system

Abstract

Provide a system. A wearable device is used to acquire voice data. a speech recognition means for converting speech data into text data; natural language processing means for analyzing text data and extracting keywords and important phrases; A grouping mechanism for grouping and organizing notes into themes based on extracted keywords and phrases; a database storage means for structuring the organized notes and storing them in a personal database; An interactive AI means that enables dialogue with the user based on a personal database, A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, there has been a demand for tools that allow individuals to reflect on their daily thoughts and learning. However, manually taking and organizing notes is cumbersome and inefficient. In particular, there are limited systems available that allow users to easily capture notes via voice input using wearable devices, group them, organize them by theme, store them in a database, and then reflect on them. Furthermore, there is a lack of a mechanism for centrally managing these notes and allowing users to easily access them interactively. This makes it difficult to effectively record, organize, and utilize notes and ideas, preventing users from making the most of their daily discoveries and learning. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for acquiring voice data using a wearable device is provided. Next, the voice data is converted into text data using a voice recognition means, and keywords and important phrases are extracted from the text data using a natural language processing means. A grouping means is provided for grouping notes and organizing them by theme based on the extracted keywords and phrases. Next, a database storage means is provided for structuring the organized notes and storing them in a personal database. Finally, an interactive AI means is provided that enables interaction with the user based on the personal database, allowing the user to easily search and refer to past notes and effectively reflect on their own thoughts and learning. In this way, the present invention builds a system that centrally supports the acquisition, organization, storage, and utilization of daily notes and ideas.

[0006] A "wearable device" is an electronic device that can be worn on the human body and has functions such as acquiring voice data, inputting data, and displaying data.

[0007] "Speech recognition means" is a general term for technology and devices for converting voice data into text data, analyzing voice input and outputting the content as text.

[0008] "Natural language processing means" is a general term for technologies and devices that analyze text data and extract keywords and important phrases, analyzing context and meaning.

[0009] "Grouping means" is a general term for techniques and devices that group similar notes together based on extracted keywords and phrases, and then assign a theme to each group to organize them.

[0010] "Database storage means" is a general term for any technology or device used to store organized and structured data in a database and preserve it in an accessible format when needed.

[0011] "Interactive AI means" is a general term for artificial intelligence technologies and devices that generate and provide interactive responses in natural language to user inquiries based on data stored in a personal database.

[0012] A "personal database" is a database that stores information such as a user's personal notes and ideas in a structured form, making it easy to search and refer to. [Brief explanation of the drawings]

[0013] [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 illustrating 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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos and stores them in a database.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0035] System Overview

[0036] The system mainly consists of the following elements:

[0037] 1. Wearable devices: have the ability to acquire voice data.

[0038] 2. Speech recognition means: converts voice data into text data.

[0039] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[0040] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[0041] 5. Database storage method: Organized notes are structured and stored in a database.

[0042] 6. Interactive AI means: Provide AI that allows users to retrieve information from a database and reflect on it in an interactive format.

[0043] Acquiring voice input and converting it to text

[0044] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[0045] The device receives this voice data and converts it into text data by sending it to a voice recognition API (e.g., a cloud-based voice recognition service).

[0046] Natural Language Processing and Grouping

[0047] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[0048] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[0049] The server automatically groups notes based on the extracted keywords and phrases, grouping related notes together—for example, associating them with other notes that share the keywords "meeting" and "strategy."

[0050] Saving to a database

[0051] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0052] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[0053] Dialogue with AI

[0054] Users use a smartphone or PC interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0055] The server receives the user's request and retrieves the relevant information from a personal database.

[0056] A conversational AI solution uses this information to generate a natural language response and present it to the user, such as "There is a memo that says 'You need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[0057] Specific examples

[0058] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[0059] 2. Example of text conversion: A speech recognition tool converts the text into "We need to talk about our new marketing strategy at tomorrow's meeting."

[0060] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means organizes them into the theme "marketing strategy."

[0061] 4. Example of saving to database: Save to database as "October 5, 2023" and "Meeting notes on marketing strategy."

[0062] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[0063] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] Users enter voice notes into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0067] Step 2:

[0068] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[0069] Step 3:

[0070] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, such as "We need to talk about our new marketing strategy in tomorrow's meeting."

[0071] Step 4:

[0072] The server receives the text data from the speech recognition API and analyzes it using a natural language processing library (e.g., spaCy or NLTK). This involves grammatical and morphological analysis of the text data.

[0073] Step 5:

[0074] The server extracts keywords and important phrases from the analysis results, such as "meeting," "new marketing strategy," "speak," and "necessary."

[0075] Step 6:

[0076] The server groups notes based on the extracted keywords and phrases, for example, grouping a note with the theme "marketing strategy" with other notes containing the keyword "meeting."

[0077] Step 7:

[0078] The server structures the organized notes. For example, it generates data in JSON format such as "October 5, 2023" and "Meeting notes on marketing strategy."

[0079] Step 8:

[0080] The server stores the structured data in a personal database, which allows notes to be organized by date and subject.

[0081] Step 9:

[0082] A user launches a conversational AI assistant application and sends a request to view past notes, for example, "Show me the notes from last week's marketing strategy meeting."

[0083] Step 10:

[0084] The server receives the user's request and searches the personal database for relevant notes, for example, using the search criteria "marketing strategy," "meeting," and "last week."

[0085] Step 11:

[0086] The server passes the search results to a conversational AI engine, which generates a natural-language response for the user, such as "There is a memo that says 'I need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[0087] Step 12:

[0088] Users can receive responses from the AI, reflect on their own thoughts and learnings, and ask the AI ​​for more detailed information if necessary.

[0089] As described above, this system provides consistent support from voice input to data organization, storage, and review.

[0090] Example 1

[0091] 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."

[0092] Conventional note-taking and management systems require users to manually input information, which is time-consuming and labor-intensive. Furthermore, it is difficult to efficiently organize and manage notes, making it difficult to quickly search for and reference necessary information. This reduces user efficiency, especially in business and academic activities.

[0093] 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.

[0094] In this invention, the server includes means for acquiring voice data using a wearable device, speech recognition means for converting the voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, storage means for structuring the organized notes and storing them in a database, interactive artificial intelligence means for enabling a dialogue with a user based on the database, means for receiving a request from a user and searching past notes, and means for generating a response in natural language based on the search results and presenting it to the user. This allows a user to easily and quickly acquire notes through voice input and then efficiently organize and restore them.

[0095] A "wearable device" is a small electronic device that can be worn by a user and has the function of acquiring voice data.

[0096] "Speech recognition means" refers to a technique or device for converting voice data into text data.

[0097] "Natural language processing means" refers to technology or equipment for analyzing text data and extracting keywords and important phrases.

[0098] A "grouping means" is a technique or device for grouping notes based on extracted keywords or phrases and organizing them by theme.

[0099] "Storage means" is a technique or device for storing grouped and structured notes in a database.

[0100] A "database" is a collection of structured data that is organized and can be efficiently managed, searched, and referenced.

[0101] "Interactive artificial intelligence means" refers to an artificial intelligence technology or device that enables a natural language dialogue with a user and provides information based on the user's request.

[0102] A "request" is a request or command sent by a user to obtain some information.

[0103] A "retrieval means" is a technique or device for retrieving relevant data from a database based on a request.

[0104] The "means for generating a response" is a technology or device for generating a response to the user in natural language based on the search results.

[0105] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos into a database. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0106] Acquiring voice input and converting it to text

[0107] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0108] The device receives this voice data and sends it in real time to a voice recognition API (e.g., Google (registered trademark) Cloud Speech-to-Text or Amazon Transcribe), which converts the voice data into text data.

[0109] The server receives the converted text data from the speech recognition API and uses it for subsequent processing.

[0110] Natural Language Processing and Grouping

[0111] The server analyzes the converted text data using a natural language processing library (e.g., spaCy or NLTK).

[0112] Keywords and important phrases are extracted from the analysis results. At this stage, keywords such as "meeting," "new marketing strategy," "speak," and "necessary" are picked up.

[0113] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme, for example, associating them with other notes that share the keywords "meeting" and "strategy."

[0114] Saving to a database

[0115] The server structures the grouped notes by theme and stores them in a database in a format such as JSON. Possible databases include MySQL (registered trademark) and MongoDB.

[0116] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[0117] Dialogue with AI

[0118] The user uses an interface such as a smartphone or PC to send a request to view past notes, for example, by entering a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[0119] The server receives the user's request and retrieves relevant information from a personal database.

[0120] The conversational AI tool generates a response in natural language based on this information and presents it to the user, for example, "There is a memo that says 'You need to talk about the new marketing strategy at a meeting on October 5, 2023."

[0121] Specific use cases

[0122] 1. Voice input example:

[0123] The user utters, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0124] 2. Text example:

[0125] The speech recognition means converts this into text: "We need to talk about our new marketing strategy in tomorrow's meeting."

[0126] 3. Parsing and Grouping Examples:

[0127] The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them together under the theme "marketing strategy."

[0128] 4. Example of saving to database:

[0129] Save this in the database as "October 5, 2023" and "Meeting notes on marketing strategy."

[0130] 5. Examples of AI dialogue:

[0131] The user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[0132] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1:

[0135] A user initiates a voice memo using a wearable device. The user dictates, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0136] Input: User's voice data

[0137] Output: Temporary audio data file on the device

[0138] What happens: The user presses a button on the wearable device or uses a voice command to initiate voice input.

[0139] Step 2:

[0140] The device sends voice data to the voice recognition API in real time and receives it as text data.

[0141] Input: Audio data file

[0142] Output: Recognized text data

[0143] Specific operation: The device sends voice data to a cloud-based speech recognition service and obtains text data in real time.

[0144] Step 3:

[0145] The server receives the text data and analyzes it using a natural language processing library.

[0146] Input: Speech-recognized text data (e.g., "I need to talk about a new marketing strategy at tomorrow's meeting.")

[0147] Output: Keywords and key phrases (e.g., "meeting," "new marketing strategy," "speak," "need")

[0148] Specific operation: The server analyzes the text data and automatically extracts keywords and important phrases.

[0149] Step 4:

[0150] The server automatically groups notes based on extracted keywords and phrases, consolidating related notes.

[0151] Input: Keywords and key phrases

[0152] Output: Grouped memo data

[0153] What it does: The server uses a clustering algorithm to organize related notes into themes.

[0154] Step 5:

[0155] The server structures the grouped notes by theme and stores them in a database.

[0156] Input: Grouped memo data

[0157] Output: Structured memo data stored in a database

[0158] Specific operation: The server structures the data in JSON format or similar and stores it in a database such as MySQL or MongoDB.

[0159] Step 6:

[0160] A user can use a smartphone or computer to send a request to view a specific note, for example, "Show me the notes from last week's meeting on marketing strategy."

[0161] Input: User request (prompt)

[0162] Output: Request data to the server

[0163] Specific Action: A user enters a request via voice or text to search for a specific note.

[0164] Step 7:

[0165] The server receives requests from users and retrieves relevant information from a personal database.

[0166] Input: User request (prompt)

[0167] Output: Search results

[0168] Specific behavior: The server queries the data in the database and retrieves the relevant note data.

[0169] Step 8:

[0170] The server uses conversational artificial intelligence means to generate a response in natural language based on the search results and present it to the user, for example, "There is a memo that says 'You need to talk about a new marketing strategy at a meeting' on October 5, 2023."

[0171] Input: Search results

[0172] Output: Response to the user

[0173] What it does: The server uses the generative AI model to generate a natural language response and sends it to the user's device.

[0174] In this way, users can conveniently and efficiently record information through voice memos and quickly obtain the information they need through interactive artificial intelligence.

[0175] (Application example 1)

[0176] 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."

[0177] Conventional security systems rely on paper or digital forms to record on-site situations, which often lacks immediacy and accuracy. It's also difficult to quickly organize the information acquired and use it as meaningful data. This leads to delays in emergency response and post-incident feedback, resulting in issues that reduce the efficiency and quality of security operations.

[0178] 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.

[0179] In this invention, the server includes: means for acquiring voice data using a wearable device; speech recognition means for converting the voice data into text data; natural language processing means for analyzing the text data and extracting keywords and important phrases; grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases; database storage means for structuring the organized notes and saving them in a personal database; means for sending a request for the user to refer to or review past notes based on the personal database; interactive AI means for searching the personal database for relevant information in response to the request, generating a response in natural language using a generative AI model, and presenting it to the user; and means for acquiring voice notes related to specific locations and situations in security operations, automatically identifying urgency and importance based on specific keywords and phrases, and displaying relevant notes preferentially. This enables on-site situations to be instantly recorded and organized, enabling rapid and accurate reporting and feedback, thereby improving the efficiency and quality of security operations.

[0180] A "wearable device" is a type of information terminal worn by a user, and is a device that has the function of acquiring voice data.

[0181] "Speech recognition means" is a technology for analyzing acquired voice data and converting it into text data.

[0182] "Natural language processing means" is a technology that analyzes text data and extracts keywords and important phrases.

[0183] "Grouping method" is a technique for grouping notes based on extracted keywords and phrases and organizing them by theme.

[0184] The "database storage means" is a database system that structures and stores organized notes.

[0185] "Interactive AI means" is a technology that uses a personal database to allow users to send requests to refer to or review past notes, searches for related information in response to the request, and generates a response in natural language using a generative AI model, which is then presented to the user.

[0186] A "generative AI model" is a model in which artificial intelligence learns from large datasets and engages in natural language dialogue and text generation.

[0187] A "prompt sentence" is a sentence that a user inputs to give specific instructions or questions to a conversational AI.

[0188] "Audio data" refers to sound data acquired by a user through a wearable device.

[0189] "Text data" refers to character data converted by a voice recognition means.

[0190] System Overview

[0191] The present invention mainly comprises the following elements:

[0192] 1. Wearable devices: These devices have the ability to acquire voice data. Examples include smart glasses and head-mounted displays.

[0193] 2. Speech recognition means: Converts voice data into text data. For example, a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text) is used.

[0194] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases. Examples include libraries like spaCy and NLTK.

[0195] 4. Grouping method: Group notes based on extracted keywords and phrases and organize them by theme.

[0196] 5. Database storage: Organize and structure your notes and store them in a personal database. Examples include Firebase and MongoDB.

[0197] 6. Conversational AI means: Based on a personal database, users send requests to refer to or review past notes, and a generative AI model generates and presents a response. Examples include OpenAI (registered trademark) GPT-3 (registered trademark).

[0198] Operation flow

[0199] Acquiring voice data and converting it to text

[0200] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[0201] The device receives this voice data and sends it to a voice recognition API, converting the voice data into text data.

[0202] Natural Language Processing and Grouping

[0203] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[0204] Keywords and important phrases such as "suspicious person" and "south gate" are extracted from the analyzed text data.

[0205] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme (e.g., "report of suspicious person spotted").

[0206] Saving to a database

[0207] The server structures the grouped notes by theme and saves them in a database in a format such as JSON. For example, it saves them as "October 7, 2023" and "Suspicious Person Discovery Report."

[0208] Dialogue with AI

[0209] The user uses smart glasses or a smartphone to send a request such as, "Show me the report notes about the suspicious person spotted yesterday."

[0210] The server receives the user's request and retrieves the relevant information from a personal database.

[0211] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user, for example, "There have been reports of a suspicious individual being spotted at the south gate on October 7, 2023."

[0212] Examples of concrete examples and prompts

[0213] 1. Example of voice input: The user voice inputs, "I have spotted a suspicious person at the south gate."

[0214] 2. Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[0215] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate," and the grouping means organizes them into the theme "report of suspicious person discovery."

[0216] 4. Example of saving to a database: The database saving method saves the data in the database as "October 7, 2023" and "Suspicious person discovery report."

[0217] 5. Example of AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[0218] Examples of prompt statements

[0219] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[0220] "Show me your notes about last night's surveillance."

[0221] "Any reports of unusual events this morning?"

[0222] This system instantly records and organizes on-site situations, thereby improving the efficiency and quality of security operations.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] Acquiring voice input

[0226] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[0227] Input: User's voice data

[0228] Output: Saved as audio data on the device.

[0229] Step 2:

[0230] Converting audio data to text

[0231] The device sends the captured voice data in real time to a cloud-based voice recognition API, which converts the voice data into text.

[0232] Input: Audio data

[0233] Output: Text data

[0234] Specific operation: The device sends voice data to the API and receives text data returned by the API.

[0235] Step 3:

[0236] Text data analysis

[0237] The server analyzes the converted text data using a natural language processing library (e.g., spaCy, NLTK) to extract keywords and important phrases.

[0238] Input: Text data

[0239] Output: A list of keywords and key phrases

[0240] Specific operation: The server analyzes the text data using a natural language processing library and extracts keywords and important phrases.

[0241] Step 4:

[0242] Note grouping

[0243] The server groups the notes based on the extracted keywords and phrases and organizes them into themes, such as "reporting suspicious person sightings."

[0244] Input: List of keywords and key phrases

[0245] Output: Grouped notes

[0246] What it does: The server automatically groups notes based on the relevance of keywords and phrases, organizing them by theme.

[0247] Step 5:

[0248] Saving to a database

[0249] The server structures the grouped notes and stores them in a personal database in a format such as JSON.

[0250] Input: Grouped notes

[0251] Output: Notes stored in the database

[0252] What it does: The server structures the organized notes and stores them in a database system.

[0253] Step 6:

[0254] Request a note

[0255] A user can use smart glasses or a smartphone to send a request to view past notes, for example, "Show me the report notes about the suspicious person spotted yesterday."

[0256] Input: User request

[0257] Output: Request to server

[0258] What happens: A user sends a request to a server through their device.

[0259] Step 7:

[0260] Data retrieval and response generation

[0261] Based on the user's request, the server searches for relevant information from a personal database and uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user.

[0262] Input: User request

[0263] Output: Natural language response

[0264] What it does: The server searches for relevant information from a personal database, uses a generative AI model to generate a natural language response, and sends it back to the user.

[0265] Examples of specific examples and prompts

[0266] Specific examples

[0267] User voice input: The user voice inputs, "We have spotted a suspicious person at the south gate."

[0268] Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[0269] Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate", and the grouping means organizes them into "report of suspicious person discovery".

[0270] Example of database storage: The memo is saved in the database as "October 7, 2023" and "Suspicious person discovered report."

[0271] Example of an AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[0272] Prompt Sentence Examples

[0273] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[0274] "Show me your notes about last night's surveillance."

[0275] "Any reports of unusual events this morning?"

[0276] 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.

[0277] This invention is a system that allows users to easily take voice memos through a wearable device, automatically grouping, organizing themes, structuring the memos, and saving them in a database, and then adding emotional information using an emotion engine.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0278] System Overview

[0279] The system mainly consists of the following elements:

[0280] 1. Wearable devices: have the ability to acquire voice data.

[0281] 2. Speech recognition means: converts voice data into text data.

[0282] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[0283] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[0284] 5. Database storage method: Organized notes are structured and stored in a database.

[0285] 6. Emotion engine: Analyzes emotions from voice data and adds that emotional information to text data.

[0286] 7. Interactive AI: Provides AI that allows users to retrieve information from a database and reflect on it interactively.

[0287] Acquisition of voice input, conversion to text, and sentiment analysis

[0288] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[0289] The terminal receives this voice data in real time and stores it in a data buffer.

[0290] The device sends the stored voice data to a voice recognition API (e.g., a cloud-based voice recognition service) and converts the voice data into text data.

[0291] The server receives the text data and uses an emotion engine to analyze the user's emotions during voice input, adding emotional information (e.g., joy, sadness, anger) to the text data.

[0292] Natural Language Processing and Grouping

[0293] The server analyzes using a natural language processing library (e.g., spaCy or NLTK).

[0294] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[0295] The server automatically groups notes based on the extracted keywords and phrases, and aggregates related notes. Furthermore, emotional information is also added to the notes. For example, a note may be associated with other notes containing keywords like "meeting" or "strategy" and tagged as having a "positive emotion."

[0296] Saving to a database

[0297] The server then structures the grouped notes by theme and stores them in a personal database in a format such as JSON, along with emotional information.

[0298] For example, data such as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive" is generated.

[0299] Dialogue with AI

[0300] Users use a smartphone, computer, or other interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0301] The server receives the user's request and searches for relevant notes in the personal database, including emotional information.

[0302] Based on this information, the conversational AI generates a response in natural language that takes emotion into account and presents it to the user, for example, "There is a memo that says 'I need to talk about a new marketing strategy at a meeting' on October 5, 2023. This memo contains positive emotion."

[0303] Specific examples

[0304] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[0305] 2. Example of text conversion and sentiment analysis: A speech recognition tool converts the text "We need to talk about our new marketing strategy at tomorrow's meeting" into text, and a sentiment engine adds the sentiment tag "positive."

[0306] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them into the theme "marketing strategy" and adds emotional information.

[0307] 4. Example of saving to database: Save to database as "October 5, 2023", "Meeting notes on marketing strategy", "Sentiment: Positive".

[0308] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There is a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.' This note has a positive sentiment."

[0309] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing and saving those memos, adding emotional information, and even reviewing them using AI.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] The user enters a voice note into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0313] Step 2:

[0314] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[0315] Step 3:

[0316] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, which is output as an output such as, "We need to talk about our new marketing strategy at tomorrow's meeting."

[0317] Step 4:

[0318] The server receives text data from the speech recognition API. In parallel, it sends the voice data to the emotion engine to analyze the user's emotions. The results are combined with the text data and added as "emotion information (e.g., positive, negative)."

[0319] Step 5:

[0320] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK), which includes grammatical analysis, morphological analysis, and keyword extraction.

[0321] Step 6:

[0322] The server extracts keywords and important phrases from the analyzed text data, such as "meeting," "new marketing strategy," "speak," and "necessary." Furthermore, emotional information is also included in the text data. For example, "Keywords: meeting, marketing strategy" and "Emotional information: positive."

[0323] Step 7:

[0324] The server then groups notes based on the extracted keywords and phrases. For example, it could group notes with the theme "marketing strategy" with other notes containing the keyword "meeting." It also takes into account emotional information and tags them with "positive emotion."

[0325] Step 8:

[0326] The server stores structured memo data in a personal database, including date, theme, keywords, and sentiment information. For example, "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[0327] Step 9:

[0328] Users can use their smartphones or computers to send requests to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0329] Step 10:

[0330] The server receives the user's request and searches for the relevant notes in the personal database. The search criteria include not only keywords but also emotional information. For example, "Marketing Strategy," "Meeting," "Last Week," and "Emotion: Positive."

[0331] Step 11:

[0332] The server then passes the data to a conversational AI engine based on the search results, and responds to the user in natural language. For example, it provides results in the form of, "On October 5, 2023, it was noted that 'We need to talk about a new marketing strategy at a meeting.' This note contains positive sentiment."

[0333] Step 12:

[0334] Users can receive responses from the AI ​​and reflect on their own thoughts and learnings. Based on the emotional information, users can review past notes while taking into account their own emotional state. They can also ask the AI ​​for further information if they need more detailed information.

[0335] In this way, the system provides consistent support from voice input to organizing and saving data, adding emotional information, and reviewing it.

[0336] Example 2

[0337] 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."

[0338] In conventional note-taking systems, organizing and categorizing voice memos, as well as adding emotional information, is done manually, which requires time and effort from the user. Searching past notes is also inefficient, and it is particularly difficult to search and review them while taking emotional information into account. There is a need for a system that can solve these problems and manage voice memos efficiently and effectively.

[0339] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, database storage means for structuring the organized notes and storing them in a personal database, interactive AI means for enabling dialogue with the user based on the personal database, and emotion engine means for adding emotional information to the text data. This enables automatic acquisition, organization, and addition of emotional information to voice memos, as well as effective search and review.

[0340] A "wearable device" is a device that is worn by a user and has the function of acquiring voice data.

[0341] "Voice data" refers to data in which the voice signal input by the user is recorded in digital format.

[0342] "Text data" is digital data that has been converted from voice data into character information.

[0343] "Speech recognition means" refers to processing means that has the function of analyzing voice data and converting it into corresponding text data.

[0344] A "natural language processing means" is a processing means that has the function of analyzing text data and extracting keywords and important phrases.

[0345] The "grouping means" is a processing means having the function of organizing and grouping memos by theme based on extracted keywords and phrases.

[0346] The "database storage means" is a processing means having the function of structuring the organized notes and storing them in a personal database.

[0347] A "personal database" is a database for storing a user's personal notes and information.

[0348] "Interactive AI means" refers to a processing means having artificial intelligence functions that enable dialogue with the user based on a personal database.

[0349] The "emotion engine means" is a processing means having a function of adding emotion information to text data.

[0350] "Emotional information" is digital data that indicates the user's emotional state (e.g., joy, sadness, anger) at the time of input.

[0351] A "data buffer" is a memory area for temporarily storing received audio data.

[0352] A "cloud-based speech recognition API" is a speech recognition service accessible via the internet and a programming interface that provides the functionality to convert speech data into text data.

[0353] "Analysis" is the process of understanding the meaning and structure of input data.

[0354] A "keyword" is a word or phrase that is considered to be particularly important in the text data.

[0355] This system allows users to easily take voice memos through a wearable device, automatically grouping, organizing, and structuring the memos into a database, and then adding emotional information using an emotion engine. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0356] System Overview

[0357] The system consists of the following main elements:

[0358] 1. Wearable devices: Used to capture user voice data. Examples include smartwatches and earphones.

[0359] 2. Terminal: A device that receives voice data from a wearable device and sends it to a cloud-based voice recognition API.

[0360] 3. Server: Receives the text data returned from the speech recognition API, analyzes the data using an emotion engine and natural language processing library, and groups and stores it in a database.

[0361] 4. Personal Database: A database for storing organized notes in a structured manner.

[0362] 5. Conversational AI: Based on a user request, it searches for relevant notes from a personal database and uses them for reflection.

[0363] System Operation

[0364] Acquisition of voice input, conversion to text, and sentiment analysis

[0365] The user uses the wearable device to input a voice memo saying, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0366] The device captures this audio data in real time and stores it in a data buffer.

[0367] The device sends the stored voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[0368] The speech recognition API converts the speech data into text data and returns the result to the device.

[0369] The terminal transmits the acquired text data to the server.

[0370] The server receives the text data and sends it to an emotion engine (e.g., IBM Watson® Tone Analyzer).

[0371] The emotion engine analyzes text data and detects the user's emotional information (e.g., joy, sadness, anger).

[0372] The server prepares the text data with the added emotion information for further processing.

[0373] Natural Language Processing and Grouping

[0374] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK).

[0375] Extract keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need") from the analyzed text data.

[0376] The server groups related notes based on extracted keywords and phrases and organizes them by theme.

[0377] For example, associate it with other notes that have keywords like "meeting" and "strategy" and tag it as "positive sentiment."

[0378] Saving to a database

[0379] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0380] For example, data might be saved as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[0381] Dialogue with AI

[0382] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[0383] The server receives the user's request and searches the personal database for the corresponding note.

[0384] Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a memo that says, 'I need to talk about a new marketing strategy at a meeting on October 5, 2023.' This memo contains positive emotions."

[0385] This invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing those memos, saving them, adding emotional information, and even reviewing them using AI.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1:

[0388] A user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy at tomorrow's meeting." At this time, the wearable device collects voice data and transmits it to the device.

[0389] Input: User's voice memo

[0390] Output: Audio data from the wearable device to the terminal

[0391] Step 2:

[0392] The device stores the received voice data in a data buffer in real time, and then sends the voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[0393] Input: Audio data received from a wearable device

[0394] Output: Audio data sent to a cloud-based speech recognition API

[0395] Step 3:

[0396] The cloud-based speech recognition API converts the received voice data into text data, which is then sent back to the device.

[0397] Input: Audio data

[0398] Output: Text data

[0399] Step 4:

[0400] The device sends the acquired text data to a server, which then receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[0401] Input: Text data

[0402] Output: Text data sent to the server

[0403] Step 5:

[0404] The emotion engine analyzes the text data and detects the user's emotional information (e.g., joy, sadness, anger). The server adds the emotional information to the text data and proceeds to the next processing step.

[0405] Input: Text data

[0406] Output: Text data with emotional information added

[0407] Step 6:

[0408] The server analyzes the sentiment-enhanced text data using a natural language processing library (e.g., spaCy or NLTK), extracting keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need").

[0409] Input: Text data with emotional information

[0410] Output: Extracted keywords and phrases

[0411] Step 7:

[0412] The server organizes notes into themes based on keywords and phrases, grouping related notes together—for example, associating notes with the keywords "meeting" and "strategy" with other notes and tagging them as "positive sentiment."

[0413] Input: Extracted keywords or phrases

[0414] Output: Grouped notes and sentiment tags

[0415] Step 8:

[0416] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0417] Input: Grouped notes and sentiment tags

[0418] Output: Structured notes stored in a personal database

[0419] Step 9:

[0420] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[0421] Input: User request

[0422] Output: The prompt sent to the server

[0423] Step 10:

[0424] The server receives the user's request and searches for the relevant note in the personal database. Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a note on October 5, 2023, that says, 'I need to talk at a meeting about a new marketing strategy.' This note contains positive emotions."

[0425] Input: User request

[0426] Output: A response message to the user

[0427] (Application example 2)

[0428] 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."

[0429] Autonomous vehicles require a system that can easily record the situation, instructions, and driver emotions while driving, automatically organize and group them, and review them later. However, existing systems have difficulty analyzing voice data and adding emotional information, and it is also difficult to efficiently search and check the data. To solve these issues, a system is needed that can easily take voice memos while driving, automatically analyze and organize them, and manage them by adding emotional information.

[0430] 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.

[0431] In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting the voice data into text data, and natural language processing means for analyzing the text data and extracting keywords and important phrases. This enables an interactive system to be installed in an autonomous vehicle, which includes an emotion engine that adds emotional information based on recorded voice data, generates responses in natural language that take the emotional information into consideration, and provides the responses to a display device or smartphone in the vehicle.

[0432] A "wearable device" is a device that can be worn by a user and includes means for acquiring audio data.

[0433] The "voice recognition means" is a device or system that has the function of analyzing acquired voice data and converting it into text data.

[0434] A "natural language processing means" is a system that analyzes text data and extracts keywords and important phrases.

[0435] The "grouping means" is a system that has the function of grouping and organizing notes by theme based on extracted keywords and phrases.

[0436] The "database storage means" is a system that has the function of structuring organized notes and storing them in a database.

[0437] "Interactive AI means" is an artificial intelligence system that enables dialogue with users based on a database.

[0438] The "Emotion Engine" is a system that has the function of analyzing and adding emotional information based on recorded voice data.

[0439] An "interactive system" is a system that generates and provides responses in natural language to in-vehicle displays or smartphones while taking emotional information into account.

[0440] The following elements are required to implement this invention: wearable device, voice recognition means, natural language processing means, grouping means, database storage means, interactive AI means, emotion engine, and interactive system. By integrating all of these elements, it becomes possible to efficiently acquire and manage voice memos in autonomous vehicles.

[0441] System Configuration

[0442] 1. Wearable devices

[0443] Users can easily take voice memos using a wearable device equipped with a microphone. The device is intended for use in autonomous vehicles, allowing hands-free voice input.

[0444] 2. Voice Recognition Method

[0445] The voice data is received in real time and converted into text data using a voice recognition means (such as a voice recognition API). For example, a cloud-based voice recognition service can be used.

[0446] 3. Natural Language Processing Methods

[0447] The server uses natural language processing libraries (e.g., spaCy or NLTK) to analyze the text data and extract keywords and important phrases, which allows it to automatically assess the importance of the information.

[0448] 4. Grouping Methods

[0449] The server then groups the voice memos based on the extracted keywords and phrases, organizing them by theme so that users can easily refer to them later.

[0450] 5. Database storage method

[0451] The organized voice memos are stored in a personal database in formats such as JSON, which ensures data integrity and efficient searching.

[0452] 6. Emotion Engine

[0453] Emotional information is added to the voice memo. Using an emotion engine, emotions such as joy, sadness, and anger are analyzed from the user's voice and tagged.

[0454] 7. Conversational AI methods

[0455] Users can use an in-car display or smartphone to send a request to view past notes, and a conversational AI mechanism responds, searching the database for the relevant note and generating a response in natural language.

[0456] Specific examples of processing

[0457] Voice input example

[0458] While driving, the user uses the wearable device to input a memo by voice, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan." This voice data is received in real time and converted by a voice recognition means into text data, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan."

[0459] Text analysis examples

[0460] Through analysis, the keywords "ahead," "cutting in," and "red sedan" are extracted, and these are organized using a grouping method. Furthermore, the emotion engine adds the emotional information of "anger."

[0461] Data storage and AI response examples

[0462] The date is saved in the personal database as "October 5, 2023," "Sudden cut-in," and "Emotion: Anger." Later, when the user requests, "Tell me what happened while you were driving today," the conversational AI means responds, "There is a note that says, 'On October 5, 2023, there was a sudden cut-in 100 meters ahead. The vehicle was a red sedan.' The emotion was anger."

[0463] Prompt Sentence Examples

[0464] Examples of prompts based on input voice data include:

[0465] "There was just a sudden cut-off about 100 meters ahead of me. The vehicle was a red sedan."

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1: The user uses the microphone on the wearable device to input a voice memo. For example, they might say, "There was a sudden cut-off 100 meters ahead. This vehicle was a red sedan." This input is captured by the wearable device and sent to the terminal.

[0468] Step 2: The device receives the voice data in real time and stores it in a data buffer. It then sends the voice data to a cloud-based speech recognition API, which converts the voice data into text data. The output is the text data, "There was a sudden cut-off just now, 100 meters ahead. This vehicle was a red sedan."

[0469] Step 3: The server passes the received text data to a natural language processing tool (e.g., spaCy or NLTK) to extract keywords and important phrases. The input is text data, and the output is the main keywords and phrases, such as "ahead," "cut in," and "red sedan."

[0470] Step 4: The server groups the voice memos based on the extracted keywords and phrases. The data is organized by theme. For example, memos containing the keywords "ahead," "cutting in," and "red sedan" are grouped under "unexpected incidents while driving."

[0471] Step 5: The server applies an emotion engine to the grouped data to analyze the user's emotion at the time of voice input. The input is text data, and an emotion tag (e.g., "anger") is added as the output.

[0472] Step 6: The server saves the notes with emotion information in a personal database as structured data (e.g., JSON format). The input is the organized and grouped note data, and the output is saved in the database.

[0473] Step 7: The user sends a request to view past notes from their smartphone or in-car display. For example, they might type, "Tell me what happened while driving today." This input is sent to the server.

[0474] Step 8: The server searches the personal database for the relevant note and generates a natural language response based on the search results. The input is the user's request, and the output is a response such as "There is a note that says 'There was a sudden cut-off 100 meters ahead. The vehicle was a red sedan' on October 5, 2023. The emotion is anger."

[0475] Step 9: The generated natural language response is sent to a display device in the car or to the user's smartphone, where the user can review the information. The output can be a visual display or a text message.

[0476] 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.

[0477] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0478] 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.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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."

[0492] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos and stores them in a database.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0493] System Overview

[0494] The system mainly consists of the following elements:

[0495] 1. Wearable devices: have the ability to acquire voice data.

[0496] 2. Speech recognition means: converts voice data into text data.

[0497] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[0498] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[0499] 5. Database storage method: Organized notes are structured and stored in a database.

[0500] 6. Interactive AI means: Provide AI that allows users to retrieve information from a database and reflect on it in an interactive format.

[0501] Acquiring voice input and converting it to text

[0502] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[0503] The device receives this voice data and converts it into text data by sending it to a voice recognition API (e.g., a cloud-based voice recognition service).

[0504] Natural Language Processing and Grouping

[0505] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[0506] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[0507] The server automatically groups notes based on the extracted keywords and phrases, grouping related notes together—for example, associating them with other notes that share the keywords "meeting" and "strategy."

[0508] Saving to a database

[0509] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0510] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[0511] Dialogue with AI

[0512] Users use a smartphone or PC interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0513] The server receives the user's request and retrieves the relevant information from a personal database.

[0514] A conversational AI solution uses this information to generate a natural language response and present it to the user, such as "There is a memo that says 'You need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[0515] Specific examples

[0516] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[0517] 2. Example of text conversion: A speech recognition tool converts the text into "We need to talk about our new marketing strategy at tomorrow's meeting."

[0518] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means organizes them into the theme "marketing strategy."

[0519] 4. Example of saving to database: Save to database as "October 5, 2023" and "Meeting notes on marketing strategy."

[0520] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[0521] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[0522] The processing flow will be explained below.

[0523] Step 1:

[0524] Users enter voice notes into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0525] Step 2:

[0526] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[0527] Step 3:

[0528] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, such as "We need to talk about our new marketing strategy in tomorrow's meeting."

[0529] Step 4:

[0530] The server receives the text data from the speech recognition API and analyzes it using a natural language processing library (e.g., spaCy or NLTK). This involves grammatical and morphological analysis of the text data.

[0531] Step 5:

[0532] The server extracts keywords and important phrases from the analysis results, such as "meeting," "new marketing strategy," "speak," and "necessary."

[0533] Step 6:

[0534] The server groups notes based on the extracted keywords and phrases, for example, grouping a note with the theme "marketing strategy" with other notes containing the keyword "meeting."

[0535] Step 7:

[0536] The server structures the organized notes. For example, it generates data in JSON format such as "October 5, 2023" and "Meeting notes on marketing strategy."

[0537] Step 8:

[0538] The server stores the structured data in a personal database, which allows notes to be organized by date and subject.

[0539] Step 9:

[0540] A user launches a conversational AI assistant application and sends a request to view past notes, for example, "Show me the notes from last week's marketing strategy meeting."

[0541] Step 10:

[0542] The server receives the user's request and searches the personal database for relevant notes, for example, using the search criteria "marketing strategy," "meeting," and "last week."

[0543] Step 11:

[0544] The server passes the search results to a conversational AI engine, which generates a natural-language response for the user, such as "There is a memo that says 'I need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[0545] Step 12:

[0546] Users can receive responses from the AI, reflect on their own thoughts and learnings, and ask the AI ​​for more detailed information if necessary.

[0547] As described above, this system provides consistent support from voice input to data organization, storage, and review.

[0548] Example 1

[0549] 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."

[0550] Conventional note-taking and management systems require users to manually input information, which is time-consuming and labor-intensive. Furthermore, it is difficult to efficiently organize and manage notes, making it difficult to quickly search for and reference necessary information. This reduces user efficiency, especially in business and academic activities.

[0551] 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.

[0552] In this invention, the server includes means for acquiring voice data using a wearable device, speech recognition means for converting the voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, storage means for structuring the organized notes and storing them in a database, interactive artificial intelligence means for enabling a dialogue with a user based on the database, means for receiving a request from a user and searching past notes, and means for generating a response in natural language based on the search results and presenting it to the user. This allows a user to easily and quickly acquire notes through voice input and then efficiently organize and restore them.

[0553] A "wearable device" is a small electronic device that can be worn by a user and has the function of acquiring voice data.

[0554] "Speech recognition means" refers to a technique or device for converting voice data into text data.

[0555] "Natural language processing means" refers to technology or equipment for analyzing text data and extracting keywords and important phrases.

[0556] A "grouping means" is a technique or device for grouping notes based on extracted keywords or phrases and organizing them by theme.

[0557] "Storage means" is a technique or device for storing grouped and structured notes in a database.

[0558] A "database" is a collection of structured data that is organized and can be efficiently managed, searched, and referenced.

[0559] "Interactive artificial intelligence means" refers to an artificial intelligence technology or device that enables a natural language dialogue with a user and provides information based on the user's request.

[0560] A "request" is a request or command sent by a user to obtain some information.

[0561] A "retrieval means" is a technique or device for retrieving relevant data from a database based on a request.

[0562] The "means for generating a response" is a technology or device for generating a response to the user in natural language based on the search results.

[0563] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos into a database. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0564] Acquiring voice input and converting it to text

[0565] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0566] The device receives this voice data and sends it in real time to a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), which converts the voice data into text data.

[0567] The server receives the converted text data from the speech recognition API and uses it for subsequent processing.

[0568] Natural Language Processing and Grouping

[0569] The server analyzes the converted text data using a natural language processing library (e.g., spaCy or NLTK).

[0570] Keywords and important phrases are extracted from the analysis results. At this stage, keywords such as "meeting," "new marketing strategy," "speak," and "necessary" are picked up.

[0571] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme, for example, associating them with other notes that share the keywords "meeting" and "strategy."

[0572] Saving to a database

[0573] The server structures the grouped notes by theme and stores them in a database in a format such as JSON, possibly using a database such as MySQL or MongoDB.

[0574] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[0575] Dialogue with AI

[0576] The user uses an interface such as a smartphone or PC to send a request to view past notes, for example, by entering a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[0577] The server receives the user's request and retrieves relevant information from a personal database.

[0578] The conversational AI tool generates a response in natural language based on this information and presents it to the user, for example, "There is a memo that says 'You need to talk about the new marketing strategy at a meeting on October 5, 2023."

[0579] Specific use cases

[0580] 1. Voice input example:

[0581] The user utters, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0582] 2. Text example:

[0583] The speech recognition means converts this into text: "We need to talk about our new marketing strategy in tomorrow's meeting."

[0584] 3. Parsing and Grouping Examples:

[0585] The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them together under the theme "marketing strategy."

[0586] 4. Example of saving to database:

[0587] Save this in the database as "October 5, 2023" and "Meeting notes on marketing strategy."

[0588] 5. Examples of AI dialogue:

[0589] The user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[0590] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[0591] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0592] Step 1:

[0593] A user initiates a voice memo using a wearable device. The user dictates, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0594] Input: User's voice data

[0595] Output: Temporary audio data file on the device

[0596] What happens: The user presses a button on the wearable device or uses a voice command to initiate voice input.

[0597] Step 2:

[0598] The device sends voice data to the voice recognition API in real time and receives it as text data.

[0599] Input: Audio data file

[0600] Output: Recognized text data

[0601] Specific operation: The device sends voice data to a cloud-based speech recognition service and obtains text data in real time.

[0602] Step 3:

[0603] The server receives the text data and analyzes it using a natural language processing library.

[0604] Input: Speech-recognized text data (e.g., "I need to talk about a new marketing strategy at tomorrow's meeting.")

[0605] Output: Keywords and key phrases (e.g., "meeting," "new marketing strategy," "speak," "need")

[0606] Specific operation: The server analyzes the text data and automatically extracts keywords and important phrases.

[0607] Step 4:

[0608] The server automatically groups notes based on extracted keywords and phrases, consolidating related notes.

[0609] Input: Keywords and key phrases

[0610] Output: Grouped memo data

[0611] What it does: The server uses a clustering algorithm to organize related notes into themes.

[0612] Step 5:

[0613] The server structures the grouped notes by theme and stores them in a database.

[0614] Input: Grouped memo data

[0615] Output: Structured memo data stored in a database

[0616] Specific operation: The server structures the data in JSON format or similar and stores it in a database such as MySQL or MongoDB.

[0617] Step 6:

[0618] A user can use a smartphone or computer to send a request to view a specific note, for example, "Show me the notes from last week's meeting on marketing strategy."

[0619] Input: User request (prompt)

[0620] Output: Request data to the server

[0621] Specific Action: A user enters a request via voice or text to search for a specific note.

[0622] Step 7:

[0623] The server receives requests from users and retrieves relevant information from a personal database.

[0624] Input: User request (prompt)

[0625] Output: Search results

[0626] Specific behavior: The server queries the data in the database and retrieves the relevant note data.

[0627] Step 8:

[0628] The server uses conversational artificial intelligence means to generate a response in natural language based on the search results and present it to the user, for example, "There is a memo that says 'You need to talk about a new marketing strategy at a meeting' on October 5, 2023."

[0629] Input: Search results

[0630] Output: Response to the user

[0631] What it does: The server uses the generative AI model to generate a natural language response and sends it to the user's device.

[0632] In this way, users can conveniently and efficiently record information through voice memos and quickly obtain the information they need through interactive artificial intelligence.

[0633] (Application example 1)

[0634] 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."

[0635] Conventional security systems rely on paper or digital forms to record on-site situations, which often lacks immediacy and accuracy. It's also difficult to quickly organize the information acquired and use it as meaningful data. This leads to delays in emergency response and post-incident feedback, resulting in issues that reduce the efficiency and quality of security operations.

[0636] 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.

[0637] In this invention, the server includes: means for acquiring voice data using a wearable device; speech recognition means for converting the voice data into text data; natural language processing means for analyzing the text data and extracting keywords and important phrases; grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases; database storage means for structuring the organized notes and saving them in a personal database; means for sending a request for the user to refer to or review past notes based on the personal database; interactive AI means for searching the personal database for relevant information in response to the request, generating a response in natural language using a generative AI model, and presenting it to the user; and means for acquiring voice notes related to specific locations and situations in security operations, automatically identifying urgency and importance based on specific keywords and phrases, and displaying relevant notes preferentially. This enables on-site situations to be instantly recorded and organized, enabling rapid and accurate reporting and feedback, thereby improving the efficiency and quality of security operations.

[0638] A "wearable device" is a type of information terminal worn by a user, and is a device that has the function of acquiring voice data.

[0639] "Speech recognition means" is a technology for analyzing acquired voice data and converting it into text data.

[0640] "Natural language processing means" is a technology that analyzes text data and extracts keywords and important phrases.

[0641] "Grouping method" is a technique for grouping notes based on extracted keywords and phrases and organizing them by theme.

[0642] The "database storage means" is a database system that structures and stores organized notes.

[0643] "Interactive AI means" is a technology that uses a personal database to allow users to send requests to refer to or review past notes, searches for related information in response to the request, and generates a response in natural language using a generative AI model, which is then presented to the user.

[0644] A "generative AI model" is a model in which artificial intelligence learns from large datasets and engages in natural language dialogue and text generation.

[0645] A "prompt sentence" is a sentence that a user inputs to give specific instructions or questions to a conversational AI.

[0646] "Audio data" refers to sound data acquired by a user through a wearable device.

[0647] "Text data" refers to character data converted by a voice recognition means.

[0648] System Overview

[0649] The present invention mainly comprises the following elements:

[0650] 1. Wearable devices: These devices have the ability to acquire voice data. Examples include smart glasses and head-mounted displays.

[0651] 2. Speech recognition means: Converts voice data into text data. For example, a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text) is used.

[0652] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases. Examples include libraries like spaCy and NLTK.

[0653] 4. Grouping method: Group notes based on extracted keywords and phrases and organize them by theme.

[0654] 5. Database storage: Organize and structure your notes and store them in a personal database. Examples include Firebase and MongoDB.

[0655] 6. Conversational AI methods: Based on a personal database, users send requests to refer to or review past notes, and a generative AI model generates and presents a response. A specific example is OpenAI GPT-3.

[0656] Operation flow

[0657] Acquiring voice data and converting it to text

[0658] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[0659] The device receives this voice data and sends it to a voice recognition API, converting the voice data into text data.

[0660] Natural Language Processing and Grouping

[0661] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[0662] Keywords and important phrases such as "suspicious person" and "south gate" are extracted from the analyzed text data.

[0663] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme (e.g., "report of suspicious person spotted").

[0664] Saving to a database

[0665] The server structures the grouped notes by theme and saves them in a database in a format such as JSON. For example, it saves them as "October 7, 2023" and "Suspicious Person Discovery Report."

[0666] Dialogue with AI

[0667] The user uses smart glasses or a smartphone to send a request such as, "Show me the report notes about the suspicious person spotted yesterday."

[0668] The server receives the user's request and retrieves the relevant information from a personal database.

[0669] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user, for example, "There have been reports of a suspicious individual being spotted at the south gate on October 7, 2023."

[0670] Examples of concrete examples and prompts

[0671] 1. Example of voice input: The user voice inputs, "I have spotted a suspicious person at the south gate."

[0672] 2. Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[0673] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate," and the grouping means organizes them into the theme "report of suspicious person discovery."

[0674] 4. Example of saving to a database: The database saving method saves the data in the database as "October 7, 2023" and "Suspicious person discovery report."

[0675] 5. Example of AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[0676] Examples of prompt statements

[0677] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[0678] "Show me your notes about last night's surveillance."

[0679] "Any reports of unusual events this morning?"

[0680] This system instantly records and organizes on-site situations, thereby improving the efficiency and quality of security operations.

[0681] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0682] Step 1:

[0683] Acquiring voice input

[0684] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[0685] Input: User's voice data

[0686] Output: Saved as audio data on the device.

[0687] Step 2:

[0688] Converting audio data to text

[0689] The device sends the captured voice data in real time to a cloud-based voice recognition API, which converts the voice data into text.

[0690] Input: Audio data

[0691] Output: Text data

[0692] Specific operation: The device sends voice data to the API and receives text data returned by the API.

[0693] Step 3:

[0694] Text data analysis

[0695] The server analyzes the converted text data using a natural language processing library (e.g., spaCy, NLTK) to extract keywords and important phrases.

[0696] Input: Text data

[0697] Output: A list of keywords and key phrases

[0698] Specific operation: The server analyzes the text data using a natural language processing library and extracts keywords and important phrases.

[0699] Step 4:

[0700] Note grouping

[0701] The server groups the notes based on the extracted keywords and phrases and organizes them into themes, such as "reporting suspicious person sightings."

[0702] Input: List of keywords and key phrases

[0703] Output: Grouped notes

[0704] What it does: The server automatically groups notes based on the relevance of keywords and phrases, organizing them by theme.

[0705] Step 5:

[0706] Saving to a database

[0707] The server structures the grouped notes and stores them in a personal database in a format such as JSON.

[0708] Input: Grouped notes

[0709] Output: Notes stored in the database

[0710] What it does: The server structures the organized notes and stores them in a database system.

[0711] Step 6:

[0712] Request a note

[0713] A user can use smart glasses or a smartphone to send a request to view past notes, for example, "Show me the report notes about the suspicious person spotted yesterday."

[0714] Input: User request

[0715] Output: Request to server

[0716] What happens: A user sends a request to a server through their device.

[0717] Step 7:

[0718] Data retrieval and response generation

[0719] Based on the user's request, the server searches for relevant information from a personal database and uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user.

[0720] Input: User request

[0721] Output: Natural language response

[0722] What it does: The server searches for relevant information from a personal database, uses a generative AI model to generate a natural language response, and sends it back to the user.

[0723] Examples of specific examples and prompts

[0724] Specific examples

[0725] User voice input: The user voice inputs, "We have spotted a suspicious person at the south gate."

[0726] Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[0727] Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate", and the grouping means organizes them into "report of suspicious person discovery".

[0728] Example of database storage: The memo is saved in the database as "October 7, 2023" and "Suspicious person discovered report."

[0729] Example of an AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[0730] Prompt Sentence Examples

[0731] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[0732] "Show me your notes about last night's surveillance."

[0733] "Any reports of unusual events this morning?"

[0734] 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.

[0735] This invention is a system that allows users to easily take voice memos through a wearable device, automatically grouping, organizing themes, structuring the memos, and saving them in a database, and then adding emotional information using an emotion engine.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0736] System Overview

[0737] The system mainly consists of the following elements:

[0738] 1. Wearable devices: have the ability to acquire voice data.

[0739] 2. Speech recognition means: converts voice data into text data.

[0740] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[0741] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[0742] 5. Database storage method: Organized notes are structured and stored in a database.

[0743] 6. Emotion engine: Analyzes emotions from voice data and adds that emotional information to text data.

[0744] 7. Interactive AI: Provides AI that allows users to retrieve information from a database and reflect on it interactively.

[0745] Acquisition of voice input, conversion to text, and sentiment analysis

[0746] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[0747] The terminal receives this voice data in real time and stores it in a data buffer.

[0748] The device sends the stored voice data to a voice recognition API (e.g., a cloud-based voice recognition service) and converts the voice data into text data.

[0749] The server receives the text data and uses an emotion engine to analyze the user's emotions during voice input, adding emotional information (e.g., joy, sadness, anger) to the text data.

[0750] Natural Language Processing and Grouping

[0751] The server analyzes using a natural language processing library (e.g., spaCy or NLTK).

[0752] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[0753] The server automatically groups notes based on the extracted keywords and phrases, and aggregates related notes. Furthermore, emotional information is also added to the notes. For example, a note may be associated with other notes containing keywords like "meeting" or "strategy" and tagged as having a "positive emotion."

[0754] Saving to a database

[0755] The server then structures the grouped notes by theme and stores them in a personal database in a format such as JSON, along with emotional information.

[0756] For example, data such as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive" is generated.

[0757] Dialogue with AI

[0758] Users use a smartphone, computer, or other interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0759] The server receives the user's request and searches for relevant notes in the personal database, including emotional information.

[0760] Based on this information, the conversational AI generates a response in natural language that takes emotion into account and presents it to the user, for example, "There is a memo that says 'I need to talk about a new marketing strategy at a meeting' on October 5, 2023. This memo contains positive emotion."

[0761] Specific examples

[0762] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[0763] 2. Example of text conversion and sentiment analysis: A speech recognition tool converts the text "We need to talk about our new marketing strategy at tomorrow's meeting" into text, and a sentiment engine adds the sentiment tag "positive."

[0764] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them into the theme "marketing strategy" and adds emotional information.

[0765] 4. Example of saving to database: Save to database as "October 5, 2023", "Meeting notes on marketing strategy", "Sentiment: Positive".

[0766] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There is a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.' This note has a positive sentiment."

[0767] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing and saving those memos, adding emotional information, and even reviewing them using AI.

[0768] The processing flow will be explained below.

[0769] Step 1:

[0770] The user enters a voice note into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0771] Step 2:

[0772] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[0773] Step 3:

[0774] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, which is output as an output such as, "We need to talk about our new marketing strategy at tomorrow's meeting."

[0775] Step 4:

[0776] The server receives text data from the speech recognition API. In parallel, it sends the voice data to the emotion engine to analyze the user's emotions. The results are combined with the text data and added as "emotion information (e.g., positive, negative)."

[0777] Step 5:

[0778] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK), which includes grammatical analysis, morphological analysis, and keyword extraction.

[0779] Step 6:

[0780] The server extracts keywords and important phrases from the analyzed text data, such as "meeting," "new marketing strategy," "speak," and "necessary." Furthermore, emotional information is also included in the text data. For example, "Keywords: meeting, marketing strategy" and "Emotional information: positive."

[0781] Step 7:

[0782] The server then groups notes based on the extracted keywords and phrases. For example, it could group notes with the theme "marketing strategy" with other notes containing the keyword "meeting." It also takes into account emotional information and tags them with "positive emotion."

[0783] Step 8:

[0784] The server stores structured memo data in a personal database, including date, theme, keywords, and sentiment information. For example, "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[0785] Step 9:

[0786] Users can use their smartphones or computers to send requests to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0787] Step 10:

[0788] The server receives the user's request and searches for the relevant notes in the personal database. The search criteria include not only keywords but also emotional information. For example, "Marketing Strategy," "Meeting," "Last Week," and "Emotion: Positive."

[0789] Step 11:

[0790] The server then passes the data to a conversational AI engine based on the search results, and responds to the user in natural language. For example, it provides results in the form of, "On October 5, 2023, it was noted that 'We need to talk about a new marketing strategy at a meeting.' This note contains positive sentiment."

[0791] Step 12:

[0792] Users can receive responses from the AI ​​and reflect on their own thoughts and learnings. Based on the emotional information, users can review past notes while taking into account their own emotional state. They can also ask the AI ​​for further information if they need more detailed information.

[0793] In this way, the system provides consistent support from voice input to organizing and saving data, adding emotional information, and reviewing it.

[0794] Example 2

[0795] 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."

[0796] In conventional note-taking systems, organizing and categorizing voice memos, as well as adding emotional information, is done manually, which requires time and effort from the user. Searching past notes is also inefficient, and it is particularly difficult to search and review them while taking emotional information into account. There is a need for a system that can solve these problems and manage voice memos efficiently and effectively.

[0797] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, database storage means for structuring the organized notes and storing them in a personal database, interactive AI means for enabling dialogue with the user based on the personal database, and emotion engine means for adding emotional information to the text data. This enables automatic acquisition, organization, and addition of emotional information to voice memos, as well as effective search and review.

[0798] A "wearable device" is a device that is worn by a user and has the function of acquiring voice data.

[0799] "Voice data" refers to data in which the voice signal input by the user is recorded in digital format.

[0800] "Text data" is digital data that has been converted from voice data into character information.

[0801] "Speech recognition means" refers to processing means that has the function of analyzing voice data and converting it into corresponding text data.

[0802] A "natural language processing means" is a processing means that has the function of analyzing text data and extracting keywords and important phrases.

[0803] The "grouping means" is a processing means having the function of organizing and grouping memos by theme based on extracted keywords and phrases.

[0804] The "database storage means" is a processing means having the function of structuring the organized notes and storing them in a personal database.

[0805] A "personal database" is a database for storing a user's personal notes and information.

[0806] "Interactive AI means" refers to a processing means having artificial intelligence functions that enable dialogue with the user based on a personal database.

[0807] The "emotion engine means" is a processing means having a function of adding emotion information to text data.

[0808] "Emotional information" is digital data that indicates the user's emotional state (e.g., joy, sadness, anger) at the time of input.

[0809] A "data buffer" is a memory area for temporarily storing received audio data.

[0810] A "cloud-based speech recognition API" is a speech recognition service accessible via the internet and a programming interface that provides the functionality to convert speech data into text data.

[0811] "Analysis" is the process of understanding the meaning and structure of input data.

[0812] A "keyword" is a word or phrase that is considered to be particularly important in the text data.

[0813] This system allows users to easily take voice memos through a wearable device, automatically grouping, organizing, and structuring the memos into a database, and then adding emotional information using an emotion engine. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0814] System Overview

[0815] The system consists of the following main elements:

[0816] 1. Wearable devices: Used to capture user voice data. Examples include smartwatches and earphones.

[0817] 2. Terminal: A device that receives voice data from a wearable device and sends it to a cloud-based voice recognition API.

[0818] 3. Server: Receives the text data returned from the speech recognition API, analyzes the data using an emotion engine and natural language processing library, and groups and stores it in a database.

[0819] 4. Personal Database: A database for storing organized notes in a structured manner.

[0820] 5. Conversational AI: Based on a user request, it searches for relevant notes from a personal database and uses them for reflection.

[0821] System Operation

[0822] Acquisition of voice input, conversion to text, and sentiment analysis

[0823] The user uses the wearable device to input a voice memo saying, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0824] The device captures this audio data in real time and stores it in a data buffer.

[0825] The device sends the stored voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[0826] The speech recognition API converts the speech data into text data and returns the result to the device.

[0827] The terminal transmits the acquired text data to the server.

[0828] The server receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[0829] The emotion engine analyzes text data and detects the user's emotional information (e.g., joy, sadness, anger).

[0830] The server prepares the text data with the added emotion information for further processing.

[0831] Natural Language Processing and Grouping

[0832] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK).

[0833] Extract keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need") from the analyzed text data.

[0834] The server groups related notes based on extracted keywords and phrases and organizes them by theme.

[0835] For example, associate it with other notes that have keywords like "meeting" and "strategy" and tag it as "positive sentiment."

[0836] Saving to a database

[0837] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0838] For example, data might be saved as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[0839] Dialogue with AI

[0840] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[0841] The server receives the user's request and searches the personal database for the corresponding note.

[0842] Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a memo that says, 'I need to talk about a new marketing strategy at a meeting on October 5, 2023.' This memo contains positive emotions."

[0843] This invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing those memos, saving them, adding emotional information, and even reviewing them using AI.

[0844] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0845] Step 1:

[0846] A user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy at tomorrow's meeting." At this time, the wearable device collects voice data and transmits it to the device.

[0847] Input: User's voice memo

[0848] Output: Audio data from the wearable device to the terminal

[0849] Step 2:

[0850] The device stores the received voice data in a data buffer in real time, and then sends the voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[0851] Input: Audio data received from a wearable device

[0852] Output: Audio data sent to a cloud-based speech recognition API

[0853] Step 3:

[0854] The cloud-based speech recognition API converts the received voice data into text data, which is then sent back to the device.

[0855] Input: Audio data

[0856] Output: Text data

[0857] Step 4:

[0858] The device sends the acquired text data to a server, which then receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[0859] Input: Text data

[0860] Output: Text data sent to the server

[0861] Step 5:

[0862] The emotion engine analyzes the text data and detects the user's emotional information (e.g., joy, sadness, anger). The server adds the emotional information to the text data and proceeds to the next processing step.

[0863] Input: Text data

[0864] Output: Text data with emotional information added

[0865] Step 6:

[0866] The server analyzes the sentiment-enhanced text data using a natural language processing library (e.g., spaCy or NLTK), extracting keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need").

[0867] Input: Text data with emotional information

[0868] Output: Extracted keywords and phrases

[0869] Step 7:

[0870] The server organizes notes into themes based on keywords and phrases, grouping related notes together—for example, associating notes with the keywords "meeting" and "strategy" with other notes and tagging them as "positive sentiment."

[0871] Input: Extracted keywords or phrases

[0872] Output: Grouped notes and sentiment tags

[0873] Step 8:

[0874] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0875] Input: Grouped notes and sentiment tags

[0876] Output: Structured notes stored in a personal database

[0877] Step 9:

[0878] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[0879] Input: User request

[0880] Output: The prompt sent to the server

[0881] Step 10:

[0882] The server receives the user's request and searches for the relevant note in the personal database. Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a note on October 5, 2023, that says, 'I need to talk at a meeting about a new marketing strategy.' This note contains positive emotions."

[0883] Input: User request

[0884] Output: A response message to the user

[0885] (Application example 2)

[0886] 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."

[0887] Autonomous vehicles require a system that can easily record the situation, instructions, and driver emotions while driving, automatically organize and group them, and review them later. However, existing systems have difficulty analyzing voice data and adding emotional information, and it is also difficult to efficiently search and check the data. To solve these issues, a system is needed that can easily take voice memos while driving, automatically analyze and organize them, and manage them by adding emotional information.

[0888] 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.

[0889] In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting the voice data into text data, and natural language processing means for analyzing the text data and extracting keywords and important phrases. This enables an interactive system to be installed in an autonomous vehicle, which includes an emotion engine that adds emotional information based on recorded voice data, generates responses in natural language that take the emotional information into consideration, and provides the responses to a display device or smartphone in the vehicle.

[0890] A "wearable device" is a device that can be worn by a user and includes means for acquiring audio data.

[0891] The "voice recognition means" is a device or system that has the function of analyzing acquired voice data and converting it into text data.

[0892] A "natural language processing means" is a system that analyzes text data and extracts keywords and important phrases.

[0893] The "grouping means" is a system that has the function of grouping and organizing notes by theme based on extracted keywords and phrases.

[0894] The "database storage means" is a system that has the function of structuring organized notes and storing them in a database.

[0895] "Interactive AI means" is an artificial intelligence system that enables dialogue with users based on a database.

[0896] The "Emotion Engine" is a system that has the function of analyzing and adding emotional information based on recorded voice data.

[0897] An "interactive system" is a system that generates and provides responses in natural language to in-vehicle displays or smartphones while taking emotional information into account.

[0898] The following elements are required to implement this invention: wearable device, voice recognition means, natural language processing means, grouping means, database storage means, interactive AI means, emotion engine, and interactive system. By integrating all of these elements, it becomes possible to efficiently acquire and manage voice memos in autonomous vehicles.

[0899] System Configuration

[0900] 1. Wearable devices

[0901] Users can easily take voice memos using a wearable device equipped with a microphone. The device is intended for use in autonomous vehicles, allowing hands-free voice input.

[0902] 2. Voice Recognition Method

[0903] The voice data is received in real time and converted into text data using a voice recognition means (such as a voice recognition API). For example, a cloud-based voice recognition service can be used.

[0904] 3. Natural Language Processing Methods

[0905] The server uses natural language processing libraries (e.g., spaCy or NLTK) to analyze the text data and extract keywords and important phrases, which allows it to automatically assess the importance of the information.

[0906] 4. Grouping Methods

[0907] The server then groups the voice memos based on the extracted keywords and phrases, organizing them by theme so that users can easily refer to them later.

[0908] 5. Database storage method

[0909] The organized voice memos are stored in a personal database in formats such as JSON, which ensures data integrity and efficient searching.

[0910] 6. Emotion Engine

[0911] Emotional information is added to the voice memo. Using an emotion engine, emotions such as joy, sadness, and anger are analyzed from the user's voice and tagged.

[0912] 7. Conversational AI methods

[0913] Users can use an in-car display or smartphone to send a request to view past notes, and a conversational AI mechanism responds, searching the database for the relevant note and generating a response in natural language.

[0914] Specific examples of processing

[0915] Voice input example

[0916] While driving, the user uses the wearable device to input a memo by voice, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan." This voice data is received in real time and converted by a voice recognition means into text data, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan."

[0917] Text analysis examples

[0918] Through analysis, the keywords "ahead," "cutting in," and "red sedan" are extracted, and these are organized using a grouping method. Furthermore, the emotion engine adds the emotional information of "anger."

[0919] Data storage and AI response examples

[0920] The date is saved in the personal database as "October 5, 2023," "Sudden cut-in," and "Emotion: Anger." Later, when the user requests, "Tell me what happened while you were driving today," the conversational AI means responds, "There is a note that says, 'On October 5, 2023, there was a sudden cut-in 100 meters ahead. The vehicle was a red sedan.' The emotion was anger."

[0921] Prompt Sentence Examples

[0922] Examples of prompts based on input voice data include:

[0923] "There was just a sudden cut-off about 100 meters ahead of me. The vehicle was a red sedan."

[0924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0925] Step 1: The user uses the microphone on the wearable device to input a voice memo. For example, they might say, "There was a sudden cut-off 100 meters ahead. This vehicle was a red sedan." This input is captured by the wearable device and sent to the terminal.

[0926] Step 2: The device receives the voice data in real time and stores it in a data buffer. It then sends the voice data to a cloud-based speech recognition API, which converts the voice data into text data. The output is the text data, "There was a sudden cut-off just now, 100 meters ahead. This vehicle was a red sedan."

[0927] Step 3: The server passes the received text data to a natural language processing tool (e.g., spaCy or NLTK) to extract keywords and important phrases. The input is text data, and the output is the main keywords and phrases, such as "ahead," "cut in," and "red sedan."

[0928] Step 4: The server groups the voice memos based on the extracted keywords and phrases. The data is organized by theme. For example, memos containing the keywords "ahead," "cutting in," and "red sedan" are grouped under "unexpected incidents while driving."

[0929] Step 5: The server applies an emotion engine to the grouped data to analyze the user's emotion at the time of voice input. The input is text data, and an emotion tag (e.g., "anger") is added as the output.

[0930] Step 6: The server saves the notes with emotion information in a personal database as structured data (e.g., JSON format). The input is the organized and grouped note data, and the output is saved in the database.

[0931] Step 7: The user sends a request to view past notes from their smartphone or in-car display. For example, they might type, "Tell me what happened while driving today." This input is sent to the server.

[0932] Step 8: The server searches the personal database for the relevant note and generates a natural language response based on the search results. The input is the user's request, and the output is a response such as "There is a note that says 'There was a sudden cut-off 100 meters ahead. The vehicle was a red sedan' on October 5, 2023. The emotion is anger."

[0933] Step 9: The generated natural language response is sent to a display device in the car or to the user's smartphone, where the user can review the information. The output can be a visual display or a text message.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] [Third embodiment]

[0938] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0939] 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.

[0940] 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).

[0941] 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.

[0942] 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.

[0943] 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).

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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."

[0950] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos and stores them in a database.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[0951] System Overview

[0952] The system mainly consists of the following elements:

[0953] 1. Wearable devices: have the ability to acquire voice data.

[0954] 2. Speech recognition means: converts voice data into text data.

[0955] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[0956] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[0957] 5. Database storage method: Organized notes are structured and stored in a database.

[0958] 6. Interactive AI means: Provide AI that allows users to retrieve information from a database and reflect on it in an interactive format.

[0959] Acquiring voice input and converting it to text

[0960] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[0961] The device receives this voice data and converts it into text data by sending it to a voice recognition API (e.g., a cloud-based voice recognition service).

[0962] Natural Language Processing and Grouping

[0963] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[0964] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[0965] The server automatically groups notes based on the extracted keywords and phrases, grouping related notes together—for example, associating them with other notes that share the keywords "meeting" and "strategy."

[0966] Saving to a database

[0967] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[0968] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[0969] Dialogue with AI

[0970] Users use a smartphone or PC interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[0971] The server receives the user's request and retrieves the relevant information from a personal database.

[0972] A conversational AI solution uses this information to generate a natural language response and present it to the user, such as "There is a memo that says 'You need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[0973] Specific examples

[0974] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[0975] 2. Example of text conversion: A speech recognition tool converts the text into "We need to talk about our new marketing strategy at tomorrow's meeting."

[0976] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means organizes them into the theme "marketing strategy."

[0977] 4. Example of saving to database: Save to database as "October 5, 2023" and "Meeting notes on marketing strategy."

[0978] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[0979] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[0980] The processing flow will be explained below.

[0981] Step 1:

[0982] Users enter voice notes into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[0983] Step 2:

[0984] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[0985] Step 3:

[0986] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, such as "We need to talk about our new marketing strategy in tomorrow's meeting."

[0987] Step 4:

[0988] The server receives the text data from the speech recognition API and analyzes it using a natural language processing library (e.g., spaCy or NLTK). This involves grammatical and morphological analysis of the text data.

[0989] Step 5:

[0990] The server extracts keywords and important phrases from the analysis results, such as "meeting," "new marketing strategy," "speak," and "necessary."

[0991] Step 6:

[0992] The server groups notes based on the extracted keywords and phrases, for example, grouping a note with the theme "marketing strategy" with other notes containing the keyword "meeting."

[0993] Step 7:

[0994] The server structures the organized notes. For example, it generates data in JSON format such as "October 5, 2023" and "Meeting notes on marketing strategy."

[0995] Step 8:

[0996] The server stores the structured data in a personal database, which allows notes to be organized by date and subject.

[0997] Step 9:

[0998] A user launches a conversational AI assistant application and sends a request to view past notes, for example, "Show me the notes from last week's marketing strategy meeting."

[0999] Step 10:

[1000] The server receives the user's request and searches the personal database for relevant notes, for example, using the search criteria "marketing strategy," "meeting," and "last week."

[1001] Step 11:

[1002] The server passes the search results to a conversational AI engine, which generates a natural-language response for the user, such as "There is a memo that says 'I need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[1003] Step 12:

[1004] Users can receive responses from the AI, reflect on their own thoughts and learnings, and ask the AI ​​for more detailed information if necessary.

[1005] As described above, this system provides consistent support from voice input to data organization, storage, and review.

[1006] Example 1

[1007] 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."

[1008] Conventional note-taking and management systems require users to manually input information, which is time-consuming and labor-intensive. Furthermore, it is difficult to efficiently organize and manage notes, making it difficult to quickly search for and reference necessary information. This reduces user efficiency, especially in business and academic activities.

[1009] 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.

[1010] In this invention, the server includes means for acquiring voice data using a wearable device, speech recognition means for converting the voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, storage means for structuring the organized notes and storing them in a database, interactive artificial intelligence means for enabling a dialogue with a user based on the database, means for receiving a request from a user and searching past notes, and means for generating a response in natural language based on the search results and presenting it to the user. This allows a user to easily and quickly acquire notes through voice input and then efficiently organize and restore them.

[1011] A "wearable device" is a small electronic device that can be worn by a user and has the function of acquiring voice data.

[1012] "Speech recognition means" refers to a technique or device for converting voice data into text data.

[1013] "Natural language processing means" refers to technology or equipment for analyzing text data and extracting keywords and important phrases.

[1014] A "grouping means" is a technique or device for grouping notes based on extracted keywords or phrases and organizing them by theme.

[1015] "Storage means" is a technique or device for storing grouped and structured notes in a database.

[1016] A "database" is a collection of structured data that is organized and can be efficiently managed, searched, and referenced.

[1017] "Interactive artificial intelligence means" refers to an artificial intelligence technology or device that enables a natural language dialogue with a user and provides information based on the user's request.

[1018] A "request" is a request or command sent by a user to obtain some information.

[1019] A "retrieval means" is a technique or device for retrieving relevant data from a database based on a request.

[1020] The "means for generating a response" is a technology or device for generating a response to the user in natural language based on the search results.

[1021] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos into a database. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1022] Acquiring voice input and converting it to text

[1023] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1024] The device receives this voice data and sends it in real time to a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), which converts the voice data into text data.

[1025] The server receives the converted text data from the speech recognition API and uses it for subsequent processing.

[1026] Natural Language Processing and Grouping

[1027] The server analyzes the converted text data using a natural language processing library (e.g., spaCy or NLTK).

[1028] Keywords and important phrases are extracted from the analysis results. At this stage, keywords such as "meeting," "new marketing strategy," "speak," and "necessary" are picked up.

[1029] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme, for example, associating them with other notes that share the keywords "meeting" and "strategy."

[1030] Saving to a database

[1031] The server structures the grouped notes by theme and stores them in a database in a format such as JSON, possibly using a database such as MySQL or MongoDB.

[1032] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[1033] Dialogue with AI

[1034] The user uses an interface such as a smartphone or PC to send a request to view past notes, for example, by entering a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[1035] The server receives the user's request and retrieves relevant information from a personal database.

[1036] The conversational AI tool generates a response in natural language based on this information and presents it to the user, for example, "There is a memo that says 'You need to talk about the new marketing strategy at a meeting on October 5, 2023."

[1037] Specific use cases

[1038] 1. Voice input example:

[1039] The user utters, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1040] 2. Text example:

[1041] The speech recognition means converts this into text: "We need to talk about our new marketing strategy in tomorrow's meeting."

[1042] 3. Parsing and Grouping Examples:

[1043] The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them together under the theme "marketing strategy."

[1044] 4. Example of saving to database:

[1045] Save this in the database as "October 5, 2023" and "Meeting notes on marketing strategy."

[1046] 5. Examples of AI dialogue:

[1047] The user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[1048] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[1049] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1050] Step 1:

[1051] A user initiates a voice memo using a wearable device. The user dictates, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1052] Input: User's voice data

[1053] Output: Temporary audio data file on the device

[1054] What happens: The user presses a button on the wearable device or uses a voice command to initiate voice input.

[1055] Step 2:

[1056] The device sends voice data to the voice recognition API in real time and receives it as text data.

[1057] Input: Audio data file

[1058] Output: Recognized text data

[1059] Specific operation: The device sends voice data to a cloud-based speech recognition service and obtains text data in real time.

[1060] Step 3:

[1061] The server receives the text data and analyzes it using a natural language processing library.

[1062] Input: Speech-recognized text data (e.g., "I need to talk about a new marketing strategy at tomorrow's meeting.")

[1063] Output: Keywords and key phrases (e.g., "meeting," "new marketing strategy," "speak," "need")

[1064] Specific operation: The server analyzes the text data and automatically extracts keywords and important phrases.

[1065] Step 4:

[1066] The server automatically groups notes based on extracted keywords and phrases, consolidating related notes.

[1067] Input: Keywords and key phrases

[1068] Output: Grouped memo data

[1069] What it does: The server uses a clustering algorithm to organize related notes into themes.

[1070] Step 5:

[1071] The server structures the grouped notes by theme and stores them in a database.

[1072] Input: Grouped memo data

[1073] Output: Structured memo data stored in a database

[1074] Specific operation: The server structures the data in JSON format or similar and stores it in a database such as MySQL or MongoDB.

[1075] Step 6:

[1076] A user can use a smartphone or computer to send a request to view a specific note, for example, "Show me the notes from last week's meeting on marketing strategy."

[1077] Input: User request (prompt)

[1078] Output: Request data to the server

[1079] Specific Action: A user enters a request via voice or text to search for a specific note.

[1080] Step 7:

[1081] The server receives requests from users and retrieves relevant information from a personal database.

[1082] Input: User request (prompt)

[1083] Output: Search results

[1084] Specific behavior: The server queries the data in the database and retrieves the relevant note data.

[1085] Step 8:

[1086] The server uses conversational artificial intelligence means to generate a response in natural language based on the search results and present it to the user, for example, "There is a memo that says 'You need to talk about a new marketing strategy at a meeting' on October 5, 2023."

[1087] Input: Search results

[1088] Output: Response to the user

[1089] What it does: The server uses the generative AI model to generate a natural language response and sends it to the user's device.

[1090] In this way, users can conveniently and efficiently record information through voice memos and quickly obtain the information they need through interactive artificial intelligence.

[1091] (Application example 1)

[1092] 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."

[1093] Conventional security systems rely on paper or digital forms to record on-site situations, which often lacks immediacy and accuracy. It's also difficult to quickly organize the information acquired and use it as meaningful data. This leads to delays in emergency response and post-incident feedback, resulting in issues that reduce the efficiency and quality of security operations.

[1094] 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.

[1095] In this invention, the server includes: means for acquiring voice data using a wearable device; speech recognition means for converting the voice data into text data; natural language processing means for analyzing the text data and extracting keywords and important phrases; grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases; database storage means for structuring the organized notes and saving them in a personal database; means for sending a request for the user to refer to or review past notes based on the personal database; interactive AI means for searching the personal database for relevant information in response to the request, generating a response in natural language using a generative AI model, and presenting it to the user; and means for acquiring voice notes related to specific locations and situations in security operations, automatically identifying urgency and importance based on specific keywords and phrases, and displaying relevant notes preferentially. This enables on-site situations to be instantly recorded and organized, enabling rapid and accurate reporting and feedback, thereby improving the efficiency and quality of security operations.

[1096] A "wearable device" is a type of information terminal worn by a user, and is a device that has the function of acquiring voice data.

[1097] "Speech recognition means" is a technology for analyzing acquired voice data and converting it into text data.

[1098] "Natural language processing means" is a technology that analyzes text data and extracts keywords and important phrases.

[1099] "Grouping method" is a technique for grouping notes based on extracted keywords and phrases and organizing them by theme.

[1100] The "database storage means" is a database system that structures and stores organized notes.

[1101] "Interactive AI means" is a technology that uses a personal database to allow users to send requests to refer to or review past notes, searches for related information in response to the request, and generates a response in natural language using a generative AI model, which is then presented to the user.

[1102] A "generative AI model" is a model in which artificial intelligence learns from large datasets and engages in natural language dialogue and text generation.

[1103] A "prompt sentence" is a sentence that a user inputs to give specific instructions or questions to a conversational AI.

[1104] "Audio data" refers to sound data acquired by a user through a wearable device.

[1105] "Text data" refers to character data converted by a voice recognition means.

[1106] System Overview

[1107] The present invention mainly comprises the following elements:

[1108] 1. Wearable devices: These devices have the ability to acquire voice data. Examples include smart glasses and head-mounted displays.

[1109] 2. Speech recognition means: Converts voice data into text data. For example, a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text) is used.

[1110] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases. Examples include libraries like spaCy and NLTK.

[1111] 4. Grouping method: Group notes based on extracted keywords and phrases and organize them by theme.

[1112] 5. Database storage: Organize and structure your notes and store them in a personal database. Examples include Firebase and MongoDB.

[1113] 6. Conversational AI methods: Based on a personal database, users send requests to refer to or review past notes, and a generative AI model generates and presents a response. A specific example is OpenAI GPT-3.

[1114] Operation flow

[1115] Acquiring voice data and converting it to text

[1116] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[1117] The device receives this voice data and sends it to a voice recognition API, converting the voice data into text data.

[1118] Natural Language Processing and Grouping

[1119] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[1120] Keywords and important phrases such as "suspicious person" and "south gate" are extracted from the analyzed text data.

[1121] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme (e.g., "report of suspicious person spotted").

[1122] Saving to a database

[1123] The server structures the grouped notes by theme and saves them in a database in a format such as JSON. For example, it saves them as "October 7, 2023" and "Suspicious Person Discovery Report."

[1124] Dialogue with AI

[1125] The user uses smart glasses or a smartphone to send a request such as, "Show me the report notes about the suspicious person spotted yesterday."

[1126] The server receives the user's request and retrieves the relevant information from a personal database.

[1127] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user, for example, "There have been reports of a suspicious individual being spotted at the south gate on October 7, 2023."

[1128] Examples of concrete examples and prompts

[1129] 1. Example of voice input: The user voice inputs, "I have spotted a suspicious person at the south gate."

[1130] 2. Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[1131] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate," and the grouping means organizes them into the theme "report of suspicious person discovery."

[1132] 4. Example of saving to a database: The database saving method saves the data in the database as "October 7, 2023" and "Suspicious person discovery report."

[1133] 5. Example of AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[1134] Examples of prompt statements

[1135] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[1136] "Show me your notes about last night's surveillance."

[1137] "Any reports of unusual events this morning?"

[1138] This system instantly records and organizes on-site situations, thereby improving the efficiency and quality of security operations.

[1139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1140] Step 1:

[1141] Acquiring voice input

[1142] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[1143] Input: User's voice data

[1144] Output: Saved as audio data on the device.

[1145] Step 2:

[1146] Converting audio data to text

[1147] The device sends the captured voice data in real time to a cloud-based voice recognition API, which converts the voice data into text.

[1148] Input: Audio data

[1149] Output: Text data

[1150] Specific operation: The device sends voice data to the API and receives text data returned by the API.

[1151] Step 3:

[1152] Text data analysis

[1153] The server analyzes the converted text data using a natural language processing library (e.g., spaCy, NLTK) to extract keywords and important phrases.

[1154] Input: Text data

[1155] Output: A list of keywords and key phrases

[1156] Specific operation: The server analyzes the text data using a natural language processing library and extracts keywords and important phrases.

[1157] Step 4:

[1158] Note grouping

[1159] The server groups the notes based on the extracted keywords and phrases and organizes them into themes, such as "reporting suspicious person sightings."

[1160] Input: List of keywords and key phrases

[1161] Output: Grouped notes

[1162] What it does: The server automatically groups notes based on the relevance of keywords and phrases, organizing them by theme.

[1163] Step 5:

[1164] Saving to a database

[1165] The server structures the grouped notes and stores them in a personal database in a format such as JSON.

[1166] Input: Grouped notes

[1167] Output: Notes stored in the database

[1168] What it does: The server structures the organized notes and stores them in a database system.

[1169] Step 6:

[1170] Request a note

[1171] A user can use smart glasses or a smartphone to send a request to view past notes, for example, "Show me the report notes about the suspicious person spotted yesterday."

[1172] Input: User request

[1173] Output: Request to server

[1174] What happens: A user sends a request to a server through their device.

[1175] Step 7:

[1176] Data retrieval and response generation

[1177] Based on the user's request, the server searches for relevant information from a personal database and uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user.

[1178] Input: User request

[1179] Output: Natural language response

[1180] What it does: The server searches for relevant information from a personal database, uses a generative AI model to generate a natural language response, and sends it back to the user.

[1181] Examples of specific examples and prompts

[1182] Specific examples

[1183] User voice input: The user voice inputs, "We have spotted a suspicious person at the south gate."

[1184] Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[1185] Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate", and the grouping means organizes them into "report of suspicious person discovery".

[1186] Example of database storage: The memo is saved in the database as "October 7, 2023" and "Suspicious person discovered report."

[1187] Example of an AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[1188] Prompt Sentence Examples

[1189] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[1190] "Show me your notes about last night's surveillance."

[1191] "Any reports of unusual events this morning?"

[1192] 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.

[1193] This invention is a system that allows users to easily take voice memos through a wearable device, automatically grouping, organizing themes, structuring the memos, and saving them in a database, and then adding emotional information using an emotion engine.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1194] System Overview

[1195] The system mainly consists of the following elements:

[1196] 1. Wearable devices: have the ability to acquire voice data.

[1197] 2. Speech recognition means: converts voice data into text data.

[1198] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[1199] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[1200] 5. Database storage method: Organized notes are structured and stored in a database.

[1201] 6. Emotion engine: Analyzes emotions from voice data and adds that emotional information to text data.

[1202] 7. Interactive AI: Provides AI that allows users to retrieve information from a database and reflect on it interactively.

[1203] Acquisition of voice input, conversion to text, and sentiment analysis

[1204] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[1205] The terminal receives this voice data in real time and stores it in a data buffer.

[1206] The device sends the stored voice data to a voice recognition API (e.g., a cloud-based voice recognition service) and converts the voice data into text data.

[1207] The server receives the text data and uses an emotion engine to analyze the user's emotions during voice input, adding emotional information (e.g., joy, sadness, anger) to the text data.

[1208] Natural Language Processing and Grouping

[1209] The server analyzes using a natural language processing library (e.g., spaCy or NLTK).

[1210] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[1211] The server automatically groups notes based on the extracted keywords and phrases, and aggregates related notes. Furthermore, emotional information is also added to the notes. For example, a note may be associated with other notes containing keywords like "meeting" or "strategy" and tagged as having a "positive emotion."

[1212] Saving to a database

[1213] The server then structures the grouped notes by theme and stores them in a personal database in a format such as JSON, along with emotional information.

[1214] For example, data such as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive" is generated.

[1215] Dialogue with AI

[1216] Users use a smartphone, computer, or other interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[1217] The server receives the user's request and searches for relevant notes in the personal database, including emotional information.

[1218] Based on this information, the conversational AI generates a response in natural language that takes emotion into account and presents it to the user, for example, "There is a memo that says 'I need to talk about a new marketing strategy at a meeting' on October 5, 2023. This memo contains positive emotion."

[1219] Specific examples

[1220] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[1221] 2. Example of text conversion and sentiment analysis: A speech recognition tool converts the text "We need to talk about our new marketing strategy at tomorrow's meeting" into text, and a sentiment engine adds the sentiment tag "positive."

[1222] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them into the theme "marketing strategy" and adds emotional information.

[1223] 4. Example of saving to database: Save to database as "October 5, 2023", "Meeting notes on marketing strategy", "Sentiment: Positive".

[1224] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There is a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.' This note has a positive sentiment."

[1225] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing and saving those memos, adding emotional information, and even reviewing them using AI.

[1226] The processing flow will be explained below.

[1227] Step 1:

[1228] The user enters a voice note into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1229] Step 2:

[1230] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[1231] Step 3:

[1232] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, which is output as an output such as, "We need to talk about our new marketing strategy at tomorrow's meeting."

[1233] Step 4:

[1234] The server receives text data from the speech recognition API. In parallel, it sends the voice data to the emotion engine to analyze the user's emotions. The results are combined with the text data and added as "emotion information (e.g., positive, negative)."

[1235] Step 5:

[1236] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK), which includes grammatical analysis, morphological analysis, and keyword extraction.

[1237] Step 6:

[1238] The server extracts keywords and important phrases from the analyzed text data, such as "meeting," "new marketing strategy," "speak," and "necessary." Furthermore, emotional information is also included in the text data. For example, "Keywords: meeting, marketing strategy" and "Emotional information: positive."

[1239] Step 7:

[1240] The server then groups notes based on the extracted keywords and phrases. For example, it could group notes with the theme "marketing strategy" with other notes containing the keyword "meeting." It also takes into account emotional information and tags them with "positive emotion."

[1241] Step 8:

[1242] The server stores structured memo data in a personal database, including date, theme, keywords, and sentiment information. For example, "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[1243] Step 9:

[1244] Users can use their smartphones or computers to send requests to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[1245] Step 10:

[1246] The server receives the user's request and searches for the relevant notes in the personal database. The search criteria include not only keywords but also emotional information. For example, "Marketing Strategy," "Meeting," "Last Week," and "Emotion: Positive."

[1247] Step 11:

[1248] The server then passes the data to a conversational AI engine based on the search results, and responds to the user in natural language. For example, it provides results in the form of, "On October 5, 2023, it was noted that 'We need to talk about a new marketing strategy at a meeting.' This note contains positive sentiment."

[1249] Step 12:

[1250] Users can receive responses from the AI ​​and reflect on their own thoughts and learnings. Based on the emotional information, users can review past notes while taking into account their own emotional state. They can also ask the AI ​​for further information if they need more detailed information.

[1251] In this way, the system provides consistent support from voice input to organizing and saving data, adding emotional information, and reviewing it.

[1252] Example 2

[1253] 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."

[1254] In conventional note-taking systems, organizing and categorizing voice memos, as well as adding emotional information, is done manually, which requires time and effort from the user. Searching past notes is also inefficient, and it is particularly difficult to search and review them while taking emotional information into account. There is a need for a system that can solve these problems and manage voice memos efficiently and effectively.

[1255] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, database storage means for structuring the organized notes and storing them in a personal database, interactive AI means for enabling dialogue with the user based on the personal database, and emotion engine means for adding emotional information to the text data. This enables automatic acquisition, organization, and addition of emotional information to voice memos, as well as effective search and review.

[1256] A "wearable device" is a device that is worn by a user and has the function of acquiring voice data.

[1257] "Voice data" refers to data in which the voice signal input by the user is recorded in digital format.

[1258] "Text data" is digital data that has been converted from voice data into character information.

[1259] "Speech recognition means" refers to processing means that has the function of analyzing voice data and converting it into corresponding text data.

[1260] A "natural language processing means" is a processing means that has the function of analyzing text data and extracting keywords and important phrases.

[1261] The "grouping means" is a processing means having the function of organizing and grouping memos by theme based on extracted keywords and phrases.

[1262] The "database storage means" is a processing means having the function of structuring the organized notes and storing them in a personal database.

[1263] A "personal database" is a database for storing a user's personal notes and information.

[1264] "Interactive AI means" refers to a processing means having artificial intelligence functions that enable dialogue with the user based on a personal database.

[1265] The "emotion engine means" is a processing means having a function of adding emotion information to text data.

[1266] "Emotional information" is digital data that indicates the user's emotional state (e.g., joy, sadness, anger) at the time of input.

[1267] A "data buffer" is a memory area for temporarily storing received audio data.

[1268] A "cloud-based speech recognition API" is a speech recognition service accessible via the internet and a programming interface that provides the functionality to convert speech data into text data.

[1269] "Analysis" is the process of understanding the meaning and structure of input data.

[1270] A "keyword" is a word or phrase that is considered to be particularly important in the text data.

[1271] This system allows users to easily take voice memos through a wearable device, automatically grouping, organizing, and structuring the memos into a database, and then adding emotional information using an emotion engine. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1272] System Overview

[1273] The system consists of the following main elements:

[1274] 1. Wearable devices: Used to capture user voice data. Examples include smartwatches and earphones.

[1275] 2. Terminal: A device that receives voice data from a wearable device and sends it to a cloud-based voice recognition API.

[1276] 3. Server: Receives the text data returned from the speech recognition API, analyzes the data using an emotion engine and natural language processing library, and groups and stores it in a database.

[1277] 4. Personal Database: A database for storing organized notes in a structured manner.

[1278] 5. Conversational AI: Based on a user request, it searches for relevant notes from a personal database and uses them for reflection.

[1279] System Operation

[1280] Acquisition of voice input, conversion to text, and sentiment analysis

[1281] The user uses the wearable device to input a voice memo saying, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1282] The device captures this audio data in real time and stores it in a data buffer.

[1283] The device sends the stored voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[1284] The speech recognition API converts the speech data into text data and returns the result to the device.

[1285] The terminal transmits the acquired text data to the server.

[1286] The server receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[1287] The emotion engine analyzes text data and detects the user's emotional information (e.g., joy, sadness, anger).

[1288] The server prepares the text data with the added emotion information for further processing.

[1289] Natural Language Processing and Grouping

[1290] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK).

[1291] Extract keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need") from the analyzed text data.

[1292] The server groups related notes based on extracted keywords and phrases and organizes them by theme.

[1293] For example, associate it with other notes that have keywords like "meeting" and "strategy" and tag it as "positive sentiment."

[1294] Saving to a database

[1295] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[1296] For example, data might be saved as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[1297] Dialogue with AI

[1298] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[1299] The server receives the user's request and searches the personal database for the corresponding note.

[1300] Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a memo that says, 'I need to talk about a new marketing strategy at a meeting on October 5, 2023.' This memo contains positive emotions."

[1301] This invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing those memos, saving them, adding emotional information, and even reviewing them using AI.

[1302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1303] Step 1:

[1304] A user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy at tomorrow's meeting." At this time, the wearable device collects voice data and transmits it to the device.

[1305] Input: User's voice memo

[1306] Output: Audio data from the wearable device to the terminal

[1307] Step 2:

[1308] The device stores the received voice data in a data buffer in real time, and then sends the voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[1309] Input: Audio data received from a wearable device

[1310] Output: Audio data sent to a cloud-based speech recognition API

[1311] Step 3:

[1312] The cloud-based speech recognition API converts the received voice data into text data, which is then sent back to the device.

[1313] Input: Audio data

[1314] Output: Text data

[1315] Step 4:

[1316] The device sends the acquired text data to a server, which then receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[1317] Input: Text data

[1318] Output: Text data sent to the server

[1319] Step 5:

[1320] The emotion engine analyzes the text data and detects the user's emotional information (e.g., joy, sadness, anger). The server adds the emotional information to the text data and proceeds to the next processing step.

[1321] Input: Text data

[1322] Output: Text data with emotional information added

[1323] Step 6:

[1324] The server analyzes the sentiment-enhanced text data using a natural language processing library (e.g., spaCy or NLTK), extracting keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need").

[1325] Input: Text data with emotional information

[1326] Output: Extracted keywords and phrases

[1327] Step 7:

[1328] The server organizes notes into themes based on keywords and phrases, grouping related notes together—for example, associating notes with the keywords "meeting" and "strategy" with other notes and tagging them as "positive sentiment."

[1329] Input: Extracted keywords or phrases

[1330] Output: Grouped notes and sentiment tags

[1331] Step 8:

[1332] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[1333] Input: Grouped notes and sentiment tags

[1334] Output: Structured notes stored in a personal database

[1335] Step 9:

[1336] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[1337] Input: User request

[1338] Output: The prompt sent to the server

[1339] Step 10:

[1340] The server receives the user's request and searches for the relevant note in the personal database. Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a note on October 5, 2023, that says, 'I need to talk at a meeting about a new marketing strategy.' This note contains positive emotions."

[1341] Input: User request

[1342] Output: A response message to the user

[1343] (Application example 2)

[1344] 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."

[1345] Autonomous vehicles require a system that can easily record the situation, instructions, and driver emotions while driving, automatically organize and group them, and review them later. However, existing systems have difficulty analyzing voice data and adding emotional information, and it is also difficult to efficiently search and check the data. To solve these issues, a system is needed that can easily take voice memos while driving, automatically analyze and organize them, and manage them by adding emotional information.

[1346] 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.

[1347] In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting the voice data into text data, and natural language processing means for analyzing the text data and extracting keywords and important phrases. This enables an interactive system to be installed in an autonomous vehicle, which includes an emotion engine that adds emotional information based on recorded voice data, generates responses in natural language that take the emotional information into consideration, and provides the responses to a display device or smartphone in the vehicle.

[1348] A "wearable device" is a device that can be worn by a user and includes means for acquiring audio data.

[1349] The "voice recognition means" is a device or system that has the function of analyzing acquired voice data and converting it into text data.

[1350] A "natural language processing means" is a system that analyzes text data and extracts keywords and important phrases.

[1351] The "grouping means" is a system that has the function of grouping and organizing notes by theme based on extracted keywords and phrases.

[1352] The "database storage means" is a system that has the function of structuring organized notes and storing them in a database.

[1353] "Interactive AI means" is an artificial intelligence system that enables dialogue with users based on a database.

[1354] The "Emotion Engine" is a system that has the function of analyzing and adding emotional information based on recorded voice data.

[1355] An "interactive system" is a system that generates and provides responses in natural language to in-vehicle displays or smartphones while taking emotional information into account.

[1356] The following elements are required to implement this invention: wearable device, voice recognition means, natural language processing means, grouping means, database storage means, interactive AI means, emotion engine, and interactive system. By integrating all of these elements, it becomes possible to efficiently acquire and manage voice memos in autonomous vehicles.

[1357] System Configuration

[1358] 1. Wearable devices

[1359] Users can easily take voice memos using a wearable device equipped with a microphone. The device is intended for use in autonomous vehicles, allowing hands-free voice input.

[1360] 2. Voice Recognition Method

[1361] The voice data is received in real time and converted into text data using a voice recognition means (such as a voice recognition API). For example, a cloud-based voice recognition service can be used.

[1362] 3. Natural Language Processing Methods

[1363] The server uses natural language processing libraries (e.g., spaCy or NLTK) to analyze the text data and extract keywords and important phrases, which allows it to automatically assess the importance of the information.

[1364] 4. Grouping Methods

[1365] The server then groups the voice memos based on the extracted keywords and phrases, organizing them by theme so that users can easily refer to them later.

[1366] 5. Database storage method

[1367] The organized voice memos are stored in a personal database in formats such as JSON, which ensures data integrity and efficient searching.

[1368] 6. Emotion Engine

[1369] Emotional information is added to the voice memo. Using an emotion engine, emotions such as joy, sadness, and anger are analyzed from the user's voice and tagged.

[1370] 7. Conversational AI methods

[1371] Users can use an in-car display or smartphone to send a request to view past notes, and a conversational AI mechanism responds, searching the database for the relevant note and generating a response in natural language.

[1372] Specific examples of processing

[1373] Voice input example

[1374] While driving, the user uses the wearable device to input a memo by voice, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan." This voice data is received in real time and converted by a voice recognition means into text data, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan."

[1375] Text analysis examples

[1376] Through analysis, the keywords "ahead," "cutting in," and "red sedan" are extracted, and these are organized using a grouping method. Furthermore, the emotion engine adds the emotional information of "anger."

[1377] Data storage and AI response examples

[1378] The date is saved in the personal database as "October 5, 2023," "Sudden cut-in," and "Emotion: Anger." Later, when the user requests, "Tell me what happened while you were driving today," the conversational AI means responds, "There is a note that says, 'On October 5, 2023, there was a sudden cut-in 100 meters ahead. The vehicle was a red sedan.' The emotion was anger."

[1379] Prompt Sentence Examples

[1380] Examples of prompts based on input voice data include:

[1381] "There was just a sudden cut-off about 100 meters ahead of me. The vehicle was a red sedan."

[1382] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1383] Step 1: The user uses the microphone on the wearable device to input a voice memo. For example, they might say, "There was a sudden cut-off 100 meters ahead. This vehicle was a red sedan." This input is captured by the wearable device and sent to the terminal.

[1384] Step 2: The device receives the voice data in real time and stores it in a data buffer. It then sends the voice data to a cloud-based speech recognition API, which converts the voice data into text data. The output is the text data, "There was a sudden cut-off just now, 100 meters ahead. This vehicle was a red sedan."

[1385] Step 3: The server passes the received text data to a natural language processing tool (e.g., spaCy or NLTK) to extract keywords and important phrases. The input is text data, and the output is the main keywords and phrases, such as "ahead," "cut in," and "red sedan."

[1386] Step 4: The server groups the voice memos based on the extracted keywords and phrases. The data is organized by theme. For example, memos containing the keywords "ahead," "cutting in," and "red sedan" are grouped under "unexpected incidents while driving."

[1387] Step 5: The server applies an emotion engine to the grouped data to analyze the user's emotion at the time of voice input. The input is text data, and an emotion tag (e.g., "anger") is added as the output.

[1388] Step 6: The server saves the notes with emotion information in a personal database as structured data (e.g., JSON format). The input is the organized and grouped note data, and the output is saved in the database.

[1389] Step 7: The user sends a request to view past notes from their smartphone or in-car display. For example, they might type, "Tell me what happened while driving today." This input is sent to the server.

[1390] Step 8: The server searches the personal database for the relevant note and generates a natural language response based on the search results. The input is the user's request, and the output is a response such as "There is a note that says 'There was a sudden cut-off 100 meters ahead. The vehicle was a red sedan' on October 5, 2023. The emotion is anger."

[1391] Step 9: The generated natural language response is sent to a display device in the car or to the user's smartphone, where the user can review the information. The output can be a visual display or a text message.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] [Fourth embodiment]

[1396] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1397] 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.

[1398] 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).

[1399] 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.

[1400] 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.

[1401] 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).

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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."

[1409] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos and stores them in a database.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1410] System Overview

[1411] The system mainly consists of the following elements:

[1412] 1. Wearable devices: have the ability to acquire voice data.

[1413] 2. Speech recognition means: converts voice data into text data.

[1414] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[1415] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[1416] 5. Database storage method: Organized notes are structured and stored in a database.

[1417] 6. Interactive AI means: Provide AI that allows users to retrieve information from a database and reflect on it in an interactive format.

[1418] Acquiring voice input and converting it to text

[1419] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[1420] The device receives this voice data and converts it into text data by sending it to a voice recognition API (e.g., a cloud-based voice recognition service).

[1421] Natural Language Processing and Grouping

[1422] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[1423] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[1424] The server automatically groups notes based on the extracted keywords and phrases, grouping related notes together—for example, associating them with other notes that share the keywords "meeting" and "strategy."

[1425] Saving to a database

[1426] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[1427] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[1428] Dialogue with AI

[1429] Users use a smartphone or PC interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[1430] The server receives the user's request and retrieves the relevant information from a personal database.

[1431] A conversational AI solution uses this information to generate a natural language response and present it to the user, such as "There is a memo that says 'You need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[1432] Specific examples

[1433] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[1434] 2. Example of text conversion: A speech recognition tool converts the text into "We need to talk about our new marketing strategy at tomorrow's meeting."

[1435] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means organizes them into the theme "marketing strategy."

[1436] 4. Example of saving to database: Save to database as "October 5, 2023" and "Meeting notes on marketing strategy."

[1437] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[1438] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[1439] The processing flow will be explained below.

[1440] Step 1:

[1441] Users enter voice notes into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1442] Step 2:

[1443] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[1444] Step 3:

[1445] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, such as "We need to talk about our new marketing strategy in tomorrow's meeting."

[1446] Step 4:

[1447] The server receives the text data from the speech recognition API and analyzes it using a natural language processing library (e.g., spaCy or NLTK). This involves grammatical and morphological analysis of the text data.

[1448] Step 5:

[1449] The server extracts keywords and important phrases from the analysis results, such as "meeting," "new marketing strategy," "speak," and "necessary."

[1450] Step 6:

[1451] The server groups notes based on the extracted keywords and phrases, for example, grouping a note with the theme "marketing strategy" with other notes containing the keyword "meeting."

[1452] Step 7:

[1453] The server structures the organized notes. For example, it generates data in JSON format such as "October 5, 2023" and "Meeting notes on marketing strategy."

[1454] Step 8:

[1455] The server stores the structured data in a personal database, which allows notes to be organized by date and subject.

[1456] Step 9:

[1457] A user launches a conversational AI assistant application and sends a request to view past notes, for example, "Show me the notes from last week's marketing strategy meeting."

[1458] Step 10:

[1459] The server receives the user's request and searches the personal database for relevant notes, for example, using the search criteria "marketing strategy," "meeting," and "last week."

[1460] Step 11:

[1461] The server passes the search results to a conversational AI engine, which generates a natural-language response for the user, such as "There is a memo that says 'I need to speak at a meeting about a new marketing strategy' on October 5, 2023."

[1462] Step 12:

[1463] Users can receive responses from the AI, reflect on their own thoughts and learnings, and ask the AI ​​for more detailed information if necessary.

[1464] As described above, this system provides consistent support from voice input to data organization, storage, and review.

[1465] Example 1

[1466] 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."

[1467] Conventional note-taking and management systems require users to manually input information, which is time-consuming and labor-intensive. Furthermore, it is difficult to efficiently organize and manage notes, making it difficult to quickly search for and reference necessary information. This reduces user efficiency, especially in business and academic activities.

[1468] 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.

[1469] In this invention, the server includes means for acquiring voice data using a wearable device, speech recognition means for converting the voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, storage means for structuring the organized notes and storing them in a database, interactive artificial intelligence means for enabling a dialogue with a user based on the database, means for receiving a request from a user and searching past notes, and means for generating a response in natural language based on the search results and presenting it to the user. This allows a user to easily and quickly acquire notes through voice input and then efficiently organize and restore them.

[1470] A "wearable device" is a small electronic device that can be worn by a user and has the function of acquiring voice data.

[1471] "Speech recognition means" refers to a technique or device for converting voice data into text data.

[1472] "Natural language processing means" refers to technology or equipment for analyzing text data and extracting keywords and important phrases.

[1473] A "grouping means" is a technique or device for grouping notes based on extracted keywords or phrases and organizing them by theme.

[1474] "Storage means" is a technique or device for storing grouped and structured notes in a database.

[1475] A "database" is a collection of structured data that is organized and can be efficiently managed, searched, and referenced.

[1476] "Interactive artificial intelligence means" refers to an artificial intelligence technology or device that enables a natural language dialogue with a user and provides information based on the user's request.

[1477] A "request" is a request or command sent by a user to obtain some information.

[1478] A "retrieval means" is a technique or device for retrieving relevant data from a database based on a request.

[1479] The "means for generating a response" is a technology or device for generating a response to the user in natural language based on the search results.

[1480] This invention is a system that allows users to easily take voice memos through a wearable device, and automatically groups, organizes, and structures the memos into a database. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1481] Acquiring voice input and converting it to text

[1482] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1483] The device receives this voice data and sends it in real time to a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), which converts the voice data into text data.

[1484] The server receives the converted text data from the speech recognition API and uses it for subsequent processing.

[1485] Natural Language Processing and Grouping

[1486] The server analyzes the converted text data using a natural language processing library (e.g., spaCy or NLTK).

[1487] Keywords and important phrases are extracted from the analysis results. At this stage, keywords such as "meeting," "new marketing strategy," "speak," and "necessary" are picked up.

[1488] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme, for example, associating them with other notes that share the keywords "meeting" and "strategy."

[1489] Saving to a database

[1490] The server structures the grouped notes by theme and stores them in a database in a format such as JSON, possibly using a database such as MySQL or MongoDB.

[1491] For example, notes can be categorized and saved as "October 5, 2023" and "Meeting notes on marketing strategy."

[1492] Dialogue with AI

[1493] The user uses an interface such as a smartphone or PC to send a request to view past notes, for example, by entering a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[1494] The server receives the user's request and retrieves relevant information from a personal database.

[1495] The conversational AI tool generates a response in natural language based on this information and presents it to the user, for example, "There is a memo that says 'You need to talk about the new marketing strategy at a meeting on October 5, 2023."

[1496] Specific use cases

[1497] 1. Voice input example:

[1498] The user utters, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1499] 2. Text example:

[1500] The speech recognition means converts this into text: "We need to talk about our new marketing strategy in tomorrow's meeting."

[1501] 3. Parsing and Grouping Examples:

[1502] The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them together under the theme "marketing strategy."

[1503] 4. Example of saving to database:

[1504] Save this in the database as "October 5, 2023" and "Meeting notes on marketing strategy."

[1505] 5. Examples of AI dialogue:

[1506] The user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There's a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.'"

[1507] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device to automatically organizing and saving those memos, and then reviewing them using AI.

[1508] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1509] Step 1:

[1510] A user initiates a voice memo using a wearable device. The user dictates, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1511] Input: User's voice data

[1512] Output: Temporary audio data file on the device

[1513] What happens: The user presses a button on the wearable device or uses a voice command to initiate voice input.

[1514] Step 2:

[1515] The device sends voice data to the voice recognition API in real time and receives it as text data.

[1516] Input: Audio data file

[1517] Output: Recognized text data

[1518] Specific operation: The device sends voice data to a cloud-based speech recognition service and obtains text data in real time.

[1519] Step 3:

[1520] The server receives the text data and analyzes it using a natural language processing library.

[1521] Input: Speech-recognized text data (e.g., "I need to talk about a new marketing strategy at tomorrow's meeting.")

[1522] Output: Keywords and key phrases (e.g., "meeting," "new marketing strategy," "speak," "need")

[1523] Specific operation: The server analyzes the text data and automatically extracts keywords and important phrases.

[1524] Step 4:

[1525] The server automatically groups notes based on extracted keywords and phrases, consolidating related notes.

[1526] Input: Keywords and key phrases

[1527] Output: Grouped memo data

[1528] What it does: The server uses a clustering algorithm to organize related notes into themes.

[1529] Step 5:

[1530] The server structures the grouped notes by theme and stores them in a database.

[1531] Input: Grouped memo data

[1532] Output: Structured memo data stored in a database

[1533] Specific operation: The server structures the data in JSON format or similar and stores it in a database such as MySQL or MongoDB.

[1534] Step 6:

[1535] A user can use a smartphone or computer to send a request to view a specific note, for example, "Show me the notes from last week's meeting on marketing strategy."

[1536] Input: User request (prompt)

[1537] Output: Request data to the server

[1538] Specific Action: A user enters a request via voice or text to search for a specific note.

[1539] Step 7:

[1540] The server receives requests from users and retrieves relevant information from a personal database.

[1541] Input: User request (prompt)

[1542] Output: Search results

[1543] Specific behavior: The server queries the data in the database and retrieves the relevant note data.

[1544] Step 8:

[1545] The server uses conversational artificial intelligence means to generate a response in natural language based on the search results and present it to the user, for example, "There is a memo that says 'You need to talk about a new marketing strategy at a meeting' on October 5, 2023."

[1546] Input: Search results

[1547] Output: Response to the user

[1548] What it does: The server uses the generative AI model to generate a natural language response and sends it to the user's device.

[1549] In this way, users can conveniently and efficiently record information through voice memos and quickly obtain the information they need through interactive artificial intelligence.

[1550] (Application example 1)

[1551] 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."

[1552] Conventional security systems rely on paper or digital forms to record on-site situations, which often lacks immediacy and accuracy. It's also difficult to quickly organize the information acquired and use it as meaningful data. This leads to delays in emergency response and post-incident feedback, resulting in issues that reduce the efficiency and quality of security operations.

[1553] 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.

[1554] In this invention, the server includes: means for acquiring voice data using a wearable device; speech recognition means for converting the voice data into text data; natural language processing means for analyzing the text data and extracting keywords and important phrases; grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases; database storage means for structuring the organized notes and saving them in a personal database; means for sending a request for the user to refer to or review past notes based on the personal database; interactive AI means for searching the personal database for relevant information in response to the request, generating a response in natural language using a generative AI model, and presenting it to the user; and means for acquiring voice notes related to specific locations and situations in security operations, automatically identifying urgency and importance based on specific keywords and phrases, and displaying relevant notes preferentially. This enables on-site situations to be instantly recorded and organized, enabling rapid and accurate reporting and feedback, thereby improving the efficiency and quality of security operations.

[1555] A "wearable device" is a type of information terminal worn by a user, and is a device that has the function of acquiring voice data.

[1556] "Speech recognition means" is a technology for analyzing acquired voice data and converting it into text data.

[1557] "Natural language processing means" is a technology that analyzes text data and extracts keywords and important phrases.

[1558] "Grouping method" is a technique for grouping notes based on extracted keywords and phrases and organizing them by theme.

[1559] The "database storage means" is a database system that structures and stores organized notes.

[1560] "Interactive AI means" is a technology that uses a personal database to allow users to send requests to refer to or review past notes, searches for related information in response to the request, and generates a response in natural language using a generative AI model, which is then presented to the user.

[1561] A "generative AI model" is a model in which artificial intelligence learns from large datasets and engages in natural language dialogue and text generation.

[1562] A "prompt sentence" is a sentence that a user inputs to give specific instructions or questions to a conversational AI.

[1563] "Audio data" refers to sound data acquired by a user through a wearable device.

[1564] "Text data" refers to character data converted by a voice recognition means.

[1565] System Overview

[1566] The present invention mainly comprises the following elements:

[1567] 1. Wearable devices: These devices have the ability to acquire voice data. Examples include smart glasses and head-mounted displays.

[1568] 2. Speech recognition means: Converts voice data into text data. For example, a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text) is used.

[1569] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases. Examples include libraries like spaCy and NLTK.

[1570] 4. Grouping method: Group notes based on extracted keywords and phrases and organize them by theme.

[1571] 5. Database storage: Organize and structure your notes and store them in a personal database. Examples include Firebase and MongoDB.

[1572] 6. Conversational AI methods: Based on a personal database, users send requests to refer to or review past notes, and a generative AI model generates and presents a response. A specific example is OpenAI GPT-3.

[1573] Operation flow

[1574] Acquiring voice data and converting it to text

[1575] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[1576] The device receives this voice data and sends it to a voice recognition API, converting the voice data into text data.

[1577] Natural Language Processing and Grouping

[1578] The server receives the converted text data and analyzes it using a natural language processing library (e.g., spaCy or NLTK).

[1579] Keywords and important phrases such as "suspicious person" and "south gate" are extracted from the analyzed text data.

[1580] The server automatically groups notes based on extracted keywords and phrases, organizing related notes by theme (e.g., "report of suspicious person spotted").

[1581] Saving to a database

[1582] The server structures the grouped notes by theme and saves them in a database in a format such as JSON. For example, it saves them as "October 7, 2023" and "Suspicious Person Discovery Report."

[1583] Dialogue with AI

[1584] The user uses smart glasses or a smartphone to send a request such as, "Show me the report notes about the suspicious person spotted yesterday."

[1585] The server receives the user's request and retrieves the relevant information from a personal database.

[1586] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user, for example, "There have been reports of a suspicious individual being spotted at the south gate on October 7, 2023."

[1587] Examples of concrete examples and prompts

[1588] 1. Example of voice input: The user voice inputs, "I have spotted a suspicious person at the south gate."

[1589] 2. Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[1590] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate," and the grouping means organizes them into the theme "report of suspicious person discovery."

[1591] 4. Example of saving to a database: The database saving method saves the data in the database as "October 7, 2023" and "Suspicious person discovery report."

[1592] 5. Example of AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[1593] Examples of prompt statements

[1594] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[1595] "Show me your notes about last night's surveillance."

[1596] "Any reports of unusual events this morning?"

[1597] This system instantly records and organizes on-site situations, thereby improving the efficiency and quality of security operations.

[1598] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1599] Step 1:

[1600] Acquiring voice input

[1601] The user uses a wearable device (e.g., smart glasses or a head-mounted display) to input a voice memo, for example, "We have spotted a suspicious person at the south gate."

[1602] Input: User's voice data

[1603] Output: Saved as audio data on the device.

[1604] Step 2:

[1605] Converting audio data to text

[1606] The device sends the captured voice data in real time to a cloud-based voice recognition API, which converts the voice data into text.

[1607] Input: Audio data

[1608] Output: Text data

[1609] Specific operation: The device sends voice data to the API and receives text data returned by the API.

[1610] Step 3:

[1611] Text data analysis

[1612] The server analyzes the converted text data using a natural language processing library (e.g., spaCy, NLTK) to extract keywords and important phrases.

[1613] Input: Text data

[1614] Output: A list of keywords and key phrases

[1615] Specific operation: The server analyzes the text data using a natural language processing library and extracts keywords and important phrases.

[1616] Step 4:

[1617] Note grouping

[1618] The server groups the notes based on the extracted keywords and phrases and organizes them into themes, such as "reporting suspicious person sightings."

[1619] Input: List of keywords and key phrases

[1620] Output: Grouped notes

[1621] What it does: The server automatically groups notes based on the relevance of keywords and phrases, organizing them by theme.

[1622] Step 5:

[1623] Saving to a database

[1624] The server structures the grouped notes and stores them in a personal database in a format such as JSON.

[1625] Input: Grouped notes

[1626] Output: Notes stored in the database

[1627] What it does: The server structures the organized notes and stores them in a database system.

[1628] Step 6:

[1629] Request a note

[1630] A user can use smart glasses or a smartphone to send a request to view past notes, for example, "Show me the report notes about the suspicious person spotted yesterday."

[1631] Input: User request

[1632] Output: Request to server

[1633] What happens: A user sends a request to a server through their device.

[1634] Step 7:

[1635] Data retrieval and response generation

[1636] Based on the user's request, the server searches for relevant information from a personal database and uses a generative AI model (e.g., OpenAI GPT-3) to generate a response in natural language and present it to the user.

[1637] Input: User request

[1638] Output: Natural language response

[1639] What it does: The server searches for relevant information from a personal database, uses a generative AI model to generate a natural language response, and sends it back to the user.

[1640] Examples of specific examples and prompts

[1641] Specific examples

[1642] User voice input: The user voice inputs, "We have spotted a suspicious person at the south gate."

[1643] Example of text conversion: The speech recognition means converts the text into "We have spotted a suspicious person at the south gate."

[1644] Example of analysis and grouping: The natural language processing means extracts the keywords "suspicious person" and "south gate", and the grouping means organizes them into "report of suspicious person discovery".

[1645] Example of database storage: The memo is saved in the database as "October 7, 2023" and "Suspicious person discovered report."

[1646] Example of an AI dialogue: A user requests, "Show me the report memo about the suspicious person spotted yesterday," and the conversational AI means responds, "There is a report that a suspicious person was spotted at the south gate on October 7, 2023."

[1647] Prompt Sentence Examples

[1648] "Please tell me the report about the suspicious person spotted at the south gate yesterday."

[1649] "Show me your notes about last night's surveillance."

[1650] "Any reports of unusual events this morning?"

[1651] 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.

[1652] This invention is a system that allows users to easily take voice memos through a wearable device, automatically grouping, organizing themes, structuring the memos, and saving them in a database, and then adding emotional information using an emotion engine.Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1653] System Overview

[1654] The system mainly consists of the following elements:

[1655] 1. Wearable devices: have the ability to acquire voice data.

[1656] 2. Speech recognition means: converts voice data into text data.

[1657] 3. Natural language processing tools: Analyze text data and extract keywords and important phrases.

[1658] 4. Grouping methods: Group notes based on keywords or phrases and organize them by theme.

[1659] 5. Database storage method: Organized notes are structured and stored in a database.

[1660] 6. Emotion engine: Analyzes emotions from voice data and adds that emotional information to text data.

[1661] 7. Interactive AI: Provides AI that allows users to retrieve information from a database and reflect on it interactively.

[1662] Acquisition of voice input, conversion to text, and sentiment analysis

[1663] The user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as "I need to talk about a new marketing strategy in tomorrow's meeting."

[1664] The terminal receives this voice data in real time and stores it in a data buffer.

[1665] The device sends the stored voice data to a voice recognition API (e.g., a cloud-based voice recognition service) and converts the voice data into text data.

[1666] The server receives the text data and uses an emotion engine to analyze the user's emotions during voice input, adding emotional information (e.g., joy, sadness, anger) to the text data.

[1667] Natural Language Processing and Grouping

[1668] The server analyzes using a natural language processing library (e.g., spaCy or NLTK).

[1669] Keywords and important phrases such as "meeting," "new marketing strategy," "speak," and "necessary" are extracted from the analyzed text data.

[1670] The server automatically groups notes based on the extracted keywords and phrases, and aggregates related notes. Furthermore, emotional information is also added to the notes. For example, a note may be associated with other notes containing keywords like "meeting" or "strategy" and tagged as having a "positive emotion."

[1671] Saving to a database

[1672] The server then structures the grouped notes by theme and stores them in a personal database in a format such as JSON, along with emotional information.

[1673] For example, data such as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive" is generated.

[1674] Dialogue with AI

[1675] Users use a smartphone, computer, or other interface to send a request to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[1676] The server receives the user's request and searches for relevant notes in the personal database, including emotional information.

[1677] Based on this information, the conversational AI generates a response in natural language that takes emotion into account and presents it to the user, for example, "There is a memo that says 'I need to talk about a new marketing strategy at a meeting' on October 5, 2023. This memo contains positive emotion."

[1678] Specific examples

[1679] 1. Voice input example: "I need to talk about a new marketing strategy in tomorrow's meeting."

[1680] 2. Example of text conversion and sentiment analysis: A speech recognition tool converts the text "We need to talk about our new marketing strategy at tomorrow's meeting" into text, and a sentiment engine adds the sentiment tag "positive."

[1681] 3. Example of analysis and grouping: The natural language processing means extracts the keywords "meeting" and "new marketing strategy," and the grouping means groups them into the theme "marketing strategy" and adds emotional information.

[1682] 4. Example of saving to database: Save to database as "October 5, 2023", "Meeting notes on marketing strategy", "Sentiment: Positive".

[1683] 5. Example of an AI conversation: A user requests, "Show me the notes from last week's meeting about our marketing strategy," and the AI ​​responds, "There is a note that says, 'We need to talk about our new marketing strategy in a meeting on October 5, 2023.' This note has a positive sentiment."

[1684] In this way, the present invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing and saving those memos, adding emotional information, and even reviewing them using AI.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] The user enters a voice note into the wearable device, for example, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1688] Step 2:

[1689] The terminal receives the voice data in real time and stores it in a data buffer, where it is converted into a digital format.

[1690] Step 3:

[1691] The device sends the stored voice data to a speech recognition API (e.g., a cloud-based speech recognition service) and converts the voice data into text data, which is output as an output such as, "We need to talk about our new marketing strategy at tomorrow's meeting."

[1692] Step 4:

[1693] The server receives text data from the speech recognition API. In parallel, it sends the voice data to the emotion engine to analyze the user's emotions. The results are combined with the text data and added as "emotion information (e.g., positive, negative)."

[1694] Step 5:

[1695] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK), which includes grammatical analysis, morphological analysis, and keyword extraction.

[1696] Step 6:

[1697] The server extracts keywords and important phrases from the analyzed text data, such as "meeting," "new marketing strategy," "speak," and "necessary." Furthermore, emotional information is also included in the text data. For example, "Keywords: meeting, marketing strategy" and "Emotional information: positive."

[1698] Step 7:

[1699] The server then groups notes based on the extracted keywords and phrases. For example, it could group notes with the theme "marketing strategy" with other notes containing the keyword "meeting." It also takes into account emotional information and tags them with "positive emotion."

[1700] Step 8:

[1701] The server stores structured memo data in a personal database, including date, theme, keywords, and sentiment information. For example, "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[1702] Step 9:

[1703] Users can use their smartphones or computers to send requests to view past notes, for example, by typing, "Show me the notes from last week's meeting on marketing strategy."

[1704] Step 10:

[1705] The server receives the user's request and searches for the relevant notes in the personal database. The search criteria include not only keywords but also emotional information. For example, "Marketing Strategy," "Meeting," "Last Week," and "Emotion: Positive."

[1706] Step 11:

[1707] The server then passes the data to a conversational AI engine based on the search results, and responds to the user in natural language. For example, it provides results in the form of, "On October 5, 2023, it was noted that 'We need to talk about a new marketing strategy at a meeting.' This note contains positive sentiment."

[1708] Step 12:

[1709] Users can receive responses from the AI ​​and reflect on their own thoughts and learnings. Based on the emotional information, users can review past notes while taking into account their own emotional state. They can also ask the AI ​​for further information if they need more detailed information.

[1710] In this way, the system provides consistent support from voice input to organizing and saving data, adding emotional information, and reviewing it.

[1711] Example 2

[1712] 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."

[1713] In conventional note-taking systems, organizing and categorizing voice memos, as well as adding emotional information, is done manually, which requires time and effort from the user. Searching past notes is also inefficient, and it is particularly difficult to search and review them while taking emotional information into account. There is a need for a system that can solve these problems and manage voice memos efficiently and effectively.

[1714] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting voice data into text data, natural language processing means for analyzing the text data and extracting keywords and important phrases, grouping means for grouping and organizing notes by theme based on the extracted keywords and phrases, database storage means for structuring the organized notes and storing them in a personal database, interactive AI means for enabling dialogue with the user based on the personal database, and emotion engine means for adding emotional information to the text data. This enables automatic acquisition, organization, and addition of emotional information to voice memos, as well as effective search and review.

[1715] A "wearable device" is a device that is worn by a user and has the function of acquiring voice data.

[1716] "Voice data" refers to data in which the voice signal input by the user is recorded in digital format.

[1717] "Text data" is digital data that has been converted from voice data into character information.

[1718] "Speech recognition means" refers to processing means that has the function of analyzing voice data and converting it into corresponding text data.

[1719] A "natural language processing means" is a processing means that has the function of analyzing text data and extracting keywords and important phrases.

[1720] The "grouping means" is a processing means having the function of organizing and grouping memos by theme based on extracted keywords and phrases.

[1721] The "database storage means" is a processing means having the function of structuring the organized notes and storing them in a personal database.

[1722] A "personal database" is a database for storing a user's personal notes and information.

[1723] "Interactive AI means" refers to a processing means having artificial intelligence functions that enable dialogue with the user based on a personal database.

[1724] The "emotion engine means" is a processing means having a function of adding emotion information to text data.

[1725] "Emotional information" is digital data that indicates the user's emotional state (e.g., joy, sadness, anger) at the time of input.

[1726] A "data buffer" is a memory area for temporarily storing received audio data.

[1727] A "cloud-based speech recognition API" is a speech recognition service accessible via the internet and a programming interface that provides the functionality to convert speech data into text data.

[1728] "Analysis" is the process of understanding the meaning and structure of input data.

[1729] A "keyword" is a word or phrase that is considered to be particularly important in the text data.

[1730] This system allows users to easily take voice memos through a wearable device, automatically grouping, organizing, and structuring the memos into a database, and then adding emotional information using an emotion engine. Furthermore, based on this database, users can reflect on their own thoughts and learning through dialogue with AI.

[1731] System Overview

[1732] The system consists of the following main elements:

[1733] 1. Wearable devices: Used to capture user voice data. Examples include smartwatches and earphones.

[1734] 2. Terminal: A device that receives voice data from a wearable device and sends it to a cloud-based voice recognition API.

[1735] 3. Server: Receives the text data returned from the speech recognition API, analyzes the data using an emotion engine and natural language processing library, and groups and stores it in a database.

[1736] 4. Personal Database: A database for storing organized notes in a structured manner.

[1737] 5. Conversational AI: Based on a user request, it searches for relevant notes from a personal database and uses them for reflection.

[1738] System Operation

[1739] Acquisition of voice input, conversion to text, and sentiment analysis

[1740] The user uses the wearable device to input a voice memo saying, "I need to talk about a new marketing strategy in tomorrow's meeting."

[1741] The device captures this audio data in real time and stores it in a data buffer.

[1742] The device sends the stored voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[1743] The speech recognition API converts the speech data into text data and returns the result to the device.

[1744] The terminal transmits the acquired text data to the server.

[1745] The server receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[1746] The emotion engine analyzes text data and detects the user's emotional information (e.g., joy, sadness, anger).

[1747] The server prepares the text data with the added emotion information for further processing.

[1748] Natural Language Processing and Grouping

[1749] The server analyzes the text data using a natural language processing library (e.g., spaCy or NLTK).

[1750] Extract keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need") from the analyzed text data.

[1751] The server groups related notes based on extracted keywords and phrases and organizes them by theme.

[1752] For example, associate it with other notes that have keywords like "meeting" and "strategy" and tag it as "positive sentiment."

[1753] Saving to a database

[1754] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[1755] For example, data might be saved as "October 5, 2023," "Meeting notes on marketing strategy," and "Sentiment: Positive."

[1756] Dialogue with AI

[1757] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[1758] The server receives the user's request and searches the personal database for the corresponding note.

[1759] Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a memo that says, 'I need to talk about a new marketing strategy at a meeting on October 5, 2023.' This memo contains positive emotions."

[1760] This invention provides a system that consistently supports everything from taking voice memos using a wearable device, to automatically organizing those memos, saving them, adding emotional information, and even reviewing them using AI.

[1761] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1762] Step 1:

[1763] A user uses a wearable device (e.g., a smartwatch or earphones) to input a note by voice, such as, "I need to talk about a new marketing strategy at tomorrow's meeting." At this time, the wearable device collects voice data and transmits it to the device.

[1764] Input: User's voice memo

[1765] Output: Audio data from the wearable device to the terminal

[1766] Step 2:

[1767] The device stores the received voice data in a data buffer in real time, and then sends the voice data to a cloud-based speech recognition API (e.g., Google Cloud Speech-to-Text).

[1768] Input: Audio data received from a wearable device

[1769] Output: Audio data sent to a cloud-based speech recognition API

[1770] Step 3:

[1771] The cloud-based speech recognition API converts the received voice data into text data, which is then sent back to the device.

[1772] Input: Audio data

[1773] Output: Text data

[1774] Step 4:

[1775] The device sends the acquired text data to a server, which then receives the text data and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[1776] Input: Text data

[1777] Output: Text data sent to the server

[1778] Step 5:

[1779] The emotion engine analyzes the text data and detects the user's emotional information (e.g., joy, sadness, anger). The server adds the emotional information to the text data and proceeds to the next processing step.

[1780] Input: Text data

[1781] Output: Text data with emotional information added

[1782] Step 6:

[1783] The server analyzes the sentiment-enhanced text data using a natural language processing library (e.g., spaCy or NLTK), extracting keywords and important phrases (e.g., "meeting," "new marketing strategy," "speak," "need").

[1784] Input: Text data with emotional information

[1785] Output: Extracted keywords and phrases

[1786] Step 7:

[1787] The server organizes notes into themes based on keywords and phrases, grouping related notes together—for example, associating notes with the keywords "meeting" and "strategy" with other notes and tagging them as "positive sentiment."

[1788] Input: Extracted keywords or phrases

[1789] Output: Grouped notes and sentiment tags

[1790] Step 8:

[1791] The server structures the grouped notes by theme and stores them in a personal database in a format such as JSON.

[1792] Input: Grouped notes and sentiment tags

[1793] Output: Structured notes stored in a personal database

[1794] Step 9:

[1795] A user uses an interface (e.g., a smartphone or a PC) to submit a request to view past notes, for example, by typing a prompt such as "Show me the notes from last week's meeting on marketing strategy."

[1796] Input: User request

[1797] Output: The prompt sent to the server

[1798] Step 10:

[1799] The server receives the user's request and searches for the relevant note in the personal database. Based on the search results, the conversational AI generates a natural language response, including emotional information, and presents it to the user. For example, it might respond, "There is a note on October 5, 2023, that says, 'I need to talk at a meeting about a new marketing strategy.' This note contains positive emotions."

[1800] Input: User request

[1801] Output: A response message to the user

[1802] (Application example 2)

[1803] 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."

[1804] Autonomous vehicles require a system that can easily record the situation, instructions, and driver emotions while driving, automatically organize and group them, and review them later. However, existing systems have difficulty analyzing voice data and adding emotional information, and it is also difficult to efficiently search and check the data. To solve these issues, a system is needed that can easily take voice memos while driving, automatically analyze and organize them, and manage them by adding emotional information.

[1805] 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.

[1806] In this invention, the server includes means for acquiring voice data using a wearable device, voice recognition means for converting the voice data into text data, and natural language processing means for analyzing the text data and extracting keywords and important phrases. This enables an interactive system to be installed in an autonomous vehicle, which includes an emotion engine that adds emotional information based on recorded voice data, generates responses in natural language that take the emotional information into consideration, and provides the responses to a display device or smartphone in the vehicle.

[1807] A "wearable device" is a device that can be worn by a user and includes means for acquiring audio data.

[1808] The "voice recognition means" is a device or system that has the function of analyzing acquired voice data and converting it into text data.

[1809] A "natural language processing means" is a system that analyzes text data and extracts keywords and important phrases.

[1810] The "grouping means" is a system that has the function of grouping and organizing notes by theme based on extracted keywords and phrases.

[1811] The "database storage means" is a system that has the function of structuring organized notes and storing them in a database.

[1812] "Interactive AI means" is an artificial intelligence system that enables dialogue with users based on a database.

[1813] The "Emotion Engine" is a system that has the function of analyzing and adding emotional information based on recorded voice data.

[1814] An "interactive system" is a system that generates and provides responses in natural language to in-vehicle displays or smartphones while taking emotional information into account.

[1815] The following elements are required to implement this invention: wearable device, voice recognition means, natural language processing means, grouping means, database storage means, interactive AI means, emotion engine, and interactive system. By integrating all of these elements, it becomes possible to efficiently acquire and manage voice memos in autonomous vehicles.

[1816] System Configuration

[1817] 1. Wearable devices

[1818] Users can easily take voice memos using a wearable device equipped with a microphone. The device is intended for use in autonomous vehicles, allowing hands-free voice input.

[1819] 2. Voice Recognition Method

[1820] The voice data is received in real time and converted into text data using a voice recognition means (such as a voice recognition API). For example, a cloud-based voice recognition service can be used.

[1821] 3. Natural Language Processing Methods

[1822] The server uses natural language processing libraries (e.g., spaCy or NLTK) to analyze the text data and extract keywords and important phrases, which allows it to automatically assess the importance of the information.

[1823] 4. Grouping Methods

[1824] The server then groups the voice memos based on the extracted keywords and phrases, organizing them by theme so that users can easily refer to them later.

[1825] 5. Database storage method

[1826] The organized voice memos are stored in a personal database in formats such as JSON, which ensures data integrity and efficient searching.

[1827] 6. Emotion Engine

[1828] Emotional information is added to the voice memo. Using an emotion engine, emotions such as joy, sadness, and anger are analyzed from the user's voice and tagged.

[1829] 7. Conversational AI methods

[1830] Users can use an in-car display or smartphone to send a request to view past notes, and a conversational AI mechanism responds, searching the database for the relevant note and generating a response in natural language.

[1831] Specific examples of processing

[1832] Voice input example

[1833] While driving, the user uses the wearable device to input a memo by voice, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan." This voice data is received in real time and converted by a voice recognition means into text data, saying, "There was just a sudden cut-in 100 meters ahead. This vehicle was a red sedan."

[1834] Text analysis examples

[1835] Through analysis, the keywords "ahead," "cutting in," and "red sedan" are extracted, and these are organized using a grouping method. Furthermore, the emotion engine adds the emotional information of "anger."

[1836] Data storage and AI response examples

[1837] The date is saved in the personal database as "October 5, 2023," "Sudden cut-in," and "Emotion: Anger." Later, when the user requests, "Tell me what happened while you were driving today," the conversational AI means responds, "There is a note that says, 'On October 5, 2023, there was a sudden cut-in 100 meters ahead. The vehicle was a red sedan.' The emotion was anger."

[1838] Prompt Sentence Examples

[1839] Examples of prompts based on input voice data include:

[1840] "There was just a sudden cut-off about 100 meters ahead of me. The vehicle was a red sedan."

[1841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1842] Step 1: The user uses the microphone on the wearable device to input a voice memo. For example, they might say, "There was a sudden cut-off 100 meters ahead. This vehicle was a red sedan." This input is captured by the wearable device and sent to the terminal.

[1843] Step 2: The device receives the voice data in real time and stores it in a data buffer. It then sends the voice data to a cloud-based speech recognition API, which converts the voice data into text data. The output is the text data, "There was a sudden cut-off just now, 100 meters ahead. This vehicle was a red sedan."

[1844] Step 3: The server passes the received text data to a natural language processing tool (e.g., spaCy or NLTK) to extract keywords and important phrases. The input is text data, and the output is the main keywords and phrases, such as "ahead," "cut in," and "red sedan."

[1845] Step 4: The server groups the voice memos based on the extracted keywords and phrases. The data is organized by theme. For example, memos containing the keywords "ahead," "cutting in," and "red sedan" are grouped under "unexpected incidents while driving."

[1846] Step 5: The server applies an emotion engine to the grouped data to analyze the user's emotion at the time of voice input. The input is text data, and an emotion tag (e.g., "anger") is added as the output.

[1847] Step 6: The server saves the notes with emotion information in a personal database as structured data (e.g., JSON format). The input is the organized and grouped note data, and the output is saved in the database.

[1848] Step 7: The user sends a request to view past notes from their smartphone or in-car display. For example, they might type, "Tell me what happened while driving today." This input is sent to the server.

[1849] Step 8: The server searches the personal database for the relevant note and generates a natural language response based on the search results. The input is the user's request, and the output is a response such as "There is a note that says 'There was a sudden cut-off 100 meters ahead. The vehicle was a red sedan' on October 5, 2023. The emotion is anger."

[1850] Step 9: The generated natural language response is sent to a display device in the car or to the user's smartphone, where the user can review the information. The output can be a visual display or a text message.

[1851] 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.

[1852] 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.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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).

[1858] 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.

[1859] 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."

[1860] 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.

[1861] 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).

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] The following is further disclosed regarding the above embodiment.

[1873] (Claim 1)

[1874] A means for acquiring voice data using a wearable device;

[1875] a speech recognition means for converting speech data into text data;

[1876] natural language processing means for analyzing text data and extracting keywords and important phrases;

[1877] A grouping mechanism for grouping and organizing notes into themes based on extracted keywords and phrases;

[1878] a database storage means for structuring the organized notes and storing them in a personal database;

[1879] An interactive AI means that enables dialogue with the user based on a personal database,

[1880] A system including:

[1881] (Claim 2)

[1882] 10. The system of claim 1, further comprising means for receiving voice data in real time and storing it in a data buffer.

[1883] (Claim 3)

[1884] 2. The system according to claim 1, further comprising means for searching for data from the personal database based on the request, and generating a response to the user in natural language with the search results.

[1885] "Example 1"

[1886] (Claim 1)

[1887] A means for acquiring voice data using a wearable device;

[1888] a speech recognition means for converting speech data into text data;

[1889] natural language processing means for analyzing text data and extracting keywords and important phrases;

[1890] A grouping mechanism for grouping and organizing notes into themes based on extracted keywords and phrases;

[1891] A storage method to structure and store the organized notes in a database;

[1892] an interactive artificial intelligence means for enabling a dialogue with a user based on a database;

[1893] a means for receiving requests from a user to search past notes;

[1894] a means for generating a response in natural language based on the search results and presenting the response to the user;

[1895] A system including:

[1896] (Claim 2)

[1897] 10. The system of claim 1, further comprising means for receiving voice data in real time and storing it in a data buffer.

[1898] (Claim 3)

[1899] 2. The system according to claim 1, further comprising means for searching for data from a database based on the request, and generating a response to the user in natural language with the search results.

[1900] "Application Example 1"

[1901] (Claim 1)

[1902] A means for acquiring voice data using a wearable device;

[1903] a speech recognition means for converting speech data into text data;

[1904] natural language processing means for analyzing text data and extracting keywords and important phrases;

[1905] A grouping mechanism for grouping and organizing notes into themes based on extracted keywords and phrases;

[1906] a database storage means for structuring the organized notes and storing them in a personal database;

[1907] A means for a user to send a request to view or review past notes based on a personal database;

[1908] an interactive AI means for searching for relevant information from a personal database in response to a request, generating a response in natural language using a generative AI model, and presenting the response to the user;

[1909] A system including:

[1910] (Claim 2)

[1911] 10. The system of claim 1, further comprising means for receiving voice data in real time and storing it in a data buffer.

[1912] (Claim 3)

[1913] The system of claim 1 further comprising means for capturing voice memos relating to specific locations or situations in security operations, automatically identifying urgency and importance based on specific keywords or phrases, and displaying relevant memos with priority.

[1914] "Example 2: Combining Emotion Engines"

[1915] (Claim 1)

[1916] A means for acquiring voice data using a wearable device;

[1917] a speech recognition means for converting speech data into text data;

[1918] natural language processing means for analyzing text data and extracting keywords and important phrases;

[1919] A grouping mechanism for grouping and organizing notes into themes based on extracted keywords and phrases;

[1920] a database storage means for structuring the organized notes and storing them in a personal database;

[1921] An interactive AI means that enables dialogue with the user based on a personal database,

[1922] emotion engine means for adding emotion information to text data;

[1923] A system including:

[1924] (Claim 2)

[1925] 10. The system of claim 1, further comprising means for receiving voice data in real time and storing it in a data buffer.

[1926] (Claim 3)

[1927] 2. The system according to claim 1, further comprising means for searching for data from the personal database based on the request, and generating a response to the user in natural language with the search results.

[1928] "Application example 2 when combining emotion engines"

[1929] (Claim 1)

[1930] A means for acquiring voice data using a wearable device;

[1931] a speech recognition means for converting speech data into text data;

[1932] natural language processing means for analyzing text data and extracting keywords and important phrases;

[1933] A grouping mechanism for grouping and organizing notes into themes based on extracted keywords and phrases;

[1934] A database storage means for structuring and storing the organized notes in a database;

[1935] Interactive AI means that enables dialogue with users based on a database

[1936] An emotion engine that is installed in autonomous vehicles and adds emotional information based on recorded voice data;

[1937] an interactive system that generates a response in natural language taking into account emotional information and provides it to a display device in the vehicle or a smartphone;

[1938] A system including:

[1939] (Claim 2)

[1940] 10. The system of claim 1, further comprising means for receiving voice data in real time and storing it in a data buffer.

[1941] (Claim 3)

[1942] 10. The system according to claim 1, further comprising means for searching for data from a database based on the request and generating a search result and response in natural language. [Explanation of symbols]

[1943] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring voice data using a wearable device; a speech recognition means for converting speech data into text data; natural language processing means for analyzing text data and extracting keywords and important phrases; A grouping method for grouping and organizing notes by theme based on extracted keywords and phrases; a database storage means for structuring the organized notes and storing them in a personal database; An interactive AI means that enables dialogue with users based on a personal database; A system including:

2. 10. The system of claim 1, further comprising means for receiving audio data in real time and storing the audio data in a data buffer.

3. 2. The system according to claim 1, further comprising means for searching for data from the personal database based on the request, and generating a response to the user in natural language with the results of the search.

Images