System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a multimodal form of input from a user; means for using artificial intelligence to analyze the multimodal form of input; means for generating a visual mind map based on the analyzed data; and means for presenting the generated mind map to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The present invention addresses the challenges users face in intuitively visualizing complex ideas and thoughts, particularly those faced by project managers, creative professionals, and educators who struggle to efficiently organize their thoughts and communicate complex concepts effectively. [Means for solving the problem]

[0005] The present invention provides a system that receives multimodal input (text, audio, images, and video) from a user and analyzes it using artificial intelligence. It also provides a system that generates a visual mind map based on the analyzed data, which helps users intuitively grasp complex ideas and thoughts. It also includes a system that presents the generated mind map to the user, thereby supporting the user's creative process and enabling concise visualization of educational content.

[0006] "User" refers to a person or entity who utilizes the system to input ideas and thoughts and generate a visual mind map.

[0007] "Multimodal format" is a general term for multiple different input formats, such as text, audio, images, and video.

[0008] "Input" refers to information provided by a user to a system, and may include any one or more of text, audio, images, and video.

[0009] "Artificial Intelligence" refers to computer programs and algorithms used to analyze, understand and process data provided to them.

[0010] "Analysis" is the process of processing input data individually and converting its contents into an understandable form.

[0011] A "visual mind map" is a diagram that uses nodes and links to represent analyzed data in an intuitive way that makes it easy to understand.

[0012] "Presenting" refers to the act of displaying the generated results to the user.

[0013] A "node" is an element in a mind map that represents each data point or concept.

[0014] A "link" is a line or arrow that indicates the relationship between nodes in a mind map. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0037] Accepting user input

[0038] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0039] Sending input data to the server

[0040] The device sends the acquired user input data to the server via a dedicated API. When sending, the input data is converted into an appropriate data format, such as JSON.

[0041] Receiving and analyzing data

[0042] The server receives the input data sent by the user and begins analyzing it. This analysis includes converting the voice data into text, extracting keywords from the text data, and analyzing the content of images and video data. Artificial intelligence is used for these analyses.

[0043] Visual mind map generation

[0044] The server generates a visual mind map based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between the nodes are visualized as links. For example, when audio data such as "new project ideas" is input, the audio is converted into text, and related concepts and keywords are extracted based on the text.

[0045] Send and view mind maps on your device

[0046] The server sends the generated mind map to the device, which then visually displays the received mind map to the user, allowing the user to intuitively understand complex ideas and thoughts.

[0047] Specific examples

[0048] For example, suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text and extracts keywords. Next, it visually arranges related keywords and ideas as nodes, and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user.

[0049] This process provides a system that effectively supports users' creative processes, organizing ideas, and understanding educational content by visualizing complex ideas and thoughts concisely and intuitively.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0053] Step 2:

[0054] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[0055] Step 3:

[0056] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[0057] Step 4:

[0058] The device sends the prepared data to the server via a dedicated API endpoint.

[0059] Step 5:

[0060] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from text data, and analyzing the content of images and video data.

[0061] Step 6:

[0062] The server converts the audio data into text, analyzes the content, and extracts important keywords and concepts.

[0063] Step 7:

[0064] The server creates nodes based on the results of keyword extraction from the text, and visually represents the relationships between each node as links.

[0065] Step 8:

[0066] The server generates a visual mind map based on the parsed data, with nodes and links appropriately arranged according to user input.

[0067] Step 9:

[0068] The server sends the generated mind map to the device.

[0069] Step 10:

[0070] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[0071] Example 1

[0072] 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."

[0073] Conventional idea and thought visualization systems rely on a single input format, making it difficult to effectively visualize users' diverse thought processes and ideas. They also face the problem of requiring a lot of manual work for complex data analysis and visualization, making it inefficient. This makes it difficult to generate visual mind maps that users can intuitively understand.

[0074] 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.

[0075] In this invention, the server includes means for receiving multimodal input from a user, means for using machine learning to analyze the multimodal input, means for generating a visual concept map based on the analyzed data, and means for presenting the generated concept map to the user. This allows the user to easily input complex ideas and thoughts in a variety of input formats, and the input is analyzed and displayed as a visual concept map that is intuitively easy to understand.

[0076] A "user" is someone who uses the system to input ideas and thoughts and to view the visualized results.

[0077] "Multimodal input" refers to an input method that handles multiple different types of data, such as text, audio, images, and video, all at once.

[0078] "Machine learning" is a branch of artificial intelligence used in data analysis, and is a technology that automatically learns patterns and rules from input data and performs analysis and predictions.

[0079] A "visual conceptual diagram" is a visual map that represents extracted information using nodes (points) and links (lines), and is constructed in a way that is easy for users to intuitively understand.

[0080] A "node" is an element in a visual concept diagram that represents a single data point or idea and is associated with other nodes by links.

[0081] A "link" is a line that indicates the relationship between nodes in a visual conceptual diagram, and is a means of visually showing connections and relationships between information.

[0082] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0083] First, a user inputs ideas or thoughts using a device such as a PC or smartphone. The input format can be text, voice, image, or video. The device acquires the data based on the input format selected by the user. For example, when voice input is performed using voice recognition software on a PC, the device receives the voice data and temporarily saves it in WAV format.

[0084] Next, the device sends the acquired user input data to the server via a dedicated API. At this time, the input data is converted into an appropriate data format, such as JSON. For example, in the case of audio data, the audio file is converted to FLAC format on the device and then sent to the server in JSON format.

[0085] The server receives the input data sent by the user and begins analyzing it. The analysis is performed using the following hardware and software:

[0086] A speech recognition API to convert voice data into text (e.g., Google Cloud Speech-to-Text)

[0087] Natural language processing libraries for extracting keywords from text data (e.g., Python's NLTK)

[0088] Computer vision services for analyzing the content of image and video data (e.g., Azure Cognitive Services)

[0089] The server generates a visual conceptual diagram (mind map) based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. For example, if audio data such as "ideas for a new project" is input, the audio is converted into text, and related keywords are extracted based on that text, and nodes and links are generated as a mind map based on this. The JavaScript-based D3.js library is used to generate this mind map.

[0090] The generated mind map is sent from the server to the device, which then visually displays it to the user. For example, it can be displayed visually in a browser using HTML5 and JavaScript. This process allows users to easily and intuitively understand complex ideas and thoughts.

[0091] Here's a concrete example: Suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the speech to text using the Google Cloud Speech-to-Text API and extracts keywords using Python's NLTK library. It then visually arranges related keywords and ideas as nodes and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user in a browser.

[0092] Example prompt sentence:

[0093] "Tell me about your new project ideas."

[0094] The above is an embodiment of the present invention. This system allows users to intuitively and efficiently visualize their own ideas and thoughts, deepening their understanding.

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1:

[0097] Users input ideas and thoughts using devices such as PCs and smartphones. The input format can be text, voice, images, or video. For example, if a user selects voice input, the device's voice recognition software starts recording and captures the user's voice. Voice data is obtained as input.

[0098] Step 2:

[0099] The audio data acquired by the device is temporarily saved in WAV format. It is then converted to FLAC format and encoded in JSON format. This JSON format data is sent to the server via a dedicated API. The converted JSON data is obtained as input, and the data sent to the server is the output.

[0100] Step 3:

[0101] The server receives JSON-formatted voice data sent by the user. First, it checks the voice data for errors and verifies the data integrity. Then, it calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the voice data into text. It receives JSON-formatted voice data as input and obtains text data as output.

[0102] Step 4:

[0103] The server analyzes the text data. First, it uses a natural language processing library (e.g., Python's NLTK) to extract important keywords from the text. Specifically, it performs processes such as morphological analysis and frequency analysis to identify keywords. It receives text data as input and obtains a list of keywords as output.

[0104] Step 5:

[0105] The server generates a visual concept diagram based on the extracted keywords. Each keyword is placed as a node, and the relationships between the nodes are represented as links. The mind map is generated using the JavaScript-based D3.js library. It receives a list of keywords as input and obtains a visual concept diagram (mind map) as output.

[0106] Step 6:

[0107] The server converts the generated mind map into JSON format and sends it to the device. The device parses the received JSON format mind map data and displays it visually to the user. For example, it uses a browser to draw it using HTML5 and JavaScript. It receives JSON format mind map data as input and obtains a visual display as output.

[0108] These are the specific processing steps of this system. By utilizing a variety of user input formats and efficiently analyzing and visualizing data, a system that supports intuitive understanding is realized.

[0109] (Application example 1)

[0110] 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."

[0111] In modern economic activities and investment strategy planning, users need to efficiently organize and understand a large amount of information. However, this information is often provided in different formats, such as text, audio, images, and video, and there is a lack of tools to intuitively understand it. In addition, there is a need for concrete means to support user decision-making by visually organizing economic ideas and investment strategies. This makes it difficult for users to process information quickly and accurately and develop optimal investment strategies.

[0112] 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.

[0113] In this invention, the server includes means for receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means for generating a visual mind map based on the analyzed data, means for presenting the generated mind map to the user, and means for extracting key keywords from the analyzed data and visualizing related concepts as nodes when the multimodal input includes economic ideas or strategies, and means for presenting the visualized data as relationships between economic ideas and investment strategies, thereby enabling users to intuitively understand complex economic ideas and investment strategies and make more effective decisions.

[0114] - "Multimodal input" refers to data in different formats, such as text, audio, images, and video.

[0115] "Artificial intelligence" refers to technology for converting voice data into text and analyzing the content of text.

[0116] A "visual mind map" is a visual arrangement and display of analyzed data using nodes and links.

[0117] "Key Keywords" are important words and phrases extracted from the user's input data.

[0118] "Economic ideas" refers to ideas or strategies related to economic activity or investment.

[0119] An "investment strategy" refers to a plan for how to allocate and manage assets in anticipation of future profits.

[0120] A "node" refers to the graphical representation of each data point or concept in a mind map.

[0121] The "relationship" indicates how nodes are connected or related to each other.

[0122] This invention is a system for intuitively visualizing a user's economic ideas and investment strategies. Specific methods for implementing the invention will be described below.

[0123] Program Generation

[0124] The program is implemented primarily using a high-level programming language such as Python, and uses the following libraries and tools:

[0125] Speech Recognition: Uses the speech_recognition library to capture user voice input.

[0126] Natural Language Processing: Uses the KeyBERT library to extract key keywords from the text data extracted from the audio data.

[0127] Generate a network graph: Use the networkx library to display the relationships between keywords as a visual mind map.

[0128] Data visualization: Use the matplotlib library to display the generated mind map.

[0129] Processing Description

[0130] 1. User voice input

[0131] The server receives voice input from the user via the terminal. The voice input prompt looks like this:

[0132] Prompt users: "Tell me about any new investment strategies you're considering or market ideas you're watching."

[0133] 2. Acquiring audio data

[0134] The device uses the speech_recognition library to capture the user's voice input, and the captured voice data is sent to the server in real time.

[0135] 3. Converting Audio Data to Text

[0136] The server converts the received voice data into text using Google's speech recognition API, which is then used in the next analysis step.

[0137] 4. Keyword extraction

[0138] The server uses KeyBERT to extract key keywords from text data, allowing it to identify important elements in what users say.

[0139] 5. Generate a visual mind map

[0140] The server uses the networkx library to generate a mind map with extracted keywords as nodes and relationships between related keywords as edges.

[0141] 6. View Mind Map

[0142] The terminal visualizes the mind map sent from the server using the matplotlib library and presents it to the user, allowing the user to intuitively understand their economic ideas and investment strategies.

[0143] Specific examples

[0144] For example, if a user voice-inputs, "As a new investment strategy, I'm focusing on AI-related stocks, renewable energy, health technology, and the REIT market," the voice data is converted into text. From this text data, key keywords such as "AI-related stocks," "renewable energy," "health technology," and "REIT market" are extracted. A mind map is generated based on these keywords, visually showing their relationships. This mind map is displayed on the user's device, allowing the user to intuitively grasp the relationships between each keyword.

[0145] This invention makes it possible to efficiently organize and easily understand complex economic ideas and investment strategies, and supports user decision-making.

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] The user inputs voice data through the terminal. The user activates the voice recognition function and inputs voice data following the prompt, "Please tell us about your new investment strategy or market ideas you are interested in." The terminal then captures the voice data.

[0149] Input: User's voice data

[0150] Data processing: Acquire audio using the speech_recognition library

[0151] Output: Audio file

[0152] Step 2:

[0153] The terminal transmits the acquired voice data to the server.

[0154] Input: Audio data

[0155] Data processing: Converting audio data into JSON format

[0156] Output: Audio data (JSON format) to the server

[0157] Step 3:

[0158] The server receives the voice data and converts it into text data using a voice recognition API.

[0159] Input: Audio data in JSON format

[0160] Data processing: Convert speech to text using Google's speech recognition API

[0161] Output: Text data

[0162] Step 4:

[0163] The server analyzes the converted text data and extracts important keywords using the natural language processing library KeyBERT.

[0164] Input: Text data

[0165] Data processing: Extracting keywords using KeyBERT

[0166] Output: List of key keywords

[0167] Step 5:

[0168] The server generates a visual mind map based on the extracted keywords using the networkx library.

[0169] Input: List of primary keywords

[0170] Data processing: Using the networkx library to structure the relationships between keywords and generate nodes and edges

[0171] Output: Mind map structure (nodes and edges)

[0172] Step 6:

[0173] The server sends the generated mind map to the terminal.

[0174] Input: Mind map structure

[0175] Data processing: Convert the mind map structure into JSON format

[0176] Output: Mind map data (JSON format) to the device

[0177] Step 7:

[0178] The terminal visualizes the received mind map data and presents it to the user, using the matplotlib library for visualization.

[0179] Input: Mind map data (JSON format)

[0180] Data processing: Visualizing mind maps using the matplotlib library

[0181] Output: The mind map displayed to the user

[0182] Through the above processing steps, the user's economic ideas and investment strategies are visualized in an intuitive and easy-to-understand manner.

[0183] 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.

[0184] The present invention is a system for visually expressing a user's ideas and thoughts by combining an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0185] Accepting user input

[0186] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0187] Sending input data to the server

[0188] The device converts the acquired user input data into JSON format and prepares it for transmission. Once the data is ready for transmission, it is sent to the server via a dedicated API endpoint.

[0189] Receiving and analyzing data

[0190] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from the text data, analyzing the content of images and video data, and recognizing emotions using an emotion engine.

[0191] Emotion recognition by emotion engine

[0192] The server uses an emotion engine to analyze emotions from the user's input data. For example, in the case of voice data, it analyzes the tone and patterns of the sound to identify emotions. In the case of text data, it analyzes emotion-related vocabulary and context to recognize emotions.

[0193] Visual mind map generation

[0194] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The user's emotional state can also be reflected in the mind map, and related nodes can be indicated by changes in color or shape.

[0195] Send and view mind maps on your device

[0196] The server sends the generated mind map to the device, which then visually displays it to the user, allowing the user to intuitively understand complex ideas, thoughts, and the emotions behind them.

[0197] Specific examples

[0198] For example, suppose a user speaks about an "idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and recognizes the user's emotions (e.g., excitement or anxiety) from the voice. Next, a mind map is generated by visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[0199] This provides a new visual communication tool that visualizes complex ideas and thoughts concisely and intuitively, and also takes the user's emotions into consideration.

[0200] The processing flow will be explained below.

[0201] Step 1:

[0202] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0203] Step 2:

[0204] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[0205] Step 3:

[0206] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[0207] Step 4:

[0208] The device sends the prepared data to the server via a dedicated API endpoint.

[0209] Step 5:

[0210] The server receives the input data sent by the user and begins analysis, which includes converting voice data into text, extracting keywords from text data, and analyzing the content of image and video data.

[0211] Step 6:

[0212] The server converts the voice data into text and analyzes the content to extract important keywords and concepts. For example, if the voice data is "ideas for a new project," keywords such as "project," "idea," and "new" are extracted from the voice.

[0213] Step 7:

[0214] The server uses an emotion engine to analyze the emotion from the user's input data. In the case of voice data, the server analyzes the tone and patterns of the sound to identify the emotion. For example, it can identify whether the user is speaking excitedly or anxiously.

[0215] Step 8:

[0216] The server also analyzes the content of the text data using an emotion engine to recognize emotions, for example, identifying the user's emotions based on the frequency of positive and negative words.

[0217] Step 9:

[0218] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The nodes also reflect the user's emotional state. For example, nodes representing excited parts are displayed in bright colors, while nodes representing calm parts are displayed in calm colors.

[0219] Step 10:

[0220] The server sends the generated mind map to the device.

[0221] Step 11:

[0222] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[0223] Example 2

[0224] 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."

[0225] Conventional systems have a problem in that they are unable to reflect the user's emotional state when visually expressing a user's ideas and thoughts, making it difficult to understand intuitively. Furthermore, technologies for effectively analyzing multimodal input and generating visual mind maps based on it are insufficient. Therefore, there is a need for a communication tool that can more effectively visualize users' thoughts and take emotional factors into account.

[0226] 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 receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means using an emotion engine to recognize the user's emotions derived from the analyzed data, means for generating a visual mind map based on the analyzed data, means for reflecting the user's emotional state in the visual mind map, means for presenting the generated mind map to the user, and means for transmitting the mind map to a terminal and presenting it to the user. This makes it possible to visually express the user's thoughts and ideas together with emotional elements.

[0227] "Multimodal input" refers to data provided by a user in multiple formats, such as text, audio, images, and video.

[0228] "Artificial intelligence" refers to technology that uses computers to imitate human intelligence, and in particular refers to systems that automatically analyze and learn through data analysis and machine learning.

[0229] "Emotion engine" refers to a technology or system for analyzing and identifying emotions from user input data.

[0230] A "visual mind map" is a diagram that visually displays thoughts and information, structuring them with nodes and links.

[0231] A "node" refers to an element that represents a single entry or point of information in a mind map.

[0232] A "link" refers to a line or arrow that indicates the relationship or association between nodes.

[0233] "Terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0234] "Server" refers to a computer system that receives, analyzes, stores, and transmits data over a network.

[0235] "Analysis" refers to the process of understanding the content of data and clarifying its meaning and structure.

[0236] "Converting to text" refers to the process of converting audio data or image data into text information.

[0237] The present invention is a system for visually expressing a user's ideas and thoughts. The purpose of this system is to visually express the user's thoughts and emotions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0238] Accepting user input

[0239] Users input their ideas and thoughts using devices such as PCs or smartphones. This input can be in the form of text, voice, images, or video. Specifically, when a user voice-inputs a "new project idea," the device uses a microphone to record the voice data. In this case, the device uses a native Android or iOS application to input the voice data into the system.

[0240] Sending input data to the server

[0241] The device converts the acquired data into JSON format. For example, it encodes audio data in Base64 format. Then, it uses HTTP communication to send the JSON data to a dedicated API endpoint using the POST method. This sending process is implemented using an HTTP library. Communication between the server and the device is encrypted with SSL / TLS and kept secure.

[0242] Receiving and analyzing data

[0243] The server receives JSON data sent from the device. It uses artificial intelligence technology to analyze the data and converts the voice data into text. It also uses the Google Cloud Speech-to-Text API to convert the voice to text and extracts keywords from the text data using natural language processing libraries such as NLTK and SpaCy. For image and video data, it uses the Google Cloud Vision API to analyze the content.

[0244] emotion recognition

[0245] The server uses an emotion engine to recognize the user's emotion from the analyzed data. Specifically, it uses the Transformers library to analyze the emotion of text data. For audio data, it uses the LibROSA library to analyze the tone and patterns of the voice and then uses the IBM Watson Tone Analyzer, an emotion engine, to identify the emotion.

[0246] Visual mind map generation

[0247] The server generates a visual mind map based on the analysis results and emotion recognition results. Visualization libraries such as D3.js and Graphviz are used to generate this mind map. Each data point and important keyword is represented as a node, and the relationships between nodes are represented as links. The user's emotional state is also reflected in the color and shape of the nodes, allowing for intuitive understanding.

[0248] Send and view mind maps on your device

[0249] The server then converts the generated mind map back into JSON format and sends it to the device, which then visualizes and displays the received mind map using a web browser. This allows users to intuitively understand complex ideas, thoughts, and the emotions behind them.

[0250] Specific examples

[0251] For example, if a user speaks "an idea for a new project," the device records this voice data, encodes it, and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. Next, a mind map is generated, visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[0252] Prompt Sentence Examples

[0253] Below is an example of a prompt sentence to input to the generative AI model.

[0254] The user speaks their "idea for a new project." This speech data is converted into JSON format and sent to the server. The server converts the speech to text, extracts keywords, and recognizes sentiment. It then generates a mind map and sends it to the device for display.

[0255] As a result, this system intuitively visualizes the user's complex ideas and thoughts, incorporating emotional elements, and functions as a new visual communication tool.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1: Accepting User Input

[0258] Users use devices such as PCs and smartphones to input ideas and thoughts. This input can be in the form of text, voice, images, or video. For example, if a user voice-inputs "an idea for a new project," the device uses a microphone to record the voice data. Input: Voice. Output: Recorded voice data.

[0259] Step 2: Send input data to the server

[0260] The audio data recorded by the device is encoded in Base64 format and converted to JSON format. It is then sent to the server via an HTTP request using the POST method to a dedicated API endpoint. Input: Recorded audio data. Output: JSON format data.

[0261] Step 3: Receiving and analyzing data

[0262] The server receives JSON data sent from the device. It converts the voice data into text using the Google Cloud Speech-to-Text API. This conversion process includes decoding the voice data, sending the data, and converting it back to text. Input: Voice data in JSON format. Output: Text data.

[0263] Step 4: Keyword extraction

[0264] The server analyzes the text data using a natural language processing library (e.g., NLTK or SpaCy) and extracts key keywords. Input: Text data. Output: List of key keywords.

[0265] Step 5: Emotion Recognition

[0266] The server uses an emotion engine (for example, the Transformers library or IBM Watson Tone Analyzer) to recognize the user's emotion from text or voice data. For voice data, the LibROSA library is used to analyze the tone and patterns of the voice. Input: Text or voice data. Output: Sentiment analysis results.

[0267] Step 6: Generate a visual mind map

[0268] The server generates a visual mind map using a visualization library (e.g., D3.js or Graphviz) based on the analysis results and emotion recognition results. Keywords are arranged as nodes, and relationships are visualized as links. Emotional states are also reflected as the color and shape of the nodes. Input: List of main keywords, emotion analysis results. Output: Visual mind map.

[0269] Step 7: Send and view your mind map on your device

[0270] The server converts the generated mind map back into JSON format and sends it to the device. The device visually displays the received mind map using a web browser. Input: Visual mind map. Output: Visual mind map displayed on the device.

[0271] Specific actions

[0272] For example, when a user speaks "an idea for a new project," the device records and encodes the voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. It then uses D3.js to generate a visual mind map, which is then sent to the device for display. This allows the device to intuitively understand the user's complex thoughts and emotions.

[0273] (Application example 2)

[0274] 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."

[0275] In autonomous vehicles, it is difficult to understand the driver's emotional state and provide appropriate feedback and alerts accordingly. Because a driver's emotional state directly affects driving behavior, a system that recognizes emotions in real time and responds appropriately is required. Furthermore, conventional systems have difficulty visually grasping the user's emotions, and visualization of ideas and thoughts is limited.

[0276] 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.

[0277] In this invention, the server includes: means for receiving multimodal input from a user; means using artificial intelligence to analyze the multimodal input; means for generating a visual mind map based on the analyzed data and the user's emotions; means for presenting the generated mind map to the user; means for receiving the driver's voice and video as user input and analyzing the data in real time; and means for providing feedback and alerts to the driver based on the analysis results. This enables the system to recognize the driver's emotional state in real time and provide corresponding feedback and alerts, thereby improving driving safety and comfort. Furthermore, visually displaying the user's emotions and ideas enables more intuitive communication.

[0278] "User" refers to a person or driver who uses the system.

[0279] "Multimodal format" refers to multiple different data formats, such as text, audio, images, video, etc.

[0280] "Input" refers to data or information provided by a user.

[0281] "Artificial intelligence" refers to technology that uses machine learning algorithms to analyze data and support decision-making.

[0282] A "visual mind map" is a diagram that visually structures and displays a user's ideas, thoughts, and feelings.

[0283] "Driver" means a person using an automated vehicle.

[0284] "Real-time" means that the process from data acquisition to analysis and provision of results is carried out almost simultaneously.

[0285] "Feedback" refers to advice or information the system provides to the driver.

[0286] "Alert" refers to a warning or caution provided by the system to the driver.

[0287] "Analysis results" refers to the information obtained after artificial intelligence processes input data.

[0288] "Emotion" refers to the driver's psychological state and mood.

[0289] "Driving assist function" refers to the system's function of assisting driving according to the driver's emotional state.

[0290] The present invention provides a system for recognizing a user's emotions and visually expressing the user's ideas and thoughts based on the emotions. Specific embodiments of the present invention will be described below.

[0291] The system includes artificial intelligence to receive multimodal input from users, analyze this data, generate a visual mind map based on the analyzed data and the user's emotional state, and present this mind map to the user.

[0292] The system program works as follows: First, the driver's audio and video data is captured in real time using a smartphone. The smartphone's microphone is used for audio data, and the smartphone's camera is used for video data. This data is converted into JSON format and sent to a server via the Internet.

[0293] The server receives and analyzes the audio and video data. OpenCV is used to analyze the video data, and Pydub is used to process the audio data. Machine learning algorithms are used for emotion recognition. In particular, generative AI models can be used to recognize user emotions in real time.

[0294] Based on the analysis results, the server generates a visual mind map. This mind map is represented by colors and shapes based on the user's emotional state. For example, if the driver is excited, the nodes on the mind map will be displayed in bright colors, and if they are relaxed, they will be displayed in calm colors. This mind map is then converted back into JSON format and sent to the smartphone.

[0295] The smartphone then presents the received mind map to the user in real time. Through this visual mind map, the user can intuitively understand their own emotional state and thoughts. The system also provides emotion-based feedback and alerts to the driver while driving. For example, if the driver is frustrated, the system will play relaxing music or display a reminder notification.

[0296] As a concrete example, suppose a driver says "I'm tired today" while driving. This voice is captured by the smartphone's microphone and sent to the server. The server analyzes the voice and recognizes that the driver is tired. As a result, it responds by providing feedback to the driver saying, "I recommend you take a break." Furthermore, "fatigue" is visualized as an important node in the mind map, clearly presented to the user.

[0297] Specific examples of input prompts for a generative AI model include, "Design an API to analyze the driver's voice data and identify their emotions" and "How can I analyze the driver's facial expressions to recognize their emotions in real time?"

[0298] In this way, the present invention realizes a system that recognizes a user's emotions in real time and provides appropriate feedback and alerts to the user, thereby enabling visual understanding and safe driving assistance based on the user's emotional state.

[0299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0300] Step 1:

[0301] The user's smartphone captures audio and video of the driver.

[0302] Specifically, audio is recorded using the smartphone's microphone and video is captured using the smartphone's camera. The audio data is acquired in WAV format and the video data in JPEG format.

[0303] Input: Driver audio and video

[0304] Output: WAV format audio data, JPEG format video data

[0305] Step 2:

[0306] The smartphone converts the acquired audio and video data into JSON format.

[0307] Specifically, audio data is converted from binary format to a string, and video data is converted to a string using Base64 encoding, and then packaged into JSON.

[0308] Input: WAV format audio data, JPEG format video data

[0309] Output: A JSON object containing audio and video data

[0310] Step 3:

[0311] The smartphone sends the preprocessed JSON data to the server over the Internet.

[0312] Specifically, HTTP POST is used as the communication protocol to send data to a dedicated API endpoint.

[0313] Input: A JSON object containing audio and video data

[0314] Output: Data sent to the server

[0315] Step 4:

[0316] The server analyzes the received data.

[0317] Specifically, we use OpenCV to analyze facial expressions and movements from video data, Pydub to extract features from audio data, and machine learning algorithms to estimate emotions.

[0318] Input: JSON object (audio and video data)

[0319] Output: Emotion recognition results and analysis results

[0320] Step 5:

[0321] The server generates a visual mind map based on the emotion recognition and analysis results.

[0322] Specifically, we assign emotion data corresponding to each node as an attribute, generate links between nodes based on their relevance, and create visual elements that change color and shape depending on the emotion.

[0323] Input: Emotion recognition results and analysis results

[0324] Output: Visual mind map data

[0325] Step 6:

[0326] The server then encodes the generated mind map into JSON format again and sends it to the smartphone.

[0327] Specifically, data is sent as an HTTP POST request through a dedicated API endpoint.

[0328] Input: Visual mind map data

[0329] Output: Mind map data sent to your smartphone

[0330] Step 7:

[0331] The smartphone interprets the received mind map data and presents it visually to the user.

[0332] Specifically, it parses JSON data and displays the mind map in a suitable graphical user interface, along with context-sensitive feedback and alerts.

[0333] Input: Visual mind map data

[0334] Output: Mind map presented to the user and feedback alerts

[0335] 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.

[0336] 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.

[0337] 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.

[0338] [Second embodiment]

[0339] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0340] 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.

[0341] 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).

[0342] 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.

[0343] 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.

[0344] 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).

[0345] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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.

[0350] 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."

[0351] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0352] Accepting user input

[0353] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0354] Sending input data to the server

[0355] The device sends the acquired user input data to the server via a dedicated API. When sending, the input data is converted into an appropriate data format, such as JSON.

[0356] Receiving and analyzing data

[0357] The server receives the input data sent by the user and begins analyzing it. This analysis includes converting the voice data into text, extracting keywords from the text data, and analyzing the content of images and video data. Artificial intelligence is used for these analyses.

[0358] Visual mind map generation

[0359] The server generates a visual mind map based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between the nodes are visualized as links. For example, when audio data such as "new project ideas" is input, the audio is converted into text, and related concepts and keywords are extracted based on the text.

[0360] Send and view mind maps on your device

[0361] The server sends the generated mind map to the device, which then visually displays the received mind map to the user, allowing the user to intuitively understand complex ideas and thoughts.

[0362] Specific examples

[0363] For example, suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text and extracts keywords. Next, it visually arranges related keywords and ideas as nodes, and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user.

[0364] This process provides a system that effectively supports users' creative processes, organizing ideas, and understanding educational content by visualizing complex ideas and thoughts concisely and intuitively.

[0365] The processing flow will be explained below.

[0366] Step 1:

[0367] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0368] Step 2:

[0369] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[0370] Step 3:

[0371] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[0372] Step 4:

[0373] The device sends the prepared data to the server via a dedicated API endpoint.

[0374] Step 5:

[0375] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from text data, and analyzing the content of images and video data.

[0376] Step 6:

[0377] The server converts the audio data into text, analyzes the content, and extracts important keywords and concepts.

[0378] Step 7:

[0379] The server creates nodes based on the results of keyword extraction from the text, and visually represents the relationships between each node as links.

[0380] Step 8:

[0381] The server generates a visual mind map based on the parsed data, with nodes and links appropriately arranged according to user input.

[0382] Step 9:

[0383] The server sends the generated mind map to the device.

[0384] Step 10:

[0385] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[0386] Example 1

[0387] 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."

[0388] Conventional idea and thought visualization systems rely on a single input format, making it difficult to effectively visualize users' diverse thought processes and ideas. They also face the problem of requiring a lot of manual work for complex data analysis and visualization, making it inefficient. This makes it difficult to generate visual mind maps that users can intuitively understand.

[0389] 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.

[0390] In this invention, the server includes means for receiving multimodal input from a user, means for using machine learning to analyze the multimodal input, means for generating a visual concept map based on the analyzed data, and means for presenting the generated concept map to the user. This allows the user to easily input complex ideas and thoughts in a variety of input formats, and the input is analyzed and displayed as a visual concept map that is intuitively easy to understand.

[0391] A "user" is someone who uses the system to input ideas and thoughts and to view the visualized results.

[0392] "Multimodal input" refers to an input method that handles multiple different types of data, such as text, audio, images, and video, all at once.

[0393] "Machine learning" is a branch of artificial intelligence used in data analysis, and is a technology that automatically learns patterns and rules from input data and performs analysis and predictions.

[0394] A "visual conceptual diagram" is a visual map that represents extracted information using nodes (points) and links (lines), and is constructed in a way that is easy for users to intuitively understand.

[0395] A "node" is an element in a visual concept diagram that represents a single data point or idea and is associated with other nodes by links.

[0396] A "link" is a line that indicates the relationship between nodes in a visual conceptual diagram, and is a means of visually showing connections and relationships between information.

[0397] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0398] First, a user inputs ideas or thoughts using a device such as a PC or smartphone. The input format can be text, voice, image, or video. The device acquires the data based on the input format selected by the user. For example, when voice input is performed using voice recognition software on a PC, the device receives the voice data and temporarily saves it in WAV format.

[0399] Next, the device sends the acquired user input data to the server via a dedicated API. At this time, the input data is converted into an appropriate data format, such as JSON. For example, in the case of audio data, the audio file is converted to FLAC format on the device and then sent to the server in JSON format.

[0400] The server receives the input data sent by the user and begins analyzing it. The analysis is performed using the following hardware and software:

[0401] A speech recognition API to convert voice data into text (e.g., Google Cloud Speech-to-Text)

[0402] Natural language processing libraries for extracting keywords from text data (e.g., Python's NLTK)

[0403] Computer vision services for analyzing the content of image and video data (e.g., Azure Cognitive Services)

[0404] The server generates a visual conceptual diagram (mind map) based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. For example, if audio data such as "ideas for a new project" is input, the audio is converted into text, and related keywords are extracted based on that text, and nodes and links are generated as a mind map based on this. The JavaScript-based D3.js library is used to generate this mind map.

[0405] The generated mind map is sent from the server to the device, which then visually displays it to the user. For example, it can be displayed visually in a browser using HTML5 and JavaScript. This process allows users to easily and intuitively understand complex ideas and thoughts.

[0406] Here's a concrete example: Suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the speech to text using the Google Cloud Speech-to-Text API and extracts keywords using Python's NLTK library. It then visually arranges related keywords and ideas as nodes and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user in a browser.

[0407] Example prompt sentence:

[0408] "Tell me about your new project ideas."

[0409] The above is an embodiment of the present invention. This system allows users to intuitively and efficiently visualize their own ideas and thoughts, deepening their understanding.

[0410] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0411] Step 1:

[0412] Users input ideas and thoughts using devices such as PCs and smartphones. The input format can be text, voice, images, or video. For example, if a user selects voice input, the device's voice recognition software starts recording and captures the user's voice. Voice data is obtained as input.

[0413] Step 2:

[0414] The audio data acquired by the device is temporarily saved in WAV format. It is then converted to FLAC format and encoded in JSON format. This JSON format data is sent to the server via a dedicated API. The converted JSON data is obtained as input, and the data sent to the server is the output.

[0415] Step 3:

[0416] The server receives JSON-formatted voice data sent by the user. First, it checks the voice data for errors and verifies the data integrity. Then, it calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the voice data into text. It receives JSON-formatted voice data as input and obtains text data as output.

[0417] Step 4:

[0418] The server analyzes the text data. First, it uses a natural language processing library (e.g., Python's NLTK) to extract important keywords from the text. Specifically, it performs processes such as morphological analysis and frequency analysis to identify keywords. It receives text data as input and obtains a list of keywords as output.

[0419] Step 5:

[0420] The server generates a visual concept diagram based on the extracted keywords. Each keyword is placed as a node, and the relationships between the nodes are represented as links. The mind map is generated using the JavaScript-based D3.js library. It receives a list of keywords as input and obtains a visual concept diagram (mind map) as output.

[0421] Step 6:

[0422] The server converts the generated mind map into JSON format and sends it to the device. The device parses the received JSON format mind map data and displays it visually to the user. For example, it uses a browser to draw it using HTML5 and JavaScript. It receives JSON format mind map data as input and obtains a visual display as output.

[0423] These are the specific processing steps of this system. By utilizing a variety of user input formats and efficiently analyzing and visualizing data, a system that supports intuitive understanding is realized.

[0424] (Application example 1)

[0425] 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."

[0426] In modern economic activities and investment strategy planning, users need to efficiently organize and understand a large amount of information. However, this information is often provided in different formats, such as text, audio, images, and video, and there is a lack of tools to intuitively understand it. In addition, there is a need for concrete means to support user decision-making by visually organizing economic ideas and investment strategies. This makes it difficult for users to process information quickly and accurately and develop optimal investment strategies.

[0427] 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.

[0428] In this invention, the server includes means for receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means for generating a visual mind map based on the analyzed data, means for presenting the generated mind map to the user, and means for extracting key keywords from the analyzed data and visualizing related concepts as nodes when the multimodal input includes economic ideas or strategies, and means for presenting the visualized data as relationships between economic ideas and investment strategies, thereby enabling users to intuitively understand complex economic ideas and investment strategies and make more effective decisions.

[0429] - "Multimodal input" refers to data in different formats, such as text, audio, images, and video.

[0430] "Artificial intelligence" refers to technology for converting voice data into text and analyzing the content of text.

[0431] A "visual mind map" is a visual arrangement and display of analyzed data using nodes and links.

[0432] "Key Keywords" are important words and phrases extracted from the user's input data.

[0433] "Economic ideas" refers to ideas or strategies related to economic activity or investment.

[0434] An "investment strategy" refers to a plan for how to allocate and manage assets in anticipation of future profits.

[0435] A "node" refers to the graphical representation of each data point or concept in a mind map.

[0436] The "relationship" indicates how nodes are connected or related to each other.

[0437] This invention is a system for intuitively visualizing a user's economic ideas and investment strategies. Specific methods for implementing the invention will be described below.

[0438] Program Generation

[0439] The program is implemented primarily using a high-level programming language such as Python, and uses the following libraries and tools:

[0440] Speech Recognition: Uses the speech_recognition library to capture user voice input.

[0441] Natural Language Processing: Uses the KeyBERT library to extract key keywords from the text data extracted from the audio data.

[0442] Generate a network graph: Use the networkx library to display the relationships between keywords as a visual mind map.

[0443] Data visualization: Use the matplotlib library to display the generated mind map.

[0444] Processing Description

[0445] 1. User voice input

[0446] The server receives voice input from the user via the terminal. The voice input prompt looks like this:

[0447] Prompt users: "Tell me about any new investment strategies you're considering or market ideas you're watching."

[0448] 2. Acquiring audio data

[0449] The device uses the speech_recognition library to capture the user's voice input, and the captured voice data is sent to the server in real time.

[0450] 3. Converting Audio Data to Text

[0451] The server converts the received voice data into text using Google's speech recognition API, which is then used in the next analysis step.

[0452] 4. Keyword extraction

[0453] The server uses KeyBERT to extract key keywords from text data, allowing it to identify important elements in what users say.

[0454] 5. Generate a visual mind map

[0455] The server uses the networkx library to generate a mind map with extracted keywords as nodes and relationships between related keywords as edges.

[0456] 6. View Mind Map

[0457] The terminal visualizes the mind map sent from the server using the matplotlib library and presents it to the user, allowing the user to intuitively understand their economic ideas and investment strategies.

[0458] Specific examples

[0459] For example, if a user voice-inputs, "As a new investment strategy, I'm focusing on AI-related stocks, renewable energy, health technology, and the REIT market," the voice data is converted into text. From this text data, key keywords such as "AI-related stocks," "renewable energy," "health technology," and "REIT market" are extracted. A mind map is generated based on these keywords, visually showing their relationships. This mind map is displayed on the user's device, allowing the user to intuitively grasp the relationships between each keyword.

[0460] This invention makes it possible to efficiently organize and easily understand complex economic ideas and investment strategies, and supports user decision-making.

[0461] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0462] Step 1:

[0463] The user inputs voice data through the terminal. The user activates the voice recognition function and inputs voice data following the prompt, "Please tell us about your new investment strategy or market ideas you are interested in." The terminal then captures the voice data.

[0464] Input: User's voice data

[0465] Data processing: Acquire audio using the speech_recognition library

[0466] Output: Audio file

[0467] Step 2:

[0468] The terminal transmits the acquired voice data to the server.

[0469] Input: Audio data

[0470] Data processing: Converting audio data into JSON format

[0471] Output: Audio data (JSON format) to the server

[0472] Step 3:

[0473] The server receives the voice data and converts it into text data using a voice recognition API.

[0474] Input: Audio data in JSON format

[0475] Data processing: Convert speech to text using Google's speech recognition API

[0476] Output: Text data

[0477] Step 4:

[0478] The server analyzes the converted text data and extracts important keywords using the natural language processing library KeyBERT.

[0479] Input: Text data

[0480] Data processing: Extracting keywords using KeyBERT

[0481] Output: List of key keywords

[0482] Step 5:

[0483] The server generates a visual mind map based on the extracted keywords using the networkx library.

[0484] Input: List of primary keywords

[0485] Data processing: Using the networkx library to structure the relationships between keywords and generate nodes and edges

[0486] Output: Mind map structure (nodes and edges)

[0487] Step 6:

[0488] The server sends the generated mind map to the terminal.

[0489] Input: Mind map structure

[0490] Data processing: Convert the mind map structure into JSON format

[0491] Output: Mind map data (JSON format) to the device

[0492] Step 7:

[0493] The terminal visualizes the received mind map data and presents it to the user, using the matplotlib library for visualization.

[0494] Input: Mind map data (JSON format)

[0495] Data processing: Visualizing mind maps using the matplotlib library

[0496] Output: The mind map displayed to the user

[0497] Through the above processing steps, the user's economic ideas and investment strategies are visualized in an intuitive and easy-to-understand manner.

[0498] 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.

[0499] The present invention is a system for visually expressing a user's ideas and thoughts by combining an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0500] Accepting user input

[0501] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0502] Sending input data to the server

[0503] The device converts the acquired user input data into JSON format and prepares it for transmission. Once the data is ready for transmission, it is sent to the server via a dedicated API endpoint.

[0504] Receiving and analyzing data

[0505] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from the text data, analyzing the content of images and video data, and recognizing emotions using an emotion engine.

[0506] Emotion recognition by emotion engine

[0507] The server uses an emotion engine to analyze emotions from the user's input data. For example, in the case of voice data, it analyzes the tone and patterns of the sound to identify emotions. In the case of text data, it analyzes emotion-related vocabulary and context to recognize emotions.

[0508] Visual mind map generation

[0509] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The user's emotional state can also be reflected in the mind map, and related nodes can be indicated by changes in color or shape.

[0510] Send and view mind maps on your device

[0511] The server sends the generated mind map to the device, which then visually displays it to the user, allowing the user to intuitively understand complex ideas, thoughts, and the emotions behind them.

[0512] Specific examples

[0513] For example, suppose a user speaks about an "idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and recognizes the user's emotions (e.g., excitement or anxiety) from the voice. Next, a mind map is generated by visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[0514] This provides a new visual communication tool that visualizes complex ideas and thoughts concisely and intuitively, and also takes the user's emotions into consideration.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0518] Step 2:

[0519] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[0520] Step 3:

[0521] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[0522] Step 4:

[0523] The device sends the prepared data to the server via a dedicated API endpoint.

[0524] Step 5:

[0525] The server receives the input data sent by the user and begins analysis, which includes converting voice data into text, extracting keywords from text data, and analyzing the content of image and video data.

[0526] Step 6:

[0527] The server converts the voice data into text and analyzes the content to extract important keywords and concepts. For example, if the voice data is "ideas for a new project," keywords such as "project," "idea," and "new" are extracted from the voice.

[0528] Step 7:

[0529] The server uses an emotion engine to analyze the emotion from the user's input data. In the case of voice data, the server analyzes the tone and patterns of the sound to identify the emotion. For example, it can identify whether the user is speaking excitedly or anxiously.

[0530] Step 8:

[0531] The server also analyzes the content of the text data using an emotion engine to recognize emotions, for example, identifying the user's emotions based on the frequency of positive and negative words.

[0532] Step 9:

[0533] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The nodes also reflect the user's emotional state. For example, nodes representing excited parts are displayed in bright colors, while nodes representing calm parts are displayed in calm colors.

[0534] Step 10:

[0535] The server sends the generated mind map to the device.

[0536] Step 11:

[0537] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[0538] Example 2

[0539] 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."

[0540] Conventional systems have a problem in that they are unable to reflect the user's emotional state when visually expressing a user's ideas and thoughts, making it difficult to understand intuitively. Furthermore, technologies for effectively analyzing multimodal input and generating visual mind maps based on it are insufficient. Therefore, there is a need for a communication tool that can more effectively visualize users' thoughts and take emotional factors into account.

[0541] 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 receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means using an emotion engine to recognize the user's emotions derived from the analyzed data, means for generating a visual mind map based on the analyzed data, means for reflecting the user's emotional state in the visual mind map, means for presenting the generated mind map to the user, and means for transmitting the mind map to a terminal and presenting it to the user. This makes it possible to visually express the user's thoughts and ideas together with emotional elements.

[0542] "Multimodal input" refers to data provided by a user in multiple formats, such as text, audio, images, and video.

[0543] "Artificial intelligence" refers to technology that uses computers to imitate human intelligence, and in particular refers to systems that automatically analyze and learn through data analysis and machine learning.

[0544] "Emotion engine" refers to a technology or system for analyzing and identifying emotions from user input data.

[0545] A "visual mind map" is a diagram that visually displays thoughts and information, structuring them with nodes and links.

[0546] A "node" refers to an element that represents a single entry or point of information in a mind map.

[0547] A "link" refers to a line or arrow that indicates the relationship or association between nodes.

[0548] "Terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0549] "Server" refers to a computer system that receives, analyzes, stores, and transmits data over a network.

[0550] "Analysis" refers to the process of understanding the content of data and clarifying its meaning and structure.

[0551] "Converting to text" refers to the process of converting audio data or image data into text information.

[0552] The present invention is a system for visually expressing a user's ideas and thoughts. The purpose of this system is to visually express the user's thoughts and emotions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0553] Accepting user input

[0554] Users input their ideas and thoughts using devices such as PCs or smartphones. This input can be in the form of text, voice, images, or video. Specifically, when a user voice-inputs a "new project idea," the device uses a microphone to record the voice data. In this case, the device uses a native Android or iOS application to input the voice data into the system.

[0555] Sending input data to the server

[0556] The device converts the acquired data into JSON format. For example, it encodes audio data in Base64 format. Then, it uses HTTP communication to send the JSON data to a dedicated API endpoint using the POST method. This sending process is implemented using an HTTP library. Communication between the server and the device is encrypted with SSL / TLS and kept secure.

[0557] Receiving and analyzing data

[0558] The server receives JSON data sent from the device. It uses artificial intelligence technology to analyze the data and converts the voice data into text. It also uses the Google Cloud Speech-to-Text API to convert the voice to text and extracts keywords from the text data using natural language processing libraries such as NLTK and SpaCy. For image and video data, it uses the Google Cloud Vision API to analyze the content.

[0559] emotion recognition

[0560] The server uses an emotion engine to recognize the user's emotion from the analyzed data. Specifically, it uses the Transformers library to analyze the emotion of text data. For audio data, it uses the LibROSA library to analyze the tone and patterns of the voice and then uses the IBM Watson Tone Analyzer, an emotion engine, to identify the emotion.

[0561] Visual mind map generation

[0562] The server generates a visual mind map based on the analysis results and emotion recognition results. Visualization libraries such as D3.js and Graphviz are used to generate this mind map. Each data point and important keyword is represented as a node, and the relationships between nodes are represented as links. The user's emotional state is also reflected in the color and shape of the nodes, allowing for intuitive understanding.

[0563] Send and view mind maps on your device

[0564] The server then converts the generated mind map back into JSON format and sends it to the device, which then visualizes and displays the received mind map using a web browser. This allows users to intuitively understand complex ideas, thoughts, and the emotions behind them.

[0565] Specific examples

[0566] For example, if a user speaks "an idea for a new project," the device records this voice data, encodes it, and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. Next, a mind map is generated, visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[0567] Prompt Sentence Examples

[0568] Below is an example of a prompt sentence to input to the generative AI model.

[0569] The user speaks their "idea for a new project." This speech data is converted into JSON format and sent to the server. The server converts the speech to text, extracts keywords, and recognizes sentiment. It then generates a mind map and sends it to the device for display.

[0570] As a result, this system intuitively visualizes the user's complex ideas and thoughts, incorporating emotional elements, and functions as a new visual communication tool.

[0571] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0572] Step 1: Accepting User Input

[0573] Users use devices such as PCs and smartphones to input ideas and thoughts. This input can be in the form of text, voice, images, or video. For example, if a user voice-inputs "an idea for a new project," the device uses a microphone to record the voice data. Input: Voice. Output: Recorded voice data.

[0574] Step 2: Send input data to the server

[0575] The audio data recorded by the device is encoded in Base64 format and converted to JSON format. It is then sent to the server via an HTTP request using the POST method to a dedicated API endpoint. Input: Recorded audio data. Output: JSON format data.

[0576] Step 3: Receiving and analyzing data

[0577] The server receives JSON data sent from the device. It converts the voice data into text using the Google Cloud Speech-to-Text API. This conversion process includes decoding the voice data, sending the data, and converting it back to text. Input: Voice data in JSON format. Output: Text data.

[0578] Step 4: Keyword extraction

[0579] The server analyzes the text data using a natural language processing library (e.g., NLTK or SpaCy) and extracts key keywords. Input: Text data. Output: List of key keywords.

[0580] Step 5: Emotion Recognition

[0581] The server uses an emotion engine (for example, the Transformers library or IBM Watson Tone Analyzer) to recognize the user's emotion from text or voice data. For voice data, the LibROSA library is used to analyze the tone and patterns of the voice. Input: Text or voice data. Output: Sentiment analysis results.

[0582] Step 6: Generate a visual mind map

[0583] The server generates a visual mind map using a visualization library (e.g., D3.js or Graphviz) based on the analysis results and emotion recognition results. Keywords are arranged as nodes, and relationships are visualized as links. Emotional states are also reflected as the color and shape of the nodes. Input: List of main keywords, emotion analysis results. Output: Visual mind map.

[0584] Step 7: Send and view your mind map on your device

[0585] The server converts the generated mind map back into JSON format and sends it to the device. The device visually displays the received mind map using a web browser. Input: Visual mind map. Output: Visual mind map displayed on the device.

[0586] Specific actions

[0587] For example, when a user speaks "an idea for a new project," the device records and encodes the voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. It then uses D3.js to generate a visual mind map, which is then sent to the device for display. This allows the device to intuitively understand the user's complex thoughts and emotions.

[0588] (Application example 2)

[0589] 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."

[0590] In autonomous vehicles, it is difficult to understand the driver's emotional state and provide appropriate feedback and alerts accordingly. Because a driver's emotional state directly affects driving behavior, a system that recognizes emotions in real time and responds appropriately is required. Furthermore, conventional systems have difficulty visually grasping the user's emotions, and visualization of ideas and thoughts is limited.

[0591] 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.

[0592] In this invention, the server includes: means for receiving multimodal input from a user; means using artificial intelligence to analyze the multimodal input; means for generating a visual mind map based on the analyzed data and the user's emotions; means for presenting the generated mind map to the user; means for receiving the driver's voice and video as user input and analyzing the data in real time; and means for providing feedback and alerts to the driver based on the analysis results. This enables the system to recognize the driver's emotional state in real time and provide corresponding feedback and alerts, thereby improving driving safety and comfort. Furthermore, visually displaying the user's emotions and ideas enables more intuitive communication.

[0593] "User" refers to a person or driver who uses the system.

[0594] "Multimodal format" refers to multiple different data formats, such as text, audio, images, video, etc.

[0595] "Input" refers to data or information provided by a user.

[0596] "Artificial intelligence" refers to technology that uses machine learning algorithms to analyze data and support decision-making.

[0597] A "visual mind map" is a diagram that visually structures and displays a user's ideas, thoughts, and feelings.

[0598] "Driver" means a person using an automated vehicle.

[0599] "Real-time" means that the process from data acquisition to analysis and provision of results is carried out almost simultaneously.

[0600] "Feedback" refers to advice or information the system provides to the driver.

[0601] "Alert" refers to a warning or caution provided by the system to the driver.

[0602] "Analysis results" refers to the information obtained after artificial intelligence processes input data.

[0603] "Emotion" refers to the driver's psychological state and mood.

[0604] "Driving assist function" refers to the system's function of assisting driving according to the driver's emotional state.

[0605] The present invention provides a system for recognizing a user's emotions and visually expressing the user's ideas and thoughts based on the emotions. Specific embodiments of the present invention will be described below.

[0606] The system includes artificial intelligence to receive multimodal input from users, analyze this data, generate a visual mind map based on the analyzed data and the user's emotional state, and present this mind map to the user.

[0607] The system program works as follows: First, the driver's audio and video data is captured in real time using a smartphone. The smartphone's microphone is used for audio data, and the smartphone's camera is used for video data. This data is converted into JSON format and sent to a server via the Internet.

[0608] The server receives and analyzes the audio and video data. OpenCV is used to analyze the video data, and Pydub is used to process the audio data. Machine learning algorithms are used for emotion recognition. In particular, generative AI models can be used to recognize user emotions in real time.

[0609] Based on the analysis results, the server generates a visual mind map. This mind map is represented by colors and shapes based on the user's emotional state. For example, if the driver is excited, the nodes on the mind map will be displayed in bright colors, and if they are relaxed, they will be displayed in calm colors. This mind map is then converted back into JSON format and sent to the smartphone.

[0610] The smartphone then presents the received mind map to the user in real time. Through this visual mind map, the user can intuitively understand their own emotional state and thoughts. The system also provides emotion-based feedback and alerts to the driver while driving. For example, if the driver is frustrated, the system will play relaxing music or display a reminder notification.

[0611] As a concrete example, suppose a driver says "I'm tired today" while driving. This voice is captured by the smartphone's microphone and sent to the server. The server analyzes the voice and recognizes that the driver is tired. As a result, it responds by providing feedback to the driver saying, "I recommend you take a break." Furthermore, "fatigue" is visualized as an important node in the mind map, clearly presented to the user.

[0612] Specific examples of input prompts for a generative AI model include, "Design an API to analyze the driver's voice data and identify their emotions" and "How can I analyze the driver's facial expressions to recognize their emotions in real time?"

[0613] In this way, the present invention realizes a system that recognizes a user's emotions in real time and provides appropriate feedback and alerts to the user, thereby enabling visual understanding and safe driving assistance based on the user's emotional state.

[0614] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0615] Step 1:

[0616] The user's smartphone captures audio and video of the driver.

[0617] Specifically, audio is recorded using the smartphone's microphone and video is captured using the smartphone's camera. The audio data is acquired in WAV format and the video data in JPEG format.

[0618] Input: Driver audio and video

[0619] Output: WAV format audio data, JPEG format video data

[0620] Step 2:

[0621] The smartphone converts the acquired audio and video data into JSON format.

[0622] Specifically, audio data is converted from binary format to a string, and video data is converted to a string using Base64 encoding, and then packaged into JSON.

[0623] Input: WAV format audio data, JPEG format video data

[0624] Output: A JSON object containing audio and video data

[0625] Step 3:

[0626] The smartphone sends the preprocessed JSON data to the server over the Internet.

[0627] Specifically, HTTP POST is used as the communication protocol to send data to a dedicated API endpoint.

[0628] Input: A JSON object containing audio and video data

[0629] Output: Data sent to the server

[0630] Step 4:

[0631] The server analyzes the received data.

[0632] Specifically, we use OpenCV to analyze facial expressions and movements from video data, Pydub to extract features from audio data, and machine learning algorithms to estimate emotions.

[0633] Input: JSON object (audio and video data)

[0634] Output: Emotion recognition results and analysis results

[0635] Step 5:

[0636] The server generates a visual mind map based on the emotion recognition and analysis results.

[0637] Specifically, we assign emotion data corresponding to each node as an attribute, generate links between nodes based on their relevance, and create visual elements that change color and shape depending on the emotion.

[0638] Input: Emotion recognition results and analysis results

[0639] Output: Visual mind map data

[0640] Step 6:

[0641] The server then encodes the generated mind map into JSON format again and sends it to the smartphone.

[0642] Specifically, data is sent as an HTTP POST request through a dedicated API endpoint.

[0643] Input: Visual mind map data

[0644] Output: Mind map data sent to your smartphone

[0645] Step 7:

[0646] The smartphone interprets the received mind map data and presents it visually to the user.

[0647] Specifically, it parses JSON data and displays the mind map in a suitable graphical user interface, along with context-sensitive feedback and alerts.

[0648] Input: Visual mind map data

[0649] Output: Mind map presented to the user and feedback alerts

[0650] 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.

[0651] 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.

[0652] 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.

[0653] [Third embodiment]

[0654] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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."

[0666] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0667] Accepting user input

[0668] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0669] Sending input data to the server

[0670] The device sends the acquired user input data to the server via a dedicated API. When sending, the input data is converted into an appropriate data format, such as JSON.

[0671] Receiving and analyzing data

[0672] The server receives the input data sent by the user and begins analyzing it. This analysis includes converting the voice data into text, extracting keywords from the text data, and analyzing the content of images and video data. Artificial intelligence is used for these analyses.

[0673] Visual mind map generation

[0674] The server generates a visual mind map based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between the nodes are visualized as links. For example, when audio data such as "new project ideas" is input, the audio is converted into text, and related concepts and keywords are extracted based on the text.

[0675] Send and view mind maps on your device

[0676] The server sends the generated mind map to the device, which then visually displays the received mind map to the user, allowing the user to intuitively understand complex ideas and thoughts.

[0677] Specific examples

[0678] For example, suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text and extracts keywords. Next, it visually arranges related keywords and ideas as nodes, and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user.

[0679] This process provides a system that effectively supports users' creative processes, organizing ideas, and understanding educational content by visualizing complex ideas and thoughts concisely and intuitively.

[0680] The processing flow will be explained below.

[0681] Step 1:

[0682] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0683] Step 2:

[0684] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[0685] Step 3:

[0686] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[0687] Step 4:

[0688] The device sends the prepared data to the server via a dedicated API endpoint.

[0689] Step 5:

[0690] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from text data, and analyzing the content of images and video data.

[0691] Step 6:

[0692] The server converts the audio data into text, analyzes the content, and extracts important keywords and concepts.

[0693] Step 7:

[0694] The server creates nodes based on the results of keyword extraction from the text, and visually represents the relationships between each node as links.

[0695] Step 8:

[0696] The server generates a visual mind map based on the parsed data, with nodes and links appropriately arranged according to user input.

[0697] Step 9:

[0698] The server sends the generated mind map to the device.

[0699] Step 10:

[0700] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[0701] Example 1

[0702] 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."

[0703] Conventional idea and thought visualization systems rely on a single input format, making it difficult to effectively visualize users' diverse thought processes and ideas. They also face the problem of requiring a lot of manual work for complex data analysis and visualization, making it inefficient. This makes it difficult to generate visual mind maps that users can intuitively understand.

[0704] 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.

[0705] In this invention, the server includes means for receiving multimodal input from a user, means for using machine learning to analyze the multimodal input, means for generating a visual concept map based on the analyzed data, and means for presenting the generated concept map to the user. This allows the user to easily input complex ideas and thoughts in a variety of input formats, and the input is analyzed and displayed as a visual concept map that is intuitively easy to understand.

[0706] A "user" is someone who uses the system to input ideas and thoughts and to view the visualized results.

[0707] "Multimodal input" refers to an input method that handles multiple different types of data, such as text, audio, images, and video, all at once.

[0708] "Machine learning" is a branch of artificial intelligence used in data analysis, and is a technology that automatically learns patterns and rules from input data and performs analysis and predictions.

[0709] A "visual conceptual diagram" is a visual map that represents extracted information using nodes (points) and links (lines), and is constructed in a way that is easy for users to intuitively understand.

[0710] A "node" is an element in a visual concept diagram that represents a single data point or idea and is associated with other nodes by links.

[0711] A "link" is a line that indicates the relationship between nodes in a visual conceptual diagram, and is a means of visually showing connections and relationships between information.

[0712] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0713] First, a user inputs ideas or thoughts using a device such as a PC or smartphone. The input format can be text, voice, image, or video. The device acquires the data based on the input format selected by the user. For example, when voice input is performed using voice recognition software on a PC, the device receives the voice data and temporarily saves it in WAV format.

[0714] Next, the device sends the acquired user input data to the server via a dedicated API. At this time, the input data is converted into an appropriate data format, such as JSON. For example, in the case of audio data, the audio file is converted to FLAC format on the device and then sent to the server in JSON format.

[0715] The server receives the input data sent by the user and begins analyzing it. The analysis is performed using the following hardware and software:

[0716] A speech recognition API to convert voice data into text (e.g., Google Cloud Speech-to-Text)

[0717] Natural language processing libraries for extracting keywords from text data (e.g., Python's NLTK)

[0718] Computer vision services for analyzing the content of image and video data (e.g., Azure Cognitive Services)

[0719] The server generates a visual conceptual diagram (mind map) based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. For example, if audio data such as "ideas for a new project" is input, the audio is converted into text, and related keywords are extracted based on that text, and nodes and links are generated as a mind map based on this. The JavaScript-based D3.js library is used to generate this mind map.

[0720] The generated mind map is sent from the server to the device, which then visually displays it to the user. For example, it can be displayed visually in a browser using HTML5 and JavaScript. This process allows users to easily and intuitively understand complex ideas and thoughts.

[0721] Here's a concrete example: Suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the speech to text using the Google Cloud Speech-to-Text API and extracts keywords using Python's NLTK library. It then visually arranges related keywords and ideas as nodes and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user in a browser.

[0722] Example prompt sentence:

[0723] "Tell me about your new project ideas."

[0724] The above is an embodiment of the present invention. This system allows users to intuitively and efficiently visualize their own ideas and thoughts, deepening their understanding.

[0725] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0726] Step 1:

[0727] Users input ideas and thoughts using devices such as PCs and smartphones. The input format can be text, voice, images, or video. For example, if a user selects voice input, the device's voice recognition software starts recording and captures the user's voice. Voice data is obtained as input.

[0728] Step 2:

[0729] The audio data acquired by the device is temporarily saved in WAV format. It is then converted to FLAC format and encoded in JSON format. This JSON format data is sent to the server via a dedicated API. The converted JSON data is obtained as input, and the data sent to the server is the output.

[0730] Step 3:

[0731] The server receives JSON-formatted voice data sent by the user. First, it checks the voice data for errors and verifies the data integrity. Then, it calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the voice data into text. It receives JSON-formatted voice data as input and obtains text data as output.

[0732] Step 4:

[0733] The server analyzes the text data. First, it uses a natural language processing library (e.g., Python's NLTK) to extract important keywords from the text. Specifically, it performs processes such as morphological analysis and frequency analysis to identify keywords. It receives text data as input and obtains a list of keywords as output.

[0734] Step 5:

[0735] The server generates a visual concept diagram based on the extracted keywords. Each keyword is placed as a node, and the relationships between the nodes are represented as links. The mind map is generated using the JavaScript-based D3.js library. It receives a list of keywords as input and obtains a visual concept diagram (mind map) as output.

[0736] Step 6:

[0737] The server converts the generated mind map into JSON format and sends it to the device. The device parses the received JSON format mind map data and displays it visually to the user. For example, it uses a browser to draw it using HTML5 and JavaScript. It receives JSON format mind map data as input and obtains a visual display as output.

[0738] These are the specific processing steps of this system. By utilizing a variety of user input formats and efficiently analyzing and visualizing data, a system that supports intuitive understanding is realized.

[0739] (Application example 1)

[0740] 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."

[0741] In modern economic activities and investment strategy planning, users need to efficiently organize and understand a large amount of information. However, this information is often provided in different formats, such as text, audio, images, and video, and there is a lack of tools to intuitively understand it. In addition, there is a need for concrete means to support user decision-making by visually organizing economic ideas and investment strategies. This makes it difficult for users to process information quickly and accurately and develop optimal investment strategies.

[0742] 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.

[0743] In this invention, the server includes means for receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means for generating a visual mind map based on the analyzed data, means for presenting the generated mind map to the user, and means for extracting key keywords from the analyzed data and visualizing related concepts as nodes when the multimodal input includes economic ideas or strategies, and means for presenting the visualized data as relationships between economic ideas and investment strategies, thereby enabling users to intuitively understand complex economic ideas and investment strategies and make more effective decisions.

[0744] - "Multimodal input" refers to data in different formats, such as text, audio, images, and video.

[0745] "Artificial intelligence" refers to technology for converting voice data into text and analyzing the content of text.

[0746] A "visual mind map" is a visual arrangement and display of analyzed data using nodes and links.

[0747] "Key Keywords" are important words and phrases extracted from the user's input data.

[0748] "Economic ideas" refers to ideas or strategies related to economic activity or investment.

[0749] An "investment strategy" refers to a plan for how to allocate and manage assets in anticipation of future profits.

[0750] A "node" refers to the graphical representation of each data point or concept in a mind map.

[0751] The "relationship" indicates how nodes are connected or related to each other.

[0752] This invention is a system for intuitively visualizing a user's economic ideas and investment strategies. Specific methods for implementing the invention will be described below.

[0753] Program Generation

[0754] The program is implemented primarily using a high-level programming language such as Python, and uses the following libraries and tools:

[0755] Speech Recognition: Uses the speech_recognition library to capture user voice input.

[0756] Natural Language Processing: Uses the KeyBERT library to extract key keywords from the text data extracted from the audio data.

[0757] Generate a network graph: Use the networkx library to display the relationships between keywords as a visual mind map.

[0758] Data visualization: Use the matplotlib library to display the generated mind map.

[0759] Processing Description

[0760] 1. User voice input

[0761] The server receives voice input from the user via the terminal. The voice input prompt looks like this:

[0762] Prompt users: "Tell me about any new investment strategies you're considering or market ideas you're watching."

[0763] 2. Acquiring audio data

[0764] The device uses the speech_recognition library to capture the user's voice input, and the captured voice data is sent to the server in real time.

[0765] 3. Converting Audio Data to Text

[0766] The server converts the received voice data into text using Google's speech recognition API, which is then used in the next analysis step.

[0767] 4. Keyword extraction

[0768] The server uses KeyBERT to extract key keywords from text data, allowing it to identify important elements in what users say.

[0769] 5. Generate a visual mind map

[0770] The server uses the networkx library to generate a mind map with extracted keywords as nodes and relationships between related keywords as edges.

[0771] 6. View Mind Map

[0772] The terminal visualizes the mind map sent from the server using the matplotlib library and presents it to the user, allowing the user to intuitively understand their economic ideas and investment strategies.

[0773] Specific examples

[0774] For example, if a user voice-inputs, "As a new investment strategy, I'm focusing on AI-related stocks, renewable energy, health technology, and the REIT market," the voice data is converted into text. From this text data, key keywords such as "AI-related stocks," "renewable energy," "health technology," and "REIT market" are extracted. A mind map is generated based on these keywords, visually showing their relationships. This mind map is displayed on the user's device, allowing the user to intuitively grasp the relationships between each keyword.

[0775] This invention makes it possible to efficiently organize and easily understand complex economic ideas and investment strategies, and supports user decision-making.

[0776] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0777] Step 1:

[0778] The user inputs voice data through the terminal. The user activates the voice recognition function and inputs voice data following the prompt, "Please tell us about your new investment strategy or market ideas you are interested in." The terminal then captures the voice data.

[0779] Input: User's voice data

[0780] Data processing: Acquire audio using the speech_recognition library

[0781] Output: Audio file

[0782] Step 2:

[0783] The terminal transmits the acquired voice data to the server.

[0784] Input: Audio data

[0785] Data processing: Converting audio data into JSON format

[0786] Output: Audio data (JSON format) to the server

[0787] Step 3:

[0788] The server receives the voice data and converts it into text data using a voice recognition API.

[0789] Input: Audio data in JSON format

[0790] Data processing: Convert speech to text using Google's speech recognition API

[0791] Output: Text data

[0792] Step 4:

[0793] The server analyzes the converted text data and extracts important keywords using the natural language processing library KeyBERT.

[0794] Input: Text data

[0795] Data processing: Extracting keywords using KeyBERT

[0796] Output: List of key keywords

[0797] Step 5:

[0798] The server generates a visual mind map based on the extracted keywords using the networkx library.

[0799] Input: List of primary keywords

[0800] Data processing: Using the networkx library to structure the relationships between keywords and generate nodes and edges

[0801] Output: Mind map structure (nodes and edges)

[0802] Step 6:

[0803] The server sends the generated mind map to the terminal.

[0804] Input: Mind map structure

[0805] Data processing: Convert the mind map structure into JSON format

[0806] Output: Mind map data (JSON format) to the device

[0807] Step 7:

[0808] The terminal visualizes the received mind map data and presents it to the user, using the matplotlib library for visualization.

[0809] Input: Mind map data (JSON format)

[0810] Data processing: Visualizing mind maps using the matplotlib library

[0811] Output: The mind map displayed to the user

[0812] Through the above processing steps, the user's economic ideas and investment strategies are visualized in an intuitive and easy-to-understand manner.

[0813] 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.

[0814] The present invention is a system for visually expressing a user's ideas and thoughts by combining an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0815] Accepting user input

[0816] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0817] Sending input data to the server

[0818] The device converts the acquired user input data into JSON format and prepares it for transmission. Once the data is ready for transmission, it is sent to the server via a dedicated API endpoint.

[0819] Receiving and analyzing data

[0820] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from the text data, analyzing the content of images and video data, and recognizing emotions using an emotion engine.

[0821] Emotion recognition by emotion engine

[0822] The server uses an emotion engine to analyze emotions from the user's input data. For example, in the case of voice data, it analyzes the tone and patterns of the sound to identify emotions. In the case of text data, it analyzes emotion-related vocabulary and context to recognize emotions.

[0823] Visual mind map generation

[0824] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The user's emotional state can also be reflected in the mind map, and related nodes can be indicated by changes in color or shape.

[0825] Send and view mind maps on your device

[0826] The server sends the generated mind map to the device, which then visually displays it to the user, allowing the user to intuitively understand complex ideas, thoughts, and the emotions behind them.

[0827] Specific examples

[0828] For example, suppose a user speaks about an "idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and recognizes the user's emotions (e.g., excitement or anxiety) from the voice. Next, a mind map is generated by visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[0829] This provides a new visual communication tool that visualizes complex ideas and thoughts concisely and intuitively, and also takes the user's emotions into consideration.

[0830] The processing flow will be explained below.

[0831] Step 1:

[0832] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0833] Step 2:

[0834] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[0835] Step 3:

[0836] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[0837] Step 4:

[0838] The device sends the prepared data to the server via a dedicated API endpoint.

[0839] Step 5:

[0840] The server receives the input data sent by the user and begins analysis, which includes converting voice data into text, extracting keywords from text data, and analyzing the content of image and video data.

[0841] Step 6:

[0842] The server converts the voice data into text and analyzes the content to extract important keywords and concepts. For example, if the voice data is "ideas for a new project," keywords such as "project," "idea," and "new" are extracted from the voice.

[0843] Step 7:

[0844] The server uses an emotion engine to analyze the emotion from the user's input data. In the case of voice data, the server analyzes the tone and patterns of the sound to identify the emotion. For example, it can identify whether the user is speaking excitedly or anxiously.

[0845] Step 8:

[0846] The server also analyzes the content of the text data using an emotion engine to recognize emotions, for example, identifying the user's emotions based on the frequency of positive and negative words.

[0847] Step 9:

[0848] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The nodes also reflect the user's emotional state. For example, nodes representing excited parts are displayed in bright colors, while nodes representing calm parts are displayed in calm colors.

[0849] Step 10:

[0850] The server sends the generated mind map to the device.

[0851] Step 11:

[0852] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[0853] Example 2

[0854] 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."

[0855] Conventional systems have a problem in that they are unable to reflect the user's emotional state when visually expressing a user's ideas and thoughts, making it difficult to understand intuitively. Furthermore, technologies for effectively analyzing multimodal input and generating visual mind maps based on it are insufficient. Therefore, there is a need for a communication tool that can more effectively visualize users' thoughts and take emotional factors into account.

[0856] 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 receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means using an emotion engine to recognize the user's emotions derived from the analyzed data, means for generating a visual mind map based on the analyzed data, means for reflecting the user's emotional state in the visual mind map, means for presenting the generated mind map to the user, and means for transmitting the mind map to a terminal and presenting it to the user. This makes it possible to visually express the user's thoughts and ideas together with emotional elements.

[0857] "Multimodal input" refers to data provided by a user in multiple formats, such as text, audio, images, and video.

[0858] "Artificial intelligence" refers to technology that uses computers to imitate human intelligence, and in particular refers to systems that automatically analyze and learn through data analysis and machine learning.

[0859] "Emotion engine" refers to a technology or system for analyzing and identifying emotions from user input data.

[0860] A "visual mind map" is a diagram that visually displays thoughts and information, structuring them with nodes and links.

[0861] A "node" refers to an element that represents a single entry or point of information in a mind map.

[0862] A "link" refers to a line or arrow that indicates the relationship or association between nodes.

[0863] "Terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0864] "Server" refers to a computer system that receives, analyzes, stores, and transmits data over a network.

[0865] "Analysis" refers to the process of understanding the content of data and clarifying its meaning and structure.

[0866] "Converting to text" refers to the process of converting audio data or image data into text information.

[0867] The present invention is a system for visually expressing a user's ideas and thoughts. The purpose of this system is to visually express the user's thoughts and emotions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0868] Accepting user input

[0869] Users input their ideas and thoughts using devices such as PCs or smartphones. This input can be in the form of text, voice, images, or video. Specifically, when a user voice-inputs a "new project idea," the device uses a microphone to record the voice data. In this case, the device uses a native Android or iOS application to input the voice data into the system.

[0870] Sending input data to the server

[0871] The device converts the acquired data into JSON format. For example, it encodes audio data in Base64 format. Then, it uses HTTP communication to send the JSON data to a dedicated API endpoint using the POST method. This sending process is implemented using an HTTP library. Communication between the server and the device is encrypted with SSL / TLS and kept secure.

[0872] Receiving and analyzing data

[0873] The server receives JSON data sent from the device. It uses artificial intelligence technology to analyze the data and converts the voice data into text. It also uses the Google Cloud Speech-to-Text API to convert the voice to text and extracts keywords from the text data using natural language processing libraries such as NLTK and SpaCy. For image and video data, it uses the Google Cloud Vision API to analyze the content.

[0874] emotion recognition

[0875] The server uses an emotion engine to recognize the user's emotion from the analyzed data. Specifically, it uses the Transformers library to analyze the emotion of text data. For audio data, it uses the LibROSA library to analyze the tone and patterns of the voice and then uses the IBM Watson Tone Analyzer, an emotion engine, to identify the emotion.

[0876] Visual mind map generation

[0877] The server generates a visual mind map based on the analysis results and emotion recognition results. Visualization libraries such as D3.js and Graphviz are used to generate this mind map. Each data point and important keyword is represented as a node, and the relationships between nodes are represented as links. The user's emotional state is also reflected in the color and shape of the nodes, allowing for intuitive understanding.

[0878] Send and view mind maps on your device

[0879] The server then converts the generated mind map back into JSON format and sends it to the device, which then visualizes and displays the received mind map using a web browser. This allows users to intuitively understand complex ideas, thoughts, and the emotions behind them.

[0880] Specific examples

[0881] For example, if a user speaks "an idea for a new project," the device records this voice data, encodes it, and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. Next, a mind map is generated, visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[0882] Prompt Sentence Examples

[0883] Below is an example of a prompt sentence to input to the generative AI model.

[0884] The user speaks their "idea for a new project." This speech data is converted into JSON format and sent to the server. The server converts the speech to text, extracts keywords, and recognizes sentiment. It then generates a mind map and sends it to the device for display.

[0885] As a result, this system intuitively visualizes the user's complex ideas and thoughts, incorporating emotional elements, and functions as a new visual communication tool.

[0886] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0887] Step 1: Accepting User Input

[0888] Users use devices such as PCs and smartphones to input ideas and thoughts. This input can be in the form of text, voice, images, or video. For example, if a user voice-inputs "an idea for a new project," the device uses a microphone to record the voice data. Input: Voice. Output: Recorded voice data.

[0889] Step 2: Send input data to the server

[0890] The audio data recorded by the device is encoded in Base64 format and converted to JSON format. It is then sent to the server via an HTTP request using the POST method to a dedicated API endpoint. Input: Recorded audio data. Output: JSON format data.

[0891] Step 3: Receiving and analyzing data

[0892] The server receives JSON data sent from the device. It converts the voice data into text using the Google Cloud Speech-to-Text API. This conversion process includes decoding the voice data, sending the data, and converting it back to text. Input: Voice data in JSON format. Output: Text data.

[0893] Step 4: Keyword extraction

[0894] The server analyzes the text data using a natural language processing library (e.g., NLTK or SpaCy) and extracts key keywords. Input: Text data. Output: List of key keywords.

[0895] Step 5: Emotion Recognition

[0896] The server uses an emotion engine (for example, the Transformers library or IBM Watson Tone Analyzer) to recognize the user's emotion from text or voice data. For voice data, the LibROSA library is used to analyze the tone and patterns of the voice. Input: Text or voice data. Output: Sentiment analysis results.

[0897] Step 6: Generate a visual mind map

[0898] The server generates a visual mind map using a visualization library (e.g., D3.js or Graphviz) based on the analysis results and emotion recognition results. Keywords are arranged as nodes, and relationships are visualized as links. Emotional states are also reflected as the color and shape of the nodes. Input: List of main keywords, emotion analysis results. Output: Visual mind map.

[0899] Step 7: Send and view your mind map on your device

[0900] The server converts the generated mind map back into JSON format and sends it to the device. The device visually displays the received mind map using a web browser. Input: Visual mind map. Output: Visual mind map displayed on the device.

[0901] Specific actions

[0902] For example, when a user speaks "an idea for a new project," the device records and encodes the voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. It then uses D3.js to generate a visual mind map, which is then sent to the device for display. This allows the device to intuitively understand the user's complex thoughts and emotions.

[0903] (Application example 2)

[0904] 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."

[0905] In autonomous vehicles, it is difficult to understand the driver's emotional state and provide appropriate feedback and alerts accordingly. Because a driver's emotional state directly affects driving behavior, a system that recognizes emotions in real time and responds appropriately is required. Furthermore, conventional systems have difficulty visually grasping the user's emotions, and visualization of ideas and thoughts is limited.

[0906] 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.

[0907] In this invention, the server includes: means for receiving multimodal input from a user; means using artificial intelligence to analyze the multimodal input; means for generating a visual mind map based on the analyzed data and the user's emotions; means for presenting the generated mind map to the user; means for receiving the driver's voice and video as user input and analyzing the data in real time; and means for providing feedback and alerts to the driver based on the analysis results. This enables the system to recognize the driver's emotional state in real time and provide corresponding feedback and alerts, thereby improving driving safety and comfort. Furthermore, visually displaying the user's emotions and ideas enables more intuitive communication.

[0908] "User" refers to a person or driver who uses the system.

[0909] "Multimodal format" refers to multiple different data formats, such as text, audio, images, video, etc.

[0910] "Input" refers to data or information provided by a user.

[0911] "Artificial intelligence" refers to technology that uses machine learning algorithms to analyze data and support decision-making.

[0912] A "visual mind map" is a diagram that visually structures and displays a user's ideas, thoughts, and feelings.

[0913] "Driver" means a person using an automated vehicle.

[0914] "Real-time" means that the process from data acquisition to analysis and provision of results is carried out almost simultaneously.

[0915] "Feedback" refers to advice or information the system provides to the driver.

[0916] "Alert" refers to a warning or caution provided by the system to the driver.

[0917] "Analysis results" refers to the information obtained after artificial intelligence processes input data.

[0918] "Emotion" refers to the driver's psychological state and mood.

[0919] "Driving assist function" refers to the system's function of assisting driving according to the driver's emotional state.

[0920] The present invention provides a system for recognizing a user's emotions and visually expressing the user's ideas and thoughts based on the emotions. Specific embodiments of the present invention will be described below.

[0921] The system includes artificial intelligence to receive multimodal input from users, analyze this data, generate a visual mind map based on the analyzed data and the user's emotional state, and present this mind map to the user.

[0922] The system program works as follows: First, the driver's audio and video data is captured in real time using a smartphone. The smartphone's microphone is used for audio data, and the smartphone's camera is used for video data. This data is converted into JSON format and sent to a server via the Internet.

[0923] The server receives and analyzes the audio and video data. OpenCV is used to analyze the video data, and Pydub is used to process the audio data. Machine learning algorithms are used for emotion recognition. In particular, generative AI models can be used to recognize user emotions in real time.

[0924] Based on the analysis results, the server generates a visual mind map. This mind map is represented by colors and shapes based on the user's emotional state. For example, if the driver is excited, the nodes on the mind map will be displayed in bright colors, and if they are relaxed, they will be displayed in calm colors. This mind map is then converted back into JSON format and sent to the smartphone.

[0925] The smartphone then presents the received mind map to the user in real time. Through this visual mind map, the user can intuitively understand their own emotional state and thoughts. The system also provides emotion-based feedback and alerts to the driver while driving. For example, if the driver is frustrated, the system will play relaxing music or display a reminder notification.

[0926] As a concrete example, suppose a driver says "I'm tired today" while driving. This voice is captured by the smartphone's microphone and sent to the server. The server analyzes the voice and recognizes that the driver is tired. As a result, it responds by providing feedback to the driver saying, "I recommend you take a break." Furthermore, "fatigue" is visualized as an important node in the mind map, clearly presented to the user.

[0927] Specific examples of input prompts for a generative AI model include, "Design an API to analyze the driver's voice data and identify their emotions" and "How can I analyze the driver's facial expressions to recognize their emotions in real time?"

[0928] In this way, the present invention realizes a system that recognizes a user's emotions in real time and provides appropriate feedback and alerts to the user, thereby enabling visual understanding and safe driving assistance based on the user's emotional state.

[0929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0930] Step 1:

[0931] The user's smartphone captures audio and video of the driver.

[0932] Specifically, audio is recorded using the smartphone's microphone and video is captured using the smartphone's camera. The audio data is acquired in WAV format and the video data in JPEG format.

[0933] Input: Driver audio and video

[0934] Output: WAV format audio data, JPEG format video data

[0935] Step 2:

[0936] The smartphone converts the acquired audio and video data into JSON format.

[0937] Specifically, audio data is converted from binary format to a string, and video data is converted to a string using Base64 encoding, and then packaged into JSON.

[0938] Input: WAV format audio data, JPEG format video data

[0939] Output: A JSON object containing audio and video data

[0940] Step 3:

[0941] The smartphone sends the preprocessed JSON data to the server over the Internet.

[0942] Specifically, HTTP POST is used as the communication protocol to send data to a dedicated API endpoint.

[0943] Input: A JSON object containing audio and video data

[0944] Output: Data sent to the server

[0945] Step 4:

[0946] The server analyzes the received data.

[0947] Specifically, we use OpenCV to analyze facial expressions and movements from video data, Pydub to extract features from audio data, and machine learning algorithms to estimate emotions.

[0948] Input: JSON object (audio and video data)

[0949] Output: Emotion recognition results and analysis results

[0950] Step 5:

[0951] The server generates a visual mind map based on the emotion recognition and analysis results.

[0952] Specifically, we assign emotion data corresponding to each node as an attribute, generate links between nodes based on their relevance, and create visual elements that change color and shape depending on the emotion.

[0953] Input: Emotion recognition results and analysis results

[0954] Output: Visual mind map data

[0955] Step 6:

[0956] The server then encodes the generated mind map into JSON format again and sends it to the smartphone.

[0957] Specifically, data is sent as an HTTP POST request through a dedicated API endpoint.

[0958] Input: Visual mind map data

[0959] Output: Mind map data sent to your smartphone

[0960] Step 7:

[0961] The smartphone interprets the received mind map data and presents it visually to the user.

[0962] Specifically, it parses JSON data and displays the mind map in a suitable graphical user interface, along with context-sensitive feedback and alerts.

[0963] Input: Visual mind map data

[0964] Output: Mind map presented to the user and feedback alerts

[0965] 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.

[0966] 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.

[0967] 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.

[0968] [Fourth embodiment]

[0969] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0970] 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.

[0971] 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).

[0972] 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.

[0973] 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.

[0974] 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).

[0975] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0976] 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.

[0977] 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.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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."

[0982] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[0983] Accepting user input

[0984] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[0985] Sending input data to the server

[0986] The device sends the acquired user input data to the server via a dedicated API. When sending, the input data is converted into an appropriate data format, such as JSON.

[0987] Receiving and analyzing data

[0988] The server receives the input data sent by the user and begins analyzing it. This analysis includes converting the voice data into text, extracting keywords from the text data, and analyzing the content of images and video data. Artificial intelligence is used for these analyses.

[0989] Visual mind map generation

[0990] The server generates a visual mind map based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between the nodes are visualized as links. For example, when audio data such as "new project ideas" is input, the audio is converted into text, and related concepts and keywords are extracted based on the text.

[0991] Send and view mind maps on your device

[0992] The server sends the generated mind map to the device, which then visually displays the received mind map to the user, allowing the user to intuitively understand complex ideas and thoughts.

[0993] Specific examples

[0994] For example, suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text and extracts keywords. Next, it visually arranges related keywords and ideas as nodes, and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user.

[0995] This process provides a system that effectively supports users' creative processes, organizing ideas, and understanding educational content by visualizing complex ideas and thoughts concisely and intuitively.

[0996] The processing flow will be explained below.

[0997] Step 1:

[0998] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[0999] Step 2:

[1000] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[1001] Step 3:

[1002] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[1003] Step 4:

[1004] The device sends the prepared data to the server via a dedicated API endpoint.

[1005] Step 5:

[1006] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from text data, and analyzing the content of images and video data.

[1007] Step 6:

[1008] The server converts the audio data into text, analyzes the content, and extracts important keywords and concepts.

[1009] Step 7:

[1010] The server creates nodes based on the results of keyword extraction from the text, and visually represents the relationships between each node as links.

[1011] Step 8:

[1012] The server generates a visual mind map based on the parsed data, with nodes and links appropriately arranged according to user input.

[1013] Step 9:

[1014] The server sends the generated mind map to the device.

[1015] Step 10:

[1016] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[1017] Example 1

[1018] 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."

[1019] Conventional idea and thought visualization systems rely on a single input format, making it difficult to effectively visualize users' diverse thought processes and ideas. They also face the problem of requiring a lot of manual work for complex data analysis and visualization, making it inefficient. This makes it difficult to generate visual mind maps that users can intuitively understand.

[1020] 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.

[1021] In this invention, the server includes means for receiving multimodal input from a user, means for using machine learning to analyze the multimodal input, means for generating a visual concept map based on the analyzed data, and means for presenting the generated concept map to the user. This allows the user to easily input complex ideas and thoughts in a variety of input formats, and the input is analyzed and displayed as a visual concept map that is intuitively easy to understand.

[1022] A "user" is someone who uses the system to input ideas and thoughts and to view the visualized results.

[1023] "Multimodal input" refers to an input method that handles multiple different types of data, such as text, audio, images, and video, all at once.

[1024] "Machine learning" is a branch of artificial intelligence used in data analysis, and is a technology that automatically learns patterns and rules from input data and performs analysis and predictions.

[1025] A "visual conceptual diagram" is a visual map that represents extracted information using nodes (points) and links (lines), and is constructed in a way that is easy for users to intuitively understand.

[1026] A "node" is an element in a visual concept diagram that represents a single data point or idea and is associated with other nodes by links.

[1027] A "link" is a line that indicates the relationship between nodes in a visual conceptual diagram, and is a means of visually showing connections and relationships between information.

[1028] The present invention is a system for intuitively visualizing a user's ideas and thoughts, and is implemented as follows.

[1029] First, a user inputs ideas or thoughts using a device such as a PC or smartphone. The input format can be text, voice, image, or video. The device acquires the data based on the input format selected by the user. For example, when voice input is performed using voice recognition software on a PC, the device receives the voice data and temporarily saves it in WAV format.

[1030] Next, the device sends the acquired user input data to the server via a dedicated API. At this time, the input data is converted into an appropriate data format, such as JSON. For example, in the case of audio data, the audio file is converted to FLAC format on the device and then sent to the server in JSON format.

[1031] The server receives the input data sent by the user and begins analyzing it. The analysis is performed using the following hardware and software:

[1032] A speech recognition API to convert voice data into text (e.g., Google Cloud Speech-to-Text)

[1033] Natural language processing libraries for extracting keywords from text data (e.g., Python's NLTK)

[1034] Computer vision services for analyzing the content of image and video data (e.g., Azure Cognitive Services)

[1035] The server generates a visual conceptual diagram (mind map) based on the analyzed data. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. For example, if audio data such as "ideas for a new project" is input, the audio is converted into text, and related keywords are extracted based on that text, and nodes and links are generated as a mind map based on this. The JavaScript-based D3.js library is used to generate this mind map.

[1036] The generated mind map is sent from the server to the device, which then visually displays it to the user. For example, it can be displayed visually in a browser using HTML5 and JavaScript. This process allows users to easily and intuitively understand complex ideas and thoughts.

[1037] Here's a concrete example: Suppose a user speaks "an idea for a new project." The device records this voice data and sends it to the server. The server converts the speech to text using the Google Cloud Speech-to-Text API and extracts keywords using Python's NLTK library. It then visually arranges related keywords and ideas as nodes and generates a mind map with their relationships as links. This mind map is sent to the device and finally displayed to the user in a browser.

[1038] Example prompt sentence:

[1039] "Tell me about your new project ideas."

[1040] The above is an embodiment of the present invention. This system allows users to intuitively and efficiently visualize their own ideas and thoughts, deepening their understanding.

[1041] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1042] Step 1:

[1043] Users input ideas and thoughts using devices such as PCs and smartphones. The input format can be text, voice, images, or video. For example, if a user selects voice input, the device's voice recognition software starts recording and captures the user's voice. Voice data is obtained as input.

[1044] Step 2:

[1045] The audio data acquired by the device is temporarily saved in WAV format. It is then converted to FLAC format and encoded in JSON format. This JSON format data is sent to the server via a dedicated API. The converted JSON data is obtained as input, and the data sent to the server is the output.

[1046] Step 3:

[1047] The server receives JSON-formatted voice data sent by the user. First, it checks the voice data for errors and verifies the data integrity. Then, it calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the voice data into text. It receives JSON-formatted voice data as input and obtains text data as output.

[1048] Step 4:

[1049] The server analyzes the text data. First, it uses a natural language processing library (e.g., Python's NLTK) to extract important keywords from the text. Specifically, it performs processes such as morphological analysis and frequency analysis to identify keywords. It receives text data as input and obtains a list of keywords as output.

[1050] Step 5:

[1051] The server generates a visual concept diagram based on the extracted keywords. Each keyword is placed as a node, and the relationships between the nodes are represented as links. The mind map is generated using the JavaScript-based D3.js library. It receives a list of keywords as input and obtains a visual concept diagram (mind map) as output.

[1052] Step 6:

[1053] The server converts the generated mind map into JSON format and sends it to the device. The device parses the received JSON format mind map data and displays it visually to the user. For example, it uses a browser to draw it using HTML5 and JavaScript. It receives JSON format mind map data as input and obtains a visual display as output.

[1054] These are the specific processing steps of this system. By utilizing a variety of user input formats and efficiently analyzing and visualizing data, a system that supports intuitive understanding is realized.

[1055] (Application example 1)

[1056] 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."

[1057] In modern economic activities and investment strategy planning, users need to efficiently organize and understand a large amount of information. However, this information is often provided in different formats, such as text, audio, images, and video, and there is a lack of tools to intuitively understand it. In addition, there is a need for concrete means to support user decision-making by visually organizing economic ideas and investment strategies. This makes it difficult for users to process information quickly and accurately and develop optimal investment strategies.

[1058] 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.

[1059] In this invention, the server includes means for receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means for generating a visual mind map based on the analyzed data, means for presenting the generated mind map to the user, and means for extracting key keywords from the analyzed data and visualizing related concepts as nodes when the multimodal input includes economic ideas or strategies, and means for presenting the visualized data as relationships between economic ideas and investment strategies, thereby enabling users to intuitively understand complex economic ideas and investment strategies and make more effective decisions.

[1060] - "Multimodal input" refers to data in different formats, such as text, audio, images, and video.

[1061] "Artificial intelligence" refers to technology for converting voice data into text and analyzing the content of text.

[1062] A "visual mind map" is a visual arrangement and display of analyzed data using nodes and links.

[1063] "Key Keywords" are important words and phrases extracted from the user's input data.

[1064] "Economic ideas" refers to ideas or strategies related to economic activity or investment.

[1065] An "investment strategy" refers to a plan for how to allocate and manage assets in anticipation of future profits.

[1066] A "node" refers to the graphical representation of each data point or concept in a mind map.

[1067] The "relationship" indicates how nodes are connected or related to each other.

[1068] This invention is a system for intuitively visualizing a user's economic ideas and investment strategies. Specific methods for implementing the invention will be described below.

[1069] Program Generation

[1070] The program is implemented primarily using a high-level programming language such as Python, and uses the following libraries and tools:

[1071] Speech Recognition: Uses the speech_recognition library to capture user voice input.

[1072] Natural Language Processing: Uses the KeyBERT library to extract key keywords from the text data extracted from the audio data.

[1073] Generate a network graph: Use the networkx library to display the relationships between keywords as a visual mind map.

[1074] Data visualization: Use the matplotlib library to display the generated mind map.

[1075] Processing Description

[1076] 1. User voice input

[1077] The server receives voice input from the user via the terminal. The voice input prompt looks like this:

[1078] Prompt users: "Tell me about any new investment strategies you're considering or market ideas you're watching."

[1079] 2. Acquiring audio data

[1080] The device uses the speech_recognition library to capture the user's voice input, and the captured voice data is sent to the server in real time.

[1081] 3. Converting Audio Data to Text

[1082] The server converts the received voice data into text using Google's speech recognition API, which is then used in the next analysis step.

[1083] 4. Keyword extraction

[1084] The server uses KeyBERT to extract key keywords from text data, allowing it to identify important elements in what users say.

[1085] 5. Generate a visual mind map

[1086] The server uses the networkx library to generate a mind map with extracted keywords as nodes and relationships between related keywords as edges.

[1087] 6. View Mind Map

[1088] The terminal visualizes the mind map sent from the server using the matplotlib library and presents it to the user, allowing the user to intuitively understand their economic ideas and investment strategies.

[1089] Specific examples

[1090] For example, if a user voice-inputs, "As a new investment strategy, I'm focusing on AI-related stocks, renewable energy, health technology, and the REIT market," the voice data is converted into text. From this text data, key keywords such as "AI-related stocks," "renewable energy," "health technology," and "REIT market" are extracted. A mind map is generated based on these keywords, visually showing their relationships. This mind map is displayed on the user's device, allowing the user to intuitively grasp the relationships between each keyword.

[1091] This invention makes it possible to efficiently organize and easily understand complex economic ideas and investment strategies, and supports user decision-making.

[1092] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1093] Step 1:

[1094] The user inputs voice data through the terminal. The user activates the voice recognition function and inputs voice data following the prompt, "Please tell us about your new investment strategy or market ideas you are interested in." The terminal then captures the voice data.

[1095] Input: User's voice data

[1096] Data processing: Acquire audio using the speech_recognition library

[1097] Output: Audio file

[1098] Step 2:

[1099] The terminal transmits the acquired voice data to the server.

[1100] Input: Audio data

[1101] Data processing: Converting audio data into JSON format

[1102] Output: Audio data (JSON format) to the server

[1103] Step 3:

[1104] The server receives the voice data and converts it into text data using a voice recognition API.

[1105] Input: Audio data in JSON format

[1106] Data processing: Convert speech to text using Google's speech recognition API

[1107] Output: Text data

[1108] Step 4:

[1109] The server analyzes the converted text data and extracts important keywords using the natural language processing library KeyBERT.

[1110] Input: Text data

[1111] Data processing: Extracting keywords using KeyBERT

[1112] Output: List of key keywords

[1113] Step 5:

[1114] The server generates a visual mind map based on the extracted keywords using the networkx library.

[1115] Input: List of primary keywords

[1116] Data processing: Using the networkx library to structure the relationships between keywords and generate nodes and edges

[1117] Output: Mind map structure (nodes and edges)

[1118] Step 6:

[1119] The server sends the generated mind map to the terminal.

[1120] Input: Mind map structure

[1121] Data processing: Convert the mind map structure into JSON format

[1122] Output: Mind map data (JSON format) to the device

[1123] Step 7:

[1124] The terminal visualizes the received mind map data and presents it to the user, using the matplotlib library for visualization.

[1125] Input: Mind map data (JSON format)

[1126] Data processing: Visualizing mind maps using the matplotlib library

[1127] Output: The mind map displayed to the user

[1128] Through the above processing steps, the user's economic ideas and investment strategies are visualized in an intuitive and easy-to-understand manner.

[1129] 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.

[1130] The present invention is a system for visually expressing a user's ideas and thoughts by combining an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[1131] Accepting user input

[1132] Users input ideas and thoughts using devices such as PCs or smartphones. The input format can be text, audio, images, or video. The device acquires the data based on the input format selected by the user.

[1133] Sending input data to the server

[1134] The device converts the acquired user input data into JSON format and prepares it for transmission. Once the data is ready for transmission, it is sent to the server via a dedicated API endpoint.

[1135] Receiving and analyzing data

[1136] The server receives the input data sent by the user and begins analysis, which includes converting speech to text, extracting keywords from the text data, analyzing the content of images and video data, and recognizing emotions using an emotion engine.

[1137] Emotion recognition by emotion engine

[1138] The server uses an emotion engine to analyze emotions from the user's input data. For example, in the case of voice data, it analyzes the tone and patterns of the sound to identify emotions. In the case of text data, it analyzes emotion-related vocabulary and context to recognize emotions.

[1139] Visual mind map generation

[1140] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The user's emotional state can also be reflected in the mind map, and related nodes can be indicated by changes in color or shape.

[1141] Send and view mind maps on your device

[1142] The server sends the generated mind map to the device, which then visually displays it to the user, allowing the user to intuitively understand complex ideas, thoughts, and the emotions behind them.

[1143] Specific examples

[1144] For example, suppose a user speaks about an "idea for a new project." The device records this voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and recognizes the user's emotions (e.g., excitement or anxiety) from the voice. Next, a mind map is generated by visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[1145] This provides a new visual communication tool that visualizes complex ideas and thoughts concisely and intuitively, and also takes the user's emotions into consideration.

[1146] The processing flow will be explained below.

[1147] Step 1:

[1148] Users select the format (text, audio, image, video) in which to input their ideas and thoughts from the device's UI.

[1149] Step 2:

[1150] The device receives input data based on the user's selected format, for example, starts recording for audio, or takes a photo or selects a file for image or video.

[1151] Step 3:

[1152] The terminal converts the user input data it acquires into JSON format and prepares it for transmission.

[1153] Step 4:

[1154] The device sends the prepared data to the server via a dedicated API endpoint.

[1155] Step 5:

[1156] The server receives the input data sent by the user and begins analysis, which includes converting voice data into text, extracting keywords from text data, and analyzing the content of image and video data.

[1157] Step 6:

[1158] The server converts the voice data into text and analyzes the content to extract important keywords and concepts. For example, if the voice data is "ideas for a new project," keywords such as "project," "idea," and "new" are extracted from the voice.

[1159] Step 7:

[1160] The server uses an emotion engine to analyze the emotion from the user's input data. In the case of voice data, the server analyzes the tone and patterns of the sound to identify the emotion. For example, it can identify whether the user is speaking excitedly or anxiously.

[1161] Step 8:

[1162] The server also analyzes the content of the text data using an emotion engine to recognize emotions, for example, identifying the user's emotions based on the frequency of positive and negative words.

[1163] Step 9:

[1164] The server generates a visual mind map based on the analyzed data and emotion recognition results. Each data point and important keyword is represented as a node, and the relationships between nodes are visualized as links. The nodes also reflect the user's emotional state. For example, nodes representing excited parts are displayed in bright colors, while nodes representing calm parts are displayed in calm colors.

[1165] Step 10:

[1166] The server sends the generated mind map to the device.

[1167] Step 11:

[1168] The device visually displays the received mind map to the user, who can then review the displayed mind map and make edits or adjustments as needed.

[1169] Example 2

[1170] 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."

[1171] Conventional systems have a problem in that they are unable to reflect the user's emotional state when visually expressing a user's ideas and thoughts, making it difficult to understand intuitively. Furthermore, technologies for effectively analyzing multimodal input and generating visual mind maps based on it are insufficient. Therefore, there is a need for a communication tool that can more effectively visualize users' thoughts and take emotional factors into account.

[1172] 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 receiving multimodal input from a user, means using artificial intelligence to analyze the multimodal input, means using an emotion engine to recognize the user's emotions derived from the analyzed data, means for generating a visual mind map based on the analyzed data, means for reflecting the user's emotional state in the visual mind map, means for presenting the generated mind map to the user, and means for transmitting the mind map to a terminal and presenting it to the user. This makes it possible to visually express the user's thoughts and ideas together with emotional elements.

[1173] "Multimodal input" refers to data provided by a user in multiple formats, such as text, audio, images, and video.

[1174] "Artificial intelligence" refers to technology that uses computers to imitate human intelligence, and in particular refers to systems that automatically analyze and learn through data analysis and machine learning.

[1175] "Emotion engine" refers to a technology or system for analyzing and identifying emotions from user input data.

[1176] A "visual mind map" is a diagram that visually displays thoughts and information, structuring them with nodes and links.

[1177] A "node" refers to an element that represents a single entry or point of information in a mind map.

[1178] A "link" refers to a line or arrow that indicates the relationship or association between nodes.

[1179] "Terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[1180] "Server" refers to a computer system that receives, analyzes, stores, and transmits data over a network.

[1181] "Analysis" refers to the process of understanding the content of data and clarifying its meaning and structure.

[1182] "Converting to text" refers to the process of converting audio data or image data into text information.

[1183] The present invention is a system for visually expressing a user's ideas and thoughts. The purpose of this system is to visually express the user's thoughts and emotions by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[1184] Accepting user input

[1185] Users input their ideas and thoughts using devices such as PCs or smartphones. This input can be in the form of text, voice, images, or video. Specifically, when a user voice-inputs a "new project idea," the device uses a microphone to record the voice data. In this case, the device uses a native Android or iOS application to input the voice data into the system.

[1186] Sending input data to the server

[1187] The device converts the acquired data into JSON format. For example, it encodes audio data in Base64 format. Then, it uses HTTP communication to send the JSON data to a dedicated API endpoint using the POST method. This sending process is implemented using an HTTP library. Communication between the server and the device is encrypted with SSL / TLS and kept secure.

[1188] Receiving and analyzing data

[1189] The server receives JSON data sent from the device. It uses artificial intelligence technology to analyze the data and converts the voice data into text. It also uses the Google Cloud Speech-to-Text API to convert the voice to text and extracts keywords from the text data using natural language processing libraries such as NLTK and SpaCy. For image and video data, it uses the Google Cloud Vision API to analyze the content.

[1190] emotion recognition

[1191] The server uses an emotion engine to recognize the user's emotion from the analyzed data. Specifically, it uses the Transformers library to analyze the emotion of text data. For audio data, it uses the LibROSA library to analyze the tone and patterns of the voice and then uses the IBM Watson Tone Analyzer, an emotion engine, to identify the emotion.

[1192] Visual mind map generation

[1193] The server generates a visual mind map based on the analysis results and emotion recognition results. Visualization libraries such as D3.js and Graphviz are used to generate this mind map. Each data point and important keyword is represented as a node, and the relationships between nodes are represented as links. The user's emotional state is also reflected in the color and shape of the nodes, allowing for intuitive understanding.

[1194] Send and view mind maps on your device

[1195] The server then converts the generated mind map back into JSON format and sends it to the device, which then visualizes and displays the received mind map using a web browser. This allows users to intuitively understand complex ideas, thoughts, and the emotions behind them.

[1196] Specific examples

[1197] For example, if a user speaks "an idea for a new project," the device records this voice data, encodes it, and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. Next, a mind map is generated, visually arranging related keywords and ideas as nodes and linking their relationships. The results of emotion recognition are also reflected in each node. For example, nodes representing excited parts are displayed in bright colors, and nodes representing calm parts are displayed in calm colors. This mind map is sent to the device and finally displayed to the user.

[1198] Prompt Sentence Examples

[1199] Below is an example of a prompt sentence to input to the generative AI model.

[1200] The user speaks their "idea for a new project." This speech data is converted into JSON format and sent to the server. The server converts the speech to text, extracts keywords, and recognizes sentiment. It then generates a mind map and sends it to the device for display.

[1201] As a result, this system intuitively visualizes the user's complex ideas and thoughts, incorporating emotional elements, and functions as a new visual communication tool.

[1202] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1203] Step 1: Accepting User Input

[1204] Users use devices such as PCs and smartphones to input ideas and thoughts. This input can be in the form of text, voice, images, or video. For example, if a user voice-inputs "an idea for a new project," the device uses a microphone to record the voice data. Input: Voice. Output: Recorded voice data.

[1205] Step 2: Send input data to the server

[1206] The audio data recorded by the device is encoded in Base64 format and converted to JSON format. It is then sent to the server via an HTTP request using the POST method to a dedicated API endpoint. Input: Recorded audio data. Output: JSON format data.

[1207] Step 3: Receiving and analyzing data

[1208] The server receives JSON data sent from the device. It converts the voice data into text using the Google Cloud Speech-to-Text API. This conversion process includes decoding the voice data, sending the data, and converting it back to text. Input: Voice data in JSON format. Output: Text data.

[1209] Step 4: Keyword extraction

[1210] The server analyzes the text data using a natural language processing library (e.g., NLTK or SpaCy) and extracts key keywords. Input: Text data. Output: List of key keywords.

[1211] Step 5: Emotion Recognition

[1212] The server uses an emotion engine (for example, the Transformers library or IBM Watson Tone Analyzer) to recognize the user's emotion from text or voice data. For voice data, the LibROSA library is used to analyze the tone and patterns of the voice. Input: Text or voice data. Output: Sentiment analysis results.

[1213] Step 6: Generate a visual mind map

[1214] The server generates a visual mind map using a visualization library (e.g., D3.js or Graphviz) based on the analysis results and emotion recognition results. Keywords are arranged as nodes, and relationships are visualized as links. Emotional states are also reflected as the color and shape of the nodes. Input: List of main keywords, emotion analysis results. Output: Visual mind map.

[1215] Step 7: Send and view your mind map on your device

[1216] The server converts the generated mind map back into JSON format and sends it to the device. The device visually displays the received mind map using a web browser. Input: Visual mind map. Output: Visual mind map displayed on the device.

[1217] Specific actions

[1218] For example, when a user speaks "an idea for a new project," the device records and encodes the voice data and sends it to the server. The server converts the voice data into text, extracts keywords, and uses an emotion engine to recognize the user's emotions. It then uses D3.js to generate a visual mind map, which is then sent to the device for display. This allows the device to intuitively understand the user's complex thoughts and emotions.

[1219] (Application example 2)

[1220] 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."

[1221] In autonomous vehicles, it is difficult to understand the driver's emotional state and provide appropriate feedback and alerts accordingly. Because a driver's emotional state directly affects driving behavior, a system that recognizes emotions in real time and responds appropriately is required. Furthermore, conventional systems have difficulty visually grasping the user's emotions, and visualization of ideas and thoughts is limited.

[1222] 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.

[1223] In this invention, the server includes: means for receiving multimodal input from a user; means using artificial intelligence to analyze the multimodal input; means for generating a visual mind map based on the analyzed data and the user's emotions; means for presenting the generated mind map to the user; means for receiving the driver's voice and video as user input and analyzing the data in real time; and means for providing feedback and alerts to the driver based on the analysis results. This enables the system to recognize the driver's emotional state in real time and provide corresponding feedback and alerts, thereby improving driving safety and comfort. Furthermore, visually displaying the user's emotions and ideas enables more intuitive communication.

[1224] "User" refers to a person or driver who uses the system.

[1225] "Multimodal format" refers to multiple different data formats, such as text, audio, images, video, etc.

[1226] "Input" refers to data or information provided by a user.

[1227] "Artificial intelligence" refers to technology that uses machine learning algorithms to analyze data and support decision-making.

[1228] A "visual mind map" is a diagram that visually structures and displays a user's ideas, thoughts, and feelings.

[1229] "Driver" means a person using an automated vehicle.

[1230] "Real-time" means that the process from data acquisition to analysis and provision of results is carried out almost simultaneously.

[1231] "Feedback" refers to advice or information the system provides to the driver.

[1232] "Alert" refers to a warning or caution provided by the system to the driver.

[1233] "Analysis results" refers to the information obtained after artificial intelligence processes input data.

[1234] "Emotion" refers to the driver's psychological state and mood.

[1235] "Driving assist function" refers to the system's function of assisting driving according to the driver's emotional state.

[1236] The present invention provides a system for recognizing a user's emotions and visually expressing the user's ideas and thoughts based on the emotions. Specific embodiments of the present invention will be described below.

[1237] The system includes artificial intelligence to receive multimodal input from users, analyze this data, generate a visual mind map based on the analyzed data and the user's emotional state, and present this mind map to the user.

[1238] The system program works as follows: First, the driver's audio and video data is captured in real time using a smartphone. The smartphone's microphone is used for audio data, and the smartphone's camera is used for video data. This data is converted into JSON format and sent to a server via the Internet.

[1239] The server receives and analyzes the audio and video data. OpenCV is used to analyze the video data, and Pydub is used to process the audio data. Machine learning algorithms are used for emotion recognition. In particular, generative AI models can be used to recognize user emotions in real time.

[1240] Based on the analysis results, the server generates a visual mind map. This mind map is represented by colors and shapes based on the user's emotional state. For example, if the driver is excited, the nodes on the mind map will be displayed in bright colors, and if they are relaxed, they will be displayed in calm colors. This mind map is then converted back into JSON format and sent to the smartphone.

[1241] The smartphone then presents the received mind map to the user in real time. Through this visual mind map, the user can intuitively understand their own emotional state and thoughts. The system also provides emotion-based feedback and alerts to the driver while driving. For example, if the driver is frustrated, the system will play relaxing music or display a reminder notification.

[1242] As a concrete example, suppose a driver says "I'm tired today" while driving. This voice is captured by the smartphone's microphone and sent to the server. The server analyzes the voice and recognizes that the driver is tired. As a result, it responds by providing feedback to the driver saying, "I recommend you take a break." Furthermore, "fatigue" is visualized as an important node in the mind map, clearly presented to the user.

[1243] Specific examples of input prompts for a generative AI model include, "Design an API to analyze the driver's voice data and identify their emotions" and "How can I analyze the driver's facial expressions to recognize their emotions in real time?"

[1244] In this way, the present invention realizes a system that recognizes a user's emotions in real time and provides appropriate feedback and alerts to the user, thereby enabling visual understanding and safe driving assistance based on the user's emotional state.

[1245] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1246] Step 1:

[1247] The user's smartphone captures audio and video of the driver.

[1248] Specifically, audio is recorded using the smartphone's microphone and video is captured using the smartphone's camera. The audio data is acquired in WAV format and the video data in JPEG format.

[1249] Input: Driver audio and video

[1250] Output: WAV format audio data, JPEG format video data

[1251] Step 2:

[1252] The smartphone converts the acquired audio and video data into JSON format.

[1253] Specifically, audio data is converted from binary format to a string, and video data is converted to a string using Base64 encoding, and then packaged into JSON.

[1254] Input: WAV format audio data, JPEG format video data

[1255] Output: A JSON object containing audio and video data

[1256] Step 3:

[1257] The smartphone sends the preprocessed JSON data to the server over the Internet.

[1258] Specifically, HTTP POST is used as the communication protocol to send data to a dedicated API endpoint.

[1259] Input: A JSON object containing audio and video data

[1260] Output: Data sent to the server

[1261] Step 4:

[1262] The server analyzes the received data.

[1263] Specifically, we use OpenCV to analyze facial expressions and movements from video data, Pydub to extract features from audio data, and machine learning algorithms to estimate emotions.

[1264] Input: JSON object (audio and video data)

[1265] Output: Emotion recognition results and analysis results

[1266] Step 5:

[1267] The server generates a visual mind map based on the emotion recognition and analysis results.

[1268] Specifically, we assign emotion data corresponding to each node as an attribute, generate links between nodes based on their relevance, and create visual elements that change color and shape depending on the emotion.

[1269] Input: Emotion recognition results and analysis results

[1270] Output: Visual mind map data

[1271] Step 6:

[1272] The server then encodes the generated mind map into JSON format again and sends it to the smartphone.

[1273] Specifically, data is sent as an HTTP POST request through a dedicated API endpoint.

[1274] Input: Visual mind map data

[1275] Output: Mind map data sent to your smartphone

[1276] Step 7:

[1277] The smartphone interprets the received mind map data and presents it visually to the user.

[1278] Specifically, it parses JSON data and displays the mind map in a suitable graphical user interface, along with context-sensitive feedback and alerts.

[1279] Input: Visual mind map data

[1280] Output: Mind map presented to the user and feedback alerts

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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).

[1288] 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.

[1289] 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."

[1290] 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.

[1291] 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).

[1292] 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.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] The following is further disclosed regarding the above embodiment.

[1303] (Claim 1)

[1304] means for receiving multimodal input from a user;

[1305] artificial intelligence means for analyzing said multimodal input;

[1306] means for generating a visual mind map based on the analyzed data;

[1307] A system including means for presenting the generated mind map to a user.

[1308] (Claim 2)

[1309] 2. The system of claim 1, wherein the multimodal input includes at least one of text, audio, images, and video.

[1310] (Claim 3)

[1311] means for said artificial intelligence to convert voice data into text;

[1312] means for analyzing the content of the audio data;

[1313] 2. The system of claim 1, further comprising means for incorporating the analysis results into a mind map as visual nodes.

[1314] "Example 1"

[1315] (Claim 1)

[1316] means for receiving multimodal input from a user;

[1317] a machine learning based means for analyzing said multimodal input;

[1318] means for generating a visual conceptual diagram based on the analyzed data;

[1319] The system further comprises means for presenting the generated concept map to a user.

[1320] (Claim 2)

[1321] 2. The system of claim 1, wherein the multimodal input includes at least one of text, audio, images, and video.

[1322] (Claim 3)

[1323] means for converting said voice data into text;

[1324] means for analyzing the content of the audio data;

[1325] 2. The system according to claim 1, further comprising means for incorporating the analysis results into a concept diagram as visual nodes.

[1326] "Application Example 1"

[1327] (Claim 1)

[1328] a means for receiving multimodal input from a user;

[1329] artificial intelligence means for analyzing said multimodal input;

[1330] means for generating a visual mind map based on the analyzed data;

[1331] means for presenting the generated mind map to a user;

[1332] means for extracting key keywords from the analyzed data and visualizing related concepts as nodes when the multimodal input contains economic-related ideas and strategies;

[1333] The system includes means for presenting the visualized data as relevant to economic ideas and investment strategies.

[1334] (Claim 2)

[1335] 2. The system of claim 1, wherein the multimodal input includes at least one of text, audio, images, and video.

[1336] (Claim 3)

[1337] means for said artificial intelligence to convert voice data into text;

[1338] means for analyzing the content of the audio data;

[1339] a means for incorporating the keywords extracted as a result of the analysis into a mind map as visual nodes;

[1340] 2. The system of claim 1, further comprising means for presenting the mind map to a user in a format specialized for visualizing economic ideas and investment strategies.

[1341] "Example 2: Combining Emotion Engines"

[1342] (Claim 1)

[1343] means for receiving multimodal input from a user;

[1344] artificial intelligence means for analyzing said multimodal input;

[1345] means for generating a visual mind map based on the analyzed data;

[1346] means for presenting the generated mind map to a user;

[1347] means using an emotion engine to recognize the user's emotion derived from the analyzed data;

[1348] means for reflecting the emotional state of the user in a visual mind map;

[1349] A system including:

[1350] (Claim 2)

[1351] 2. The system of claim 1, wherein the multimodal input includes at least one of text, audio, images, and video.

[1352] (Claim 3)

[1353] means for said artificial intelligence to convert voice data into text;

[1354] means for analyzing the content of the audio data;

[1355] means for incorporating the analysis results into a mind map as visual nodes;

[1356] means for causing said visual nodes to reflect a user's emotional state;

[1357] The system according to claim 1, further comprising means for transmitting the mind map to a terminal and presenting the mind map to a user.

[1358] "Application example 2 when combining emotion engines"

[1359] (Claim 1)

[1360] means for receiving multimodal input from a user;

[1361] artificial intelligence means for analyzing said multimodal input;

[1362] means for generating a visual mind map based on the analyzed data and the user's emotions;

[1363] means for presenting the generated mind map to a user;

[1364] means for receiving driver audio and video user input and analyzing this data in real time;

[1365] A means for providing feedback or alerts to the driver based on the analysis results.

[1366] A system including:

[1367] (Claim 2)

[1368] 2. The system of claim 1, wherein the multimodal input includes at least one of text, audio, images, and video.

[1369] (Claim 3)

[1370] means for said artificial intelligence to convert voice data into text;

[1371] means for analyzing the content of the audio data;

[1372] means for incorporating the analysis results into a mind map as visual nodes;

[1373] means for providing driving assistance functions based on the emotional state of the driver;

[1374] 2. The system of claim 1, further comprising: [Explanation of symbols]

[1375] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving multimodal input from a user; artificial intelligence means for analyzing said multimodal input; means for generating a visual mind map based on the analyzed data; A system including means for presenting the generated mind map to a user.

2. 10. The system of claim 1, wherein the multimodal input includes at least one of text, audio, images, and video.

3. means for said artificial intelligence to convert voice data into text; means for analyzing the content of the audio data; 2. The system of claim 1, further comprising means for incorporating the analysis results into a mind map as visual nodes.

Images