system

Abstract

We provide the system. [Solution] A means of receiving audio and converting audio data into text data, A means for analyzing the aforementioned text data and searching for and retrieving information based on the received instructions, A means of generating a graph using the received data, A means of incorporating the generated graph into the display information, A means to save the work history and revert to a previous state based on instructions, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the creation of conventional homepages and presentation materials, it was necessary to manually create and modify graphs, which consumed a large amount of time and labor. For this reason, there was a problem of imposing an excessive burden on workers and reducing work efficiency. In particular, it was very difficult to perform history management while quickly reflecting complex instructions.

Means for Solving the Problems

[0005] This invention provides a system for automatically creating and modifying graphs in web pages and presentation materials using voice commands. First, it includes means for converting voice to text, analyzing the commands from the text, and searching for and retrieving the necessary data. Furthermore, it includes means for automatically generating graphs using that data and incorporating them into display information. In addition, it includes means for saving the work history and allowing the system to revert to previous states based on the commands, thereby reducing the burden on the user and enabling efficient work.

[0006] "Means for receiving voice" refers to a device or technology for inputting the user's voice as a digital signal.

[0007] "Methods for converting audio data into text data" refers to technologies for analyzing audio signals and converting them into corresponding strings of characters.

[0008] "Means for analyzing text data" refers to algorithms or programs that understand instructions from input strings and guide the user to appropriate processing.

[0009] "Means for searching and retrieving information" refers to a system for extracting necessary information from databases or external sources according to specified conditions.

[0010] "Means of generating graphs using data" refers to tools or software that automatically create graphs that visually represent acquired data.

[0011] "Means for incorporating generated graphs into display information" refers to technologies that enable the creation of graphs to be embedded and displayed in a specified format in documents or web pages.

[0012] "Means for saving work history" refers to a database or storage system that records the operation history and change history of a system so that it can be referenced later.

[0013] A "means to revert to a previous state" refers to a function that restores the system's state to a specific previous state based on saved history. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system of the present invention enables the automatic creation and modification of graphs using voice commands in order to improve work efficiency in creating websites and presentation materials. Specific embodiments are described below.

[0036] The user inputs work instructions by voice through a microphone. For example, they might give instructions such as, "Create a pie chart using annual sales data." The terminal receives this voice input as digital voice data and converts it into text data using a speech recognition module. This text data is then analyzed and sent to a server to determine what processing should be performed.

[0037] The server parses the received text data and searches the database for the necessary information. For example, it retrieves relevant annual sales data from the sales database. Based on the retrieved data, the server automatically generates graphs. In this case, for example, it generates a pie chart of a specified format using a graph generation module. The graph is created in the optimal format with the specified style and colors applied.

[0038] The generated graph is sent to the device and embedded in a designated location on the homepage or presentation materials. During this process, the display format is adjusted to maintain consistency with the design and other elements. Once the display is complete, the user reviews the results on the screen.

[0039] Furthermore, this system has a function to automatically save the work history. This means that if a user gives a voice command such as "revert to the previous state," the terminal will transmit that command to the server, and the server will refer to the history database and restore the system to the previous state.

[0040] Thus, the system of the present invention allows users to efficiently create and modify graphs with simple voice commands, significantly reducing their workload. For example, it is extremely useful when marketing personnel need to quickly visualize recent sales data for regular meeting reports.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user gives voice commands to the microphone. For example, they might input specific instructions such as, "Create a pie chart using sales data."

[0044] Step 2:

[0045] The device acquires audio from the microphone as digital data and transmits that audio data to a speech recognition module. The speech recognition module converts the audio data into text data.

[0046] Step 3:

[0047] The terminal receives the converted text data and sends its contents to the server. At this time, the text data must be properly formatted for analysis.

[0048] Step 4:

[0049] The server analyzes the received text data and determines what type of graph to create. It also determines where the necessary data is located and prepares to retrieve it from databases or APIs.

[0050] Step 5:

[0051] The server accesses the database and retrieves sales data that matches the specified conditions. It then formats the retrieved data for graph creation and sends it to the graph generation module.

[0052] Step 6:

[0053] The server uses a graph generation module to create a pie chart based on the acquired data. The graph is generated in the specified format (color and layout).

[0054] Step 7:

[0055] The device receives the generated graph and embeds it in the designated location within the webpage or presentation materials. It adjusts the display format to maintain design consistency.

[0056] Step 8:

[0057] The server saves a history of the series of processes in a history database. This makes it possible to revert to a previous state when a user gives a command such as "return to the original state."

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] Currently, data visualization when creating websites and presentation materials is often done manually by users, which presents inefficiency. Furthermore, the difficulty in quickly reproducing necessary data based on past work history leads to the problem of requiring significant time for information correction and updates. There is a need for technology to solve these problems and improve work efficiency.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for receiving voice and converting the voice signal into text information, means for searching and retrieving information from a database based on instructions, and means for generating visual data using the retrieved information. This allows users to easily visualize data through voice input and quickly recall information by referring to past work history.

[0063] "Audio signals" are digital data representations of human speech acquired by audio equipment such as microphones.

[0064] "Character information" refers to data that is represented as a corresponding string of characters after analyzing an audio signal using speech recognition technology.

[0065] A "database" is a collection of data built to enable efficient information retrieval and management, allowing for the rapid retrieval of necessary information in response to specific queries.

[0066] "Visual data" refers to information presented visually, such as graphs and charts, that are digitally generated based on acquired numerical data and information.

[0067] "Work history" refers to a record of a series of operations performed by a user within a system and the data generated, and is information used to refer to or restore past states.

[0068] "Voice feedback" refers to a function in which a system responds to user instructions by providing confirmation or a verbal response to those instructions.

[0069] "Network-based speech recognition technology" refers to technology that converts speech signals into text information through speech recognition services provided via the internet or any other network.

[0070] This system aims to efficiently visualize information by automatically generating visual data based on user voice instructions. Users can input instructions by voice using a microphone. These voice instructions are received as digital audio by the terminal and converted into text data using speech recognition technology. The speech recognition technology used is a speech recognition service provided over the network.

[0071] The terminal sends the converted text data to the server. The server analyzes this text data and searches and retrieves the necessary information from the database based on the specified information. The database is expected to contain, for example, sales data and market analysis information.

[0072] The server generates visual data based on the acquired information. For example, data analysis and graph generation software (e.g., Matplotlib, Plotly) is used to generate this visual data. At this stage, the data's style, color, and formatting are also applied.

[0073] The generated visual data is returned to the device and incorporated into homepages and presentation materials according to the user's instructions. The user can review the visual data and provide instructions for modifications or additional information as needed.

[0074] Furthermore, this system automatically records the work history, and allows users to easily restore past work states by giving voice commands such as "revert to previous state."

[0075] For example, when a marketing professional visualizes the latest data for a weekly meeting, they can use this system to quickly and accurately prepare the data and create efficient presentation materials. A possible prompt would be, "Create a pie chart using the most recent sales data." In this way, the system significantly reduces the user's burden and automates data visualization.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The user gives work instructions by voice using a microphone. The input is a voice signal, such as "Show the latest sales data as a pie chart." The terminal acquires this voice signal as digital audio data.

[0079] Step 2:

[0080] The terminal uses speech recognition technology to convert digital voice data into text information. This conversion process utilizes a speech recognition service over the network. The output is data in text format, converted from voice commands.

[0081] Step 3:

[0082] The terminal sends the converted text data to the server. The input is text data, and based on this, the server analyzes the received text data to determine what information is needed. This analysis generates a specific database query.

[0083] Step 4:

[0084] The server queries the database based on the analysis results to retrieve and obtain the necessary information. For example, it extracts sales information for a specific period from the sales database. The output is the dataset required for graph generation.

[0085] Step 5:

[0086] The server generates visual data using the acquired dataset. This process utilizes data analysis and graph generation modules, adjusting the graph style and layout as needed. The output is graph data in the specified format.

[0087] Step 6:

[0088] The server sends the generated graph data to the terminal. The terminal incorporates the received graph data into a homepage or presentation material according to the user's instructions. The output is a completed document with the graph positioned appropriately.

[0089] Step 7:

[0090] The user checks the completeness of the document on the device's display. At this stage, they can provide additional voice instructions as needed and make corrections or adjustments to the document.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Real-time data visualization is crucial for improving the efficiency of production management in factories. However, traditional methods involve time loss due to manual data collection and analysis, making rapid decision-making difficult. Furthermore, visualization often requires specialized knowledge, making it difficult for anyone other than skilled technicians to operate.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for receiving voice and converting voice data into text data, means for analyzing the text data and searching for and acquiring information based on instructions, and means for generating visualization materials using the received data. This enables real-time visualization of production data through display devices or mechanical devices in the factory environment, and allows for efficient factory management.

[0096] A "means for receiving sound" refers to a mechanism that can acquire and process external sound input.

[0097] "Methods for converting audio data into text data" refers to technologies that analyze acquired audio input and represent it as a corresponding string of characters.

[0098] "Means for analyzing text data and searching for and retrieving information based on received instructions" refers to the process of understanding string data and retrieving information from the appropriate database according to its content.

[0099] "Methods for generating visualization materials using received data" refer to technologies that process necessary information into a visually easy-to-understand format and display it in the form of graphs, diagrams, and other visual aids.

[0100] "Means for incorporating generated visualizations into display information" refers to a function that integrates visualized data into existing presentation materials or interfaces.

[0101] "Means for saving work history and restoring to a previous state based on instructions" refers to a technology that records the history of operations and undoes changes by restoring a specific past state.

[0102] "Means for presenting visualized data to display devices or mechanical equipment within a factory environment" refers to a function that directly displays visualized data on screens or terminals used within a factory.

[0103] This invention is a system aimed at improving the efficiency of production management within a factory. The user inputs voice instructions using a microphone. The terminal receives this voice input as digital voice data and converts it into text data using a voice recognition module. Often, an online voice recognition service on a server is used for voice recognition. This text data is sent to the server, where the instruction content is identified through analysis.

[0104] The server retrieves relevant information from the database based on instructions and obtains production data. Based on the retrieved data, the server immediately generates visualizations (e.g., graphs and charts). These visualizations are optimized in the specified format and style. The generated visualizations are transferred to display devices or machine displays within the factory and presented to the user.

[0105] For example, if a user says, "Show this week's production efficiency as a bar graph," the system will use the production data to generate a bar graph in the specified format and display it on a screen in the factory. This allows managers to check production efficiency in real time and make quick decisions.

[0106] An example of a prompt to be input into the generating AI model is "Designing a factory management application that graphs manufacturing data in real time using voice commands." This would reduce the burden on users to operate using voice commands while enabling more efficient production management tasks.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The user inputs voice commands through the microphone. The input data is unstructured voice data. This voice data is immediately captured as digital data on the device.

[0110] Step 2:

[0111] The terminal uses a speech recognition module to convert speech data into text data. The input is speech data, and the output is a string. The speech recognition module utilizes an online speech recognition service on a server to perform speech analysis.

[0112] Step 3:

[0113] Text data is sent to the server. The server analyzes this text data to identify the instructions. The input is text data, and the analysis outputs specific instructions.

[0114] Step 4:

[0115] The server searches the database according to the instructions and retrieves the necessary production data. The input is the instructions, and the output is the retrieved production data. This allows for the rapid acquisition of relevant information.

[0116] Step 5:

[0117] The server generates visualization materials based on acquired production data. The input is production data, and the output is visualization materials such as graphs. The server processes the data and generates graphs according to the specified format.

[0118] Step 6:

[0119] The generated visualizations are transferred via terminals to display devices and machinery within the factory and presented. The input is the visualization material, and the output is visual feedback in a physical display. This enables the provision of visual information.

[0120] Step 7:

[0121] The user reviews the presented information and provides additional instructions via voice as needed. This feedback loop allows for real-time data review and correction.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] The present invention aims to improve the user experience by optimizing the process of creating homepages and presentation materials through the recognition of voice commands and user emotions. By combining this with an emotion engine, the system analyzes the emotions contained in the user's voice and adjusts responses and graphs accordingly.

[0124] When a user inputs a voice command into the microphone, the device captures the audio as digital data. Next, the voice data is converted into text data through an online speech recognition service. This converted text data is then sent to a server where the specified command is analyzed.

[0125] While the server analyzes text data, its emotion engine recognizes the emotional state within the speech. This emotional state is determined by analyzing features such as tone, rhythm, and speed. Based on the analysis results, the server retrieves necessary information from the database and further adjusts the response content and graph design based on the emotion. For example, if the user is giving instructions in a very calm tone, the system will create a graph with a standard design. On the other hand, if the user is emotionally agitated, the design can be changed to a simpler and easier-to-read design.

[0126] The generated graphs are sent to the terminal and embedded in the homepage or presentation materials. Users can review the results and provide additional instructions if necessary. Furthermore, a history of the entire process is automatically saved by the server, in case the user requests a revert to a previous state later.

[0127] For example, before a sales meeting, a user can request multiple data points for a sales report via voice prompts. If the user is nervous, the system can prepare simple, intuitively easy-to-understand graphs, enabling quick document creation. If the system determines that the user is relaxed, it can provide graphs with the usual detailed design, thus accommodating a variety of situations.

[0128] Thus, the system of the present invention recognizes the user's emotions and uses them to dynamically adjust the document creation process, thereby enabling efficient and flexible operation.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user inputs voice commands into the microphone. For example, they might say, "Create a bar graph using this month's sales data."

[0132] Step 2:

[0133] The device acquires audio from the microphone and converts that audio data into a digital format. Furthermore, it uses a speech recognition service to convert it into text data.

[0134] Step 3:

[0135] The device sends text data to the server. At the same time, the audio data itself is also sent for sentiment analysis.

[0136] Step 4:

[0137] The server analyzes text data and determines what information is needed based on user instructions. It also uses an emotion engine to recognize the user's emotional state from their voice.

[0138] Step 5:

[0139] The server accesses the database and retrieves data that meets the specified criteria (for example, this month's sales data). Simultaneously, it adjusts the style and color scheme of the generated graphs based on the sentiment analysis results.

[0140] Step 6:

[0141] The server calls a graph generation module and creates a graph using the acquired data. If the server determines that the user's emotional state is one of tension, it creates a graph with a simple and easy-to-understand design.

[0142] Step 7:

[0143] The generated graph is sent to the terminal. The terminal embeds the received graph into the specified presentation material or web page and displays the results to the user.

[0144] Step 8:

[0145] The server stores a history of the sequence of operations in a history database. This allows for quick restoration when a user requests to revert to a previous state.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] While using voice commands can improve efficiency in the computer-assisted process of creating websites and presentation materials, conventional systems fail to take into account the user's emotional state, resulting in inadequate design and information delivery. This lack of flexibility in responding to the user's emotional state prevents the provision of an optimal user experience.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes means for converting voice data into text data, means for recognizing emotional states, and means for adjusting the design based on the emotional state. This enables the creation of more effective and appropriate materials by collecting necessary information based on the user's voice instructions and dynamically changing the design according to the emotional state.

[0151] "Means for receiving voice" refers to an input device that has the function of receiving voice information from a user and converting it into a data format that can be processed.

[0152] "Means of converting to text data" refers to the processing or technology used to convert acquired audio data into text information.

[0153] "Means of recognizing emotional states" refers to technologies or algorithms used to identify a user's emotions through the analysis of voice and text data.

[0154] "Means for searching and retrieving information" refers to a function that searches for and retrieves necessary information from databases or other sources based on specified instructions.

[0155] "A method for adjusting the design and generating graphs" refers to a technology that dynamically changes the visual design based on acquired information and emotional states to generate the optimal graph.

[0156] "Means of incorporating information for display" refers to the processing and techniques used to place generated graphs and information in appropriate locations on a website or document.

[0157] "Means of saving work history" refers to technologies and processes that record the operations and changes performed by a user and save them in a format that can be referenced or restored later.

[0158] The embodiments for carrying out the present invention will be described in detail below.

[0159] This system consists of a voice input device, a computing device, an internet connection, a database, and associated software modules. Specifically, a microphone receives voice commands and acquires this voice data in digital format. The terminal converts the voice data into text data using Google® Cloud Speech-to-Text or equivalent online speech recognition technology.

[0160] The converted text data is sent to the server. The server analyzes this text data using natural language processing libraries (e.g., NLTK or spaCy). In doing so, it utilizes machine learning models (e.g., speech emotion recognition models using TENSORFLOW® or PyTorch) to recognize emotional states using acoustic features obtained from the speech.

[0161] Once an emotional state is recognized, the server retrieves relevant information from the database. Based on this information, it uses a generative AI model (e.g., DALL-E or Midjourney) to dynamically adjust the design based on the emotion and generate a graph. This generation process involves providing the AI ​​model with prompts such as, "Create a simple graph design for when the user is feeling anxious."

[0162] Finally, the generated graphs are sent to the terminal and incorporated into the homepage or presentation materials. This allows users to review the results and modify or add further instructions as needed. The server also saves the operation history, making it easy for users to revert to previous states. For example, when creating materials for a sales meeting, a graph with an optimal design based on the user's emotions can be quickly generated and effectively reflected in the materials.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The user inputs voice commands through the microphone. The device acquires this voice as digital data. The input voice data is sent to an online speech recognition service such as Google Cloud Speech-to-Text. The data is transmitted over the network, and the voice is converted to text. The output is text data that reflects the user's spoken content.

[0166] Step 2:

[0167] The terminal sends the converted text data to the server. The server analyzes the text data using a natural language processing library. Specifically, it performs syntactic analysis and keyword extraction to accurately identify the user's instructions. As a result of the analysis, structured data related to the instructions is output.

[0168] Step 3:

[0169] The server uses an emotion engine to recognize the emotional state in the speech. It analyzes features obtained from the speech data (tone, rhythm, speed, etc.) and uses a machine learning model to identify the user's emotion. This process results in the current emotional state (e.g., calm, tense) being output.

[0170] Step 4:

[0171] The server searches and retrieves relevant information from the database based on the recognized emotional state and analyzed instructions. Furthermore, it utilizes a generative AI model to adjust the design according to the emotion and generate the necessary graphs. Specifically, it provides prompt text to the AI ​​model to obtain appropriate visual representations. The output of this step is an optimized graph tailored to the user's emotional state.

[0172] Step 5:

[0173] The generated graphs are sent to the terminal and incorporated into presentation materials and website content. Users can view the graphs on their terminal and provide additional instructions as needed. The server also automatically saves the work history, providing a basis for reverting to previous states. The output of this procedure is the information provided in the form of a final document.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] In today's consumer environment, effectively explaining products and services to customers requires dynamic information generation and presentation that responds to their emotional state. However, traditional static materials and one-way information provision make it difficult to make effective proposals that meet customer needs, resulting in a challenge in improving customer satisfaction.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for receiving voice and converting the voice data into text data, means for analyzing the user's emotional state and dynamically adjusting a graph according to that state, and means for incorporating the generated graph into output information. This makes it possible to provide information that fits the customer's emotions in real time.

[0179] A "sound receiving device" is a device that acquires the sound emitted by the user as an electronic signal and processes it as sound data.

[0180] "Text data" refers to a data format that represents audio data as a string of characters and stores or processes it in digital format.

[0181] A "device for collecting and acquiring information" is a device that, based on input instructions, retrieves necessary information from an external or internal database.

[0182] A "device for analyzing emotional states" is a device that identifies and analyzes a user's emotions and psychological state based on their voice characteristics and expressions.

[0183] A "dynamic graph adjustment device" is a device that takes into account the user's emotional state and changes the design of the graph and the way information is displayed, thereby optimizing it instantly.

[0184] A "device for incorporating output information" is a device for integrating generated graphs and data into information for presentations and displays.

[0185] A "device for maintaining work history" is a device that stores records of operations and data processing performed in the past so that they can be referenced later.

[0186] The system for carrying out the present invention consists of a voice input device, an emotion analysis engine, a graph generation module, and an output display. When a user inputs a voice command into the voice input device, the voice is acquired as a digital signal. Next, an online speech recognition service (e.g., Google Cloud Speech-to-Text) is used to convert the voice data into text data. The terminal analyzes the converted text data and collects and retrieves the necessary information from a database according to the content of the command.

[0187] Subsequently, an emotion analysis engine (for example, IBM Watson® Tone Analyzer) is used to determine the user's emotional state from their voice. Based on the determined emotion, a graph generation module generates a graph with the optimal design and content. This graph is then incorporated into an output display for presentation to the user.

[0188] For example, when a salesperson in a physical store uses smart glasses to introduce a product to a customer, if the customer's emotions are analyzed as being excited, a simple graph that can be quickly understood will be displayed. Conversely, if the customer is calm and seeking information, a graph containing more detailed information will be presented.

[0189] An example of a prompt message is an instruction such as, "Tell me the key selling points of the following product." This prompt allows the system to immediately provide appropriate information that is tailored to the customer's emotions.

[0190] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0191] Step 1:

[0192] The user gives instructions by voice to a voice input device. The input voice is acquired as a digital signal by the device and sent directly to an online voice recognition service. Here, the voice input is converted into digital data.

[0193] Step 2:

[0194] The device uses an online speech recognition service to convert speech data into text data. Specifically, it performs frequency analysis and phoneme analysis of the speech via a service such as Google Cloud Speech-to-Text, and then converts it into a sequence of characters. The output of this process is text data containing instructions.

[0195] Step 3:

[0196] The server receives the converted text data and parses its contents. Based on the parsing results, it collects information related to the instructions from the database. At this stage, natural language processing techniques are used to parse the text and extract keys for the relevant information. The output is a list of the relevant information.

[0197] Step 4:

[0198] The server uses an emotion analysis engine, such as IBM Watson Tone Analyzer, to determine the emotional state of the voice based on the text data. The analyzed emotion data is then used to identify the user's psychological state. The output is the recognized emotion information.

[0199] Step 5:

[0200] The server creates a plan to generate the optimal graph based on the acquired emotional and related information. The graph generation module adjusts the design and information display to match the user's psychological state, dynamically constructing the graph. The output is the generated graph.

[0201] Step 6:

[0202] The generated graph is embedded by the terminal into an output display (e.g., the display of smart glasses) and presented visually to the user or customer. The user can view the results and provide additional voice input if further instructions are needed. The final output of this process is visual data on the display.

[0203] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0204] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0209] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0210] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0211] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0212] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0213] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0214] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0215] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0216] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0217] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0218] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0219] The system of the present invention enables the automatic creation and modification of graphs using voice commands in order to improve work efficiency in creating websites and presentation materials. Specific embodiments are described below.

[0220] The user inputs work instructions by voice through a microphone. For example, they might give instructions such as, "Create a pie chart using annual sales data." The terminal receives this voice input as digital voice data and converts it into text data using a speech recognition module. This text data is then analyzed and sent to a server to determine what processing should be performed.

[0221] The server parses the received text data and searches the database for the necessary information. For example, it retrieves relevant annual sales data from the sales database. Based on the retrieved data, the server automatically generates graphs. In this case, for example, it generates a pie chart of a specified format using a graph generation module. The graph is created in the optimal format with the specified style and colors applied.

[0222] The generated graph is sent to the device and embedded in a designated location on the homepage or presentation materials. During this process, the display format is adjusted to maintain consistency with the design and other elements. Once the display is complete, the user reviews the results on the screen.

[0223] Furthermore, this system has a function to automatically save the work history. This means that if a user gives a voice command such as "revert to the previous state," the terminal will transmit that command to the server, and the server will refer to the history database and restore the system to the previous state.

[0224] Thus, the system of the present invention allows users to efficiently create and modify graphs with simple voice commands, significantly reducing their workload. For example, it is extremely useful when marketing personnel need to quickly visualize recent sales data for regular meeting reports.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The user gives voice commands to the microphone. For example, they might input specific instructions such as, "Create a pie chart using sales data."

[0228] Step 2:

[0229] The device acquires audio from the microphone as digital data and transmits that audio data to a speech recognition module. The speech recognition module converts the audio data into text data.

[0230] Step 3:

[0231] The terminal receives the converted text data and sends its contents to the server. At this time, the text data must be properly formatted for analysis.

[0232] Step 4:

[0233] The server analyzes the received text data and determines what type of graph to create. It also determines where the necessary data is located and prepares to retrieve it from databases or APIs.

[0234] Step 5:

[0235] The server accesses the database and retrieves sales data that matches the specified conditions. It then formats the retrieved data for graph creation and sends it to the graph generation module.

[0236] Step 6:

[0237] The server uses a graph generation module to create a pie chart based on the acquired data. The graph is generated in the specified format (color and layout).

[0238] Step 7:

[0239] The device receives the generated graph and embeds it in the designated location within the webpage or presentation materials. It adjusts the display format to maintain design consistency.

[0240] Step 8:

[0241] The server saves a history of the series of processes in a history database. This makes it possible to revert to a previous state when a user gives a command such as "return to the original state."

[0242] (Example 1)

[0243] Next, we will describe Example 1. 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."

[0244] Currently, data visualization when creating websites and presentation materials is often done manually by users, which presents inefficiency. Furthermore, the difficulty in quickly reproducing necessary data based on past work history leads to the problem of requiring significant time for information correction and updates. There is a need for technology to solve these problems and improve work efficiency.

[0245] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0246] In this invention, the server includes means for receiving voice and converting the voice signal into text information, means for searching and retrieving information from a database based on instructions, and means for generating visual data using the retrieved information. This allows users to easily visualize data through voice input and quickly recall information by referring to past work history.

[0247] "Audio signals" are digital data representations of human speech acquired by audio equipment such as microphones.

[0248] "Character information" refers to data that is represented as a corresponding string of characters after analyzing an audio signal using speech recognition technology.

[0249] A "database" is a collection of data built to enable efficient information retrieval and management, allowing for the rapid retrieval of necessary information in response to specific queries.

[0250] "Visual data" refers to information presented visually, such as graphs and charts, that are digitally generated based on acquired numerical data and information.

[0251] "Work history" refers to a record of a series of operations performed by a user within a system and the data generated, and is information used to refer to or restore past states.

[0252] "Voice feedback" refers to a function in which a system responds to user instructions by providing confirmation or a verbal response to those instructions.

[0253] "Network-based speech recognition technology" refers to technology that converts speech signals into text information through speech recognition services provided via the internet or any other network.

[0254] This system aims to efficiently visualize information by automatically generating visual data based on user voice instructions. Users can input instructions by voice using a microphone. These voice instructions are received as digital audio by the terminal and converted into text data using speech recognition technology. The speech recognition technology used is a speech recognition service provided over the network.

[0255] The terminal sends the converted text data to the server. The server analyzes this text data and searches and retrieves the necessary information from the database based on the specified information. The database is expected to contain, for example, sales data and market analysis information.

[0256] The server generates visual data based on the acquired information. For example, data analysis and graph generation software (e.g., Matplotlib, Plotly) is used to generate this visual data. At this stage, the data's style, color, and formatting are also applied.

[0257] The generated visual data is returned to the device and incorporated into homepages and presentation materials according to the user's instructions. The user can review the visual data and provide instructions for modifications or additional information as needed.

[0258] Furthermore, this system automatically records the work history, and allows users to easily restore past work states by giving voice commands such as "revert to previous state."

[0259] For example, when a marketing professional visualizes the latest data for a weekly meeting, they can use this system to quickly and accurately prepare the data and create efficient presentation materials. A possible prompt would be, "Create a pie chart using the most recent sales data." In this way, the system significantly reduces the user's burden and automates data visualization.

[0260] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0261] Step 1:

[0262] The user gives work instructions by voice using a microphone. The input is a voice signal, such as "Show the latest sales data as a pie chart." The terminal acquires this voice signal as digital audio data.

[0263] Step 2:

[0264] The terminal uses speech recognition technology to convert digital voice data into text information. This conversion process utilizes a speech recognition service over the network. The output is data in text format, converted from voice commands.

[0265] Step 3:

[0266] The terminal sends the converted text data to the server. The input is text data, and based on this, the server analyzes the received text data to determine what information is needed. This analysis generates a specific database query.

[0267] Step 4:

[0268] The server queries the database based on the analysis results to retrieve and obtain the necessary information. For example, it extracts sales information for a specific period from the sales database. The output is the dataset required for graph generation.

[0269] Step 5:

[0270] The server generates visual data using the acquired dataset. This process utilizes data analysis and graph generation modules, adjusting the graph style and layout as needed. The output is graph data in the specified format.

[0271] Step 6:

[0272] The server sends the generated graph data to the terminal. The terminal incorporates the received graph data into a homepage or presentation material according to the user's instructions. The output is a completed document with the graph positioned appropriately.

[0273] Step 7:

[0274] The user checks the completeness of the document on the device's display. At this stage, they can provide additional voice instructions as needed and make corrections or adjustments to the document.

[0275] (Application Example 1)

[0276] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0277] Real-time data visualization is crucial for improving the efficiency of production management in factories. However, traditional methods involve time loss due to manual data collection and analysis, making rapid decision-making difficult. Furthermore, visualization often requires specialized knowledge, making it difficult for anyone other than skilled technicians to operate.

[0278] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0279] In this invention, the server includes means for receiving voice and converting voice data into text data, means for analyzing the text data and searching for and acquiring information based on instructions, and means for generating visualization materials using the received data. This enables real-time visualization of production data through display devices or mechanical devices in the factory environment, and allows for efficient factory management.

[0280] A "means for receiving sound" refers to a mechanism that can acquire and process external sound input.

[0281] "Methods for converting audio data into text data" refers to technologies that analyze acquired audio input and represent it as a corresponding string of characters.

[0282] The "means for analyzing text data and retrieving and obtaining information based on the received instructions" is a process of understanding string data and extracting information from an appropriate database according to its content.

[0283] The "means for generating visualization materials using the received data" is a technology that processes the necessary information into a form that is easy to visually understand and displays it in a form such as a graph or chart.

[0284] The "means for incorporating the generated visualization materials into display information" is a function of integrating the visualized data into existing presentation materials or interfaces.

[0285] The "means for saving the work history and returning to a past state based on an instruction" is a technology for canceling changes by recording the history of operations and restoring a specific past state.

[0286] The "means for presenting visualization materials to a display device or a mechanical device within the factory environment" is a function of directly displaying the visualized data on a screen or a terminal used within the factory.

[0287] This invention is a system aimed at improving the efficiency of production management within a factory. The user inputs voice instructions using a microphone. The terminal receives this voice input as digital voice data and converts it into text data using a voice recognition module. In many cases, an online voice recognition service on the server is used for voice recognition. This text data is transmitted to the server, and the content of the instruction is identified through analysis.

[0288] The server searches for relevant information from the database based on the instruction and obtains production data. Based on the obtained data, the server immediately generates visualization materials (e.g., graphs and charts). This visualization material is optimized in the specified format and style. The generated visualization material is transferred to the display of a display device or a mechanical device within the factory and presented to the user.

[0289] For example, if a user says, "Show this week's production efficiency as a bar graph," the system will use the production data to generate a bar graph in the specified format and display it on a screen in the factory. This allows managers to check production efficiency in real time and make quick decisions.

[0290] An example of a prompt to be input into the generating AI model is "Designing a factory management application that graphs manufacturing data in real time using voice commands." This would reduce the burden on users to operate using voice commands while enabling more efficient production management tasks.

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0292] Step 1:

[0293] The user inputs voice commands through the microphone. The input data is unstructured voice data. This voice data is immediately captured as digital data on the device.

[0294] Step 2:

[0295] The terminal uses a speech recognition module to convert speech data into text data. The input is speech data, and the output is a string. The speech recognition module utilizes an online speech recognition service on a server to perform speech analysis.

[0296] Step 3:

[0297] Text data is sent to the server. The server analyzes this text data to identify the instructions. The input is text data, and the analysis outputs specific instructions.

[0298] Step 4:

[0299] The server searches the database according to the instruction content and obtains the necessary production data. The input is the instruction content, and the output is the obtained production data. Thereby, the relevant information can be obtained quickly.

[0300] Step 5:

[0301] The server generates visualization materials based on the obtained production data. The input is the production data, and the output is visualization materials such as graphs. Data processing is performed to generate graphs according to the specified format.

[0302] Step 6:

[0303] The generated visualization materials are transferred and presented to the display devices and mechanical devices in the factory via the terminal. The input is the visualization materials, and the output is the visual feedback in the physical display. Thereby, visual information can be provided.

[0304] Step 7:

[0305] The user checks the presented information and gives additional instructions verbally if necessary. With this feedback loop, real-time data checking and correction are possible.

[0306] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model  59 and perform specific processing using the user's emotion.

[0307] The system of the present invention aims to optimize the creation process of a homepage or presentation materials by recognizing voice instructions and the user's emotion, and to improve the user experience. By combining an emotion engine, this system analyzes the emotion contained in the user's voice and makes responses or adjusts graphs according to the emotion.

[0308] When a user inputs a voice command into the microphone, the device captures the audio as digital data. Next, the voice data is converted into text data through an online speech recognition service. This converted text data is then sent to a server where the specified command is analyzed.

[0309] While the server analyzes text data, its emotion engine recognizes the emotional state within the speech. This emotional state is determined by analyzing features such as tone, rhythm, and speed. Based on the analysis results, the server retrieves necessary information from the database and further adjusts the response content and graph design based on the emotion. For example, if the user is giving instructions in a very calm tone, the system will create a graph with a standard design. On the other hand, if the user is emotionally agitated, the design can be changed to a simpler and easier-to-read design.

[0310] The generated graphs are sent to the terminal and embedded in the homepage or presentation materials. Users can review the results and provide additional instructions if necessary. Furthermore, a history of the entire process is automatically saved by the server, in case the user requests a revert to a previous state later.

[0311] For example, before a sales meeting, a user can request multiple data points for a sales report via voice prompts. If the user is nervous, the system can prepare simple, intuitively easy-to-understand graphs, enabling quick document creation. If the system determines that the user is relaxed, it can provide graphs with the usual detailed design, thus accommodating a variety of situations.

[0312] Thus, the system of the present invention recognizes the user's emotions and uses them to dynamically adjust the document creation process, thereby enabling efficient and flexible operation.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The user inputs voice commands into the microphone. For example, they might say, "Create a bar graph using this month's sales data."

[0316] Step 2:

[0317] The device acquires audio from the microphone and converts that audio data into a digital format. Furthermore, it uses a speech recognition service to convert it into text data.

[0318] Step 3:

[0319] The device sends text data to the server. At the same time, the audio data itself is also sent for sentiment analysis.

[0320] Step 4:

[0321] The server analyzes text data and determines what information is needed based on user instructions. It also uses an emotion engine to recognize the user's emotional state from their voice.

[0322] Step 5:

[0323] The server accesses the database and retrieves data that meets the specified criteria (for example, this month's sales data). Simultaneously, it adjusts the style and color scheme of the generated graphs based on the sentiment analysis results.

[0324] Step 6:

[0325] The server calls a graph generation module and creates a graph using the acquired data. If the server determines that the user's emotional state is one of tension, it creates a graph with a simple and easy-to-understand design.

[0326] Step 7:

[0327] The generated graph is sent to the terminal. The terminal embeds the received graph into the specified presentation material or web page and displays the results to the user.

[0328] Step 8:

[0329] The server stores a history of the sequence of operations in a history database. This allows for quick restoration when a user requests to revert to a previous state.

[0330] (Example 2)

[0331] Next, we will describe Example 2. 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".

[0332] While using voice commands can improve efficiency in the computer-assisted process of creating websites and presentation materials, conventional systems fail to take into account the user's emotional state, resulting in inadequate design and information delivery. This lack of flexibility in responding to the user's emotional state prevents the provision of an optimal user experience.

[0333] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0334] In this invention, the server includes means for converting voice data into text data, means for recognizing emotional states, and means for adjusting the design based on the emotional state. This enables the creation of more effective and appropriate materials by collecting necessary information based on the user's voice instructions and dynamically changing the design according to the emotional state.

[0335] "Means for receiving voice" refers to an input device that has the function of receiving voice information from a user and converting it into a data format that can be processed.

[0336] "Means of converting to text data" refers to the processing or technology used to convert acquired audio data into text information.

[0337] "Means of recognizing emotional states" refers to technologies or algorithms used to identify a user's emotions through the analysis of voice and text data.

[0338] "Means for searching and retrieving information" refers to a function that searches for and retrieves necessary information from databases or other sources based on specified instructions.

[0339] "A method for adjusting the design and generating graphs" refers to a technology that dynamically changes the visual design based on acquired information and emotional states to generate the optimal graph.

[0340] "Means of incorporating information for display" refers to the processing and techniques used to place generated graphs and information in appropriate locations on a website or document.

[0341] "Means of saving work history" refers to technologies and processes that record the operations and changes performed by a user and save them in a format that can be referenced or restored later.

[0342] The embodiments for carrying out the present invention will be described in detail below.

[0343] This system consists of a voice input device, a computing device, an internet connection, a database, and associated software modules. Specifically, the microphone receives voice commands and acquires this voice data in digital format. The terminal then converts the voice data into text data using Google Cloud Speech-to-Text or equivalent online speech recognition technology.

[0344] The converted text data is sent to the server. The server analyzes this text data using natural language processing libraries (e.g., NLTK or spaCy). In doing so, it utilizes machine learning models (e.g., speech emotion recognition models using TensorFlow or PyTorch) to recognize emotional states using acoustic features obtained from the speech.

[0345] Once an emotional state is recognized, the server retrieves relevant information from the database. Based on this information, it uses a generative AI model (e.g., DALL-E or Midjourney) to dynamically adjust the design based on the emotion and generate a graph. This generation process involves providing the AI ​​model with prompts such as, "Create a simple graph design for when the user is feeling anxious."

[0346] Finally, the generated graphs are sent to the terminal and incorporated into the homepage or presentation materials. This allows users to review the results and modify or add further instructions as needed. The server also saves the operation history, making it easy for users to revert to previous states. For example, when creating materials for a sales meeting, a graph with an optimal design based on the user's emotions can be quickly generated and effectively reflected in the materials.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The user inputs voice commands through the microphone. The device acquires this voice as digital data. The input voice data is sent to an online speech recognition service such as Google Cloud Speech-to-Text. The data is transmitted over the network, and the voice is converted to text. The output is text data that reflects the user's spoken content.

[0350] Step 2:

[0351] The terminal sends the converted text data to the server. The server analyzes the text data using a natural language processing library. Specifically, it performs syntactic analysis and keyword extraction to accurately identify the user's instructions. As a result of the analysis, structured data related to the instructions is output.

[0352] Step 3:

[0353] The server uses an emotion engine to recognize the emotional state in the speech. It analyzes features obtained from the speech data (tone, rhythm, speed, etc.) and uses a machine learning model to identify the user's emotion. This process results in the current emotional state (e.g., calm, tense) being output.

[0354] Step 4:

[0355] The server searches and retrieves relevant information from the database based on the recognized emotional state and analyzed instructions. Furthermore, it utilizes a generative AI model to adjust the design according to the emotion and generate the necessary graphs. Specifically, it provides prompt text to the AI ​​model to obtain appropriate visual representations. The output of this step is an optimized graph tailored to the user's emotional state.

[0356] Step 5:

[0357] The generated graphs are sent to the terminal and incorporated into presentation materials and website content. Users can view the graphs on their terminal and provide additional instructions as needed. The server also automatically saves the work history, providing a basis for reverting to previous states. The output of this procedure is the information provided in the form of a final document.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0360] In today's consumer environment, effectively explaining products and services to customers requires dynamic information generation and presentation that responds to their emotional state. However, traditional static materials and one-way information provision make it difficult to make effective proposals that meet customer needs, resulting in a challenge in improving customer satisfaction.

[0361] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0362] In this invention, the server includes means for receiving voice and converting the voice data into text data, means for analyzing the user's emotional state and dynamically adjusting a graph according to that state, and means for incorporating the generated graph into output information. This makes it possible to provide information that fits the customer's emotions in real time.

[0363] A "sound receiving device" is a device that acquires the sound emitted by the user as an electronic signal and processes it as sound data.

[0364] "Text data" refers to a data format that represents audio data as a string of characters and stores or processes it in digital format.

[0365] A "device for collecting and acquiring information" is a device that, based on input instructions, retrieves necessary information from an external or internal database.

[0366] A "device for analyzing emotional states" is a device that identifies and analyzes a user's emotions and psychological state based on their voice characteristics and expressions.

[0367] A "dynamic graph adjustment device" is a device that takes into account the user's emotional state and changes the design of the graph and the way information is displayed, thereby optimizing it instantly.

[0368] A "device for incorporating output information" is a device for integrating generated graphs and data into information for presentations and displays.

[0369] A "device for maintaining work history" is a device that stores records of operations and data processing performed in the past so that they can be referenced later.

[0370] The system for carrying out the present invention consists of a voice input device, an emotion analysis engine, a graph generation module, and an output display. When a user inputs a voice command into the voice input device, the voice is acquired as a digital signal. Next, an online speech recognition service (e.g., Google Cloud Speech-to-Text) is used to convert the voice data into text data. The terminal analyzes the converted text data and collects and retrieves the necessary information from a database according to the content of the command.

[0371] Subsequently, an emotion analysis engine (such as IBM Watson Tone Analyzer) is used to determine the user's emotional state from their voice. Based on the determined emotion, a graph generation module generates a graph with an optimal design and content. This graph is then incorporated into an output display for presentation to the user.

[0372] For example, when a salesperson in a physical store uses smart glasses to introduce a product to a customer, if the customer's emotions are analyzed as being excited, a simple graph that can be quickly understood will be displayed. Conversely, if the customer is calm and seeking information, a graph containing more detailed information will be presented.

[0373] An example of a prompt message is an instruction such as, "Tell me the key selling points of the following product." This prompt allows the system to immediately provide appropriate information that is tailored to the customer's emotions.

[0374] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0375] Step 1:

[0376] The user gives instructions by voice to a voice input device. The input voice is acquired as a digital signal by the device and sent directly to an online voice recognition service. Here, the voice input is converted into digital data.

[0377] Step 2:

[0378] The device uses an online speech recognition service to convert speech data into text data. Specifically, it performs frequency analysis and phoneme analysis of the speech via a service such as Google Cloud Speech-to-Text, and then converts it into a sequence of characters. The output of this process is text data containing instructions.

[0379] Step 3:

[0380] The server receives the converted text data and parses its contents. Based on the parsing results, it collects information related to the instructions from the database. At this stage, natural language processing techniques are used to parse the text and extract keys for the relevant information. The output is a list of the relevant information.

[0381] Step 4:

[0382] The server uses an emotion analysis engine, such as IBM Watson Tone Analyzer, to determine the emotional state of the voice based on the text data. The analyzed emotion data is then used to identify the user's psychological state. The output is the recognized emotion information.

[0383] Step 5:

[0384] The server creates a plan to generate the optimal graph based on the acquired emotional and related information. The graph generation module adjusts the design and information display to match the user's psychological state, dynamically constructing the graph. The output is the generated graph.

[0385] Step 6:

[0386] The generated graph is embedded by the terminal into an output display (e.g., the display of smart glasses) and presented visually to the user or customer. The user can view the results and provide additional voice input if further instructions are needed. The final output of this process is visual data on the display.

[0387] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0388] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0389] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0393] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0394] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0395] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0396] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0397] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0398] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0399] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0400] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0401] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0402] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0403] The system of the present invention enables the automatic creation and modification of graphs using voice commands in order to improve work efficiency in creating websites and presentation materials. Specific embodiments are described below.

[0404] The user inputs work instructions by voice through a microphone. For example, they might give instructions such as, "Create a pie chart using annual sales data." The terminal receives this voice input as digital voice data and converts it into text data using a speech recognition module. This text data is then analyzed and sent to a server to determine what processing should be performed.

[0405] The server parses the received text data and searches the database for the necessary information. For example, it retrieves relevant annual sales data from the sales database. Based on the retrieved data, the server automatically generates graphs. In this case, for example, it generates a pie chart of a specified format using a graph generation module. The graph is created in the optimal format with the specified style and colors applied.

[0406] The generated graph is sent to the device and embedded in a designated location on the homepage or presentation materials. During this process, the display format is adjusted to maintain consistency with the design and other elements. Once the display is complete, the user reviews the results on the screen.

[0407] Furthermore, this system has a function to automatically save the work history. This means that if a user gives a voice command such as "revert to the previous state," the terminal will transmit that command to the server, and the server will refer to the history database and restore the system to the previous state.

[0408] Thus, the system of the present invention allows users to efficiently create and modify graphs with simple voice commands, significantly reducing their workload. For example, it is extremely useful when marketing personnel need to quickly visualize recent sales data for regular meeting reports.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The user gives voice commands to the microphone. For example, they might input specific instructions such as, "Create a pie chart using sales data."

[0412] Step 2:

[0413] The device acquires audio from the microphone as digital data and transmits that audio data to a speech recognition module. The speech recognition module converts the audio data into text data.

[0414] Step 3:

[0415] The terminal receives the converted text data and sends its contents to the server. At this time, the text data must be properly formatted for analysis.

[0416] Step 4:

[0417] The server analyzes the received text data and determines what type of graph to create. It also determines where the necessary data is located and prepares to retrieve it from databases or APIs.

[0418] Step 5:

[0419] The server accesses the database and retrieves sales data that matches the specified conditions. It then formats the retrieved data for graph creation and sends it to the graph generation module.

[0420] Step 6:

[0421] The server uses a graph generation module to create a pie chart based on the acquired data. The graph is generated in the specified format (color and layout).

[0422] Step 7:

[0423] The device receives the generated graph and embeds it in the designated location within the webpage or presentation materials. It adjusts the display format to maintain design consistency.

[0424] Step 8:

[0425] The server saves a history of the series of processes in a history database. This makes it possible to revert to a previous state when a user gives a command such as "return to the original state."

[0426] (Example 1)

[0427] Next, we will describe Example 1. 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."

[0428] Currently, data visualization when creating websites and presentation materials is often done manually by users, which presents inefficiency. Furthermore, the difficulty in quickly reproducing necessary data based on past work history leads to the problem of requiring significant time for information correction and updates. There is a need for technology to solve these problems and improve work efficiency.

[0429] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0430] In this invention, the server includes means for receiving voice and converting the voice signal into text information, means for searching and retrieving information from a database based on instructions, and means for generating visual data using the retrieved information. This allows users to easily visualize data through voice input and quickly recall information by referring to past work history.

[0431] "Audio signals" are digital data representations of human speech acquired by audio equipment such as microphones.

[0432] "Character information" refers to data that is represented as a corresponding string of characters after analyzing an audio signal using speech recognition technology.

[0433] A "database" is a collection of data built to enable efficient information retrieval and management, allowing for the rapid retrieval of necessary information in response to specific queries.

[0434] "Visual data" refers to information presented visually, such as graphs and charts, that are digitally generated based on acquired numerical data and information.

[0435] "Work history" refers to a record of a series of operations performed by a user within a system and the data generated, and is information used to refer to or restore past states.

[0436] "Voice feedback" refers to a function in which a system responds to user instructions by providing confirmation or a verbal response to those instructions.

[0437] "Network-based speech recognition technology" refers to technology that converts speech signals into text information through speech recognition services provided via the internet or any other network.

[0438] This system aims to efficiently visualize information by automatically generating visual data based on user voice instructions. Users can input instructions by voice using a microphone. These voice instructions are received as digital audio by the terminal and converted into text data using speech recognition technology. The speech recognition technology used is a speech recognition service provided over the network.

[0439] The terminal sends the converted text data to the server. The server analyzes this text data and searches and retrieves the necessary information from the database based on the specified information. The database is expected to contain, for example, sales data and market analysis information.

[0440] The server generates visual data based on the acquired information. For example, data analysis and graph generation software (e.g., Matplotlib, Plotly) is used to generate this visual data. At this stage, the data's style, color, and formatting are also applied.

[0441] The generated visual data is returned to the device and incorporated into homepages and presentation materials according to the user's instructions. The user can review the visual data and provide instructions for modifications or additional information as needed.

[0442] Furthermore, this system automatically records the work history, and allows users to easily restore past work states by giving voice commands such as "revert to previous state."

[0443] For example, when a marketing professional visualizes the latest data for a weekly meeting, they can use this system to quickly and accurately prepare the data and create efficient presentation materials. A possible prompt would be, "Create a pie chart using the most recent sales data." In this way, the system significantly reduces the user's burden and automates data visualization.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The user gives work instructions by voice using a microphone. The input is a voice signal, such as "Show the latest sales data as a pie chart." The terminal acquires this voice signal as digital audio data.

[0447] Step 2:

[0448] The terminal uses speech recognition technology to convert digital voice data into text information. This conversion process utilizes a speech recognition service over the network. The output is data in text format, converted from voice commands.

[0449] Step 3:

[0450] The terminal sends the converted text data to the server. The input is text data, and based on this, the server analyzes the received text data to determine what information is needed. This analysis generates a specific database query.

[0451] Step 4:

[0452] The server queries the database based on the analysis results to retrieve and obtain the necessary information. For example, it extracts sales information for a specific period from the sales database. The output is the dataset required for graph generation.

[0453] Step 5:

[0454] The server generates visual data using the acquired dataset. This process utilizes data analysis and graph generation modules, adjusting the graph style and layout as needed. The output is graph data in the specified format.

[0455] Step 6:

[0456] The server sends the generated graph data to the terminal. The terminal incorporates the received graph data into a homepage or presentation material according to the user's instructions. The output is a completed document with the graph positioned appropriately.

[0457] Step 7:

[0458] The user checks the completeness of the document on the device's display. At this stage, they can provide additional voice instructions as needed and make corrections or adjustments to the document.

[0459] (Application Example 1)

[0460] Next, we will explain Application Example 1. In the following explanation, 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."

[0461] Real-time data visualization is crucial for improving the efficiency of production management in factories. However, traditional methods involve time loss due to manual data collection and analysis, making rapid decision-making difficult. Furthermore, visualization often requires specialized knowledge, making it difficult for anyone other than skilled technicians to operate.

[0462] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0463] In this invention, the server includes means for receiving voice and converting voice data into text data, means for analyzing the text data and searching for and acquiring information based on instructions, and means for generating visualization materials using the received data. This enables real-time visualization of production data through display devices or mechanical devices in the factory environment, and allows for efficient factory management.

[0464] A "means for receiving sound" refers to a mechanism that can acquire and process external sound input.

[0465] "Methods for converting audio data into text data" refers to technologies that analyze acquired audio input and represent it as a corresponding string of characters.

[0466] "Means for analyzing text data and searching for and retrieving information based on received instructions" refers to the process of understanding string data and retrieving information from the appropriate database according to its content.

[0467] "Methods for generating visualization materials using received data" refer to technologies that process necessary information into a visually easy-to-understand format and display it in the form of graphs, diagrams, and other visual aids.

[0468] "Means for incorporating generated visualizations into display information" refers to a function that integrates visualized data into existing presentation materials or interfaces.

[0469] "Means for saving work history and restoring to a previous state based on instructions" refers to a technology that records the history of operations and undoes changes by restoring a specific past state.

[0470] "Means for presenting visualized data to display devices or mechanical equipment within a factory environment" refers to a function that directly displays visualized data on screens or terminals used within a factory.

[0471] This invention is a system aimed at improving the efficiency of production management within a factory. The user inputs voice instructions using a microphone. The terminal receives this voice input as digital voice data and converts it into text data using a voice recognition module. Often, an online voice recognition service on a server is used for voice recognition. This text data is sent to the server, where the instruction content is identified through analysis.

[0472] The server retrieves relevant information from the database based on instructions and obtains production data. Based on the retrieved data, the server immediately generates visualizations (e.g., graphs and charts). These visualizations are optimized in the specified format and style. The generated visualizations are transferred to display devices or machine displays within the factory and presented to the user.

[0473] For example, if a user says, "Show this week's production efficiency as a bar graph," the system will use the production data to generate a bar graph in the specified format and display it on a screen in the factory. This allows managers to check production efficiency in real time and make quick decisions.

[0474] An example of a prompt to be input into the generating AI model is "Designing a factory management application that graphs manufacturing data in real time using voice commands." This would reduce the burden on users to operate using voice commands while enabling more efficient production management tasks.

[0475] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0476] Step 1:

[0477] The user inputs voice commands through the microphone. The input data is unstructured voice data. This voice data is immediately captured as digital data on the device.

[0478] Step 2:

[0479] The terminal uses a speech recognition module to convert speech data into text data. The input is speech data, and the output is a string. The speech recognition module utilizes an online speech recognition service on a server to perform speech analysis.

[0480] Step 3:

[0481] Text data is sent to the server. The server analyzes this text data to identify the instructions. The input is text data, and the analysis outputs specific instructions.

[0482] Step 4:

[0483] The server searches the database according to the instructions and retrieves the necessary production data. The input is the instructions, and the output is the retrieved production data. This allows for the rapid acquisition of relevant information.

[0484] Step 5:

[0485] The server generates visualization materials based on acquired production data. The input is production data, and the output is visualization materials such as graphs. The server processes the data and generates graphs according to the specified format.

[0486] Step 6:

[0487] The generated visualizations are transferred via terminals to display devices and machinery within the factory and presented. The input is the visualization material, and the output is visual feedback in a physical display. This enables the provision of visual information.

[0488] Step 7:

[0489] The user reviews the presented information and provides additional instructions via voice as needed. This feedback loop allows for real-time data review and correction.

[0490] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0491] The present invention aims to improve the user experience by optimizing the process of creating homepages and presentation materials through the recognition of voice commands and user emotions. By combining this with an emotion engine, the system analyzes the emotions contained in the user's voice and adjusts responses and graphs accordingly.

[0492] When a user inputs a voice command into the microphone, the device captures the audio as digital data. Next, the voice data is converted into text data through an online speech recognition service. This converted text data is then sent to a server where the specified command is analyzed.

[0493] While the server analyzes text data, its emotion engine recognizes the emotional state within the speech. This emotional state is determined by analyzing features such as tone, rhythm, and speed. Based on the analysis results, the server retrieves necessary information from the database and further adjusts the response content and graph design based on the emotion. For example, if the user is giving instructions in a very calm tone, the system will create a graph with a standard design. On the other hand, if the user is emotionally agitated, the design can be changed to a simpler and easier-to-read design.

[0494] The generated graphs are sent to the terminal and embedded in the homepage or presentation materials. Users can review the results and provide additional instructions if necessary. Furthermore, a history of the entire process is automatically saved by the server, in case the user requests a revert to a previous state later.

[0495] For example, before a sales meeting, a user can request multiple data points for a sales report via voice prompts. If the user is nervous, the system can prepare simple, intuitively easy-to-understand graphs, enabling quick document creation. If the system determines that the user is relaxed, it can provide graphs with the usual detailed design, thus accommodating a variety of situations.

[0496] Thus, the system of the present invention recognizes the user's emotions and uses them to dynamically adjust the document creation process, thereby enabling efficient and flexible operation.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The user inputs voice commands into the microphone. For example, they might say, "Create a bar graph using this month's sales data."

[0500] Step 2:

[0501] The device acquires audio from the microphone and converts that audio data into a digital format. Furthermore, it uses a speech recognition service to convert it into text data.

[0502] Step 3:

[0503] The device sends text data to the server. At the same time, the audio data itself is also sent for sentiment analysis.

[0504] Step 4:

[0505] The server analyzes text data and determines what information is needed based on user instructions. It also uses an emotion engine to recognize the user's emotional state from their voice.

[0506] Step 5:

[0507] The server accesses the database and retrieves data that meets the specified criteria (for example, this month's sales data). Simultaneously, it adjusts the style and color scheme of the generated graphs based on the sentiment analysis results.

[0508] Step 6:

[0509] The server calls a graph generation module and creates a graph using the acquired data. If the server determines that the user's emotional state is one of tension, it creates a graph with a simple and easy-to-understand design.

[0510] Step 7:

[0511] The generated graph is sent to the terminal. The terminal embeds the received graph into the specified presentation material or web page and displays the results to the user.

[0512] Step 8:

[0513] The server stores a history of the sequence of operations in a history database. This allows for quick restoration when a user requests to revert to a previous state.

[0514] (Example 2)

[0515] Next, we will describe Example 2. 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."

[0516] While using voice commands can improve efficiency in the computer-assisted process of creating websites and presentation materials, conventional systems fail to take into account the user's emotional state, resulting in inadequate design and information delivery. This lack of flexibility in responding to the user's emotional state prevents the provision of an optimal user experience.

[0517] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0518] In this invention, the server includes means for converting voice data into text data, means for recognizing emotional states, and means for adjusting the design based on the emotional state. This enables the creation of more effective and appropriate materials by collecting necessary information based on the user's voice instructions and dynamically changing the design according to the emotional state.

[0519] "Means for receiving voice" refers to an input device that has the function of receiving voice information from a user and converting it into a data format that can be processed.

[0520] "Means of converting to text data" refers to the processing or technology used to convert acquired audio data into text information.

[0521] "Means of recognizing emotional states" refers to technologies or algorithms used to identify a user's emotions through the analysis of voice and text data.

[0522] "Means for searching and retrieving information" refers to a function that searches for and retrieves necessary information from databases or other sources based on specified instructions.

[0523] "A method for adjusting the design and generating graphs" refers to a technology that dynamically changes the visual design based on acquired information and emotional states to generate the optimal graph.

[0524] "Means of incorporating information for display" refers to the processing and techniques used to place generated graphs and information in appropriate locations on a website or document.

[0525] "Means of saving work history" refers to technologies and processes that record the operations and changes performed by a user and save them in a format that can be referenced or restored later.

[0526] The embodiments for carrying out the present invention will be described in detail below.

[0527] This system consists of a voice input device, a computing device, an internet connection, a database, and associated software modules. Specifically, the microphone receives voice commands and acquires this voice data in digital format. The terminal then converts the voice data into text data using Google Cloud Speech-to-Text or equivalent online speech recognition technology.

[0528] The converted text data is sent to the server. The server analyzes this text data using natural language processing libraries (e.g., NLTK or spaCy). In doing so, it utilizes machine learning models (e.g., speech emotion recognition models using TensorFlow or PyTorch) to recognize emotional states using acoustic features obtained from the speech.

[0529] Once an emotional state is recognized, the server retrieves relevant information from the database. Based on this information, it uses a generative AI model (e.g., DALL-E or Midjourney) to dynamically adjust the design based on the emotion and generate a graph. This generation process involves providing the AI ​​model with prompts such as, "Create a simple graph design for when the user is feeling anxious."

[0530] Finally, the generated graphs are sent to the terminal and incorporated into the homepage or presentation materials. This allows users to review the results and modify or add further instructions as needed. The server also saves the operation history, making it easy for users to revert to previous states. For example, when creating materials for a sales meeting, a graph with an optimal design based on the user's emotions can be quickly generated and effectively reflected in the materials.

[0531] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0532] Step 1:

[0533] The user inputs voice commands through the microphone. The device acquires this voice as digital data. The input voice data is sent to an online speech recognition service such as Google Cloud Speech-to-Text. The data is transmitted over the network, and the voice is converted to text. The output is text data that reflects the user's spoken content.

[0534] Step 2:

[0535] The terminal sends the converted text data to the server. The server analyzes the text data using a natural language processing library. Specifically, it performs syntactic analysis and keyword extraction to accurately identify the user's instructions. As a result of the analysis, structured data related to the instructions is output.

[0536] Step 3:

[0537] The server uses an emotion engine to recognize the emotional state in the speech. It analyzes features obtained from the speech data (tone, rhythm, speed, etc.) and uses a machine learning model to identify the user's emotion. This process results in the current emotional state (e.g., calm, tense) being output.

[0538] Step 4:

[0539] The server searches and retrieves relevant information from the database based on the recognized emotional state and analyzed instructions. Furthermore, it utilizes a generative AI model to adjust the design according to the emotion and generate the necessary graphs. Specifically, it provides prompt text to the AI ​​model to obtain appropriate visual representations. The output of this step is an optimized graph tailored to the user's emotional state.

[0540] Step 5:

[0541] The generated graphs are sent to the terminal and incorporated into presentation materials and website content. Users can view the graphs on their terminal and provide additional instructions as needed. The server also automatically saves the work history, providing a basis for reverting to previous states. The output of this procedure is the information provided in the form of a final document.

[0542] (Application Example 2)

[0543] Next, we will explain application example 2. In the following explanation, 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."

[0544] In today's consumer environment, effectively explaining products and services to customers requires dynamic information generation and presentation that responds to their emotional state. However, traditional static materials and one-way information provision make it difficult to make effective proposals that meet customer needs, resulting in a challenge in improving customer satisfaction.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0546] In this invention, the server includes means for receiving voice and converting the voice data into text data, means for analyzing the user's emotional state and dynamically adjusting a graph according to that state, and means for incorporating the generated graph into output information. This makes it possible to provide information that fits the customer's emotions in real time.

[0547] A "sound receiving device" is a device that acquires the sound emitted by the user as an electronic signal and processes it as sound data.

[0548] "Text data" refers to a data format that represents audio data as a string of characters and stores or processes it in digital format.

[0549] A "device for collecting and acquiring information" is a device that, based on input instructions, retrieves necessary information from an external or internal database.

[0550] A "device for analyzing emotional states" is a device that identifies and analyzes a user's emotions and psychological state based on their voice characteristics and expressions.

[0551] A "dynamic graph adjustment device" is a device that takes into account the user's emotional state and changes the design of the graph and the way information is displayed, thereby optimizing it instantly.

[0552] A "device for incorporating output information" is a device for integrating generated graphs and data into information for presentations and displays.

[0553] A "device for maintaining work history" is a device that stores records of operations and data processing performed in the past so that they can be referenced later.

[0554] The system for carrying out the present invention consists of a voice input device, an emotion analysis engine, a graph generation module, and an output display. When a user inputs a voice command into the voice input device, the voice is acquired as a digital signal. Next, an online speech recognition service (e.g., Google Cloud Speech-to-Text) is used to convert the voice data into text data. The terminal analyzes the converted text data and collects and retrieves the necessary information from a database according to the content of the command.

[0555] Subsequently, an emotion analysis engine (such as IBM Watson Tone Analyzer) is used to determine the user's emotional state from their voice. Based on the determined emotion, a graph generation module generates a graph with an optimal design and content. This graph is then incorporated into an output display for presentation to the user.

[0556] For example, when a salesperson in a physical store uses smart glasses to introduce a product to a customer, if the customer's emotions are analyzed as being excited, a simple graph that can be quickly understood will be displayed. Conversely, if the customer is calm and seeking information, a graph containing more detailed information will be presented.

[0557] An example of a prompt message is an instruction such as, "Tell me the key selling points of the following product." This prompt allows the system to immediately provide appropriate information that is tailored to the customer's emotions.

[0558] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0559] Step 1:

[0560] The user gives instructions by voice to a voice input device. The input voice is acquired as a digital signal by the device and sent directly to an online voice recognition service. Here, the voice input is converted into digital data.

[0561] Step 2:

[0562] The device uses an online speech recognition service to convert speech data into text data. Specifically, it performs frequency analysis and phoneme analysis of the speech via a service such as Google Cloud Speech-to-Text, and then converts it into a sequence of characters. The output of this process is text data containing instructions.

[0563] Step 3:

[0564] The server receives the converted text data and parses its contents. Based on the parsing results, it collects information related to the instructions from the database. At this stage, natural language processing techniques are used to parse the text and extract keys for the relevant information. The output is a list of the relevant information.

[0565] Step 4:

[0566] The server uses an emotion analysis engine, such as IBM Watson Tone Analyzer, to determine the emotional state of the voice based on the text data. The analyzed emotion data is then used to identify the user's psychological state. The output is the recognized emotion information.

[0567] Step 5:

[0568] The server creates a plan to generate the optimal graph based on the acquired emotional and related information. The graph generation module adjusts the design and information display to match the user's psychological state, dynamically constructing the graph. The output is the generated graph.

[0569] Step 6:

[0570] The generated graph is embedded by the terminal into an output display (e.g., the display of smart glasses) and presented visually to the user or customer. The user can view the results and provide additional voice input if further instructions are needed. The final output of this process is visual data on the display.

[0571] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0572] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0573] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0574] [Fourth Embodiment]

[0575] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0576] As shown in Figure 7, the 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.

[0577] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0578] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0579] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0580] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0581] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0582] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0583] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0584] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0585] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0586] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0587] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0588] The system of the present invention enables the automatic creation and modification of graphs using voice commands in order to improve work efficiency in creating websites and presentation materials. Specific embodiments are described below.

[0589] The user inputs work instructions by voice through a microphone. For example, they might give instructions such as, "Create a pie chart using annual sales data." The terminal receives this voice input as digital voice data and converts it into text data using a speech recognition module. This text data is then analyzed and sent to a server to determine what processing should be performed.

[0590] The server parses the received text data and searches the database for the necessary information. For example, it retrieves relevant annual sales data from the sales database. Based on the retrieved data, the server automatically generates graphs. In this case, for example, it generates a pie chart of a specified format using a graph generation module. The graph is created in the optimal format with the specified style and colors applied.

[0591] The generated graph is sent to the device and embedded in a designated location on the homepage or presentation materials. During this process, the display format is adjusted to maintain consistency with the design and other elements. Once the display is complete, the user reviews the results on the screen.

[0592] Furthermore, this system has a function to automatically save the work history. This means that if a user gives a voice command such as "revert to the previous state," the terminal will transmit that command to the server, and the server will refer to the history database and restore the system to the previous state.

[0593] Thus, the system of the present invention allows users to efficiently create and modify graphs with simple voice commands, significantly reducing their workload. For example, it is extremely useful when marketing personnel need to quickly visualize recent sales data for regular meeting reports.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The user gives voice commands to the microphone. For example, they might input specific instructions such as, "Create a pie chart using sales data."

[0597] Step 2:

[0598] The device acquires audio from the microphone as digital data and transmits that audio data to a speech recognition module. The speech recognition module converts the audio data into text data.

[0599] Step 3:

[0600] The terminal receives the converted text data and sends its contents to the server. At this time, the text data must be properly formatted for analysis.

[0601] Step 4:

[0602] The server analyzes the received text data and determines what type of graph to create. It also determines where the necessary data is located and prepares to retrieve it from databases or APIs.

[0603] Step 5:

[0604] The server accesses the database and retrieves sales data that matches the specified conditions. It then formats the retrieved data for graph creation and sends it to the graph generation module.

[0605] Step 6:

[0606] The server uses a graph generation module to create a pie chart based on the acquired data. The graph is generated in the specified format (color and layout).

[0607] Step 7:

[0608] The device receives the generated graph and embeds it in the designated location within the webpage or presentation materials. It adjusts the display format to maintain design consistency.

[0609] Step 8:

[0610] The server saves a history of the series of processes in a history database. This makes it possible to revert to a previous state when a user gives a command such as "return to the original state."

[0611] (Example 1)

[0612] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0613] Currently, data visualization when creating websites and presentation materials is often done manually by users, which presents inefficiency. Furthermore, the difficulty in quickly reproducing necessary data based on past work history leads to the problem of requiring significant time for information correction and updates. There is a need for technology to solve these problems and improve work efficiency.

[0614] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0615] In this invention, the server includes means for receiving voice and converting the voice signal into text information, means for searching and retrieving information from a database based on instructions, and means for generating visual data using the retrieved information. This allows users to easily visualize data through voice input and quickly recall information by referring to past work history.

[0616] "Audio signals" are digital data representations of human speech acquired by audio equipment such as microphones.

[0617] "Character information" refers to data that is represented as a corresponding string of characters after analyzing an audio signal using speech recognition technology.

[0618] A "database" is a collection of data built to enable efficient information retrieval and management, allowing for the rapid retrieval of necessary information in response to specific queries.

[0619] "Visual data" refers to information presented visually, such as graphs and charts, that are digitally generated based on acquired numerical data and information.

[0620] "Work history" refers to a record of a series of operations performed by a user within a system and the data generated, and is information used to refer to or restore past states.

[0621] "Voice feedback" refers to a function in which a system responds to user instructions by providing confirmation or a verbal response to those instructions.

[0622] "Network-based speech recognition technology" refers to technology that converts speech signals into text information through speech recognition services provided via the internet or any other network.

[0623] This system aims to efficiently visualize information by automatically generating visual data based on user voice instructions. Users can input instructions by voice using a microphone. These voice instructions are received as digital audio by the terminal and converted into text data using speech recognition technology. The speech recognition technology used is a speech recognition service provided over the network.

[0624] The terminal sends the converted text data to the server. The server analyzes this text data and searches and retrieves the necessary information from the database based on the specified information. The database is expected to contain, for example, sales data and market analysis information.

[0625] The server generates visual data based on the acquired information. For example, data analysis and graph generation software (e.g., Matplotlib, Plotly) is used to generate this visual data. At this stage, the data's style, color, and formatting are also applied.

[0626] The generated visual data is returned to the device and incorporated into homepages and presentation materials according to the user's instructions. The user can review the visual data and provide instructions for modifications or additional information as needed.

[0627] Furthermore, this system automatically records the work history, and allows users to easily restore past work states by giving voice commands such as "revert to previous state."

[0628] For example, when a marketing professional visualizes the latest data for a weekly meeting, they can use this system to quickly and accurately prepare the data and create efficient presentation materials. A possible prompt would be, "Create a pie chart using the most recent sales data." In this way, the system significantly reduces the user's burden and automates data visualization.

[0629] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0630] Step 1:

[0631] The user gives work instructions by voice using a microphone. The input is a voice signal, such as "Show the latest sales data as a pie chart." The terminal acquires this voice signal as digital audio data.

[0632] Step 2:

[0633] The terminal uses speech recognition technology to convert digital voice data into text information. This conversion process utilizes a speech recognition service over the network. The output is data in text format, converted from voice commands.

[0634] Step 3:

[0635] The terminal sends the converted text data to the server. The input is text data, and based on this, the server analyzes the received text data to determine what information is needed. This analysis generates a specific database query.

[0636] Step 4:

[0637] The server queries the database based on the analysis results to retrieve and obtain the necessary information. For example, it extracts sales information for a specific period from the sales database. The output is the dataset required for graph generation.

[0638] Step 5:

[0639] The server generates visual data using the acquired dataset. This process utilizes data analysis and graph generation modules, adjusting the graph style and layout as needed. The output is graph data in the specified format.

[0640] Step 6:

[0641] The server sends the generated graph data to the terminal. The terminal incorporates the received graph data into a homepage or presentation material according to the user's instructions. The output is a completed document with the graph positioned appropriately.

[0642] Step 7:

[0643] The user checks the completeness of the document on the device's display. At this stage, they can provide additional voice instructions as needed and make corrections or adjustments to the document.

[0644] (Application Example 1)

[0645] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0646] Real-time data visualization is crucial for improving the efficiency of production management in factories. However, traditional methods involve time loss due to manual data collection and analysis, making rapid decision-making difficult. Furthermore, visualization often requires specialized knowledge, making it difficult for anyone other than skilled technicians to operate.

[0647] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0648] In this invention, the server includes means for receiving voice and converting voice data into text data, means for analyzing the text data and searching for and acquiring information based on instructions, and means for generating visualization materials using the received data. This enables real-time visualization of production data through display devices or mechanical devices in the factory environment, and allows for efficient factory management.

[0649] A "means for receiving sound" refers to a mechanism that can acquire and process external sound input.

[0650] "Methods for converting audio data into text data" refers to technologies that analyze acquired audio input and represent it as a corresponding string of characters.

[0651] "Means for analyzing text data and searching for and retrieving information based on received instructions" refers to the process of understanding string data and retrieving information from the appropriate database according to its content.

[0652] "Methods for generating visualization materials using received data" refer to technologies that process necessary information into a visually easy-to-understand format and display it in the form of graphs, diagrams, and other visual aids.

[0653] "Means for incorporating generated visualizations into display information" refers to a function that integrates visualized data into existing presentation materials or interfaces.

[0654] "Means for saving work history and restoring to a previous state based on instructions" refers to a technology that records the history of operations and undoes changes by restoring a specific past state.

[0655] "Means for presenting visualized data to display devices or mechanical equipment within a factory environment" refers to a function that directly displays visualized data on screens or terminals used within a factory.

[0656] This invention is a system aimed at improving the efficiency of production management within a factory. The user inputs voice instructions using a microphone. The terminal receives this voice input as digital voice data and converts it into text data using a voice recognition module. Often, an online voice recognition service on a server is used for voice recognition. This text data is sent to the server, where the instruction content is identified through analysis.

[0657] The server retrieves relevant information from the database based on instructions and obtains production data. Based on the retrieved data, the server immediately generates visualizations (e.g., graphs and charts). These visualizations are optimized in the specified format and style. The generated visualizations are transferred to display devices or machine displays within the factory and presented to the user.

[0658] For example, if a user says, "Show this week's production efficiency as a bar graph," the system will use the production data to generate a bar graph in the specified format and display it on a screen in the factory. This allows managers to check production efficiency in real time and make quick decisions.

[0659] An example of a prompt to be input into the generating AI model is "Designing a factory management application that graphs manufacturing data in real time using voice commands." This would reduce the burden on users to operate using voice commands while enabling more efficient production management tasks.

[0660] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0661] Step 1:

[0662] The user inputs voice commands through the microphone. The input data is unstructured voice data. This voice data is immediately captured as digital data on the device.

[0663] Step 2:

[0664] The terminal uses a speech recognition module to convert speech data into text data. The input is speech data, and the output is a string. The speech recognition module utilizes an online speech recognition service on a server to perform speech analysis.

[0665] Step 3:

[0666] Text data is sent to the server. The server analyzes this text data to identify the instructions. The input is text data, and the analysis outputs specific instructions.

[0667] Step 4:

[0668] The server searches the database according to the instructions and retrieves the necessary production data. The input is the instructions, and the output is the retrieved production data. This allows for the rapid acquisition of relevant information.

[0669] Step 5:

[0670] The server generates visualization materials based on acquired production data. The input is production data, and the output is visualization materials such as graphs. The server processes the data and generates graphs according to the specified format.

[0671] Step 6:

[0672] The generated visualizations are transferred via terminals to display devices and machinery within the factory and presented. The input is the visualization material, and the output is visual feedback in a physical display. This enables the provision of visual information.

[0673] Step 7:

[0674] The user reviews the presented information and provides additional instructions via voice as needed. This feedback loop allows for real-time data review and correction.

[0675] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0676] The present invention aims to improve the user experience by optimizing the process of creating homepages and presentation materials through the recognition of voice commands and user emotions. By combining this with an emotion engine, the system analyzes the emotions contained in the user's voice and adjusts responses and graphs accordingly.

[0677] When a user inputs a voice command into the microphone, the device captures the audio as digital data. Next, the voice data is converted into text data through an online speech recognition service. This converted text data is then sent to a server where the specified command is analyzed.

[0678] While the server analyzes text data, its emotion engine recognizes the emotional state within the speech. This emotional state is determined by analyzing features such as tone, rhythm, and speed. Based on the analysis results, the server retrieves necessary information from the database and further adjusts the response content and graph design based on the emotion. For example, if the user is giving instructions in a very calm tone, the system will create a graph with a standard design. On the other hand, if the user is emotionally agitated, the design can be changed to a simpler and easier-to-read design.

[0679] The generated graphs are sent to the terminal and embedded in the homepage or presentation materials. Users can review the results and provide additional instructions if necessary. Furthermore, a history of the entire process is automatically saved by the server, in case the user requests a revert to a previous state later.

[0680] For example, before a sales meeting, a user can request multiple data points for a sales report via voice prompts. If the user is nervous, the system can prepare simple, intuitively easy-to-understand graphs, enabling quick document creation. If the system determines that the user is relaxed, it can provide graphs with the usual detailed design, thus accommodating a variety of situations.

[0681] Thus, the system of the present invention recognizes the user's emotions and uses them to dynamically adjust the document creation process, thereby enabling efficient and flexible operation.

[0682] The following describes the processing flow.

[0683] Step 1:

[0684] The user inputs voice commands into the microphone. For example, they might say, "Create a bar graph using this month's sales data."

[0685] Step 2:

[0686] The device acquires audio from the microphone and converts that audio data into a digital format. Furthermore, it uses a speech recognition service to convert it into text data.

[0687] Step 3:

[0688] The device sends text data to the server. At the same time, the audio data itself is also sent for sentiment analysis.

[0689] Step 4:

[0690] The server analyzes text data and determines what information is needed based on user instructions. It also uses an emotion engine to recognize the user's emotional state from their voice.

[0691] Step 5:

[0692] The server accesses the database and retrieves data that meets the specified criteria (for example, this month's sales data). Simultaneously, it adjusts the style and color scheme of the generated graphs based on the sentiment analysis results.

[0693] Step 6:

[0694] The server calls a graph generation module and creates a graph using the acquired data. If the server determines that the user's emotional state is one of tension, it creates a graph with a simple and easy-to-understand design.

[0695] Step 7:

[0696] The generated graph is sent to the terminal. The terminal embeds the received graph into the specified presentation material or web page and displays the results to the user.

[0697] Step 8:

[0698] The server stores a history of the sequence of operations in a history database. This allows for quick restoration when a user requests to revert to a previous state.

[0699] (Example 2)

[0700] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0701] While using voice commands can improve efficiency in the computer-assisted process of creating websites and presentation materials, conventional systems fail to take into account the user's emotional state, resulting in inadequate design and information delivery. This lack of flexibility in responding to the user's emotional state prevents the provision of an optimal user experience.

[0702] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0703] In this invention, the server includes means for converting voice data into text data, means for recognizing emotional states, and means for adjusting the design based on the emotional state. This enables the creation of more effective and appropriate materials by collecting necessary information based on the user's voice instructions and dynamically changing the design according to the emotional state.

[0704] "Means for receiving voice" refers to an input device that has the function of receiving voice information from a user and converting it into a data format that can be processed.

[0705] "Means of converting to text data" refers to the processing or technology used to convert acquired audio data into text information.

[0706] "Means of recognizing emotional states" refers to technologies or algorithms used to identify a user's emotions through the analysis of voice and text data.

[0707] "Means for searching and retrieving information" refers to a function that searches for and retrieves necessary information from databases or other sources based on specified instructions.

[0708] "A method for adjusting the design and generating graphs" refers to a technology that dynamically changes the visual design based on acquired information and emotional states to generate the optimal graph.

[0709] "Means of incorporating information for display" refers to the processing and techniques used to place generated graphs and information in appropriate locations on a website or document.

[0710] "Means of saving work history" refers to technologies and processes that record the operations and changes performed by a user and save them in a format that can be referenced or restored later.

[0711] The embodiments for carrying out the present invention will be described in detail below.

[0712] This system consists of a voice input device, a computing device, an internet connection, a database, and associated software modules. Specifically, the microphone receives voice commands and acquires this voice data in digital format. The terminal then converts the voice data into text data using Google Cloud Speech-to-Text or equivalent online speech recognition technology.

[0713] The converted text data is sent to the server. The server analyzes this text data using natural language processing libraries (e.g., NLTK or spaCy). In doing so, it utilizes machine learning models (e.g., speech emotion recognition models using TensorFlow or PyTorch) to recognize emotional states using acoustic features obtained from the speech.

[0714] Once an emotional state is recognized, the server retrieves relevant information from the database. Based on this information, it uses a generative AI model (e.g., DALL-E or Midjourney) to dynamically adjust the design based on the emotion and generate a graph. This generation process involves providing the AI ​​model with prompts such as, "Create a simple graph design for when the user is feeling anxious."

[0715] Finally, the generated graphs are sent to the terminal and incorporated into the homepage or presentation materials. This allows users to review the results and modify or add further instructions as needed. The server also saves the operation history, making it easy for users to revert to previous states. For example, when creating materials for a sales meeting, a graph with an optimal design based on the user's emotions can be quickly generated and effectively reflected in the materials.

[0716] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0717] Step 1:

[0718] The user inputs voice commands through the microphone. The device acquires this voice as digital data. The input voice data is sent to an online speech recognition service such as Google Cloud Speech-to-Text. The data is transmitted over the network, and the voice is converted to text. The output is text data that reflects the user's spoken content.

[0719] Step 2:

[0720] The terminal sends the converted text data to the server. The server analyzes the text data using a natural language processing library. Specifically, it performs syntactic analysis and keyword extraction to accurately identify the user's instructions. As a result of the analysis, structured data related to the instructions is output.

[0721] Step 3:

[0722] The server uses an emotion engine to recognize the emotional state in the speech. It analyzes features obtained from the speech data (tone, rhythm, speed, etc.) and uses a machine learning model to identify the user's emotion. This process results in the current emotional state (e.g., calm, tense) being output.

[0723] Step 4:

[0724] The server searches and retrieves relevant information from the database based on the recognized emotional state and analyzed instructions. Furthermore, it utilizes a generative AI model to adjust the design according to the emotion and generate the necessary graphs. Specifically, it provides prompt text to the AI ​​model to obtain appropriate visual representations. The output of this step is an optimized graph tailored to the user's emotional state.

[0725] Step 5:

[0726] The generated graphs are sent to the terminal and incorporated into presentation materials and website content. Users can view the graphs on their terminal and provide additional instructions as needed. The server also automatically saves the work history, providing a basis for reverting to previous states. The output of this procedure is the information provided in the form of a final document.

[0727] (Application Example 2)

[0728] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0729] In today's consumer environment, effectively explaining products and services to customers requires dynamic information generation and presentation that responds to their emotional state. However, traditional static materials and one-way information provision make it difficult to make effective proposals that meet customer needs, resulting in a challenge in improving customer satisfaction.

[0730] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0731] In this invention, the server includes means for receiving voice and converting the voice data into text data, means for analyzing the user's emotional state and dynamically adjusting a graph according to that state, and means for incorporating the generated graph into output information. This makes it possible to provide information that fits the customer's emotions in real time.

[0732] A "sound receiving device" is a device that acquires the sound emitted by the user as an electronic signal and processes it as sound data.

[0733] "Text data" refers to a data format that represents audio data as a string of characters and stores or processes it in digital format.

[0734] A "device for collecting and acquiring information" is a device that, based on input instructions, retrieves necessary information from an external or internal database.

[0735] A "device for analyzing emotional states" is a device that identifies and analyzes a user's emotions and psychological state based on their voice characteristics and expressions.

[0736] A "dynamic graph adjustment device" is a device that takes into account the user's emotional state and changes the design of the graph and the way information is displayed, thereby optimizing it instantly.

[0737] A "device for incorporating output information" is a device for integrating generated graphs and data into information for presentations and displays.

[0738] A "device for maintaining work history" is a device that stores records of operations and data processing performed in the past so that they can be referenced later.

[0739] The system for carrying out the present invention consists of a voice input device, an emotion analysis engine, a graph generation module, and an output display. When a user inputs a voice command into the voice input device, the voice is acquired as a digital signal. Next, an online speech recognition service (e.g., Google Cloud Speech-to-Text) is used to convert the voice data into text data. The terminal analyzes the converted text data and collects and retrieves the necessary information from a database according to the content of the command.

[0740] Subsequently, an emotion analysis engine (such as IBM Watson Tone Analyzer) is used to determine the user's emotional state from their voice. Based on the determined emotion, a graph generation module generates a graph with an optimal design and content. This graph is then incorporated into an output display for presentation to the user.

[0741] For example, when a salesperson in a physical store uses smart glasses to introduce a product to a customer, if the customer's emotions are analyzed as being excited, a simple graph that can be quickly understood will be displayed. Conversely, if the customer is calm and seeking information, a graph containing more detailed information will be presented.

[0742] An example of a prompt message is an instruction such as, "Tell me the key selling points of the following product." This prompt allows the system to immediately provide appropriate information that is tailored to the customer's emotions.

[0743] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0744] Step 1:

[0745] The user gives instructions by voice to a voice input device. The input voice is acquired as a digital signal by the device and sent directly to an online voice recognition service. Here, the voice input is converted into digital data.

[0746] Step 2:

[0747] The device uses an online speech recognition service to convert speech data into text data. Specifically, it performs frequency analysis and phoneme analysis of the speech via a service such as Google Cloud Speech-to-Text, and then converts it into a sequence of characters. The output of this process is text data containing instructions.

[0748] Step 3:

[0749] The server receives the converted text data and parses its contents. Based on the parsing results, it collects information related to the instructions from the database. At this stage, natural language processing techniques are used to parse the text and extract keys for the relevant information. The output is a list of the relevant information.

[0750] Step 4:

[0751] The server uses an emotion analysis engine, such as IBM Watson Tone Analyzer, to determine the emotional state of the voice based on the text data. The analyzed emotion data is then used to identify the user's psychological state. The output is the recognized emotion information.

[0752] Step 5:

[0753] The server creates a plan to generate the optimal graph based on the acquired emotional and related information. The graph generation module adjusts the design and information display to match the user's psychological state, dynamically constructing the graph. The output is the generated graph.

[0754] Step 6:

[0755] The generated graph is embedded by the terminal into an output display (e.g., the display of smart glasses) and presented visually to the user or customer. The user can view the results and provide additional voice input if further instructions are needed. The final output of this process is visual data on the display.

[0756] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0757] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0759] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0760] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0761] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0762] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0763] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0764] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0765] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0766] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0767] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0768] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0769] 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.

[0770] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0771] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0772] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0773] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0774] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0775] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0776] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0777] The following is further disclosed regarding the embodiments described above.

[0778] (Claim 1)

[0779] A means of receiving audio and converting audio data into text data,

[0780] A means for analyzing the aforementioned text data and searching for and retrieving information based on the received instructions,

[0781] A means of generating a graph using the received data,

[0782] A means of incorporating the generated graph into the display information,

[0783] A means to save the work history and revert to a previous state based on instructions,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, further comprising means for responding to the user by voice and accurately confirming instructions.

[0787] (Claim 3)

[0788] The system according to claim 1, characterized in that the means for converting the aforementioned audio data into text uses an online speech recognition service.

[0789] "Example 1"

[0790] (Claim 1)

[0791] A means for receiving audio and converting the audio signal into text information,

[0792] Means for analyzing the aforementioned textual information and searching and retrieving information from a database based on instructions,

[0793] A means of generating visual data using acquired information,

[0794] Means for incorporating the generated visual data into information for display,

[0795] A means of recording work history and restoring to a previous state based on past instructions,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, further comprising means for providing voice feedback in response to input instructions and for confirming the content of the instructions.

[0799] (Claim 3)

[0800] The system according to claim 1, characterized in that the means for converting the aforementioned audio signal into text uses speech recognition technology via a network.

[0801] "Application Example 1"

[0802] (Claim 1)

[0803] A means of receiving audio and converting audio data into text data,

[0804] A means for analyzing the aforementioned text data and searching for and retrieving information based on the received instructions,

[0805] A means of generating visualization materials using the received data,

[0806] A means of incorporating the generated visualization data into the display information,

[0807] A means to save the work history and revert to a previous state based on instructions,

[0808] A means of displaying visualization data on a display device or mechanical device in a factory environment,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, further comprising means for responding to the user by voice and accurately confirming instructions.

[0812] (Claim 3)

[0813] The system according to claim 1, characterized in that the means for converting the aforementioned audio data into text uses an online speech recognition service.

[0814] "Example 2 of combining an emotion engine"

[0815] (Claim 1)

[0816] A means of receiving audio and converting audio data into text data,

[0817] The aforementioned text data is analyzed, and a means for recognizing emotional states during the analysis process is provided.

[0818] A means for searching and retrieving information based on recognized emotional states, adjusting the design, and generating a graph,

[0819] A means of incorporating the generated graph into the display information,

[0820] A means to save the work history and revert to a previous state based on instructions,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, comprising means for dynamically adjusting the design in accordance with emotions during the process of generating the generated graph.

[0824] (Claim 3)

[0825] The system according to claim 1, characterized in that the means for converting the aforementioned audio data into text uses external speech recognition technology.

[0826] "Application example 2 when combining with an emotional engine"

[0827] (Claim 1)

[0828] A device that receives audio and converts the audio data into text data,

[0829] A device that analyzes the aforementioned text data and collects and acquires information based on the received instructions,

[0830] A device that analyzes the user's emotional state and dynamically adjusts a graph according to that state,

[0831] A device that incorporates the generated graph into the output information,

[0832] A device that retains work history and restores to a previous state based on instructions,

[0833] A device that includes this.

[0834] (Claim 2)

[0835] The apparatus according to claim 1, which has a function to respond to the user by voice and to accurately confirm instructions.

[0836] (Claim 3)

[0837] The apparatus according to claim 1, characterized in that the apparatus for converting the aforementioned audio data into text uses an online speech recognition service. [Explanation of Symbols]

[0838] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving audio and converting audio data into text data, A means for analyzing the aforementioned text data and searching for and retrieving information based on the received instructions, A means of generating a graph using the received data, A means of incorporating the generated graph into the display information, A means to save the work history and revert to a previous state based on instructions, A system that includes this.

2. The system according to claim 1, further comprising means for responding to the user by voice and accurately confirming instructions.

3. The system according to claim 1, characterized in that the means for converting the aforementioned audio data into text uses an online speech recognition service.

Images