).

[0841] "Identification" refers to the process of identifying specific emotions or behavioral patterns from the analysis results.

[0842] "Database" refers to the digital storage for identifying emotions and behavioral patterns and other related data.

[0843] "Feedback" refers to specific advice or guidelines for users that are generated based on the analysis results.

[0844] "Generation" refers to the process of creating feedback based on data stored in a database or past data.

[0845] "Send" refers to the act of transferring the generated feedback from the server to the user's terminal.

[0846] "Display" refers to the act of visually showing the submitted feedback on the user's terminal.

[0847] System Overview

[0848] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[0849] Program processing

[0850] User diary data entry and reception

[0851] The user inputs text for the diary using a terminal. This text includes information about the user's daily life and emotions. The terminal then transmits this text data to a server. Any text input device or smartphone can be used as the hardware.

[0852] Receiving diary data and preprocessing it on the server

[0853] The server receives the diary text data sent from the device. As the received data is not suitable for analysis as is, it undergoes preprocessing. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). Preprocessing prepares the data in a format that is easy to analyze. Specific text processing libraries that are introduced include Python NLP libraries (e.g., NLTK and spaCy).

[0854] Emotion and behavioral pattern analysis

[0855] The AI ​​analysis module in the server analyzes the preprocessed text data. This analysis uses natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) within the text. Generative AI models used include the BERT and GPT series models, for example. The analysis results are stored in a database and accumulated as each user's historical data.

[0856] Generate personalized feedback

[0857] The server generates user-specific feedback based on the analysis results. This feedback generation module references the user's own past data and data from similar users to create specific advice to improve the user's daily life. Advanced natural language generation is made possible by inputting prompt sentences into the generative AI model.

[0858] Sending and Viewing Feedback

[0859] The generated feedback is sent from the server to the device. The device displays this feedback to the user in a format that is intuitively easy to understand. This allows the user to deepen their self-understanding and obtain specific guidelines for action. Notification messages, pop-up windows, and other display formats are used.

[0860] Specific examples

[0861] 1. User diary entry

[0862] The user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0863] The terminal transmits this text data to the server.

[0864] 2. Receiving and preprocessing text data on the server

[0865] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0866] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0867] Next, the words are stemmed and converted to their base forms.

[0868] 3. Conducting the analysis

[0869] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[0870] The server stores these identification results in a database.

[0871] 4. Generate feedback

[0872] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[0873] 5. Sending and Viewing Feedback

[0874] The server transmits the generated feedback data to the terminal.

[0875] The terminal displays the received feedback to the user, and the user receives specific advice.

[0876] In this way, a system is realized that provides specific and personalized feedback based on the contents of a user's diary.

[0877] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0878] Step 1: Enter and submit user diary data

[0879] A user inputs diary text into a terminal. For example, the user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." The input text data is sent by the terminal to the server. The input here is the user's diary text data, and the output is the text data sent to the server.

[0880] Step 2: Receiving diary data on the server

[0881] The server receives the diary text data sent from the terminal. The received data is temporarily stored in memory. The input here is the diary text data sent from the terminal, and the output is the data stored in memory.

[0882] Step 3: Preprocessing the text data

[0883] The server performs preprocessing on the diary text data it receives. Specifically, it performs text cleaning (removing unnecessary spaces and special characters), tokenization (dividing into words and phrases), and stemming (converting words into their base forms). The input is the diary text data stored in memory, and the output is the preprocessed text data. For example, the input "I was tired from meetings all day today, but I'm happy that the project was successful" is converted into "today," "all day," "meeting," "tiring," "project," "success," and "satisfied."

[0884] Step 4: Emotion and behavioral pattern analysis

[0885] The AI ​​analysis module on the server analyzes the preprocessed text data. It uses natural language processing technology to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The input is the preprocessed text data, and the output is the identified emotion and behavioral pattern data. For example, "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)" are identified.

[0886] Step 5: Save the analysis results to a database

[0887] The server stores the identified emotion and behavior pattern data in a database. It is important to store the data in association with past data. The input is the identified emotion and behavior pattern data, and the output is the data stored in the database.

[0888] Step 6: Generate personalized feedback

[0889] The server generates user-specific feedback based on the analysis results. It is created using a generative AI model based on the prompt text. The input is the analysis results and past user data, and the output is user-specific feedback. Specifically, it might be something like, "You seem tired today, but you seem to be feeling satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow."

[0890] Step 7: Submit your feedback

[0891] The server sends the generated feedback data to the terminal, where the input is the user-specific feedback and the output is the feedback data sent to the terminal.

[0892] Step 8: Viewing feedback

[0893] The feedback received by the device is displayed to the user in a format that allows the user to confirm specific advice. The input is the feedback data sent to the device, and the output is the feedback displayed to the user. For example, it is displayed as a notification message or a pop-up window on the device.

[0894] (Application example 1)

[0895] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0896] While existing systems have the ability to analyze users' diary data to identify their emotions and behavioral patterns, they lack the ability to recommend content appropriate to the user's mood based on the results of this identification. Therefore, there was a need for a system that would not only help users deepen their self-understanding, but also allow them to enjoy appropriate content according to their daily mood.

[0897] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0898] In this invention, the server

[0899] means for receiving user diary text data;

[0900] means for analyzing the received diary text data;

[0901] means for identifying emotions and behavioral patterns based on the analyzed data;

[0902] means for generating feedback to a user based on the identified data;

[0903] means for transmitting the generated feedback;

[0904] means for recommending appropriate content to a user based on the identified emotion;

[0905] This makes it possible to recommend content that matches the user's daily emotional state.

[0906] The "means for receiving user's diary text data" is a function for transmitting diary text data entered by the user to the server via the network and receiving it.

[0907] The "means for analyzing the received diary text data" is a function for analyzing the received diary text data grammatically and semantically using natural language processing technology.

[0908] The "means for identifying emotions and behavioral patterns based on the analyzed data" is a function for identifying the emotions and behavioral patterns of a user based on information extracted from the analyzed text data.

[0909] The "means for generating feedback to the user based on the identified data" is a function for generating personalized feedback to the user based on the identified emotions and behavioral patterns.

[0910] The "means for transmitting the generated feedback" is a function for transmitting the generated feedback to the user terminal.

[0911] The "means for recommending appropriate content to the user based on the identified emotion" is a function for obtaining content such as videos and music that is appropriate for the identified emotion from an external content providing service and recommending it to the user.

[0912] To implement this invention, a server, a user terminal, and natural language processing technology are used. The following describes specific program processing and how to use it.

[0913] First, a user inputs diary text data using their own device (e.g., a smartphone). This diary text data describes the user's daily life and emotional movements, and the device then transmits this data to a server.

[0914] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes are performed using spaCy and TextBlob, natural language processing libraries specialized for text analysis.

[0915] After preprocessing, the AI ​​analysis module on the server analyzes the text data. A generative AI model is used to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The analysis results are stored in a database.

[0916] The server then generates user-specific feedback based on the identified emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Furthermore, based on the identified emotions, the server retrieves and recommends content appropriate for the user (e.g., relaxing music or mood-boosting videos) from external content providers.

[0917] The generated feedback and recommended content are sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to obtain specific guidelines for action and appropriate content.

[0918] For example, suppose a user writes in their diary, "I'm tired from meetings all day today, but I'm satisfied that the project was a success." From this text, the analysis module reads the emotions of "fatigue" and "success" and identifies that the user is tired from their daytime activities but also feels a sense of accomplishment. Based on this analysis result, the server generates feedback such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow." It also recommends content appropriate to the user's state, such as relaxing music or inspiring movie trailers.

[0919] An example of a prompt sentence input to the generative AI model is as follows:

[0920] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[0921] This invention enables personalized content recommendations that match the user's daily emotional state, thereby improving the user's quality of life.

[0922] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0923] Step 1:

[0924] The user inputs diary text data using a terminal. Specifically, the user starts the application and describes their daily life and emotional movements in the text input box. The input diary text data is encoded on the terminal and sent to the server via the network.

[0925] Input: User's diary text data

[0926] Output: Encoded text data sent to the server

[0927] Step 2:

[0928] The server receives diary text data sent from user devices. Since the received data is not suitable for analysis as is, it undergoes preprocessing. Preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes use natural language processing libraries such as spaCy and TextBlob.

[0929] Input: Encoded diary text data

[0930] Output: Clean text data after preprocessing

[0931] Step 3:

[0932] The AI ​​analysis module in the server analyzes the pre-processed text data and uses a generative AI model to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) in the text. This uses natural language processing techniques, and the analysis results are stored in a database.

[0933] Input: Clean, preprocessed text data

[0934] Output: Emotion and behavior pattern identification results

[0935] Step 4:

[0936] The server generates user-specific feedback based on the results of identifying emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Based on the analysis results, the server also obtains and recommends content (videos, music, etc.) suitable for the user from external content providers.

[0937] Input: Emotion and behavior pattern identification results

[0938] Output: User-specific feedback and recommended content

[0939] Step 5:

[0940] The generated feedback and recommended content are sent from the server to the user's device, which then displays them in an intuitively understandable format. For example, the feedback might say, "You seem tired today, but you seem to be satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow," and provide links to relaxing music or videos that lift your spirits.

[0941] Input: User-specific feedback and suggested content

[0942] Output: Feedback and recommended content displayed on the user's device

[0943] For example, if a user enters "I'm tired from meetings all day today, but I'm happy that the project was a success," the server analyzes the text and generates appropriate feedback and content to provide to the user. An example of a prompt sentence in this case is as follows:

[0944] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[0945] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0946] System Overview

[0947] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to more accurately identify the user's emotional state and generate personalized feedback.

[0948] Program processing

[0949] User diary data entry and reception

[0950] First, the user inputs the text of the diary using the device. This text describes the user's daily life and emotional movements. The device then transmits the input text data to the server.

[0951] Receiving diary data and preprocessing it on the server

[0952] The server receives the diary text data sent from the device. The received data undergoes preprocessing before analysis. Preprocessing includes text cleaning, tokenization, stemming, etc.

[0953] Analysis by emotion engine

[0954] The emotion engine in the server analyzes the pre-processed text data. Using natural language processing techniques, the emotion engine identifies emotions (e.g., joy, sadness, anger, surprise) in the text. This identifies the user's emotional state based on the diary data.

[0955] Identifying emotions and behavioral patterns

[0956] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meetings" and "projects," from the user's text and stores them in a database.

[0957] Generate personalized feedback

[0958] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. This feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life.

[0959] Sending and Viewing Feedback

[0960] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[0961] Example

[0962] Specific processing example

[0963] 1. User diary entry

[0964] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0965] The terminal transmits this text data to the server.

[0966] 2. Receiving and preprocessing text data on the server

[0967] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[0968] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[0969] Next, the words are stemmed and converted to their base forms.

[0970] 3. Analysis by Emotion Engine

[0971] The server's emotion engine analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "satisfaction (positive emotion)."

[0972] 4. Identifying Behavioral Patterns

[0973] The server identifies the behavioral patterns in the text, such as "meetings (behavioral patterns)" and "projects (behavioral patterns)," and stores them in a database along with the analysis results.

[0974] 5. Generate feedback

[0975] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend that you get some proper rest."

[0976] 6. Sending and Viewing Feedback

[0977] The server transmits the generated feedback data to the terminal.

[0978] The terminal displays the received feedback to the user, and the user receives specific advice.

[0979] In this way, we have realized a system that can provide specific and personalized feedback based on the user's diary entries.By introducing an emotion engine, we can analyze the user's emotional state more accurately and provide more appropriate feedback.

[0980] The processing flow will be explained below.

[0981] Step 1: The user uses the terminal to input the text of the diary. For example, the user might write, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[0982] Step 2: The terminal prepares a data format for sending the input text data to the server, and sends the text to the server as an HTTP request.

[0983] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[0984] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[0985] Step 5: The emotion engine in the server analyzes the pre-processed text data. The emotion engine uses natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") from the text. The emotional state is identified.

[0986] Step 6: The server also identifies behavioral patterns (e.g., "meeting" or "project") in the diary text based on the analysis results of the emotion engine. The identified emotion and behavioral pattern information is stored in a database.

[0987] Step 7: The server's feedback generation module retrieves the emotion and behavior pattern identification results from the database and generates user-specific feedback. For example, it could generate feedback such as, "You seem tired today, but you feel satisfied with the success of the project. I recommend you get some proper rest and prepare for tomorrow."

[0988] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[0989] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[0990] Through this series of processes, users can deepen their self-understanding and obtain specific guidelines for action through emotion analysis and behavioral pattern identification using the engine.

[0991] Example 2

[0992] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0993] In systems that analyze users' diary text data, identify their emotions and behavioral patterns, and provide feedback, it is difficult to improve the accuracy of the analysis and provide personalized feedback. There is also a need for the feedback received by users to be displayed in an intuitive and easy-to-understand format.

[0994] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving diary text data of a user, means for pre-processing the received diary text data, means for analyzing the pre-processed diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for generating feedback to the user based on the identified data, means for transmitting the generated feedback, and means for displaying the feedback in a format that is intuitively easy for the user to understand. This enables highly accurate identification of emotions and behavioral patterns and provision of personalized feedback based on past data.

[0995] "User" refers to a person who uses this system to input diary text data and receives feedback on it.

[0996] "Diary text data" refers to text data in which a user describes events, feelings, and actions in their daily life.

[0997] "Means for receiving" refers to a function for transmitting diary text data from a terminal to a server.

[0998] "Preprocessing means" refers to processes such as cleaning, tokenization, and stemming that are carried out to prepare the received diary text data in a form that is easy to analyze.

[0999] "Means for analysis" refers to the function of classifying the contents of preprocessed diary text data into emotions and behavioral patterns using natural language processing technology.

[1000] "Emotion" refers to states such as joy, sadness, anger, surprise, etc. contained in the user's diary text data.

[1001] A "behavioral pattern" refers to the repetition of a specific behavior or event contained in the user's diary text data.

[1002] "Means for identifying" refers to the ability to extract emotion and behavioral patterns based on the analyzed data.

[1003] "Feedback" refers to advice and comments to the user that are generated based on the analysis and identification results.

[1004] "Means of generation" refers to the function of creating feedback for users by referring to past data and data of similar users.

[1005] "Means for sending" refers to the function of sending the generated feedback from the server to the terminal.

[1006] The "means for displaying" refers to a function for displaying the received feedback on the terminal in a format that is intuitively easy for the user to understand.

[1007] The present invention is a system that analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and provides feedback. A specific embodiment of this system will be described below.

[1008] First, a user inputs text data for a diary entry using their own device (e.g., smartphone or PC). For example, a user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." This text data describes the user's daily life and emotional movements. The device then sends the input diary text data to the server.

[1009] The server receives the diary text data sent from the device. The received data is preprocessed before analysis. This preprocessing includes the following steps:

[1010] Text cleaning: Remove unnecessary spaces and special characters from text.

[1011] Tokenization: Breaking text into meaningful units (words and phrases), such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[1012] Stemming: Converting words into their base form. For example, converting "tired" into "tired."

[1013] After preprocessing, the text data is passed to the emotion engine on the server. This emotion engine uses natural language processing techniques to analyze the text and identify emotions. For example, the following emotions can be identified:

[1014] "Tired" -> fatigue (negative emotion)

[1015] "Success" -> positive emotions

[1016] "Satisfaction" -> positive emotions

[1017] After identifying emotions, the server then identifies behavioral patterns. This is the process of extracting specific actions or events from the text. For example, behavioral patterns such as "meeting" and "project" are extracted. This identified data is then stored in a database along with the analysis results.

[1018] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. The generated feedback is created by referring to past data and data from similar users. A specific example would be the feedback, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend you get some proper rest."

[1019] The generated feedback is sent from the server to the device, which then displays the received feedback to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[1020] Example prompt sentence:

[1021] "I'm tired from meetings all day today, but I'm happy that the project was a success."

[1022] As described above, the present invention is a system that realizes highly accurate identification of emotions and behavioral patterns and provides personalized feedback based on past data.

[1023] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] The user inputs diary text data.

[1026] Specifically, the user uses the terminal and enters the following into the text input screen: "I'm tired from meetings all day today, but I'm happy that the project was a success." This input text is sent to the server as input data for the terminal.

[1027] Step 2:

[1028] The server receives the diary text data.

[1029] Specifically, the server receives diary text data sent from the device via the network and temporarily stores it in memory. The input data is raw text data, and the output at this point is text data before preprocessing.

[1030] Step 3:

[1031] The server pre-processes the diary text data.

[1032] Specifically, the server performs text cleaning, removing unnecessary spaces and special characters. Next, it performs text tokenization, dividing the sentence into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied." Finally, it performs stemming, converting the words into their base forms. The input is raw text data, and the output is cleaned, tokenized, and stemmed text data.

[1033] Step 4:

[1034] The server analyzes the preprocessed text data using an emotion engine.

[1035] Specifically, the emotion engine uses natural language processing technology to identify emotions from preprocessed text data. For example, emotions are extracted in the form of "tired" -> fatigue (negative emotion), and "success" or "satisfied" -> positive emotion. The input is preprocessed text data, and the output is identified emotion data.

[1036] Step 5:

[1037] The server identifies behavioral patterns based on the analyzed data.

[1038] Specifically, the server extracts behavioral patterns such as "meeting" and "project" from the text. This clarifies the activities the user performed. The input is text data analyzed by the emotion engine, and the output is the identified behavioral pattern data.

[1039] Step 6:

[1040] The server generates feedback to the user.

[1041] Specifically, the server generates personalized feedback based on the analysis and identification results. It also references past data and data from similar users to create specific advice such as, "You seem tired today, but you seem to be satisfied with the success of the project. I recommend you get some proper rest." The input is the identified emotion data and behavioral pattern data, and the output is the generated feedback.

[1042] Step 7:

[1043] The server generates feedback and sends it to the device.

[1044] Specifically, the server sends the generated feedback data to the terminal via the network. The input is the generated feedback, and the output is the feedback data sent to the terminal.

[1045] Step 8:

[1046] The terminal displays the sent feedback to the user.

[1047] Specifically, the device displays the received feedback in an intuitively understandable format to the user, allowing the user to receive specific advice on their own status. The input is the transmitted feedback data, and the output is the feedback displayed to the user.

[1048] (Application example 2)

[1049] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1050] Current security services do not adequately monitor users' emotional changes and behavioral patterns, making it difficult to respond quickly to sudden emotional changes or abnormal behavioral patterns. To solve this problem and ensure users' safety and security, a system is needed that analyzes diary text data, accurately identifies emotional states and behavioral patterns, and provides feedback.

[1051] 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.

[1052] In this invention, the server includes means for receiving diary text data of a user, means for analyzing the received diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for detecting abnormal behavioral patterns or sudden changes in emotions based on the generated feedback, means for sending a notification to the user based on the detected abnormality, and means for sending the generated feedback. This makes it possible to early detect abnormal emotional changes or behavioral patterns of a user and provide appropriate notifications, thereby ensuring the safety and security of the user.

[1053] "Diary text data" refers to text data entered by a user about their daily life or the events of the day.

[1054] The "receiving means" refers to a device or program that has the function of sending the diary text data entered by the user to the server and capturing that data.

[1055] The "analyzing means" refers to a device or program that has the function of analyzing the received diary text data and extracting the emotions and behavioral patterns contained therein.

[1056] "Emotion" indicates the user's inherent psychological state, such as joy, sadness, anger, or surprise.

[1057] A "behavioral pattern" refers to a series of actions or activities that a user performs in daily life or in a specific situation.

[1058] "Feedback" refers to advice or information provided to users based on analyzed emotions and behavioral patterns.

[1059] An "abnormal behavior pattern" is a behavior that is significantly different from the user's normal behavior, and is often linked to a sudden change in emotion.

[1060] A "sudden change in emotion" refers to a large change in the emotional state of a user analyzed from the diary text data in a short period of time.

[1061] The "means for sending a notification" is a device or program that has the function of sending a notification to a user or administrator based on the analysis results.

[1062] System Overview

[1063] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to identify the user's emotional state with greater accuracy, provide personalized feedback, and detect abnormalities.

[1064] Program processing

[1065] User diary data entry and reception

[1066] The user inputs diary text using a smartphone, and the input text data is sent to a server via a dedicated application.

[1067] Receiving diary data and preprocessing it on the server

[1068] The server receives the diary text data sent from the device and performs preprocessing on the received data, which includes text cleaning, tokenization, stemming, etc.

[1069] Analysis by emotion engine

[1070] The emotion engine in the server analyzes the preprocessed text data and uses natural language processing (NLP) techniques to identify emotions (such as joy, sadness, anger, and surprise) in the text. Specifically, it uses the Hugging Face Transformers library to accurately identify emotional states.

[1071] Identifying emotions and behavioral patterns

[1072] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meeting" or "project" in the text, and stores them in a database.

[1073] Generate personalized feedback

[1074] The server generates user-specific feedback based on the emotion engine's analysis results and behavioral pattern identification. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates appropriate notifications. For example, it creates specific advice such as, "You seem to be feeling stressed today. We recommend you take a rest."

[1075] Sending and Viewing Feedback

[1076] The generated feedback is sent from the server to the terminal, which displays the feedback to the user and also sends notifications to the user based on the detected anomalies.

[1077] Specific examples

[1078] 1. User diary entry

[1079] The user types, "I've been feeling very stressed today. Some things haven't gone as planned and I'm frustrated."

[1080] The terminal transmits this text data to the server.

[1081] 2. Receiving and preprocessing text data on the server

[1082] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[1083] For example, the text is tokenized and divided into words such as "today," "stress," "work," "not progressing," and "frustrated."

[1084] Next, the words are stemmed and converted to their base forms.

[1085] 3. Analysis by Emotion Engine

[1086] The server's emotion engine analyzes the text and identifies "high stress" and "medium irritation."

[1087] 4. Identifying Behavioral Patterns

[1088] The server identifies the behavioral pattern of the text, "High Work," and stores it in a database along with the analysis results.

[1089] 5. Generate feedback

[1090] Based on the analysis results, the server generates specific advice such as, "You seem to be feeling stressed today, so we recommend that you take a rest."

[1091] If an anomaly is detected, generate a notification saying "An abnormal behavior pattern has been detected. Attention required."

[1092] 6. Sending and Viewing Feedback

[1093] The server sends the generated feedback data and notification to the terminal.

[1094] The device displays the received feedback and notifications to the user.

[1095] Prompt Sentence Examples

[1096] Below are some example prompts for generative AI models:

[1097] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[1098] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[1099] Emotion analysis:

[1100] Stress: High

[1101] Irritation: Medium

[1102] Behavior Pattern:

[1103] Work: High

[1104] Assess the risk level and generate feedback.”

[1105] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1106] Step 1:

[1107] User diary data entry

[1108] A user inputs diary text using a smartphone. The input text data is sent to a server via a dedicated application. This text data describes the user's daily life and emotional movements.

[1109] Step 2:

[1110] Receiving diary text data

[1111] The server receives the diary text data sent from the terminal. At this stage, the input data itself is stored in a specified memory area of ​​the server. The input is the diary text data, and the output is the received text data.

[1112] Step 3:

[1113] Preprocessing text data

[1114] The server performs preprocessing on the received text data, including cleaning, tokenization, and stemming. Cleaning removes unnecessary special characters and noise, tokenization divides the data into words, and stemming converts words into their base forms. The input is the received text data, and the output is the preprocessed text data.

[1115] Step 4:

[1116] Analysis by emotion engine

[1117] The emotion engine in the server analyzes the preprocessed text data. It uses natural language processing techniques (e.g., Hugging Face's Transformers library) to identify the emotions contained in the text (e.g., "stress," "joy," etc.). The input is the preprocessed text data, and the output is the emotion analysis results.

[1118] Step 5:

[1119] Identifying behavioral patterns

[1120] In addition to analyzing sentiment, the server also identifies behavioral patterns within the text. This identification is done by the occurrence of specific keywords (e.g., "meeting," "project," etc.). The input is the preprocessed text data, and the output is the behavioral pattern identification results.

[1121] Step 6:

[1122] Data storage

[1123] The server stores the emotion analysis results and behavioral pattern identification results in a database. This storage process accumulates the user's diary data as past data and can be used for future analysis. The input is the emotion analysis results and behavioral pattern identification results, and the output is the data stored in the database.

[1124] Step 7:

[1125] Generate feedback

[1126] The server generates feedback for the user based on the emotion analysis results and behavioral pattern identification results. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates an appropriate notification. The input is the emotion analysis results and behavioral pattern identification results, and the output is the generated feedback message and notification.

[1127] Step 8:

[1128] Sending feedback and notifications

[1129] The server sends the generated feedback and notifications to the user's terminal. The terminal displays the received feedback and notifications to the user. The input is the generated feedback message and notification, and the output is the feedback and notification displayed on the terminal.

[1130] Specifically, the generative AI model is given a prompt like the one below, which is then analyzed and feedback is generated:

[1131] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[1132] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[1133] Emotion analysis:

[1134] Stress: High

[1135] Irritation: Medium

[1136] Behavior Pattern:

[1137] Work: High

[1138] Assess the risk level and generate feedback.”

[1139] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1140] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1141] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1142] [Fourth embodiment]

[1143] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1144] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1145] 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).

[1146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1147] 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.

[1148] 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).

[1149] 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.

[1150] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1151] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1152] 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.

[1153] 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.

[1154] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1155] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1156] System Overview

[1157] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[1158] Program processing

[1159] User diary data entry and reception

[1160] First, the user inputs the text of the diary using the terminal. This text describes the user's daily life and emotional movements. The terminal then transmits this text data to the server.

[1161] Receiving diary data and preprocessing it on the server

[1162] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms).

[1163] Emotion and behavioral pattern analysis

[1164] The AI ​​analysis module in the server analyzes the preprocessed text data. The analysis is carried out using natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) in the text. The results of this identification are stored in a database.

[1165] Generate personalized feedback

[1166] The server generates user-specific feedback based on the analysis results. This feedback generation module also takes into account past data and data from similar users to create specific advice to improve the user's daily life.

[1167] Sending and Viewing Feedback

[1168] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[1169] Example

[1170] Specific processing example

[1171] 1. User diary entry

[1172] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[1173] The terminal transmits this text data to the server.

[1174] 2. Receiving and preprocessing text data on the server

[1175] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[1176] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[1177] Next, the words are stemmed and converted to their base forms.

[1178] 3. Conducting the analysis

[1179] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[1180] The server stores these identification results in a database.

[1181] 4. Generate feedback

[1182] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[1183] 5. Sending and Viewing Feedback

[1184] The server transmits the generated feedback data to the terminal.

[1185] The terminal displays the received feedback to the user, and the user receives specific advice.

[1186] In this way, we have realized a system that can provide specific and personalized feedback from users' diary entries.

[1187] The processing flow will be explained below.

[1188] Step 1: The user uses the terminal to input the text of the diary. In the input form, the user writes, "I'm tired from meetings all day today, but I'm happy that the project was successful."

[1189] Step 2: The terminal prepares a data format for sending the input text data to the server. The terminal sends the text to the server as an HTTP request.

[1190] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[1191] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[1192] Step 5: The server's AI analysis module analyzes the preprocessed text, using natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") and behavioral patterns (e.g., "meeting," "project") within the text.

[1193] Step 6: The server stores the analysis results in a database, including tagging information for identified emotions and behavioral patterns.

[1194] Step 7: The server's feedback generation module retrieves the analysis results from the database and generates user-specific feedback, such as "You seem tired today, but you seem to be satisfied with your work success. We recommend that you take adequate rest and prepare for tomorrow."

[1195] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[1196] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[1197] Through this series of processes, the user can deepen their self-understanding and obtain specific guidelines for action.

[1198] Example 1

[1199] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1200] Conventional systems have had difficulty efficiently analyzing users' diary text data and providing personalized feedback. Furthermore, due to low accuracy in preprocessing and analysis, they were unable to accurately identify users' emotions and behavioral patterns. Furthermore, there was no established method for utilizing the analysis results to generate appropriate feedback and provide it to users. Therefore, there was a need to build a system that would deepen users' self-understanding and provide them with specific guidelines for action.

[1201] 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.

[1202] In this invention, the server includes means for receiving a user's diary text data, means for preprocessing the received diary text data by cleaning, tokenizing, and stemming, means for analyzing the preprocessed diary text data using natural language processing technology, means for identifying emotions and behavioral patterns based on the analyzed data, means for storing the identified data in a database, means for generating user-specific feedback based on the stored data and past data, means for transmitting the generated feedback to the user's terminal, and means for displaying the transmitted feedback to the user. This makes it possible to provide highly accurate and personalized feedback based on the user's diary content.

[1203] "User" refers to a person who uses the system to enter diary text data.

[1204] "Terminal" refers to a device that allows a user to input diary text data and send it to the server.

[1205] "Server" refers to the computer system that processes, analyzes, and stores received diary text data, and generates and transmits feedback.

[1206] "Diary text data" refers to text information entered by a user about their daily life and emotions.

[1207] "Preprocessing" refers to the process of converting text data into a format that is easy to analyze by performing processes such as cleaning, tokenization, and stemming on the data.

[1208] "Cleaning" refers to the process of removing unnecessary spaces and special characters from diary text data.

[1209] "Tokenization" refers to the process of dividing diary text data into words or phrases.

[1210] "Stemming" refers to the process of converting words into their base forms.

[1211] "Natural language processing technology" refers to technology for analyzing text data and identifying meaning and emotion.

[1212] "Analysis" refers to the process of identifying sentiment and behavioral patterns from preprocessed text data.

[1213] "Emotion" refers to the user's psychological state, such as joy, sadness, or anger, contained in the text data.

[1214] "Behavioral pattern" refers to elements in text data that identify user activities or behaviors (e.g., work, rest).

[1215] "Identification" refers to the process of identifying specific emotions or behavioral patterns from the analysis results.

[1216] "Database" refers to the digital storage for identifying emotions and behavioral patterns and other related data.

[1217] "Feedback" refers to specific advice or guidelines for users that are generated based on the analysis results.

[1218] "Generation" refers to the process of creating feedback based on data stored in a database or past data.

[1219] "Send" refers to the act of transferring the generated feedback from the server to the user's terminal.

[1220] "Display" refers to the act of visually showing the submitted feedback on the user's terminal.

[1221] System Overview

[1222] This system analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and then provides personalized feedback. Specifically, it includes a series of steps: receiving the user's diary text data, preprocessing it, analyzing it, identifying it, generating feedback, and sending it.

[1223] Program processing

[1224] User diary data entry and reception

[1225] The user inputs text for the diary using a terminal. This text includes information about the user's daily life and emotions. The terminal then transmits this text data to a server. Any text input device or smartphone can be used as the hardware.

[1226] Receiving diary data and preprocessing it on the server

[1227] The server receives the diary text data sent from the device. As the received data is not suitable for analysis as is, it undergoes preprocessing. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). Preprocessing prepares the data in a format that is easy to analyze. Specific text processing libraries that are introduced include Python NLP libraries (e.g., NLTK and spaCy).

[1228] Emotion and behavioral pattern analysis

[1229] The AI ​​analysis module in the server analyzes the preprocessed text data. This analysis uses natural language processing technology to identify emotions (happiness, sadness, anger, etc.) and behavioral patterns (work, rest, relationships, etc.) within the text. Generative AI models used include the BERT and GPT series models, for example. The analysis results are stored in a database and accumulated as each user's historical data.

[1230] Generate personalized feedback

[1231] The server generates user-specific feedback based on the analysis results. This feedback generation module references the user's own past data and data from similar users to create specific advice to improve the user's daily life. Advanced natural language generation is made possible by inputting prompt sentences into the generative AI model.

[1232] Sending and Viewing Feedback

[1233] The generated feedback is sent from the server to the device. The device displays this feedback to the user in a format that is intuitively easy to understand. This allows the user to deepen their self-understanding and obtain specific guidelines for action. Notification messages, pop-up windows, and other display formats are used.

[1234] Specific examples

[1235] 1. User diary entry

[1236] The user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[1237] The terminal transmits this text data to the server.

[1238] 2. Receiving and preprocessing text data on the server

[1239] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[1240] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[1241] Next, the words are stemmed and converted to their base forms.

[1242] 3. Conducting the analysis

[1243] The AI ​​analysis module analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)."

[1244] The server stores these identification results in a database.

[1245] 4. Generate feedback

[1246] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow."

[1247] 5. Sending and Viewing Feedback

[1248] The server transmits the generated feedback data to the terminal.

[1249] The terminal displays the received feedback to the user, and the user receives specific advice.

[1250] In this way, a system is realized that provides specific and personalized feedback based on the contents of a user's diary.

[1251] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1252] Step 1: Enter and submit user diary data

[1253] A user inputs diary text into a terminal. For example, the user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." The input text data is sent by the terminal to the server. The input here is the user's diary text data, and the output is the text data sent to the server.

[1254] Step 2: Receiving diary data on the server

[1255] The server receives the diary text data sent from the terminal. The received data is temporarily stored in memory. The input here is the diary text data sent from the terminal, and the output is the data stored in memory.

[1256] Step 3: Preprocessing the text data

[1257] The server performs preprocessing on the diary text data it receives. Specifically, it performs text cleaning (removing unnecessary spaces and special characters), tokenization (dividing into words and phrases), and stemming (converting words into their base forms). The input is the diary text data stored in memory, and the output is the preprocessed text data. For example, the input "I was tired from meetings all day today, but I'm happy that the project was successful" is converted into "today," "all day," "meeting," "tiring," "project," "success," and "satisfied."

[1258] Step 4: Emotion and behavioral pattern analysis

[1259] The AI ​​analysis module on the server analyzes the preprocessed text data. It uses natural language processing technology to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The input is the preprocessed text data, and the output is the identified emotion and behavioral pattern data. For example, "fatigue (negative emotion)," "success (positive emotion)," and "meeting (behavioral pattern)" are identified.

[1260] Step 5: Save the analysis results to a database

[1261] The server stores the identified emotion and behavior pattern data in a database. It is important to store the data in association with past data. The input is the identified emotion and behavior pattern data, and the output is the data stored in the database.

[1262] Step 6: Generate personalized feedback

[1263] The server generates user-specific feedback based on the analysis results. It is created using a generative AI model based on the prompt text. The input is the analysis results and past user data, and the output is user-specific feedback. Specifically, it might be something like, "You seem tired today, but you seem to be feeling satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow."

[1264] Step 7: Submit your feedback

[1265] The server sends the generated feedback data to the terminal, where the input is the user-specific feedback and the output is the feedback data sent to the terminal.

[1266] Step 8: Viewing feedback

[1267] The feedback received by the device is displayed to the user in a format that allows the user to confirm specific advice. The input is the feedback data sent to the device, and the output is the feedback displayed to the user. For example, it is displayed as a notification message or a pop-up window on the device.

[1268] (Application example 1)

[1269] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1270] While existing systems have the ability to analyze users' diary data to identify their emotions and behavioral patterns, they lack the ability to recommend content appropriate to the user's mood based on the results of this identification. Therefore, there was a need for a system that would not only help users deepen their self-understanding, but also allow them to enjoy appropriate content according to their daily mood.

[1271] 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.

[1272] In this invention, the server

[1273] means for receiving user diary text data;

[1274] means for analyzing the received diary text data;

[1275] means for identifying emotions and behavioral patterns based on the analyzed data;

[1276] means for generating feedback to a user based on the identified data;

[1277] means for transmitting the generated feedback;

[1278] means for recommending appropriate content to a user based on the identified emotion;

[1279] This makes it possible to recommend content that matches the user's daily emotional state.

[1280] The "means for receiving user's diary text data" is a function for transmitting diary text data entered by the user to the server via the network and receiving it.

[1281] The "means for analyzing the received diary text data" is a function for analyzing the received diary text data grammatically and semantically using natural language processing technology.

[1282] The "means for identifying emotions and behavioral patterns based on the analyzed data" is a function for identifying the emotions and behavioral patterns of a user based on information extracted from the analyzed text data.

[1283] The "means for generating feedback to the user based on the identified data" is a function for generating personalized feedback to the user based on the identified emotions and behavioral patterns.

[1284] The "means for transmitting the generated feedback" is a function for transmitting the generated feedback to the user terminal.

[1285] The "means for recommending appropriate content to the user based on the identified emotion" is a function for obtaining content such as videos and music that is appropriate for the identified emotion from an external content providing service and recommending it to the user.

[1286] To implement this invention, a server, a user terminal, and natural language processing technology are used. The following describes specific program processing and how to use it.

[1287] First, a user inputs diary text data using their own device (e.g., a smartphone). This diary text data describes the user's daily life and emotional movements, and the device then transmits this data to a server.

[1288] The server receives the diary text data sent from the device. The received data is inappropriate for analysis as it is, so it is preprocessed. This preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes are performed using spaCy and TextBlob, natural language processing libraries specialized for text analysis.

[1289] After preprocessing, the AI ​​analysis module on the server analyzes the text data. A generative AI model is used to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) within the text. The analysis results are stored in a database.

[1290] The server then generates user-specific feedback based on the identified emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Furthermore, based on the identified emotions, the server retrieves and recommends content appropriate for the user (e.g., relaxing music or mood-boosting videos) from external content providers.

[1291] The generated feedback and recommended content are sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to obtain specific guidelines for action and appropriate content.

[1292] For example, suppose a user writes in their diary, "I'm tired from meetings all day today, but I'm satisfied that the project was a success." From this text, the analysis module reads the emotions of "fatigue" and "success" and identifies that the user is tired from their daytime activities but also feels a sense of accomplishment. Based on this analysis result, the server generates feedback such as, "You seem tired today, but you seem to be satisfied with your success at work. I recommend that you get some proper rest and prepare for tomorrow." It also recommends content appropriate to the user's state, such as relaxing music or inspiring movie trailers.

[1293] An example of a prompt sentence input to the generative AI model is as follows:

[1294] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[1295] This invention enables personalized content recommendations that match the user's daily emotional state, thereby improving the user's quality of life.

[1296] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1297] Step 1:

[1298] The user inputs diary text data using a terminal. Specifically, the user starts the application and describes their daily life and emotional movements in the text input box. The input diary text data is encoded on the terminal and sent to the server via the network.

[1299] Input: User's diary text data

[1300] Output: Encoded text data sent to the server

[1301] Step 2:

[1302] The server receives diary text data sent from user devices. Since the received data is not suitable for analysis as is, it undergoes preprocessing. Preprocessing includes text cleaning (removing unnecessary spaces and special characters), tokenization (dividing words and phrases), and stemming (converting words to their base forms). These processes use natural language processing libraries such as spaCy and TextBlob.

[1303] Input: Encoded diary text data

[1304] Output: Clean text data after preprocessing

[1305] Step 3:

[1306] The AI ​​analysis module in the server analyzes the pre-processed text data and uses a generative AI model to identify emotions (e.g., joy, sadness, anger) and behavioral patterns (e.g., work, rest, relationships) in the text. This uses natural language processing techniques, and the analysis results are stored in a database.

[1307] Input: Clean, preprocessed text data

[1308] Output: Emotion and behavior pattern identification results

[1309] Step 4:

[1310] The server generates user-specific feedback based on the results of identifying emotions and behavioral patterns. The feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life. Based on the analysis results, the server also obtains and recommends content (videos, music, etc.) suitable for the user from external content providers.

[1311] Input: Emotion and behavior pattern identification results

[1312] Output: User-specific feedback and recommended content

[1313] Step 5:

[1314] The generated feedback and recommended content are sent from the server to the user's device, which then displays them in an intuitively understandable format. For example, the feedback might say, "You seem tired today, but you seem to be satisfied with your work success. We recommend that you get some proper rest and prepare for tomorrow," and provide links to relaxing music or videos that lift your spirits.

[1315] Input: User-specific feedback and suggested content

[1316] Output: Feedback and recommended content displayed on the user's device

[1317] For example, if a user enters "I'm tired from meetings all day today, but I'm happy that the project was a success," the server analyzes the text and generates appropriate feedback and content to provide to the user. An example of a prompt sentence in this case is as follows:

[1318] User's diary: I'm tired from meetings all day today, but I'm happy that the project was a success.

[1319] 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.

[1320] System Overview

[1321] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to more accurately identify the user's emotional state and generate personalized feedback.

[1322] Program processing

[1323] User diary data entry and reception

[1324] First, the user inputs the text of the diary using the device. This text describes the user's daily life and emotional movements. The device then transmits the input text data to the server.

[1325] Receiving diary data and preprocessing it on the server

[1326] The server receives the diary text data sent from the device. The received data undergoes preprocessing before analysis. Preprocessing includes text cleaning, tokenization, stemming, etc.

[1327] Analysis by emotion engine

[1328] The emotion engine in the server analyzes the pre-processed text data. Using natural language processing techniques, the emotion engine identifies emotions (e.g., joy, sadness, anger, surprise) in the text. This identifies the user's emotional state based on the diary data.

[1329] Identifying emotions and behavioral patterns

[1330] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meetings" and "projects," from the user's text and stores them in a database.

[1331] Generate personalized feedback

[1332] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. This feedback generation module also references past data and data from similar users to create specific advice to improve the user's daily life.

[1333] Sending and Viewing Feedback

[1334] The generated feedback is sent from the server to the device, which then displays it to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[1335] Example

[1336] Specific processing example

[1337] 1. User diary entry

[1338] Suppose a user types, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[1339] The terminal transmits this text data to the server.

[1340] 2. Receiving and preprocessing text data on the server

[1341] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[1342] For example, the text can be tokenized and split into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[1343] Next, the words are stemmed and converted to their base forms.

[1344] 3. Analysis by Emotion Engine

[1345] The server's emotion engine analyzes the text and identifies "fatigue (negative emotion)," "success (positive emotion)," and "satisfaction (positive emotion)."

[1346] 4. Identifying Behavioral Patterns

[1347] The server identifies the behavioral patterns in the text, such as "meetings (behavioral patterns)" and "projects (behavioral patterns)," and stores them in a database along with the analysis results.

[1348] 5. Generate feedback

[1349] Based on the analysis results, the server generates specific advice such as, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend that you get some proper rest."

[1350] 6. Sending and Viewing Feedback

[1351] The server transmits the generated feedback data to the terminal.

[1352] The terminal displays the received feedback to the user, and the user receives specific advice.

[1353] In this way, we have realized a system that can provide specific and personalized feedback based on the user's diary entries.By introducing an emotion engine, we can analyze the user's emotional state more accurately and provide more appropriate feedback.

[1354] The processing flow will be explained below.

[1355] Step 1: The user uses the terminal to input the text of the diary. For example, the user might write, "I'm tired from meetings all day today, but I'm happy that the project was a success."

[1356] Step 2: The terminal prepares a data format for sending the input text data to the server, and sends the text to the server as an HTTP request.

[1357] Step 3: The server receives the text data at the receiving port and temporarily stores it in memory. The received raw data is saved before being passed to the analysis module.

[1358] Step 4: The server pre-processes the text data: a cleaning process removes unnecessary spaces and special characters, a tokenization process splits the text into words and phrases, and a stemming process converts words into their root forms.

[1359] Step 5: The emotion engine in the server analyzes the pre-processed text data. The emotion engine uses natural language processing techniques to identify emotions (e.g., "fatigue," "success," "satisfaction") from the text. The emotional state is identified.

[1360] Step 6: The server also identifies behavioral patterns (e.g., "meeting" or "project") in the diary text based on the analysis results of the emotion engine. The identified emotion and behavioral pattern information is stored in a database.

[1361] Step 7: The server's feedback generation module retrieves the emotion and behavior pattern identification results from the database and generates user-specific feedback. For example, it could generate feedback such as, "You seem tired today, but you feel satisfied with the success of the project. I recommend you get some proper rest and prepare for tomorrow."

[1362] Step 8: The server converts the generated feedback data into data packets and sends them to the terminal. The feedback data is encoded in a format that is easy for the user to understand.

[1363] Step 9: The terminal displays the feedback data received from the server to the user. The feedback is displayed in a visually easy-to-understand text format or graph format.

[1364] Through this series of processes, users can deepen their self-understanding and obtain specific guidelines for action through emotion analysis and behavioral pattern identification using the engine.

[1365] Example 2

[1366] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1367] In systems that analyze users' diary text data, identify their emotions and behavioral patterns, and provide feedback, it is difficult to improve the accuracy of the analysis and provide personalized feedback. There is also a need for the feedback received by users to be displayed in an intuitive and easy-to-understand format.

[1368] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving diary text data of a user, means for pre-processing the received diary text data, means for analyzing the pre-processed diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for generating feedback to the user based on the identified data, means for transmitting the generated feedback, and means for displaying the feedback in a format that is intuitively easy for the user to understand. This enables highly accurate identification of emotions and behavioral patterns and provision of personalized feedback based on past data.

[1369] "User" refers to a person who uses this system to input diary text data and receives feedback on it.

[1370] "Diary text data" refers to text data in which a user describes events, feelings, and actions in their daily life.

[1371] "Means for receiving" refers to a function for transmitting diary text data from a terminal to a server.

[1372] "Preprocessing means" refers to processes such as cleaning, tokenization, and stemming that are carried out to prepare the received diary text data in a form that is easy to analyze.

[1373] "Means for analysis" refers to the function of classifying the contents of preprocessed diary text data into emotions and behavioral patterns using natural language processing technology.

[1374] "Emotion" refers to states such as joy, sadness, anger, surprise, etc. contained in the user's diary text data.

[1375] A "behavioral pattern" refers to the repetition of a specific behavior or event contained in the user's diary text data.

[1376] "Means for identifying" refers to the ability to extract emotion and behavioral patterns based on the analyzed data.

[1377] "Feedback" refers to advice and comments to the user that are generated based on the analysis and identification results.

[1378] "Means of generation" refers to the function of creating feedback for users by referring to past data and data of similar users.

[1379] "Means for sending" refers to the function of sending the generated feedback from the server to the terminal.

[1380] The "means for displaying" refers to a function for displaying the received feedback on the terminal in a format that is intuitively easy for the user to understand.

[1381] The present invention is a system that analyzes diary text data entered by a user, identifies the user's emotions and behavioral patterns, and provides feedback. A specific embodiment of this system will be described below.

[1382] First, a user inputs text data for a diary entry using their own device (e.g., smartphone or PC). For example, a user might input, "I'm tired from meetings all day today, but I'm happy that the project was a success." This text data describes the user's daily life and emotional movements. The device then sends the input diary text data to the server.

[1383] The server receives the diary text data sent from the device. The received data is preprocessed before analysis. This preprocessing includes the following steps:

[1384] Text cleaning: Remove unnecessary spaces and special characters from text.

[1385] Tokenization: Breaking text into meaningful units (words and phrases), such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied."

[1386] Stemming: Converting words into their base form. For example, converting "tired" into "tired."

[1387] After preprocessing, the text data is passed to the emotion engine on the server. This emotion engine uses natural language processing techniques to analyze the text and identify emotions. For example, the following emotions can be identified:

[1388] "Tired" -> fatigue (negative emotion)

[1389] "Success" -> positive emotions

[1390] "Satisfaction" -> positive emotions

[1391] After identifying emotions, the server then identifies behavioral patterns. This is the process of extracting specific actions or events from the text. For example, behavioral patterns such as "meeting" and "project" are extracted. This identified data is then stored in a database along with the analysis results.

[1392] The server generates user-specific feedback based on the analysis results of the emotion engine and the behavioral pattern identification results. The generated feedback is created by referring to past data and data from similar users. A specific example would be the feedback, "You seem tired today, but you seem to be feeling satisfied with the success of the project. I recommend you get some proper rest."

[1393] The generated feedback is sent from the server to the device, which then displays the received feedback to the user in an intuitive and easy-to-understand format, allowing the user to deepen their self-understanding and obtain specific guidelines for action.

[1394] Example prompt sentence:

[1395] "I'm tired from meetings all day today, but I'm happy that the project was a success."

[1396] As described above, the present invention is a system that realizes highly accurate identification of emotions and behavioral patterns and provides personalized feedback based on past data.

[1397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1398] Step 1:

[1399] The user inputs diary text data.

[1400] Specifically, the user uses the terminal and enters the following into the text input screen: "I'm tired from meetings all day today, but I'm happy that the project was a success." This input text is sent to the server as input data for the terminal.

[1401] Step 2:

[1402] The server receives the diary text data.

[1403] Specifically, the server receives diary text data sent from the device via the network and temporarily stores it in memory. The input data is raw text data, and the output at this point is text data before preprocessing.

[1404] Step 3:

[1405] The server pre-processes the diary text data.

[1406] Specifically, the server performs text cleaning, removing unnecessary spaces and special characters. Next, it performs text tokenization, dividing the sentence into words such as "today," "all day," "meeting," "tired," "project," "success," and "satisfied." Finally, it performs stemming, converting the words into their base forms. The input is raw text data, and the output is cleaned, tokenized, and stemmed text data.

[1407] Step 4:

[1408] The server analyzes the preprocessed text data using an emotion engine.

[1409] Specifically, the emotion engine uses natural language processing technology to identify emotions from preprocessed text data. For example, emotions are extracted in the form of "tired" -> fatigue (negative emotion), and "success" or "satisfied" -> positive emotion. The input is preprocessed text data, and the output is identified emotion data.

[1410] Step 5:

[1411] The server identifies behavioral patterns based on the analyzed data.

[1412] Specifically, the server extracts behavioral patterns such as "meeting" and "project" from the text. This clarifies the activities the user performed. The input is text data analyzed by the emotion engine, and the output is the identified behavioral pattern data.

[1413] Step 6:

[1414] The server generates feedback to the user.

[1415] Specifically, the server generates personalized feedback based on the analysis and identification results. It also references past data and data from similar users to create specific advice such as, "You seem tired today, but you seem to be satisfied with the success of the project. I recommend you get some proper rest." The input is the identified emotion data and behavioral pattern data, and the output is the generated feedback.

[1416] Step 7:

[1417] The server generates feedback and sends it to the device.

[1418] Specifically, the server sends the generated feedback data to the terminal via the network. The input is the generated feedback, and the output is the feedback data sent to the terminal.

[1419] Step 8:

[1420] The terminal displays the sent feedback to the user.

[1421] Specifically, the device displays the received feedback in an intuitively understandable format to the user, allowing the user to receive specific advice on their own status. The input is the transmitted feedback data, and the output is the feedback displayed to the user.

[1422] (Application example 2)

[1423] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1424] Current security services do not adequately monitor users' emotional changes and behavioral patterns, making it difficult to respond quickly to sudden emotional changes or abnormal behavioral patterns. To solve this problem and ensure users' safety and security, a system is needed that analyzes diary text data, accurately identifies emotional states and behavioral patterns, and provides feedback.

[1425] 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.

[1426] In this invention, the server includes means for receiving diary text data of a user, means for analyzing the received diary text data, means for identifying emotions and behavioral patterns based on the analyzed data, means for detecting abnormal behavioral patterns or sudden changes in emotions based on the generated feedback, means for sending a notification to the user based on the detected abnormality, and means for sending the generated feedback. This makes it possible to early detect abnormal emotional changes or behavioral patterns of a user and provide appropriate notifications, thereby ensuring the safety and security of the user.

[1427] "Diary text data" refers to text data entered by a user about their daily life or the events of the day.

[1428] The "receiving means" refers to a device or program that has the function of sending the diary text data entered by the user to the server and capturing that data.

[1429] The "analyzing means" refers to a device or program that has the function of analyzing the received diary text data and extracting the emotions and behavioral patterns contained therein.

[1430] "Emotion" indicates the user's inherent psychological state, such as joy, sadness, anger, or surprise.

[1431] A "behavioral pattern" refers to a series of actions or activities that a user performs in daily life or in a specific situation.

[1432] "Feedback" refers to advice or information provided to users based on analyzed emotions and behavioral patterns.

[1433] An "abnormal behavior pattern" is a behavior that is significantly different from the user's normal behavior, and is often linked to a sudden change in emotion.

[1434] A "sudden change in emotion" refers to a large change in the emotional state of a user analyzed from the diary text data in a short period of time.

[1435] The "means for sending a notification" is a device or program that has the function of sending a notification to a user or administrator based on the analysis results.

[1436] System Overview

[1437] This system analyzes diary text data entered by users, identifies their emotions and behavioral patterns, and provides feedback. In particular, by combining it with an emotion engine, it is possible to identify the user's emotional state with greater accuracy, provide personalized feedback, and detect abnormalities.

[1438] Program processing

[1439] User diary data entry and reception

[1440] The user inputs diary text using a smartphone, and the input text data is sent to a server via a dedicated application.

[1441] Receiving diary data and preprocessing it on the server

[1442] The server receives the diary text data sent from the device and performs preprocessing on the received data, which includes text cleaning, tokenization, stemming, etc.

[1443] Analysis by emotion engine

[1444] The emotion engine in the server analyzes the preprocessed text data and uses natural language processing (NLP) techniques to identify emotions (such as joy, sadness, anger, and surprise) in the text. Specifically, it uses the Hugging Face Transformers library to accurately identify emotional states.

[1445] Identifying emotions and behavioral patterns

[1446] Along with the emotions identified by the emotion engine, the server's analysis module also identifies behavioral patterns, such as "meeting" or "project" in the text, and stores them in a database.

[1447] Generate personalized feedback

[1448] The server generates user-specific feedback based on the emotion engine's analysis results and behavioral pattern identification. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates appropriate notifications. For example, it creates specific advice such as, "You seem to be feeling stressed today. We recommend you take a rest."

[1449] Sending and Viewing Feedback

[1450] The generated feedback is sent from the server to the terminal, which displays the feedback to the user and also sends notifications to the user based on the detected anomalies.

[1451] Specific examples

[1452] 1. User diary entry

[1453] The user types, "I've been feeling very stressed today. Some things haven't gone as planned and I'm frustrated."

[1454] The terminal transmits this text data to the server.

[1455] 2. Receiving and preprocessing text data on the server

[1456] The server temporarily stores the text received from the terminal in memory and performs preprocessing.

[1457] For example, the text is tokenized and divided into words such as "today," "stress," "work," "not progressing," and "frustrated."

[1458] Next, the words are stemmed and converted to their base forms.

[1459] 3. Analysis by Emotion Engine

[1460] The server's emotion engine analyzes the text and identifies "high stress" and "medium irritation."

[1461] 4. Identifying Behavioral Patterns

[1462] The server identifies the behavioral pattern of the text, "High Work," and stores it in a database along with the analysis results.

[1463] 5. Generate feedback

[1464] Based on the analysis results, the server generates specific advice such as, "You seem to be feeling stressed today, so we recommend that you take a rest."

[1465] If an anomaly is detected, generate a notification saying "An abnormal behavior pattern has been detected. Attention required."

[1466] 6. Sending and Viewing Feedback

[1467] The server sends the generated feedback data and notification to the terminal.

[1468] The device displays the received feedback and notifications to the user.

[1469] Prompt Sentence Examples

[1470] Below are some example prompts for generative AI models:

[1471] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[1472] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[1473] Emotion analysis:

[1474] Stress: High

[1475] Irritation: Medium

[1476] Behavior Pattern:

[1477] Work: High

[1478] Assess the risk level and generate feedback.”

[1479] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1480] Step 1:

[1481] User diary data entry

[1482] A user inputs diary text using a smartphone. The input text data is sent to a server via a dedicated application. This text data describes the user's daily life and emotional movements.

[1483] Step 2:

[1484] Receiving diary text data

[1485] The server receives the diary text data sent from the terminal. At this stage, the input data itself is stored in a specified memory area of ​​the server. The input is the diary text data, and the output is the received text data.

[1486] Step 3:

[1487] Preprocessing text data

[1488] The server performs preprocessing on the received text data, including cleaning, tokenization, and stemming. Cleaning removes unnecessary special characters and noise, tokenization divides the data into words, and stemming converts words into their base forms. The input is the received text data, and the output is the preprocessed text data.

[1489] Step 4:

[1490] Analysis by emotion engine

[1491] The emotion engine in the server analyzes the preprocessed text data. It uses natural language processing techniques (e.g., Hugging Face's Transformers library) to identify the emotions contained in the text (e.g., "stress," "joy," etc.). The input is the preprocessed text data, and the output is the emotion analysis results.

[1492] Step 5:

[1493] Identifying behavioral patterns

[1494] In addition to analyzing sentiment, the server also identifies behavioral patterns within the text. This identification is done by the occurrence of specific keywords (e.g., "meeting," "project," etc.). The input is the preprocessed text data, and the output is the behavioral pattern identification results.

[1495] Step 6:

[1496] Data storage

[1497] The server stores the emotion analysis results and behavioral pattern identification results in a database. This storage process accumulates the user's diary data as past data and can be used for future analysis. The input is the emotion analysis results and behavioral pattern identification results, and the output is the data stored in the database.

[1498] Step 7:

[1499] Generate feedback

[1500] The server generates feedback for the user based on the emotion analysis results and behavioral pattern identification results. If an abnormal behavioral pattern or a sudden change in emotion is detected, the server evaluates the risk level and generates an appropriate notification. The input is the emotion analysis results and behavioral pattern identification results, and the output is the generated feedback message and notification.

[1501] Step 8:

[1502] Sending feedback and notifications

[1503] The server sends the generated feedback and notifications to the user's terminal. The terminal displays the received feedback and notifications to the user. The input is the generated feedback message and notification, and the output is the feedback and notification displayed on the terminal.

[1504] Specifically, the generative AI model is given a prompt like the one below, which is then analyzed and feedback is generated:

[1505] "Analyze the following text and identify the emotions and behavioral patterns it contains:

[1506] "I was very stressed today. Some tasks didn't go as planned, and I was frustrated."

[1507] Emotion analysis:

[1508] Stress: High

[1509] Irritation: Medium

[1510] Behavior Pattern:

[1511] Work: High

[1512] Assess the risk level and generate feedback.”

[1513] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1514] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1515] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1516] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1517] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1518] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1519] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1520] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1521] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1522] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1523] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1524] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1525] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1526] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1527] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1528] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1529] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1530] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1531] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1532] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1533] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1534] The following is further disclosed regarding the above embodiment.

[1535] (Claim 1)

[1536] means for receiving user diary text data;

[1537] means for analyzing the received diary text data;

[1538] means for identifying emotions and behavioral patterns based on the analyzed data;

[1539] means for generating feedback to a user based on the identified data;

[1540] means for transmitting the generated feedback;

[1541] A system including:

[1542] (Claim 2)

[1543] The system of claim 1, further comprising means for pre-processing the received diary text data.

[1544] (Claim 3)

[1545] 10. The system of claim 1, further comprising means for storing the analyzed data in a database.

[1546] "Example 1"

[1547] (Claim 1)

[1548] means for receiving user diary text data;

[1549] means for pre-processing the received diary text data by cleaning, tokenizing and stemming;

[1550] means for analyzing the preprocessed diary text data using natural language processing technology;

[1551] means for identifying emotions and behavioral patterns based on the analyzed data;

[1552] means for storing the identified data in a database;

[1553] means for generating user-specific feedback based on the stored data and historical data;

[1554] means for transmitting the generated feedback to a user terminal;

[1555] means for displaying said submitted feedback to a user;

[1556] A system including:

[1557] (Claim 2)

[1558] 10. The system of claim 1, wherein the analysis means uses a generative AI model.

[1559] (Claim 3)

[1560] The system of claim 1 , wherein the feedback generating means generates the feedback based on a prompt sentence.

[1561] "Application Example 1"

[1562] (Claim 1)

[1563] means for receiving user diary text data;

[1564] means for analyzing the received diary text data;

[1565] means for identifying emotions and behavioral patterns based on the analyzed data;

[1566] means for generating feedback to a user based on the identified data;

[1567] means for transmitting the generated feedback;

[1568] means for recommending appropriate content to a user based on the identified emotion;

[1569] A system including:

[1570] (Claim 2)

[1571] The system of claim 1, further comprising means for pre-processing the received diary text data.

[1572] (Claim 3)

[1573] 10. The system of claim 1, further comprising means for storing the analyzed data in a database.

[1574] "Example 2: Combining Emotion Engines"

[1575] (Claim 1)

[1576] means for receiving user diary text data;

[1577] means for preprocessing the received diary text data;

[1578] means for analyzing the preprocessed diary text data;

[1579] means for identifying emotions and behavioral patterns based on the analyzed data;

[1580] means for generating feedback to a user based on the identified data;

[1581] means for transmitting the generated feedback;

[1582] a means for displaying feedback to the user in an intuitive format;

[1583] A system including:

[1584] (Claim 2)

[1585] 10. The system of claim 1, further comprising means for storing the analyzed emotion and behavior pattern data in a database.

[1586] (Claim 3)

[1587] 10. The system of claim 1, further comprising: means for generating personalized feedback based on the analyzed data and historical data.

[1588] "Application example 2 when combining emotion engines"

[1589] (Claim 1)

[1590] means for receiving user diary text data;

[1591] means for analyzing the received diary text data;

[1592] means for identifying emotions and behavioral patterns based on the analyzed data;

[1593] means for generating feedback to a user based on the identified data;

[1594] means for detecting abnormal behavioral patterns or sudden changes in emotions based on the generated feedback;

[1595] means for sending a notification to a user based on the detected anomaly;

[1596] means for transmitting the generated feedback;

[1597] A system including:

[1598] (Claim 2)

[1599] The system of claim 1, further comprising means for pre-processing the received diary text data.

[1600] (Claim 3)

[1601] 10. The system of claim 1, further comprising means for storing the analyzed data in a database. [Explanation of symbols]

[1602] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving user diary text data; means for analyzing the received diary text data; means for identifying emotions and behavioral patterns based on the analyzed data; means for generating feedback to a user based on the identified data; means for transmitting the generated feedback; A system including:

2. The system according to claim 1 , further comprising means for pre-processing the received diary text data.

3. The system of claim 1 further comprising means for storing the analyzed data in a database.

Images