System

Abstract

A system is provided.SOLUTION: This system is provided with a voice input means, a means for transmitting voice data to a server, a means for converting the voice data into text data, a means for analyzing the text data and understanding the intention of a user, a means for retrieving relevant information from a database based on the analyzed result, and a means for returning the retrieved result to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern companies, employees use vast amounts of digital documents and databases to carry out their work. However, the lack of tools to quickly and accurately search these documents and data has led to a problem of reduced work efficiency. In particular, employees often waste time searching for related information and documents during meetings or while working on a computer. This situation causes interruptions to work and reduces overall business efficiency, so a solution is needed. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. The system of the present invention allows users to easily search for materials and information through voice input. Specifically, it uses a voice input means and includes a means for transmitting voice data to a server. The server converts the voice data into text data, analyzes the text data using natural language processing (NLP) means, and understands the user's intent. It also includes a means for searching a database for related information based on the analysis results and returning the search results to the user's terminal. This makes it possible to instantly provide necessary information during meetings or while working on a PC, preventing interruptions and reduced efficiency during work.

[0006] "Audio input means" refers to a device or software that records audio and converts it into digital data.

[0007] The "means for transmitting voice data to a server" refers to a device or software that transfers the acquired voice data to a server via a network.

[0008] A "means for converting voice data into text data" is a device or software that uses voice recognition technology to convert voice data into a human-readable text format.

[0009] The "means for analyzing text data to understand user intent" refers to a device or software that uses natural language processing technology to analyze the meaning of text data and understand the user's wishes.

[0010] The "means for searching a database for related information based on the analysis results" refers to a device or software that retrieves requested information by searching a database based on the analysis results of the text data.

[0011] The "means for returning search results to the user terminal" refers to a device or software that transmits the search results obtained from the server to the user terminal via the network.

[0012] The "means for searching for file names by voice input during a conference" refers to a device or software that allows a user to give voice instructions during a conference, and identifies and searches for file names from the voice.

[0013] "Means for searching for materials by voice instructions while working on a PC" refers to a device or software that allows a user to give voice instructions while working on a PC, and identifies and searches for the necessary materials from those voice instructions.

[0014] "Means for searching for tools or functions by voice instructions while using software" refers to a device or software that allows a user to give voice instructions while using the software, and then identifies and searches for the necessary tools or functions from those voice instructions.

[0015] "Providing appropriate information according to the user's intentions" means quickly identifying and providing the necessary information and operating procedures based on the user's voice instructions. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system for efficiently searching for documents and information during work using voice input. This system improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[0038] Overall system configuration

[0039] This system mainly consists of the following elements:

[0040] A device that receives user voice input

[0041] Server that processes received voice data

[0042] Speech Recognition Engine

[0043] Natural Language Processing (NLP) Engine

[0044] Database

[0045] Specific processing

[0046] In this system, when the user inputs voice, documents and information are searched and the results are returned to the user. The specific process is explained below.

[0047] 1. Acquiring voice input

[0048] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0049] Device: Records audio through a microphone and acquires it as audio data in real time.

[0050] 2. Sending audio data

[0051] Terminal: The acquired voice data is digitized and sent to the server via the network.

[0052] 3. Analysis of audio data

[0053] Server: Receives the voice data and converts it into text using a speech recognition engine.

[0054] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[0055] 4. Database Search

[0056] Server: Based on the analysis results of the NLP engine, it searches for relevant materials and information from the company's internal database.

[0057] 5. Returning search results

[0058] Server: Returns the materials and information found as search results to the device as text data.

[0059] Terminal: Displays the received search results to the user.

[0060] Specific examples

[0061] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[0062] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[0063] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[0064] Server: Search the database for files that correspond to "last year's financial statement."

[0065] Server: Returns "2022_Financial Report.pdf" to the terminal as the search result.

[0066] Terminal: Displays the report of findings to the user.

[0067] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[0068] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[0069] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[0070] Server: Retrieves information from a database about how to use the SUM function.

[0071] Server: Returns specific usage instructions and examples to the device as search results.

[0072] Terminal: Display the found information to the user.

[0073] In this way, this system uses voice input to quickly and accurately provide the materials and information the user desires, greatly improving work efficiency.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[0077] Step 2:

[0078] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[0079] Step 3:

[0080] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[0081] Step 4:

[0082] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[0083] Step 5:

[0084] The server searches the company's internal database based on the analysis results, and the NLP engine identifies files and information related to "this year's conference materials."

[0085] Step 6:

[0086] The server compiles the documents and information found as search results into text data and returns it to the device. For example, a file name or link such as "2023_ConferenceMaterials.pdf" is sent to the device.

[0087] Step 7:

[0088] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[0089] As a specific example, the process when the user inputs "Teach me how to use the SUM function" by voice will be described.

[0090] Step 1:

[0091] The user speaks, "Tell me how to use the SUM function." The device records this speech.

[0092] Step 2:

[0093] The device digitizes the recorded audio data and sends it to the server.

[0094] Step 3:

[0095] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[0096] Step 4:

[0097] The server analyzes the text data using an NLP engine to understand the user's intent. It identifies the phrase "how to use the SUM function" and determines that the user is looking for information on how to use the function.

[0098] Step 5:

[0099] The server searches a database based on the analysis results to identify information about the specific use of the SUM function.

[0100] Step 6:

[0101] The server compiles the usage methods and specific examples found as search results into text data and returns it to the terminal, including information on specific procedures and examples.

[0102] Step 7:

[0103] The terminal displays the information received to the user. Specific instructions and procedures for using the SUM function are displayed on the screen so that the user can refer to the information.

[0104] In this way, information that meets the user's request is provided through specific steps.

[0105] Example 1

[0106] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0107] In today's information society, it is extremely important for users to be able to quickly search for the information they need from vast amounts of documents and databases, thereby improving work efficiency. Furthermore, if users could search for information by voice input without using their hands during meetings or while working, convenience for users would be greatly improved. However, conventional systems lack the precision and speed of voice-input searches, making it difficult to accurately understand the user's intent and provide appropriate information.

[0108] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0109] In this invention, the server includes a voice input means, a means for digitizing voice data and transmitting it to the server, a voice recognition means for converting the voice data into text data, a natural language processing means for analyzing the text data and understanding the user's intention, a means for searching a database for related information based on the analysis results, and a means for returning the search results to the terminal and displaying them to the user. This enables the user to quickly search for materials and information using voice input and obtain the information they need efficiently and accurately.

[0110] The "voice input means" is a device or function that picks up the user's voice and acquires it as digital voice data.

[0111] The "means for digitizing audio data and transmitting it to a server" is a process or method for converting analog audio data into a digital signal and transmitting it to a server over a network.

[0112] "Speech recognition means" refers to a technique or device for analyzing voice data and converting it into text data.

[0113] A "natural language processing means" is a technology or device that analyzes acquired text data, understands the context and meaning, and interprets the user's intentions.

[0114] A "means for retrieving relevant information from a database" is a process or method for retrieving relevant information in a database using an automatically generated query.

[0115] "Means for returning search results to the terminal for display to the user" means the process or method by which search results are organized, transmitted to the terminal, and presented to the user in a visual or other format.

[0116] The present invention relates to a system that uses voice input to efficiently search for materials and information needed while a user is working. This system significantly improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[0117] Overall system configuration

[0118] The system mainly consists of the following elements:

[0119] A device that receives user voice input

[0120] Server that processes received voice data

[0121] Speech Recognition Engine

[0122] Natural Language Processing (NLP) Engine

[0123] Database

[0124] Voice input and data transmission

[0125] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0126] Device: Records audio through a built-in microphone or a connected microphone, and acquires it as audio data in real time. This audio data is first converted into a digital signal and then transmitted to a server via a network.

[0127] Analysis of audio data

[0128] Server: The received voice data is stored in storage and converted into text data using a speech recognition engine such as the Google Speech-to-Text API.The text data is then analyzed using a natural language processing (NLP) engine such as SpaCy or NLTK to understand the user's intent.

[0129] Database search

[0130] Server: Based on the user request analyzed by the NLP engine, generates SQL queries and other search queries to search for relevant materials and information from internal databases (e.g., MySQL, PostgreSQL).

[0131] Returning and displaying search results

[0132] Server: Organizes the search results, converts them into a format that is easy for the user to understand, and sends them back to the device.

[0133] Terminal: Displays the received search results on a user interface (UI), for example, in a browser window or a dedicated app.

[0134] Specific examples

[0135] Here is a concrete example of how the system works:

[0136] Searching for materials during a meeting

[0137] User: Says, "Show me last year's financial report."

[0138] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[0139] Server: The audio is converted to "Show me last year's financial report" using the Google Speech-to-Text API and analyzed using SpaCy.

[0140] Server: Run an SQL query against the MySQL database to find files that match "Last Year's Financial Report."

[0141] Server: Search for "2022_Financial Report.pdf" in the database, generate a link, and send it to the device.

[0142] On the device: Opens the received link in a browser window and displays the PDF to the user.

[0143] Search for how to use Excel

[0144] User: Say "How do I use the SUM function?"

[0145] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[0146] Server: Convert the audio into "How do I use the SUM function?" using the Google Speech-to-Text API, and analyze it using NLTK.

[0147] Server: Run a SQL query against the PostgreSQL database to find information about how to use the SUM function.

[0148] Server: Searches the database for specific usage methods and examples of the SUM function and sends the text information to the terminal.

[0149] Device: The received text information is displayed in a dedicated app, providing the user with instructions on how to use the device.

[0150] In this way, the user can efficiently search for materials and information through voice input, and quickly and accurately obtain the information he or she needs.

[0151] Examples of prompt statements

[0152] Here are some examples of input prompts for a generative AI model:

[0153] Search for meeting materials

[0154] A user says, "Show me last year's financial report." Describe the process to convert this into text, search the database for the relevant documents, and display them.

[0155] Search for how to use Excel

[0156] A user speaks, "Tell me how to use the SUM function." Describe the process to convert this to text, search the database for the relevant information, and display it.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0160] Input: User's voice

[0161] Output: Audio data

[0162] Specific operation: By speaking into the user's microphone, the audio is received through the device's built-in microphone or a connected microphone.

[0163] Step 2:

[0164] Device: Record audio in real time through the built-in microphone or an external microphone.

[0165] Input: Audio data

[0166] Output: Digital audio data

[0167] Specific operation: The recorded voice is converted into a digital signal by the terminal's voice input system and temporarily stored in memory.

[0168] Step 3:

[0169] Terminal: Transmits digitized voice data to a server via a network.

[0170] Input: Digital audio data

[0171] Output: Transmitted digital audio data

[0172] How it works: The device compresses the digital audio data and sends it over the Internet to a server using either HTTP or HTTPS.

[0173] Step 4:

[0174] Server: The received voice data is stored in storage and passed to the voice recognition engine.

[0175] Input: Transmitted digital audio data

[0176] Output: Saved audio and text data

[0177] Specific operation: The server temporarily stores the received voice data in storage, then sends it to a speech recognition engine and converts it into text data. This process is performed using, for example, the Google Speech-to-Text API.

[0178] Step 5:

[0179] Server: Converts voice data into text data using a speech recognition engine.

[0180] Input: Saved audio data

[0181] Output: Text data

[0182] Specific operation: Analyzes received voice data and converts it into corresponding text data. This is the process of converting spoken words into written information.

[0183] Step 6:

[0184] Server: Analyzes text data using a natural language processing (NLP) engine to understand the user's intent.

[0185] Input: Text data

[0186] Output: Parsed intent data

[0187] How it works: The server sends the text data to an NLP engine (e.g., SpaCy or NLTK) for contextual analysis and intent estimation, which identifies the information or resource the user is looking for.

[0188] Step 7:

[0189] Server: Searches for relevant materials and information from the database based on the user's request analyzed by the NLP engine.

[0190] Input: Parsed intent data

[0191] Output: Search result data

[0192] Specific operation: Based on the analysis results, the generated SQL query is sent to a database (e.g., MySQL, PostgreSQL) to perform a search. Related file names and information are identified.

[0193] Step 8:

[0194] Server: Organizes the search results and converts them into a format that is easy for the user to understand.

[0195] Input: Search result data

[0196] Output: Formatted data

[0197] Specific operation: Search results are converted into a data format such as JSON or XML, and formatted to be user-friendly, such as a file link or text information.

[0198] Step 9:

[0199] Server: Returns the formatted search results to the terminal via the network.

[0200] Input: Formatted data

[0201] Output: Search result data sent

[0202] Specific operation: The formatted data is returned to the terminal and communicated using the HTTP or HTTPS protocol.

[0203] Step 10:

[0204] Terminal: Displays the received search results on a user interface (UI).

[0205] Input: Submitted search result data

[0206] Output: Displayed information

[0207] What it does: It displays search results in a browser or dedicated app, allowing users to visually access information. For example, they can click links to open files or read text information.

[0208] (Application example 1)

[0209] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0210] Conventional voice-activated information search systems have been primarily used for office work and document search during meetings. However, in factories, there are many situations where workers cannot use their hands, so there is a need for a system that can easily check the location of parts and inventory information. In particular, in large factories, where there are many parts, manually searching for information is inefficient, making it difficult to improve work efficiency.

[0211] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0212] In this invention, the server includes a voice input means, a means for transmitting voice data to the server, a means for converting the voice data into text data, a means for searching a database for related information based on the analysis results, a means for returning the search results to a user terminal, and a means for issuing voice instructions to a factory robot to search for parts lists and inventory information. This makes it possible to quickly search for parts lists and inventory information using voice instructions within the factory, greatly improving work efficiency.

[0213] The "voice input means" refers to a device or software that receives a user's voice instruction and acquires it as voice data.

[0214] "Means for transmitting voice data to a server" refers to a method or technology for digitizing the acquired voice data and transmitting it to a server via a network.

[0215] "Means for converting voice data into text data" refers to software or algorithms that use voice recognition technology to convert voice data into text information.

[0216] "Means for analyzing text data to understand user intent" refers to a system or method that uses natural language processing technology to extract user requests and intent from text data.

[0217] "Means for searching for related information from a database based on the analysis results" refers to a technique or method for querying an internal database for relevant information based on the analysis results and obtaining the necessary data.

[0218] "Means for returning search results to the user terminal" refers to a system or protocol for sending the acquired data to the user terminal and notifying the user by display or voice.

[0219] "Means for giving voice instructions to factory robots to search for parts lists and inventory information" refers to a system or method for issuing voice commands to robots in a factory and searching for parts lists and inventory information based on those commands.

[0220] The present invention is a system for quickly searching for parts lists and inventory information within a factory. A specific embodiment of this system is shown below.

[0221] System configuration

[0222] This system consists of the following elements:

[0223] Voice input means

[0224] A means of sending audio data to the server

[0225] A means of converting audio data into text data

[0226] A means of analyzing text data to understand user intent

[0227] A means of searching for related information from a database based on the analysis results

[0228] A means for returning search results to the user's device

[0229] A way to give voice commands to factory robots to retrieve parts lists and inventory information

[0230] Hardware and software used

[0231] 1. Voice input method

[0232] Hardware: Microphone

[0233] Software: Voice input module (e.g. Google Cloud Speech-to-Text API)

[0234] 2. A method for sending audio data to the server

[0235] Hardware: The robot's processor

[0236] Software: Data transmission module

[0237] 3. Means of converting audio data into text data

[0238] Hardware: Server

[0239] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[0240] 4. A means of analyzing text data to understand user intent

[0241] Hardware: Server

[0242] Software: Natural Language Processing (NLP) engines (e.g., spaCy, OpenAI GPT-4)

[0243] 5. A means of searching databases for relevant information

[0244] Hardware: Server

[0245] Software: Database management system (e.g., MySQL, PostgreSQL)

[0246] 6. Means of returning search results to the user's device

[0247] Hardware: Server

[0248] Software: Data return module

[0249] 7. A way to give voice commands to factory robots to retrieve parts lists and inventory information.

[0250] Hardware: Factory robots

[0251] Software: Robot control system

[0252] Process Overview

[0253] This system allows users to quickly search for parts lists and inventory information within a factory by giving verbal instructions. When a user gives voice input, the voice data is picked up through a microphone, digitized, and sent to a server. On the server, the voice data is converted into text data using a speech recognition engine. A natural language processing (NLP) engine then analyzes the text data to understand the user's intent. Based on the results of the analysis, relevant parts lists and inventory information are searched for in the database, and this information is then sent back from the server to the user's device, specifically the robot. The robot can display the results on a screen or provide verbal feedback using a text-to-speech engine.

[0254] Specific examples

[0255] For example, consider the case where a worker voice-inputs, "Tell me the location of part B." The system operates as follows:

[0256] 1. The microphone picks up the voice message "Tell me the location of part B" and sends it to the server.

[0257] 2. The server's speech recognition engine converts this speech into text data such as "Tell me the location of part B."

[0258] 3. The NLP engine analyzes the text data and extracts the user's intent, such as "I want to know the location of part B."

[0259] 4. The server searches the database for the "location of part B" information and retrieves the result "Location: Shelf number A3."

[0260] 5. The result is sent back to the robot, which notifies the worker via the robot's display and speaker. A voice message is output saying, "Part B is located on shelf number A3."

[0261] Prompt Sentence Examples

[0262] Below is an example of a prompt to input to a generative AI model for speech analysis (e.g., OpenAI GPT-4):

[0263] Convert the user's voice input into text and analyze its intent. Analyze the following text, extract the user's intent and request, and generate a response.

[0264] Text: "What is the stock of part A?"

[0265] In this way, workers can instantly obtain information using voice instructions, greatly improving work efficiency within the factory.

[0266] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0267] Step 1:

[0268] The user inputs voice data using a voice input means (microphone), such as "Please tell me the stock of part A."

[0269] Input: User's voice command

[0270] Output: Audio data

[0271] Specific behavior: A user speaks into a microphone, "Tell me the inventory of part A." The microphone captures the voice signal.

[0272] Step 2:

[0273] The terminal digitizes the voice data for transmission to the server, and then transmits it to the server via the network using a data transmission module.

[0274] Input: Audio data

[0275] Output: Digitized audio data

[0276] What it does: Digitizes audio data and sends it to a server over the Internet or a local network.

[0277] Step 3:

[0278] The server receives the voice data and converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[0279] Input: Digitized audio data

[0280] Output: Text data

[0281] Specific operation: The server analyzes the voice data and converts it into text such as "Please tell me the stock of part A."

[0282] Step 4:

[0283] The server analyzes the text data using a natural language processing (NLP) engine (e.g., spaCy, OpenAI GPT-4) to understand the user's intent.

[0284] Input: Text data

[0285] Output: Analysis results including user intent

[0286] Specific operation: The NLP engine extracts the user's intent, such as "I want to know the inventory of part A."

[0287] Step 5:

[0288] Based on the analysis results, the server uses a database management system (e.g., MySQL, PostgreSQL) to search for relevant information from a database.

[0289] Input: Analysis results including user intent

[0290] Output: Search results (e.g., inventory information for part A)

[0291] Specific operation: The server searches the database for inventory information corresponding to "Part A" and obtains the necessary information (e.g., inventory quantity).

[0292] Step 6:

[0293] The server returns the search results to the user's terminal, and the data return module is used to deliver the results to the robot.

[0294] Input: Search results (e.g., inventory information for part A)

[0295] Output: Displayable data (text and audio formats)

[0296] Specific actions: Organize search results and return them to the robot as text data, including information for converting the text to speech.

[0297] Step 7:

[0298] The terminal (factory robot) receives the search results and displays them on a screen or provides audio feedback using a text-to-speech engine (e.g., Google Text-to-Speech API).

[0299] Input: Displayable data (text or audio format)

[0300] Output: Feedback to the user (visual or audio output)

[0301] Specific operation: The robot will announce "There are 30 units of part A in stock" by voice and display the stock information on the screen.

[0302] In this way, a system is realized that specifically describes how voice data is processed at each step and can quickly provide related information based on the user's voice instructions.

[0303] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0304] The present invention relates to a system that uses voice input to efficiently search for materials and information during work, and further recognizes the user's emotions and provides appropriate responses. This system aims to improve the user's work efficiency and user experience through voice input, voice recognition, natural language processing, database search, emotion recognition engine, and result feedback.

[0305] Overall system configuration

[0306] This system mainly consists of the following elements:

[0307] A device that receives user voice input

[0308] Server that processes received voice data

[0309] Speech Recognition Engine

[0310] Natural Language Processing (NLP) Engine

[0311] Database

[0312] Emotion Recognition Engine

[0313] Specific processing

[0314] In this system, when the user inputs voice, materials and information are searched for and an appropriate response is provided according to the user's emotions. The specific processing is explained below.

[0315] 1. Acquiring voice input

[0316] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0317] Device: Records audio through a microphone and acquires it as audio data in real time.

[0318] 2. Sending audio data

[0319] Terminal: The acquired voice data is digitized and sent to the server via the network.

[0320] 3. Analysis of audio data

[0321] Server: Receives the voice data and converts it into text using a speech recognition engine.

[0322] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[0323] 4. Emotional Recognition

[0324] Server: Uses an emotion recognition engine to analyze the user's emotional state from the voice data.

[0325] Server: As a result, identify the user's emotions, such as excited, anxious, relaxed, etc.

[0326] 5. Database Search

[0327] Server: Based on the analysis results of the NLP engine and emotion recognition, it searches for relevant materials and information from the company's internal database.

[0328] 6. Adjusting the results

[0329] Server: The server organizes the materials and information found as search results into an appropriate format based on the user's emotions and returns it to the device. For example, if the user is feeling anxious, the server may return the information in a format that emphasizes the main points.

[0330] 7. Returning search results

[0331] Server: Sends the compiled search results to the device. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf".

[0332] Terminal: Displays the received search results to the user.

[0333] Specific examples

[0334] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[0335] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[0336] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[0337] Server: The emotion recognition engine analyzes the emotions from the user's voice and determines, for example, that the user is relaxed.

[0338] Server: Search the database for files that correspond to "last year's financial statement."

[0339] Server: Returns search results in a format that includes detailed descriptions depending on the user's relaxed state.

[0340] Terminal: Display the found financial statements to the user.

[0341] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[0342] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[0343] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[0344] Server: The emotion recognition engine determines that the user is anxious.

[0345] Server: Retrieves information from a database about the specific use of the SUM function.

[0346] Server: Return search results in a concise format that emphasizes key points and is tailored to impatient users.

[0347] Terminal: Display the found information to the user.

[0348] In this way, by combining it with an emotion recognition engine, flexible responses that adapt to the user's emotional state become possible, greatly improving work efficiency and user experience.

[0349] The processing flow will be explained below.

[0350] Step 1:

[0351] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[0352] Step 2:

[0353] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[0354] Step 3:

[0355] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[0356] Step 4:

[0357] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[0358] Step 5:

[0359] The server uses an emotion recognition engine to analyze the user's emotional state from the voice data, analyzing the tone, speed, rhythm, etc. of the voice to identify emotions such as "excited," "anxious," or "relaxed."

[0360] Step 6:

[0361] The server searches the company database based on the analysis results of the NLP engine and emotion recognition, and identifies files and information related to "this year's conference materials."

[0362] Step 7:

[0363] The server summarizes the documents and information found as search results in an appropriate format depending on the user's emotional state. For example, if a user is in a hurry, the server summarizes the information in a concise format that emphasizes the main points.

[0364] Step 8:

[0365] The server sends the search results compiled by the server to the device as text data. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf."

[0366] Step 9:

[0367] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[0368] Specific examples

[0369] Consider the case where a user speaks, "Show me last year's financial statement."

[0370] Step 1:

[0371] The user inputs voice, and the terminal records the voice.

[0372] Step 2:

[0373] The device digitizes the recorded audio and sends it to the server.

[0374] Step 3:

[0375] The server receives the voice data and converts it into "Show me last year's financial statement" using a voice recognition engine.

[0376] Step 4:

[0377] The server analyzes the text data using an NLP engine and identifies the phrase "last year's financial report."

[0378] Step 5:

[0379] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is relaxed.

[0380] Step 6:

[0381] Based on the analysis results, the server searches the database for "last year's financial statement."

[0382] Step 7:

[0383] The server compiles the search results in a format that includes detailed descriptions tailored to the user who is relaxing.

[0384] Step 8:

[0385] The server sends the search results compiled to the terminal.

[0386] Step 9:

[0387] The terminal displays the received search results to the user.

[0388] Similarly, if the user says "Tell me how to use the SUM function," the following will happen:

[0389] Step 1:

[0390] The user gives voice input, and the device records the voice.

[0391] Step 2:

[0392] The device digitizes the recorded audio and sends it to the server.

[0393] Step 3:

[0394] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[0395] Step 4:

[0396] The server analyzes the text data using an NLP engine and identifies the phrase "How to use the SUM function."

[0397] Step 5:

[0398] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is anxious.

[0399] Step 6:

[0400] The server searches the database for how to use the SUM function based on the analysis results.

[0401] Step 7:

[0402] The server summarizes the information in a concise format that emphasizes key points.

[0403] Step 8:

[0404] The server sends the compiled information to the terminal.

[0405] Step 9:

[0406] The terminal displays the received information to the user.

[0407] In this way, through specific steps, information according to the user's request is provided, and the emotion engine makes it possible to respond according to the user's emotions.

[0408] Example 2

[0409] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0410] While conventional speech recognition systems allow users to search for information through voice input, they are unable to adjust responses based on the user's emotional state, resulting in a limited user experience and low effectiveness, especially in stressful situations. Furthermore, searches using only speech recognition and natural language processing have difficulty fully understanding the user's intent, resulting in the problem of displaying inappropriate results.

[0411] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0412] In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, and means for recognizing the user's emotional state, which makes it possible to present information in a format that is adapted to the user's emotions, thereby significantly improving work efficiency and the user experience.

[0413] The "voice input means" is a means for acquiring voice information uttered by the user.

[0414] The "means for transmitting voice data to a server" refers to a means for transmitting the acquired voice data to a server via a network.

[0415] The "means for converting voice data into text data" refers to a means for converting voice data into text data expressed as a character string.

[0416] "Means for analyzing text data to understand user intent" refers to means for processing text data and understanding the content of a user's requests or questions.

[0417] The "means for searching a database for related information based on the analysis results" refers to a means for searching a database for related information based on the user's intentions.

[0418] The "means for returning search results to the user terminal" refers to a means for transmitting search results obtained from the database to the user terminal.

[0419] The "means for recognizing the user's emotional state" is a means for determining the user's current emotions from the user's voice and other information.

[0420] The "means for adjusting search results according to the user's emotions" is a means for adjusting the display format and content of search results based on the recognized emotional state of the user.

[0421] This invention relates to a system that allows users to efficiently search for materials and information through voice input, and also recognizes the user's emotions and provides appropriate responses. The system aims to improve the user's work efficiency and experience through voice input, voice recognition, natural language processing, database search, an emotion recognition engine, and feedback of the results.

[0422] Overall system configuration

[0423] This system mainly consists of the following elements:

[0424] A device that receives user voice input

[0425] Server that processes received voice data

[0426] Speech recognition engine (e.g. Google Speech-to-Text API)

[0427] Natural Language Processing (NLP) engines (e.g., OpenAI's GPT-4)

[0428] Database (e.g. Microsoft SQL Server)

[0429] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[0430] Voice input and data processing flow

[0431] 1. Acquiring voice input

[0432] Users can make requests via voice input, such as "Show me this year's meeting materials."

[0433] The device records audio through a built-in microphone and converts the audio data into a digital format in real time.

[0434] 2. Sending audio data

[0435] The terminal compresses the digitized voice data and transmits it over the network to the server, where it also encrypts the data to ensure security.

[0436] 3. Analysis of audio data

[0437] The server receives the voice data and converts it into text using a speech recognition engine, which then analyzes it with a natural language processing (NLP) engine to understand the user's intent.

[0438] 4. Emotional Recognition

[0439] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, and as a result, identifies emotions such as excitement, impatience, or relaxation.

[0440] 5. Database Search

[0441] The server searches for relevant information from the company's internal database based on the analysis results of the natural language processing engine and the emotion recognition results.

[0442] 6. Adjusting the results

[0443] The server then organizes the search results into a format appropriate for the user's emotions, for example, highlighting key points for a user who is in a hurry, and including more detailed information for a user who is relaxed.

[0444] 7. Returning search results

[0445] The server sends the formatted search results to the terminal, which then displays the received search results to the user. For example, it displays a file name such as "2023_ConferenceMaterials.pdf" as a link so that the user can click it to access the document directly.

[0446] Specific examples

[0447] Example 1: Searching for documents during a meeting

[0448] Consider a case where a user voice-inputs "Show me last year's financial report" during a meeting.

[0449] Terminal: The voice "Show me last year's financial statement" is recorded with a microphone, digitized, compressed, and sent to the server.

[0450] Server: The speech recognition engine converts the request to "Show me last year's financial report," and the NLP engine analyzes it.

[0451] Server: Determines "relaxed" using emotion recognition engine. Searches for "last year's financial report" from the database and formats it with detailed explanations.

[0452] Server: The formatted results are returned to the terminal, and the terminal displays a link to "Last Year's Financial Report.pdf".

[0453] Users can click on the link provided to view the report.

[0454] Example 2: Excel work support

[0455] Consider the case where a user is working in Excel and says, "Tell me how to use the SUM function."

[0456] Terminal: Record the audio "Teach me how to use the SUM function," digitize it, compress it, and send it to the server.

[0457] Server: The speech recognition engine converts the request to "Please tell me how to use the SUM function," and the NLP engine analyzes it.

[0458] Server: The emotion recognition engine determines that the person is in a hurry. It searches the database for ways to use the SUM function and formats it to emphasize the main points.

[0459] Server: The formatted result is sent back to the terminal, and the terminal displays a link to "How to use the SUM function.pdf".

[0460] Users: Click the link provided to learn how to use it.

[0461] As described above, this system plays a specific role at each processing step, providing flexible responses while adapting to the user's emotional state, thereby significantly improving work efficiency and user experience.

[0462] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0463] Step 1:

[0464] Acquiring voice input

[0465] Users can make requests via voice input, such as "Show me this year's meeting materials."

[0466] The device uses a built-in microphone to record audio, and noise-canceling technology is used to capture clear audio data.

[0467] The input is the user's speech, and the output is recorded voice data.

[0468] Step 2:

[0469] Sending audio data

[0470] The device digitizes the acquired voice data and converts it into a file format.

[0471] The device compresses the digitized voice data and transmits it over the network to the server, encrypting the data for security reasons.

[0472] The input is recorded audio data, and the output is a compressed and encrypted audio file.

[0473] Step 3:

[0474] Analysis of audio data

[0475] The server decompresses the audio data received via the network and temporarily stores it.

[0476] The server converts the voice data into text data using a voice recognition engine (e.g., a general voice recognition API).

[0477] The server passes the converted text data to a natural language processing (NLP) engine (e.g., a general natural language processing model) to analyze the user's intent.

[0478] The input is a compressed and encrypted audio file, and the output is text data that represents the user's intent.

[0479] Step 4:

[0480] Emotion recognition

[0481] The server uses an emotion recognition engine (e.g., a general emotion recognition API) to analyze the user's emotional state from the text or voice data.

[0482] As a result of the analysis, the server identifies the user's emotions, such as excitement, impatience, or relaxation.

[0483] The input is text data and voice data, and the output is the analysis result of the user's emotional state.

[0484] Step 5:

[0485] Database search

[0486] The server searches for relevant information from an internal database (e.g., a general database system) based on the analysis results of the natural language processing engine and the emotion recognition results.

[0487] The server performs query optimization to deliver fast and accurate search results.

[0488] The input is text data and emotional state that reflects the user's intention, and the output is the search results for related information.

[0489] Step 6:

[0490] Adjusting the results

[0491] The server organizes the materials and information obtained as search results in an appropriate format according to the user's feelings.

[0492] For example, the server formats the results to highlight key points for a user who is in a hurry, or to include more detailed information for a user who is relaxed.

[0493] The input is the search results for related information and the user's emotional state, and the output is the formatted search results.

[0494] Step 7:

[0495] Returning search results

[0496] The server sends the formatted search results to the terminal.

[0497] The terminal displays the received search results to the user.

[0498] For example, the device will display a file name such as "2023_Conference Materials.pdf" in the form of a link, allowing the user to access the document directly by clicking on it.

[0499] The input is the formatted search results, and the output is the resource links displayed to the user.

[0500] (Application example 2)

[0501] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0502] While conventional voice input systems can properly understand a user's intentions and provide necessary information, they do not respond to the user's emotional state. As a result, they are unable to respond flexibly to situations, such as when the user is in a hurry or relaxed, which can lead to a poor user experience. Furthermore, in workplaces such as factories, robots are required to efficiently understand users' voice instructions and provide appropriate responses according to their emotional state.

[0503] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, means for recognizing the user's emotion, and means for adjusting search results in a format according to the emotion. This makes it possible to accurately understand the user's intention and provide appropriate information according to the user's emotional state.

[0504] The "voice input means" is a device for receiving the user's voice and recognizing it as digital voice data.

[0505] The "means for transmitting voice data to a server" is a function for transferring acquired voice data to a server via a network.

[0506] The "means for converting voice data into text data" is a process for converting voice data into linguistic text data using voice recognition technology.

[0507] "Means for analyzing text data to understand user intent" refers to a method that uses a natural language processing (NLP) engine to analyze the meaning of text data and understand what the user is looking for.

[0508] "Means for searching for related information from a database based on the analysis results" is a function for searching for related information from a database according to the intent analyzed by the NLP engine.

[0509] "Means for returning search results to the user terminal" refers to a method for transmitting data to the terminal in order to display the searched information or materials to the user.

[0510] "Means for recognizing user emotions" refers to technology for detecting the user's emotional state (for example, relaxed, anxious, excited, etc.) from voice data or text data.

[0511] The "means for adjusting search results in a format according to emotions" is a function for adjusting and providing information in a format or presentation method according to the recognized emotional state of the user.

[0512] The present invention relates to a system that uses voice input to efficiently search for information during work, and further recognizes the user's emotions and provides appropriate responses. This system is composed of the following elements:

[0513] Overall system configuration

[0514] 1. Voice input method:

[0515] A device for user voice input. This device can be integrated into a smartphone with a microphone, smart glasses, a head-mounted display, or a factory robot. This means is used to recognize the user's voice as digital audio data.

[0516] 2. How to send audio data to the server:

[0517] The voice data acquired by the voice input means has a function to transmit it to the server via the network. This means is important for transferring the voice data to the server quickly and accurately.

[0518] 3. How to convert audio data to text data:

[0519] The server converts the acquired voice data into text data using a voice recognition engine (e.g., Google API). Through this process, the voice data is interpreted as language text.

[0520] 4. Means of analyzing text data to understand user intent:

[0521] The server analyzes the text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, it clarifies what the user is looking for.

[0522] 5. How to recognize user emotions:

[0523] The server recognizes the user's emotional state from the analyzed text and voice data using an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tools). Emotional states such as "relaxed," "anxious," and "excited" are identified.

[0524] 6. How to tailor search results based on sentiment:

[0525] The server retrieves relevant information and tailors it to the user's emotional state, for example, returning information in a concise format that emphasizes key points if the user is in a hurry.

[0526] 7. Means for returning search results to the user's device:

[0527] The server sends the adjusted search results to the user's device, allowing the device to display the information the user needs in an appropriate format.

[0528] Specific examples

[0529] 1. Example during a meeting:

[0530] If a user speaks during a meeting, "Show me last year's financial report," the system operates as follows:

[0531] Device: Records audio and sends it to the server.

[0532] Server: Converts voice data into text data and analyzes the user's intent.

[0533] Server: Recognizes the user's emotional state, determining, for example, whether they are relaxed.

[0534] Server: Searches the database for the relevant financial statements and returns them in a detailed explanatory format.

[0535] Device: View search results.

[0536] 2. Example of program code:

[0537] Example prompt sentence:

[0538] User: "Show me last year's financial statements."

[0539] System: "Last year's financial report can be found at: Meeting Materials / 2023 / Financial Report.pdf."

[0540] or

[0541] User: "How do I use the SUM function?"

[0542] System: "(Key point) The SUM function calculates the sum of a range of numbers."

[0543] This system can provide necessary information quickly and appropriately based on the user's voice input and emotional state, which is expected to significantly improve user experience and work efficiency.

[0544] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0545] Step 1:

[0546] The user gives a voice command (e.g., "Show me last year's financial statement") through the voice input means. This voice input is recorded by the microphone of the terminal. The input is taken into the system as voice data. The output is the recorded voice data.

[0547] Step 2:

[0548] The device converts the captured voice data into a digital format and sends it to the server over the network. This step involves digitizing and transferring the voice data. The input is the recorded voice data, and the output is the digital voice data sent to the server.

[0549] Step 3:

[0550] The server converts the received voice data into text data using a speech recognition engine (e.g., Google API). This conversion is the process of converting voice signals into text information. The input is digital voice data, and the output is text data.

[0551] Step 4:

[0552] The server analyzes the generated text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, the text data is processed to analyze its grammar and meaning. The input is the text data, and the output is the analysis result (identification of the user's intent).

[0553] Step 5:

[0554] The server uses an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tool) to recognize the user's emotional state from the text data and characteristics specific to the voice. Here, the user's feeling tendency is analyzed. The input is text data, and the output is the user's emotional state (e.g., relaxed, anxious).

[0555] Step 6:

[0556] The server searches for relevant information from a database based on the NLP analysis results and emotion recognition results. Specifically, it extracts relevant database entries based on the user's instructions (e.g., "last year's financial report"). The input is the NLP analysis results and emotion recognition results, and the output is a list of relevant information.

[0557] Step 7:

[0558] The server tailors search results to reflect the user's emotional state. For example, if the user is in a hurry, the server modifies the information to emphasize key points and provide a concise format. The input is the user's emotional state and a list of related information, and the output is the tailored search results.

[0559] Step 8:

[0560] The server sends the adjusted search results to the terminal, which then displays the information the user needs in an appropriate format. The input is the adjusted search results, and the output is what is displayed to the user.

[0561] Step 9:

[0562] The device helps the user prepare for the next action based on the displayed information. The input is the user's action, and the output is preparation for the next step.

[0563] This system allows users to efficiently search for information using voice and receive information in the most appropriate format depending on their emotional state.

[0564] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0565] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0566] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0567] [Second embodiment]

[0568] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0569] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0570] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0571] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0572] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0573] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0574] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0575] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0576] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0577] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0578] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0579] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0580] The present invention relates to a system for efficiently searching for documents and information during work using voice input. This system improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[0581] Overall system configuration

[0582] This system mainly consists of the following elements:

[0583] A device that receives user voice input

[0584] Server that processes received voice data

[0585] Speech Recognition Engine

[0586] Natural Language Processing (NLP) Engine

[0587] Database

[0588] Specific processing

[0589] In this system, when the user inputs voice, documents and information are searched and the results are returned to the user. The specific process is explained below.

[0590] 1. Acquiring voice input

[0591] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0592] Device: Records audio through a microphone and acquires it as audio data in real time.

[0593] 2. Sending audio data

[0594] Terminal: The acquired voice data is digitized and sent to the server via the network.

[0595] 3. Analysis of audio data

[0596] Server: Receives the voice data and converts it into text using a speech recognition engine.

[0597] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[0598] 4. Database Search

[0599] Server: Based on the analysis results of the NLP engine, it searches for relevant materials and information from the company's internal database.

[0600] 5. Returning search results

[0601] Server: Returns the materials and information found as search results to the device as text data.

[0602] Terminal: Displays the received search results to the user.

[0603] Specific examples

[0604] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[0605] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[0606] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[0607] Server: Search the database for files that correspond to "last year's financial statement."

[0608] Server: Returns "2022_Financial Report.pdf" to the terminal as the search result.

[0609] Terminal: Displays the report of findings to the user.

[0610] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[0611] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[0612] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[0613] Server: Retrieves information from a database about how to use the SUM function.

[0614] Server: Returns specific usage instructions and examples to the device as search results.

[0615] Terminal: Display the found information to the user.

[0616] In this way, this system uses voice input to quickly and accurately provide the materials and information the user desires, greatly improving work efficiency.

[0617] The processing flow will be explained below.

[0618] Step 1:

[0619] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[0620] Step 2:

[0621] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[0622] Step 3:

[0623] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[0624] Step 4:

[0625] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[0626] Step 5:

[0627] The server searches the company's internal database based on the analysis results, and the NLP engine identifies files and information related to "this year's conference materials."

[0628] Step 6:

[0629] The server compiles the documents and information found as search results into text data and returns it to the device. For example, a file name or link such as "2023_ConferenceMaterials.pdf" is sent to the device.

[0630] Step 7:

[0631] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[0632] As a specific example, the process when the user inputs "Teach me how to use the SUM function" by voice will be described.

[0633] Step 1:

[0634] The user speaks, "Tell me how to use the SUM function." The device records this speech.

[0635] Step 2:

[0636] The device digitizes the recorded audio data and sends it to the server.

[0637] Step 3:

[0638] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[0639] Step 4:

[0640] The server analyzes the text data using an NLP engine to understand the user's intent. It identifies the phrase "how to use the SUM function" and determines that the user is looking for information on how to use the function.

[0641] Step 5:

[0642] The server searches a database based on the analysis results to identify information about the specific use of the SUM function.

[0643] Step 6:

[0644] The server compiles the usage methods and specific examples found as search results into text data and returns it to the terminal, including information on specific procedures and examples.

[0645] Step 7:

[0646] The terminal displays the information received to the user. Specific instructions and procedures for using the SUM function are displayed on the screen so that the user can refer to the information.

[0647] In this way, information that meets the user's request is provided through specific steps.

[0648] Example 1

[0649] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0650] In today's information society, it is extremely important for users to be able to quickly search for the information they need from vast amounts of documents and databases, thereby improving work efficiency. Furthermore, if users could search for information by voice input without using their hands during meetings or while working, convenience for users would be greatly improved. However, conventional systems lack the precision and speed of voice-input searches, making it difficult to accurately understand the user's intent and provide appropriate information.

[0651] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0652] In this invention, the server includes a voice input means, a means for digitizing voice data and transmitting it to the server, a voice recognition means for converting the voice data into text data, a natural language processing means for analyzing the text data and understanding the user's intention, a means for searching a database for related information based on the analysis results, and a means for returning the search results to the terminal and displaying them to the user. This enables the user to quickly search for materials and information using voice input and obtain the information they need efficiently and accurately.

[0653] The "voice input means" is a device or function that picks up the user's voice and acquires it as digital voice data.

[0654] The "means for digitizing audio data and transmitting it to a server" is a process or method for converting analog audio data into a digital signal and transmitting it to a server over a network.

[0655] "Speech recognition means" refers to a technique or device for analyzing voice data and converting it into text data.

[0656] A "natural language processing means" is a technology or device that analyzes acquired text data, understands the context and meaning, and interprets the user's intentions.

[0657] A "means for retrieving relevant information from a database" is a process or method for retrieving relevant information in a database using an automatically generated query.

[0658] "Means for returning search results to the terminal for display to the user" means the process or method by which search results are organized, transmitted to the terminal, and presented to the user in a visual or other format.

[0659] The present invention relates to a system that uses voice input to efficiently search for materials and information needed while a user is working. This system significantly improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[0660] Overall system configuration

[0661] The system mainly consists of the following elements:

[0662] A device that receives user voice input

[0663] Server that processes received voice data

[0664] Speech Recognition Engine

[0665] Natural Language Processing (NLP) Engine

[0666] Database

[0667] Voice input and data transmission

[0668] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0669] Device: Records audio through a built-in microphone or a connected microphone, and acquires it as audio data in real time. This audio data is first converted into a digital signal and then transmitted to a server via a network.

[0670] Analysis of audio data

[0671] Server: The received voice data is stored in storage and converted into text data using a speech recognition engine such as the Google Speech-to-Text API.The text data is then analyzed using a natural language processing (NLP) engine such as SpaCy or NLTK to understand the user's intent.

[0672] Database search

[0673] Server: Based on the user request analyzed by the NLP engine, generates SQL queries and other search queries to search for relevant materials and information from internal databases (e.g., MySQL, PostgreSQL).

[0674] Returning and displaying search results

[0675] Server: Organizes the search results, converts them into a format that is easy for the user to understand, and sends them back to the device.

[0676] Terminal: Displays the received search results on a user interface (UI), for example, in a browser window or a dedicated app.

[0677] Specific examples

[0678] Here is a concrete example of how the system works:

[0679] Searching for materials during a meeting

[0680] User: Says, "Show me last year's financial report."

[0681] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[0682] Server: The audio is converted to "Show me last year's financial report" using the Google Speech-to-Text API and analyzed using SpaCy.

[0683] Server: Run an SQL query against the MySQL database to find files that match "Last Year's Financial Report."

[0684] Server: Search for "2022_Financial Report.pdf" in the database, generate a link, and send it to the device.

[0685] On the device: Opens the received link in a browser window and displays the PDF to the user.

[0686] Search for how to use Excel

[0687] User: Say "How do I use the SUM function?"

[0688] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[0689] Server: Convert the audio into "How do I use the SUM function?" using the Google Speech-to-Text API, and analyze it using NLTK.

[0690] Server: Run a SQL query against the PostgreSQL database to find information about how to use the SUM function.

[0691] Server: Searches the database for specific usage methods and examples of the SUM function and sends the text information to the terminal.

[0692] Device: The received text information is displayed in a dedicated app, providing the user with instructions on how to use the device.

[0693] In this way, the user can efficiently search for materials and information through voice input, and quickly and accurately obtain the information he or she needs.

[0694] Examples of prompt statements

[0695] Here are some examples of input prompts for a generative AI model:

[0696] Search for meeting materials

[0697] A user says, "Show me last year's financial report." Describe the process to convert this into text, search the database for the relevant documents, and display them.

[0698] Search for how to use Excel

[0699] A user speaks, "Tell me how to use the SUM function." Describe the process to convert this to text, search the database for the relevant information, and display it.

[0700] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0701] Step 1:

[0702] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0703] Input: User's voice

[0704] Output: Audio data

[0705] Specific operation: By speaking into the user's microphone, the audio is received through the device's built-in microphone or a connected microphone.

[0706] Step 2:

[0707] Device: Record audio in real time through the built-in microphone or an external microphone.

[0708] Input: Audio data

[0709] Output: Digital audio data

[0710] Specific operation: The recorded voice is converted into a digital signal by the terminal's voice input system and temporarily stored in memory.

[0711] Step 3:

[0712] Terminal: Transmits digitized voice data to a server via a network.

[0713] Input: Digital audio data

[0714] Output: Transmitted digital audio data

[0715] How it works: The device compresses the digital audio data and sends it over the Internet to a server using either HTTP or HTTPS.

[0716] Step 4:

[0717] Server: The received voice data is stored in storage and passed to the voice recognition engine.

[0718] Input: Transmitted digital audio data

[0719] Output: Saved audio and text data

[0720] Specific operation: The server temporarily stores the received voice data in storage, then sends it to a speech recognition engine and converts it into text data. This process is performed using, for example, the Google Speech-to-Text API.

[0721] Step 5:

[0722] Server: Converts voice data into text data using a speech recognition engine.

[0723] Input: Saved audio data

[0724] Output: Text data

[0725] Specific operation: Analyzes received voice data and converts it into corresponding text data. This is the process of converting spoken words into written information.

[0726] Step 6:

[0727] Server: Analyzes text data using a natural language processing (NLP) engine to understand the user's intent.

[0728] Input: Text data

[0729] Output: Parsed intent data

[0730] How it works: The server sends the text data to an NLP engine (e.g., SpaCy or NLTK) for contextual analysis and intent estimation, which identifies the information or resource the user is looking for.

[0731] Step 7:

[0732] Server: Searches for relevant materials and information from the database based on the user's request analyzed by the NLP engine.

[0733] Input: Parsed intent data

[0734] Output: Search result data

[0735] Specific operation: Based on the analysis results, the generated SQL query is sent to a database (e.g., MySQL, PostgreSQL) to perform a search. Related file names and information are identified.

[0736] Step 8:

[0737] Server: Organizes the search results and converts them into a format that is easy for the user to understand.

[0738] Input: Search result data

[0739] Output: Formatted data

[0740] Specific operation: Search results are converted into a data format such as JSON or XML, and formatted to be user-friendly, such as a file link or text information.

[0741] Step 9:

[0742] Server: Returns the formatted search results to the terminal via the network.

[0743] Input: Formatted data

[0744] Output: Search result data sent

[0745] Specific operation: The formatted data is returned to the terminal and communicated using the HTTP or HTTPS protocol.

[0746] Step 10:

[0747] Terminal: Displays the received search results on a user interface (UI).

[0748] Input: Submitted search result data

[0749] Output: Displayed information

[0750] What it does: It displays search results in a browser or dedicated app, allowing users to visually access information. For example, they can click links to open files or read text information.

[0751] (Application example 1)

[0752] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0753] Conventional voice-activated information search systems have been primarily used for office work and document search during meetings. However, in factories, there are many situations where workers cannot use their hands, so there is a need for a system that can easily check the location of parts and inventory information. In particular, in large factories, where there are many parts, manually searching for information is inefficient, making it difficult to improve work efficiency.

[0754] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0755] In this invention, the server includes a voice input means, a means for transmitting voice data to the server, a means for converting the voice data into text data, a means for searching a database for related information based on the analysis results, a means for returning the search results to a user terminal, and a means for issuing voice instructions to a factory robot to search for parts lists and inventory information. This makes it possible to quickly search for parts lists and inventory information using voice instructions within the factory, greatly improving work efficiency.

[0756] The "voice input means" refers to a device or software that receives a user's voice instruction and acquires it as voice data.

[0757] "Means for transmitting voice data to a server" refers to a method or technology for digitizing the acquired voice data and transmitting it to a server via a network.

[0758] "Means for converting voice data into text data" refers to software or algorithms that use voice recognition technology to convert voice data into text information.

[0759] "Means for analyzing text data to understand user intent" refers to a system or method that uses natural language processing technology to extract user requests and intent from text data.

[0760] "Means for searching for related information from a database based on the analysis results" refers to a technique or method for querying an internal database for relevant information based on the analysis results and obtaining the necessary data.

[0761] "Means for returning search results to the user terminal" refers to a system or protocol for sending the acquired data to the user terminal and notifying the user by display or voice.

[0762] "Means for giving voice instructions to factory robots to search for parts lists and inventory information" refers to a system or method for issuing voice commands to robots in a factory and searching for parts lists and inventory information based on those commands.

[0763] The present invention is a system for quickly searching for parts lists and inventory information within a factory. A specific embodiment of this system is shown below.

[0764] System configuration

[0765] This system consists of the following elements:

[0766] Voice input means

[0767] A means of sending audio data to the server

[0768] A means of converting audio data into text data

[0769] A means of analyzing text data to understand user intent

[0770] A means of searching for related information from a database based on the analysis results

[0771] A means for returning search results to the user's device

[0772] A way to give voice commands to factory robots to retrieve parts lists and inventory information

[0773] Hardware and software used

[0774] 1. Voice input method

[0775] Hardware: Microphone

[0776] Software: Voice input module (e.g. Google Cloud Speech-to-Text API)

[0777] 2. A method for sending audio data to the server

[0778] Hardware: The robot's processor

[0779] Software: Data transmission module

[0780] 3. Means of converting audio data into text data

[0781] Hardware: Server

[0782] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[0783] 4. A means of analyzing text data to understand user intent

[0784] Hardware: Server

[0785] Software: Natural Language Processing (NLP) engines (e.g., spaCy, OpenAI GPT-4)

[0786] 5. A means of searching databases for relevant information

[0787] Hardware: Server

[0788] Software: Database management system (e.g., MySQL, PostgreSQL)

[0789] 6. Means of returning search results to the user's device

[0790] Hardware: Server

[0791] Software: Data return module

[0792] 7. A way to give voice commands to factory robots to retrieve parts lists and inventory information.

[0793] Hardware: Factory robots

[0794] Software: Robot control system

[0795] Process Overview

[0796] This system allows users to quickly search for parts lists and inventory information within a factory by giving verbal instructions. When a user gives voice input, the voice data is picked up through a microphone, digitized, and sent to a server. On the server, the voice data is converted into text data using a speech recognition engine. A natural language processing (NLP) engine then analyzes the text data to understand the user's intent. Based on the results of the analysis, relevant parts lists and inventory information are searched for in the database, and this information is then sent back from the server to the user's device, specifically the robot. The robot can display the results on a screen or provide verbal feedback using a text-to-speech engine.

[0797] Specific examples

[0798] For example, consider the case where a worker voice-inputs, "Tell me the location of part B." The system operates as follows:

[0799] 1. The microphone picks up the voice message "Tell me the location of part B" and sends it to the server.

[0800] 2. The server's speech recognition engine converts this speech into text data such as "Tell me the location of part B."

[0801] 3. The NLP engine analyzes the text data and extracts the user's intent, such as "I want to know the location of part B."

[0802] 4. The server searches the database for the "location of part B" information and retrieves the result "Location: Shelf number A3."

[0803] 5. The result is sent back to the robot, which notifies the worker via the robot's display and speaker. A voice message is output saying, "Part B is located on shelf number A3."

[0804] Prompt Sentence Examples

[0805] Below is an example of a prompt to input to a generative AI model for speech analysis (e.g., OpenAI GPT-4):

[0806] Convert the user's voice input into text and analyze its intent. Analyze the following text, extract the user's intent and request, and generate a response.

[0807] Text: "What is the stock of part A?"

[0808] In this way, workers can instantly obtain information using voice instructions, greatly improving work efficiency within the factory.

[0809] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0810] Step 1:

[0811] The user inputs voice data using a voice input means (microphone), such as "Please tell me the stock of part A."

[0812] Input: User's voice command

[0813] Output: Audio data

[0814] Specific behavior: A user speaks into a microphone, "Tell me the inventory of part A." The microphone captures the voice signal.

[0815] Step 2:

[0816] The terminal digitizes the voice data for transmission to the server, and then transmits it to the server via the network using a data transmission module.

[0817] Input: Audio data

[0818] Output: Digitized audio data

[0819] What it does: Digitizes audio data and sends it to a server over the Internet or a local network.

[0820] Step 3:

[0821] The server receives the voice data and converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[0822] Input: Digitized audio data

[0823] Output: Text data

[0824] Specific operation: The server analyzes the voice data and converts it into text such as "Please tell me the stock of part A."

[0825] Step 4:

[0826] The server analyzes the text data using a natural language processing (NLP) engine (e.g., spaCy, OpenAI GPT-4) to understand the user's intent.

[0827] Input: Text data

[0828] Output: Analysis results including user intent

[0829] Specific operation: The NLP engine extracts the user's intent, such as "I want to know the inventory of part A."

[0830] Step 5:

[0831] Based on the analysis results, the server uses a database management system (e.g., MySQL, PostgreSQL) to search for relevant information from a database.

[0832] Input: Analysis results including user intent

[0833] Output: Search results (e.g., inventory information for part A)

[0834] Specific operation: The server searches the database for inventory information corresponding to "Part A" and obtains the necessary information (e.g., inventory quantity).

[0835] Step 6:

[0836] The server returns the search results to the user's terminal, and the data return module is used to deliver the results to the robot.

[0837] Input: Search results (e.g., inventory information for part A)

[0838] Output: Displayable data (text and audio formats)

[0839] Specific actions: Organize search results and return them to the robot as text data, including information for converting the text to speech.

[0840] Step 7:

[0841] The terminal (factory robot) receives the search results and displays them on a screen or provides audio feedback using a text-to-speech engine (e.g., Google Text-to-Speech API).

[0842] Input: Displayable data (text or audio format)

[0843] Output: Feedback to the user (visual or audio output)

[0844] Specific operation: The robot will announce "There are 30 units of part A in stock" by voice and display the stock information on the screen.

[0845] In this way, a system is realized that specifically describes how voice data is processed at each step and can quickly provide related information based on the user's voice instructions.

[0846] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0847] The present invention relates to a system that uses voice input to efficiently search for materials and information during work, and further recognizes the user's emotions and provides appropriate responses. This system aims to improve the user's work efficiency and user experience through voice input, voice recognition, natural language processing, database search, emotion recognition engine, and result feedback.

[0848] Overall system configuration

[0849] This system mainly consists of the following elements:

[0850] A device that receives user voice input

[0851] Server that processes received voice data

[0852] Speech Recognition Engine

[0853] Natural Language Processing (NLP) Engine

[0854] Database

[0855] Emotion Recognition Engine

[0856] Specific processing

[0857] In this system, when the user inputs voice, materials and information are searched for and an appropriate response is provided according to the user's emotions. The specific processing is explained below.

[0858] 1. Acquiring voice input

[0859] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[0860] Device: Records audio through a microphone and acquires it as audio data in real time.

[0861] 2. Sending audio data

[0862] Terminal: The acquired voice data is digitized and sent to the server via the network.

[0863] 3. Analysis of audio data

[0864] Server: Receives the voice data and converts it into text using a speech recognition engine.

[0865] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[0866] 4. Emotional Recognition

[0867] Server: Uses an emotion recognition engine to analyze the user's emotional state from the voice data.

[0868] Server: As a result, identify the user's emotions, such as excited, anxious, relaxed, etc.

[0869] 5. Database Search

[0870] Server: Based on the analysis results of the NLP engine and emotion recognition, it searches for relevant materials and information from the company's internal database.

[0871] 6. Adjusting the results

[0872] Server: The server organizes the materials and information found as search results into an appropriate format based on the user's emotions and returns it to the device. For example, if the user is feeling anxious, the server may return the information in a format that emphasizes the main points.

[0873] 7. Returning search results

[0874] Server: Sends the compiled search results to the device. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf".

[0875] Terminal: Displays the received search results to the user.

[0876] Specific examples

[0877] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[0878] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[0879] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[0880] Server: The emotion recognition engine analyzes the emotions from the user's voice and determines, for example, that the user is relaxed.

[0881] Server: Search the database for files that correspond to "last year's financial statement."

[0882] Server: Returns search results in a format that includes detailed descriptions depending on the user's relaxed state.

[0883] Terminal: Display the found financial statements to the user.

[0884] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[0885] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[0886] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[0887] Server: The emotion recognition engine determines that the user is anxious.

[0888] Server: Retrieves information from a database about the specific use of the SUM function.

[0889] Server: Return search results in a concise format that emphasizes key points and is tailored to impatient users.

[0890] Terminal: Display the found information to the user.

[0891] In this way, by combining it with an emotion recognition engine, flexible responses that adapt to the user's emotional state become possible, greatly improving work efficiency and user experience.

[0892] The processing flow will be explained below.

[0893] Step 1:

[0894] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[0895] Step 2:

[0896] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[0897] Step 3:

[0898] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[0899] Step 4:

[0900] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[0901] Step 5:

[0902] The server uses an emotion recognition engine to analyze the user's emotional state from the voice data, analyzing the tone, speed, rhythm, etc. of the voice to identify emotions such as "excited," "anxious," or "relaxed."

[0903] Step 6:

[0904] The server searches the company database based on the analysis results of the NLP engine and emotion recognition, and identifies files and information related to "this year's conference materials."

[0905] Step 7:

[0906] The server summarizes the documents and information found as search results in an appropriate format depending on the user's emotional state. For example, if a user is in a hurry, the server summarizes the information in a concise format that emphasizes the main points.

[0907] Step 8:

[0908] The server sends the search results compiled by the server to the device as text data. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf."

[0909] Step 9:

[0910] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[0911] Specific examples

[0912] Consider the case where a user speaks, "Show me last year's financial statement."

[0913] Step 1:

[0914] The user inputs voice, and the terminal records the voice.

[0915] Step 2:

[0916] The device digitizes the recorded audio and sends it to the server.

[0917] Step 3:

[0918] The server receives the voice data and converts it into "Show me last year's financial statement" using a voice recognition engine.

[0919] Step 4:

[0920] The server analyzes the text data using an NLP engine and identifies the phrase "last year's financial report."

[0921] Step 5:

[0922] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is relaxed.

[0923] Step 6:

[0924] Based on the analysis results, the server searches the database for "last year's financial statement."

[0925] Step 7:

[0926] The server compiles the search results in a format that includes detailed descriptions tailored to the user who is relaxing.

[0927] Step 8:

[0928] The server sends the search results compiled to the terminal.

[0929] Step 9:

[0930] The terminal displays the received search results to the user.

[0931] Similarly, if the user says "Tell me how to use the SUM function," the following will happen:

[0932] Step 1:

[0933] The user gives voice input, and the device records the voice.

[0934] Step 2:

[0935] The device digitizes the recorded audio and sends it to the server.

[0936] Step 3:

[0937] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[0938] Step 4:

[0939] The server analyzes the text data using an NLP engine and identifies the phrase "How to use the SUM function."

[0940] Step 5:

[0941] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is anxious.

[0942] Step 6:

[0943] The server searches the database for how to use the SUM function based on the analysis results.

[0944] Step 7:

[0945] The server summarizes the information in a concise format that emphasizes key points.

[0946] Step 8:

[0947] The server sends the compiled information to the terminal.

[0948] Step 9:

[0949] The terminal displays the received information to the user.

[0950] In this way, through specific steps, information according to the user's request is provided, and the emotion engine makes it possible to respond according to the user's emotions.

[0951] Example 2

[0952] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0953] While conventional speech recognition systems allow users to search for information through voice input, they are unable to adjust responses based on the user's emotional state, resulting in a limited user experience and low effectiveness, especially in stressful situations. Furthermore, searches using only speech recognition and natural language processing have difficulty fully understanding the user's intent, resulting in the problem of displaying inappropriate results.

[0954] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0955] In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, and means for recognizing the user's emotional state, which makes it possible to present information in a format that is adapted to the user's emotions, thereby significantly improving work efficiency and the user experience.

[0956] The "voice input means" is a means for acquiring voice information uttered by the user.

[0957] The "means for transmitting voice data to a server" refers to a means for transmitting the acquired voice data to a server via a network.

[0958] The "means for converting voice data into text data" refers to a means for converting voice data into text data expressed as a character string.

[0959] "Means for analyzing text data to understand user intent" refers to means for processing text data and understanding the content of a user's requests or questions.

[0960] The "means for searching a database for related information based on the analysis results" refers to a means for searching a database for related information based on the user's intentions.

[0961] The "means for returning search results to the user terminal" refers to a means for transmitting search results obtained from the database to the user terminal.

[0962] The "means for recognizing the user's emotional state" is a means for determining the user's current emotions from the user's voice and other information.

[0963] The "means for adjusting search results according to the user's emotions" is a means for adjusting the display format and content of search results based on the recognized emotional state of the user.

[0964] This invention relates to a system that allows users to efficiently search for materials and information through voice input, and also recognizes the user's emotions and provides appropriate responses. The system aims to improve the user's work efficiency and experience through voice input, voice recognition, natural language processing, database search, an emotion recognition engine, and feedback of the results.

[0965] Overall system configuration

[0966] This system mainly consists of the following elements:

[0967] A device that receives user voice input

[0968] Server that processes received voice data

[0969] Speech recognition engine (e.g. Google Speech-to-Text API)

[0970] Natural Language Processing (NLP) engines (e.g., OpenAI's GPT-4)

[0971] Database (e.g. Microsoft SQL Server)

[0972] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[0973] Voice input and data processing flow

[0974] 1. Acquiring voice input

[0975] Users can make requests via voice input, such as "Show me this year's meeting materials."

[0976] The device records audio through a built-in microphone and converts the audio data into a digital format in real time.

[0977] 2. Sending audio data

[0978] The terminal compresses the digitized voice data and transmits it over the network to the server, where it also encrypts the data to ensure security.

[0979] 3. Analysis of audio data

[0980] The server receives the voice data and converts it into text using a speech recognition engine, which then analyzes it with a natural language processing (NLP) engine to understand the user's intent.

[0981] 4. Emotional Recognition

[0982] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, and as a result, identifies emotions such as excitement, impatience, or relaxation.

[0983] 5. Database Search

[0984] The server searches for relevant information from the company's internal database based on the analysis results of the natural language processing engine and the emotion recognition results.

[0985] 6. Adjusting the results

[0986] The server then organizes the search results into a format appropriate for the user's emotions, for example, highlighting key points for a user who is in a hurry, and including more detailed information for a user who is relaxed.

[0987] 7. Returning search results

[0988] The server sends the formatted search results to the terminal, which then displays the received search results to the user. For example, it displays a file name such as "2023_ConferenceMaterials.pdf" as a link so that the user can click it to access the document directly.

[0989] Specific examples

[0990] Example 1: Searching for documents during a meeting

[0991] Consider a case where a user voice-inputs "Show me last year's financial report" during a meeting.

[0992] Terminal: The voice "Show me last year's financial statement" is recorded with a microphone, digitized, compressed, and sent to the server.

[0993] Server: The speech recognition engine converts the request to "Show me last year's financial report," and the NLP engine analyzes it.

[0994] Server: Determines "relaxed" using emotion recognition engine. Searches for "last year's financial report" from the database and formats it with detailed explanations.

[0995] Server: The formatted results are returned to the terminal, and the terminal displays a link to "Last Year's Financial Report.pdf".

[0996] Users can click on the link provided to view the report.

[0997] Example 2: Excel work support

[0998] Consider the case where a user is working in Excel and says, "Tell me how to use the SUM function."

[0999] Terminal: Record the audio "Teach me how to use the SUM function," digitize it, compress it, and send it to the server.

[1000] Server: The speech recognition engine converts the request to "Please tell me how to use the SUM function," and the NLP engine analyzes it.

[1001] Server: The emotion recognition engine determines that the person is in a hurry. It searches the database for ways to use the SUM function and formats it to emphasize the main points.

[1002] Server: The formatted result is sent back to the terminal, and the terminal displays a link to "How to use the SUM function.pdf".

[1003] Users: Click the link provided to learn how to use it.

[1004] As described above, this system plays a specific role at each processing step, providing flexible responses while adapting to the user's emotional state, thereby significantly improving work efficiency and user experience.

[1005] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1006] Step 1:

[1007] Acquiring voice input

[1008] Users can make requests via voice input, such as "Show me this year's meeting materials."

[1009] The device uses a built-in microphone to record audio, and noise-canceling technology is used to capture clear audio data.

[1010] The input is the user's speech, and the output is recorded voice data.

[1011] Step 2:

[1012] Sending audio data

[1013] The device digitizes the acquired voice data and converts it into a file format.

[1014] The device compresses the digitized voice data and transmits it over the network to the server, encrypting the data for security reasons.

[1015] The input is recorded audio data, and the output is a compressed and encrypted audio file.

[1016] Step 3:

[1017] Analysis of audio data

[1018] The server decompresses the audio data received via the network and temporarily stores it.

[1019] The server converts the voice data into text data using a voice recognition engine (e.g., a general voice recognition API).

[1020] The server passes the converted text data to a natural language processing (NLP) engine (e.g., a general natural language processing model) to analyze the user's intent.

[1021] The input is a compressed and encrypted audio file, and the output is text data that represents the user's intent.

[1022] Step 4:

[1023] Emotion recognition

[1024] The server uses an emotion recognition engine (e.g., a general emotion recognition API) to analyze the user's emotional state from the text or voice data.

[1025] As a result of the analysis, the server identifies the user's emotions, such as excitement, impatience, or relaxation.

[1026] The input is text data and voice data, and the output is the analysis result of the user's emotional state.

[1027] Step 5:

[1028] Database search

[1029] The server searches for relevant information from an internal database (e.g., a general database system) based on the analysis results of the natural language processing engine and the emotion recognition results.

[1030] The server performs query optimization to deliver fast and accurate search results.

[1031] The input is text data and emotional state that reflects the user's intention, and the output is the search results for related information.

[1032] Step 6:

[1033] Adjusting the results

[1034] The server organizes the materials and information obtained as search results in an appropriate format according to the user's feelings.

[1035] For example, the server formats the results to highlight key points for a user who is in a hurry, or to include more detailed information for a user who is relaxed.

[1036] The input is the search results for related information and the user's emotional state, and the output is the formatted search results.

[1037] Step 7:

[1038] Returning search results

[1039] The server sends the formatted search results to the terminal.

[1040] The terminal displays the received search results to the user.

[1041] For example, the device will display a file name such as "2023_Conference Materials.pdf" in the form of a link, allowing the user to access the document directly by clicking on it.

[1042] The input is the formatted search results, and the output is the resource links displayed to the user.

[1043] (Application example 2)

[1044] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1045] While conventional voice input systems can properly understand a user's intentions and provide necessary information, they do not respond to the user's emotional state. As a result, they are unable to respond flexibly to situations, such as when the user is in a hurry or relaxed, which can lead to a poor user experience. Furthermore, in workplaces such as factories, robots are required to efficiently understand users' voice instructions and provide appropriate responses according to their emotional state.

[1046] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, means for recognizing the user's emotion, and means for adjusting search results in a format according to the emotion. This makes it possible to accurately understand the user's intention and provide appropriate information according to the user's emotional state.

[1047] The "voice input means" is a device for receiving the user's voice and recognizing it as digital voice data.

[1048] The "means for transmitting voice data to a server" is a function for transferring acquired voice data to a server via a network.

[1049] The "means for converting voice data into text data" is a process for converting voice data into linguistic text data using voice recognition technology.

[1050] "Means for analyzing text data to understand user intent" refers to a method that uses a natural language processing (NLP) engine to analyze the meaning of text data and understand what the user is looking for.

[1051] "Means for searching for related information from a database based on the analysis results" is a function for searching for related information from a database according to the intent analyzed by the NLP engine.

[1052] "Means for returning search results to the user terminal" refers to a method for transmitting data to the terminal in order to display the searched information or materials to the user.

[1053] "Means for recognizing user emotions" refers to technology for detecting the user's emotional state (for example, relaxed, anxious, excited, etc.) from voice data or text data.

[1054] The "means for adjusting search results in a format according to emotions" is a function for adjusting and providing information in a format or presentation method according to the recognized emotional state of the user.

[1055] The present invention relates to a system that uses voice input to efficiently search for information during work, and further recognizes the user's emotions and provides appropriate responses. This system is composed of the following elements:

[1056] Overall system configuration

[1057] 1. Voice input method:

[1058] A device for user voice input. This device can be integrated into a smartphone with a microphone, smart glasses, a head-mounted display, or a factory robot. This means is used to recognize the user's voice as digital audio data.

[1059] 2. How to send audio data to the server:

[1060] The voice data acquired by the voice input means has a function to transmit it to the server via the network. This means is important for transferring the voice data to the server quickly and accurately.

[1061] 3. How to convert audio data to text data:

[1062] The server converts the acquired voice data into text data using a voice recognition engine (e.g., Google API). Through this process, the voice data is interpreted as language text.

[1063] 4. Means of analyzing text data to understand user intent:

[1064] The server analyzes the text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, it clarifies what the user is looking for.

[1065] 5. How to recognize user emotions:

[1066] The server recognizes the user's emotional state from the analyzed text and voice data using an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tools). Emotional states such as "relaxed," "anxious," and "excited" are identified.

[1067] 6. How to tailor search results based on sentiment:

[1068] The server retrieves relevant information and tailors it to the user's emotional state, for example, returning information in a concise format that emphasizes key points if the user is in a hurry.

[1069] 7. Means for returning search results to the user's device:

[1070] The server sends the adjusted search results to the user's device, allowing the device to display the information the user needs in an appropriate format.

[1071] Specific examples

[1072] 1. Example during a meeting:

[1073] If a user speaks during a meeting, "Show me last year's financial report," the system operates as follows:

[1074] Device: Records audio and sends it to the server.

[1075] Server: Converts voice data into text data and analyzes the user's intent.

[1076] Server: Recognizes the user's emotional state, determining, for example, whether they are relaxed.

[1077] Server: Searches the database for the relevant financial statements and returns them in a detailed explanatory format.

[1078] Device: View search results.

[1079] 2. Example of program code:

[1080] Example prompt sentence:

[1081] User: "Show me last year's financial statements."

[1082] System: "Last year's financial report can be found at: Meeting Materials / 2023 / Financial Report.pdf."

[1083] or

[1084] User: "How do I use the SUM function?"

[1085] System: "(Key point) The SUM function calculates the sum of a range of numbers."

[1086] This system can provide necessary information quickly and appropriately based on the user's voice input and emotional state, which is expected to significantly improve user experience and work efficiency.

[1087] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1088] Step 1:

[1089] The user gives a voice command (e.g., "Show me last year's financial statement") through the voice input means. This voice input is recorded by the microphone of the terminal. The input is taken into the system as voice data. The output is the recorded voice data.

[1090] Step 2:

[1091] The device converts the captured voice data into a digital format and sends it to the server over the network. This step involves digitizing and transferring the voice data. The input is the recorded voice data, and the output is the digital voice data sent to the server.

[1092] Step 3:

[1093] The server converts the received voice data into text data using a speech recognition engine (e.g., Google API). This conversion is the process of converting voice signals into text information. The input is digital voice data, and the output is text data.

[1094] Step 4:

[1095] The server analyzes the generated text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, the text data is processed to analyze its grammar and meaning. The input is the text data, and the output is the analysis result (identification of the user's intent).

[1096] Step 5:

[1097] The server uses an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tool) to recognize the user's emotional state from the text data and characteristics specific to the voice. Here, the user's feeling tendency is analyzed. The input is text data, and the output is the user's emotional state (e.g., relaxed, anxious).

[1098] Step 6:

[1099] The server searches for relevant information from a database based on the NLP analysis results and emotion recognition results. Specifically, it extracts relevant database entries based on the user's instructions (e.g., "last year's financial report"). The input is the NLP analysis results and emotion recognition results, and the output is a list of relevant information.

[1100] Step 7:

[1101] The server tailors search results to reflect the user's emotional state. For example, if the user is in a hurry, the server modifies the information to emphasize key points and provide a concise format. The input is the user's emotional state and a list of related information, and the output is the tailored search results.

[1102] Step 8:

[1103] The server sends the adjusted search results to the terminal, which then displays the information the user needs in an appropriate format. The input is the adjusted search results, and the output is what is displayed to the user.

[1104] Step 9:

[1105] The device helps the user prepare for the next action based on the displayed information. The input is the user's action, and the output is preparation for the next step.

[1106] This system allows users to efficiently search for information using voice and receive information in the most appropriate format depending on their emotional state.

[1107] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1109] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1110] [Third embodiment]

[1111] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1112] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1114] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1115] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1118] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1119] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1121] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1122] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1123] The present invention relates to a system for efficiently searching for documents and information during work using voice input. This system improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[1124] Overall system configuration

[1125] This system mainly consists of the following elements:

[1126] A device that receives user voice input

[1127] Server that processes received voice data

[1128] Speech Recognition Engine

[1129] Natural Language Processing (NLP) Engine

[1130] Database

[1131] Specific processing

[1132] In this system, when the user inputs voice, documents and information are searched and the results are returned to the user. The specific process is explained below.

[1133] 1. Acquiring voice input

[1134] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1135] Device: Records audio through a microphone and acquires it as audio data in real time.

[1136] 2. Sending audio data

[1137] Terminal: The acquired voice data is digitized and sent to the server via the network.

[1138] 3. Analysis of audio data

[1139] Server: Receives the voice data and converts it into text using a speech recognition engine.

[1140] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[1141] 4. Database Search

[1142] Server: Based on the analysis results of the NLP engine, it searches for relevant materials and information from the company's internal database.

[1143] 5. Returning search results

[1144] Server: Returns the materials and information found as search results to the device as text data.

[1145] Terminal: Displays the received search results to the user.

[1146] Specific examples

[1147] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[1148] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[1149] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[1150] Server: Search the database for files that correspond to "last year's financial statement."

[1151] Server: Returns "2022_Financial Report.pdf" to the terminal as the search result.

[1152] Terminal: Displays the report of findings to the user.

[1153] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[1154] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[1155] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[1156] Server: Retrieves information from a database about how to use the SUM function.

[1157] Server: Returns specific usage instructions and examples to the device as search results.

[1158] Terminal: Display the found information to the user.

[1159] In this way, this system uses voice input to quickly and accurately provide the materials and information the user desires, greatly improving work efficiency.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[1163] Step 2:

[1164] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[1165] Step 3:

[1166] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[1167] Step 4:

[1168] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[1169] Step 5:

[1170] The server searches the company's internal database based on the analysis results, and the NLP engine identifies files and information related to "this year's conference materials."

[1171] Step 6:

[1172] The server compiles the documents and information found as search results into text data and returns it to the device. For example, a file name or link such as "2023_ConferenceMaterials.pdf" is sent to the device.

[1173] Step 7:

[1174] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[1175] As a specific example, the process when the user inputs "Teach me how to use the SUM function" by voice will be described.

[1176] Step 1:

[1177] The user speaks, "Tell me how to use the SUM function." The device records this speech.

[1178] Step 2:

[1179] The device digitizes the recorded audio data and sends it to the server.

[1180] Step 3:

[1181] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[1182] Step 4:

[1183] The server analyzes the text data using an NLP engine to understand the user's intent. It identifies the phrase "how to use the SUM function" and determines that the user is looking for information on how to use the function.

[1184] Step 5:

[1185] The server searches a database based on the analysis results to identify information about the specific use of the SUM function.

[1186] Step 6:

[1187] The server compiles the usage methods and specific examples found as search results into text data and returns it to the terminal, including information on specific procedures and examples.

[1188] Step 7:

[1189] The terminal displays the information received to the user. Specific instructions and procedures for using the SUM function are displayed on the screen so that the user can refer to the information.

[1190] In this way, information that meets the user's request is provided through specific steps.

[1191] Example 1

[1192] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1193] In today's information society, it is extremely important for users to be able to quickly search for the information they need from vast amounts of documents and databases, thereby improving work efficiency. Furthermore, if users could search for information by voice input without using their hands during meetings or while working, convenience for users would be greatly improved. However, conventional systems lack the precision and speed of voice-input searches, making it difficult to accurately understand the user's intent and provide appropriate information.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1195] In this invention, the server includes a voice input means, a means for digitizing voice data and transmitting it to the server, a voice recognition means for converting the voice data into text data, a natural language processing means for analyzing the text data and understanding the user's intention, a means for searching a database for related information based on the analysis results, and a means for returning the search results to the terminal and displaying them to the user. This enables the user to quickly search for materials and information using voice input and obtain the information they need efficiently and accurately.

[1196] The "voice input means" is a device or function that picks up the user's voice and acquires it as digital voice data.

[1197] The "means for digitizing audio data and transmitting it to a server" is a process or method for converting analog audio data into a digital signal and transmitting it to a server over a network.

[1198] "Speech recognition means" refers to a technique or device for analyzing voice data and converting it into text data.

[1199] A "natural language processing means" is a technology or device that analyzes acquired text data, understands the context and meaning, and interprets the user's intentions.

[1200] A "means for retrieving relevant information from a database" is a process or method for retrieving relevant information in a database using an automatically generated query.

[1201] "Means for returning search results to the terminal for display to the user" means the process or method by which search results are organized, transmitted to the terminal, and presented to the user in a visual or other format.

[1202] The present invention relates to a system that uses voice input to efficiently search for materials and information needed while a user is working. This system significantly improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[1203] Overall system configuration

[1204] The system mainly consists of the following elements:

[1205] A device that receives user voice input

[1206] Server that processes received voice data

[1207] Speech Recognition Engine

[1208] Natural Language Processing (NLP) Engine

[1209] Database

[1210] Voice input and data transmission

[1211] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1212] Device: Records audio through a built-in microphone or a connected microphone, and acquires it as audio data in real time. This audio data is first converted into a digital signal and then transmitted to a server via a network.

[1213] Analysis of audio data

[1214] Server: The received voice data is stored in storage and converted into text data using a speech recognition engine such as the Google Speech-to-Text API.The text data is then analyzed using a natural language processing (NLP) engine such as SpaCy or NLTK to understand the user's intent.

[1215] Database search

[1216] Server: Based on the user request analyzed by the NLP engine, generates SQL queries and other search queries to search for relevant materials and information from internal databases (e.g., MySQL, PostgreSQL).

[1217] Returning and displaying search results

[1218] Server: Organizes the search results, converts them into a format that is easy for the user to understand, and sends them back to the device.

[1219] Terminal: Displays the received search results on a user interface (UI), for example, in a browser window or a dedicated app.

[1220] Specific examples

[1221] Here is a concrete example of how the system works:

[1222] Searching for materials during a meeting

[1223] User: Says, "Show me last year's financial report."

[1224] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[1225] Server: The audio is converted to "Show me last year's financial report" using the Google Speech-to-Text API and analyzed using SpaCy.

[1226] Server: Run an SQL query against the MySQL database to find files that match "Last Year's Financial Report."

[1227] Server: Search for "2022_Financial Report.pdf" in the database, generate a link, and send it to the device.

[1228] On the device: Opens the received link in a browser window and displays the PDF to the user.

[1229] Search for how to use Excel

[1230] User: Say "How do I use the SUM function?"

[1231] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[1232] Server: Convert the audio into "How do I use the SUM function?" using the Google Speech-to-Text API, and analyze it using NLTK.

[1233] Server: Run a SQL query against the PostgreSQL database to find information about how to use the SUM function.

[1234] Server: Searches the database for specific usage methods and examples of the SUM function and sends the text information to the terminal.

[1235] Device: The received text information is displayed in a dedicated app, providing the user with instructions on how to use the device.

[1236] In this way, the user can efficiently search for materials and information through voice input, and quickly and accurately obtain the information he or she needs.

[1237] Examples of prompt statements

[1238] Here are some examples of input prompts for a generative AI model:

[1239] Search for meeting materials

[1240] A user says, "Show me last year's financial report." Describe the process to convert this into text, search the database for the relevant documents, and display them.

[1241] Search for how to use Excel

[1242] A user speaks, "Tell me how to use the SUM function." Describe the process to convert this to text, search the database for the relevant information, and display it.

[1243] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1244] Step 1:

[1245] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1246] Input: User's voice

[1247] Output: Audio data

[1248] Specific operation: By speaking into the user's microphone, the audio is received through the device's built-in microphone or a connected microphone.

[1249] Step 2:

[1250] Device: Record audio in real time through the built-in microphone or an external microphone.

[1251] Input: Audio data

[1252] Output: Digital audio data

[1253] Specific operation: The recorded voice is converted into a digital signal by the terminal's voice input system and temporarily stored in memory.

[1254] Step 3:

[1255] Terminal: Transmits digitized voice data to a server via a network.

[1256] Input: Digital audio data

[1257] Output: Transmitted digital audio data

[1258] How it works: The device compresses the digital audio data and sends it over the Internet to a server using either HTTP or HTTPS.

[1259] Step 4:

[1260] Server: The received voice data is stored in storage and passed to the voice recognition engine.

[1261] Input: Transmitted digital audio data

[1262] Output: Saved audio and text data

[1263] Specific operation: The server temporarily stores the received voice data in storage, then sends it to a speech recognition engine and converts it into text data. This process is performed using, for example, the Google Speech-to-Text API.

[1264] Step 5:

[1265] Server: Converts voice data into text data using a speech recognition engine.

[1266] Input: Saved audio data

[1267] Output: Text data

[1268] Specific operation: Analyzes received voice data and converts it into corresponding text data. This is the process of converting spoken words into written information.

[1269] Step 6:

[1270] Server: Analyzes text data using a natural language processing (NLP) engine to understand the user's intent.

[1271] Input: Text data

[1272] Output: Parsed intent data

[1273] How it works: The server sends the text data to an NLP engine (e.g., SpaCy or NLTK) for contextual analysis and intent estimation, which identifies the information or resource the user is looking for.

[1274] Step 7:

[1275] Server: Searches for relevant materials and information from the database based on the user's request analyzed by the NLP engine.

[1276] Input: Parsed intent data

[1277] Output: Search result data

[1278] Specific operation: Based on the analysis results, the generated SQL query is sent to a database (e.g., MySQL, PostgreSQL) to perform a search. Related file names and information are identified.

[1279] Step 8:

[1280] Server: Organizes the search results and converts them into a format that is easy for the user to understand.

[1281] Input: Search result data

[1282] Output: Formatted data

[1283] Specific operation: Search results are converted into a data format such as JSON or XML, and formatted to be user-friendly, such as a file link or text information.

[1284] Step 9:

[1285] Server: Returns the formatted search results to the terminal via the network.

[1286] Input: Formatted data

[1287] Output: Search result data sent

[1288] Specific operation: The formatted data is returned to the terminal and communicated using the HTTP or HTTPS protocol.

[1289] Step 10:

[1290] Terminal: Displays the received search results on a user interface (UI).

[1291] Input: Submitted search result data

[1292] Output: Displayed information

[1293] What it does: It displays search results in a browser or dedicated app, allowing users to visually access information. For example, they can click links to open files or read text information.

[1294] (Application example 1)

[1295] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1296] Conventional voice-activated information search systems have been primarily used for office work and document search during meetings. However, in factories, there are many situations where workers cannot use their hands, so there is a need for a system that can easily check the location of parts and inventory information. In particular, in large factories, where there are many parts, manually searching for information is inefficient, making it difficult to improve work efficiency.

[1297] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1298] In this invention, the server includes a voice input means, a means for transmitting voice data to the server, a means for converting the voice data into text data, a means for searching a database for related information based on the analysis results, a means for returning the search results to a user terminal, and a means for issuing voice instructions to a factory robot to search for parts lists and inventory information. This makes it possible to quickly search for parts lists and inventory information using voice instructions within the factory, greatly improving work efficiency.

[1299] The "voice input means" refers to a device or software that receives a user's voice instruction and acquires it as voice data.

[1300] "Means for transmitting voice data to a server" refers to a method or technology for digitizing the acquired voice data and transmitting it to a server via a network.

[1301] "Means for converting voice data into text data" refers to software or algorithms that use voice recognition technology to convert voice data into text information.

[1302] "Means for analyzing text data to understand user intent" refers to a system or method that uses natural language processing technology to extract user requests and intent from text data.

[1303] "Means for searching for related information from a database based on the analysis results" refers to a technique or method for querying an internal database for relevant information based on the analysis results and obtaining the necessary data.

[1304] "Means for returning search results to the user terminal" refers to a system or protocol for sending the acquired data to the user terminal and notifying the user by display or voice.

[1305] "Means for giving voice instructions to factory robots to search for parts lists and inventory information" refers to a system or method for issuing voice commands to robots in a factory and searching for parts lists and inventory information based on those commands.

[1306] The present invention is a system for quickly searching for parts lists and inventory information within a factory. A specific embodiment of this system is shown below.

[1307] System configuration

[1308] This system consists of the following elements:

[1309] Voice input means

[1310] A means of sending audio data to the server

[1311] A means of converting audio data into text data

[1312] A means of analyzing text data to understand user intent

[1313] A means of searching for related information from a database based on the analysis results

[1314] A means for returning search results to the user's device

[1315] A way to give voice commands to factory robots to retrieve parts lists and inventory information

[1316] Hardware and software used

[1317] 1. Voice input method

[1318] Hardware: Microphone

[1319] Software: Voice input module (e.g. Google Cloud Speech-to-Text API)

[1320] 2. A method for sending audio data to the server

[1321] Hardware: The robot's processor

[1322] Software: Data transmission module

[1323] 3. Means of converting audio data into text data

[1324] Hardware: Server

[1325] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[1326] 4. A means of analyzing text data to understand user intent

[1327] Hardware: Server

[1328] Software: Natural Language Processing (NLP) engines (e.g., spaCy, OpenAI GPT-4)

[1329] 5. A means of searching databases for relevant information

[1330] Hardware: Server

[1331] Software: Database management system (e.g., MySQL, PostgreSQL)

[1332] 6. Means of returning search results to the user's device

[1333] Hardware: Server

[1334] Software: Data return module

[1335] 7. A way to give voice commands to factory robots to retrieve parts lists and inventory information.

[1336] Hardware: Factory robots

[1337] Software: Robot control system

[1338] Process Overview

[1339] This system allows users to quickly search for parts lists and inventory information within a factory by giving verbal instructions. When a user gives voice input, the voice data is picked up through a microphone, digitized, and sent to a server. On the server, the voice data is converted into text data using a speech recognition engine. A natural language processing (NLP) engine then analyzes the text data to understand the user's intent. Based on the results of the analysis, relevant parts lists and inventory information are searched for in the database, and this information is then sent back from the server to the user's device, specifically the robot. The robot can display the results on a screen or provide verbal feedback using a text-to-speech engine.

[1340] Specific examples

[1341] For example, consider the case where a worker voice-inputs, "Tell me the location of part B." The system operates as follows:

[1342] 1. The microphone picks up the voice message "Tell me the location of part B" and sends it to the server.

[1343] 2. The server's speech recognition engine converts this speech into text data such as "Tell me the location of part B."

[1344] 3. The NLP engine analyzes the text data and extracts the user's intent, such as "I want to know the location of part B."

[1345] 4. The server searches the database for the "location of part B" information and retrieves the result "Location: Shelf number A3."

[1346] 5. The result is sent back to the robot, which notifies the worker via the robot's display and speaker. A voice message is output saying, "Part B is located on shelf number A3."

[1347] Prompt Sentence Examples

[1348] Below is an example of a prompt to input to a generative AI model for speech analysis (e.g., OpenAI GPT-4):

[1349] Convert the user's voice input into text and analyze its intent. Analyze the following text, extract the user's intent and request, and generate a response.

[1350] Text: "What is the stock of part A?"

[1351] In this way, workers can instantly obtain information using voice instructions, greatly improving work efficiency within the factory.

[1352] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1353] Step 1:

[1354] The user inputs voice data using a voice input means (microphone), such as "Please tell me the stock of part A."

[1355] Input: User's voice command

[1356] Output: Audio data

[1357] Specific behavior: A user speaks into a microphone, "Tell me the inventory of part A." The microphone captures the voice signal.

[1358] Step 2:

[1359] The terminal digitizes the voice data for transmission to the server, and then transmits it to the server via the network using a data transmission module.

[1360] Input: Audio data

[1361] Output: Digitized audio data

[1362] What it does: Digitizes audio data and sends it to a server over the Internet or a local network.

[1363] Step 3:

[1364] The server receives the voice data and converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[1365] Input: Digitized audio data

[1366] Output: Text data

[1367] Specific operation: The server analyzes the voice data and converts it into text such as "Please tell me the stock of part A."

[1368] Step 4:

[1369] The server analyzes the text data using a natural language processing (NLP) engine (e.g., spaCy, OpenAI GPT-4) to understand the user's intent.

[1370] Input: Text data

[1371] Output: Analysis results including user intent

[1372] Specific operation: The NLP engine extracts the user's intent, such as "I want to know the inventory of part A."

[1373] Step 5:

[1374] Based on the analysis results, the server uses a database management system (e.g., MySQL, PostgreSQL) to search for relevant information from a database.

[1375] Input: Analysis results including user intent

[1376] Output: Search results (e.g., inventory information for part A)

[1377] Specific operation: The server searches the database for inventory information corresponding to "Part A" and obtains the necessary information (e.g., inventory quantity).

[1378] Step 6:

[1379] The server returns the search results to the user's terminal, and the data return module is used to deliver the results to the robot.

[1380] Input: Search results (e.g., inventory information for part A)

[1381] Output: Displayable data (text and audio formats)

[1382] Specific actions: Organize search results and return them to the robot as text data, including information for converting the text to speech.

[1383] Step 7:

[1384] The terminal (factory robot) receives the search results and displays them on a screen or provides audio feedback using a text-to-speech engine (e.g., Google Text-to-Speech API).

[1385] Input: Displayable data (text or audio format)

[1386] Output: Feedback to the user (visual or audio output)

[1387] Specific operation: The robot will announce "There are 30 units of part A in stock" by voice and display the stock information on the screen.

[1388] In this way, a system is realized that specifically describes how voice data is processed at each step and can quickly provide related information based on the user's voice instructions.

[1389] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1390] The present invention relates to a system that uses voice input to efficiently search for materials and information during work, and further recognizes the user's emotions and provides appropriate responses. This system aims to improve the user's work efficiency and user experience through voice input, voice recognition, natural language processing, database search, emotion recognition engine, and result feedback.

[1391] Overall system configuration

[1392] This system mainly consists of the following elements:

[1393] A device that receives user voice input

[1394] Server that processes received voice data

[1395] Speech Recognition Engine

[1396] Natural Language Processing (NLP) Engine

[1397] Database

[1398] Emotion Recognition Engine

[1399] Specific processing

[1400] In this system, when the user inputs voice, materials and information are searched for and an appropriate response is provided according to the user's emotions. The specific processing is explained below.

[1401] 1. Acquiring voice input

[1402] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1403] Device: Records audio through a microphone and acquires it as audio data in real time.

[1404] 2. Sending audio data

[1405] Terminal: The acquired voice data is digitized and sent to the server via the network.

[1406] 3. Analysis of audio data

[1407] Server: Receives the voice data and converts it into text using a speech recognition engine.

[1408] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[1409] 4. Emotional Recognition

[1410] Server: Uses an emotion recognition engine to analyze the user's emotional state from the voice data.

[1411] Server: As a result, identify the user's emotions, such as excited, anxious, relaxed, etc.

[1412] 5. Database Search

[1413] Server: Based on the analysis results of the NLP engine and emotion recognition, it searches for relevant materials and information from the company's internal database.

[1414] 6. Adjusting the results

[1415] Server: The server organizes the materials and information found as search results into an appropriate format based on the user's emotions and returns it to the device. For example, if the user is feeling anxious, the server may return the information in a format that emphasizes the main points.

[1416] 7. Returning search results

[1417] Server: Sends the compiled search results to the device. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf".

[1418] Terminal: Displays the received search results to the user.

[1419] Specific examples

[1420] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[1421] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[1422] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[1423] Server: The emotion recognition engine analyzes the emotions from the user's voice and determines, for example, that the user is relaxed.

[1424] Server: Search the database for files that correspond to "last year's financial statement."

[1425] Server: Returns search results in a format that includes detailed descriptions depending on the user's relaxed state.

[1426] Terminal: Display the found financial statements to the user.

[1427] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[1428] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[1429] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[1430] Server: The emotion recognition engine determines that the user is anxious.

[1431] Server: Retrieves information from a database about the specific use of the SUM function.

[1432] Server: Return search results in a concise format that emphasizes key points and is tailored to impatient users.

[1433] Terminal: Display the found information to the user.

[1434] In this way, by combining it with an emotion recognition engine, flexible responses that adapt to the user's emotional state become possible, greatly improving work efficiency and user experience.

[1435] The processing flow will be explained below.

[1436] Step 1:

[1437] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[1438] Step 2:

[1439] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[1440] Step 3:

[1441] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[1442] Step 4:

[1443] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[1444] Step 5:

[1445] The server uses an emotion recognition engine to analyze the user's emotional state from the voice data, analyzing the tone, speed, rhythm, etc. of the voice to identify emotions such as "excited," "anxious," or "relaxed."

[1446] Step 6:

[1447] The server searches the company database based on the analysis results of the NLP engine and emotion recognition, and identifies files and information related to "this year's conference materials."

[1448] Step 7:

[1449] The server summarizes the documents and information found as search results in an appropriate format depending on the user's emotional state. For example, if a user is in a hurry, the server summarizes the information in a concise format that emphasizes the main points.

[1450] Step 8:

[1451] The server sends the search results compiled by the server to the device as text data. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf."

[1452] Step 9:

[1453] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[1454] Specific examples

[1455] Consider the case where a user speaks, "Show me last year's financial statement."

[1456] Step 1:

[1457] The user inputs voice, and the terminal records the voice.

[1458] Step 2:

[1459] The device digitizes the recorded audio and sends it to the server.

[1460] Step 3:

[1461] The server receives the voice data and converts it into "Show me last year's financial statement" using a voice recognition engine.

[1462] Step 4:

[1463] The server analyzes the text data using an NLP engine and identifies the phrase "last year's financial report."

[1464] Step 5:

[1465] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is relaxed.

[1466] Step 6:

[1467] Based on the analysis results, the server searches the database for "last year's financial statement."

[1468] Step 7:

[1469] The server compiles the search results in a format that includes detailed descriptions tailored to the user who is relaxing.

[1470] Step 8:

[1471] The server sends the search results compiled to the terminal.

[1472] Step 9:

[1473] The terminal displays the received search results to the user.

[1474] Similarly, if the user says "Tell me how to use the SUM function," the following will happen:

[1475] Step 1:

[1476] The user gives voice input, and the device records the voice.

[1477] Step 2:

[1478] The device digitizes the recorded audio and sends it to the server.

[1479] Step 3:

[1480] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[1481] Step 4:

[1482] The server analyzes the text data using an NLP engine and identifies the phrase "How to use the SUM function."

[1483] Step 5:

[1484] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is anxious.

[1485] Step 6:

[1486] The server searches the database for how to use the SUM function based on the analysis results.

[1487] Step 7:

[1488] The server summarizes the information in a concise format that emphasizes key points.

[1489] Step 8:

[1490] The server sends the compiled information to the terminal.

[1491] Step 9:

[1492] The terminal displays the received information to the user.

[1493] In this way, through specific steps, information according to the user's request is provided, and the emotion engine makes it possible to respond according to the user's emotions.

[1494] Example 2

[1495] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1496] While conventional speech recognition systems allow users to search for information through voice input, they are unable to adjust responses based on the user's emotional state, resulting in a limited user experience and low effectiveness, especially in stressful situations. Furthermore, searches using only speech recognition and natural language processing have difficulty fully understanding the user's intent, resulting in the problem of displaying inappropriate results.

[1497] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1498] In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, and means for recognizing the user's emotional state, which makes it possible to present information in a format that is adapted to the user's emotions, thereby significantly improving work efficiency and the user experience.

[1499] The "voice input means" is a means for acquiring voice information uttered by the user.

[1500] The "means for transmitting voice data to a server" refers to a means for transmitting the acquired voice data to a server via a network.

[1501] The "means for converting voice data into text data" refers to a means for converting voice data into text data expressed as a character string.

[1502] "Means for analyzing text data to understand user intent" refers to means for processing text data and understanding the content of a user's requests or questions.

[1503] The "means for searching a database for related information based on the analysis results" refers to a means for searching a database for related information based on the user's intentions.

[1504] The "means for returning search results to the user terminal" refers to a means for transmitting search results obtained from the database to the user terminal.

[1505] The "means for recognizing the user's emotional state" is a means for determining the user's current emotions from the user's voice and other information.

[1506] The "means for adjusting search results according to the user's emotions" is a means for adjusting the display format and content of search results based on the recognized emotional state of the user.

[1507] This invention relates to a system that allows users to efficiently search for materials and information through voice input, and also recognizes the user's emotions and provides appropriate responses. The system aims to improve the user's work efficiency and experience through voice input, voice recognition, natural language processing, database search, an emotion recognition engine, and feedback of the results.

[1508] Overall system configuration

[1509] This system mainly consists of the following elements:

[1510] A device that receives user voice input

[1511] Server that processes received voice data

[1512] Speech recognition engine (e.g. Google Speech-to-Text API)

[1513] Natural Language Processing (NLP) engines (e.g., OpenAI's GPT-4)

[1514] Database (e.g. Microsoft SQL Server)

[1515] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[1516] Voice input and data processing flow

[1517] 1. Acquiring voice input

[1518] Users can make requests via voice input, such as "Show me this year's meeting materials."

[1519] The device records audio through a built-in microphone and converts the audio data into a digital format in real time.

[1520] 2. Sending audio data

[1521] The terminal compresses the digitized voice data and transmits it over the network to the server, where it also encrypts the data to ensure security.

[1522] 3. Analysis of audio data

[1523] The server receives the voice data and converts it into text using a speech recognition engine, which then analyzes it with a natural language processing (NLP) engine to understand the user's intent.

[1524] 4. Emotional Recognition

[1525] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, and as a result, identifies emotions such as excitement, impatience, or relaxation.

[1526] 5. Database Search

[1527] The server searches for relevant information from the company's internal database based on the analysis results of the natural language processing engine and the emotion recognition results.

[1528] 6. Adjusting the results

[1529] The server then organizes the search results into a format appropriate for the user's emotions, for example, highlighting key points for a user who is in a hurry, and including more detailed information for a user who is relaxed.

[1530] 7. Returning search results

[1531] The server sends the formatted search results to the terminal, which then displays the received search results to the user. For example, it displays a file name such as "2023_ConferenceMaterials.pdf" as a link so that the user can click it to access the document directly.

[1532] Specific examples

[1533] Example 1: Searching for documents during a meeting

[1534] Consider a case where a user voice-inputs "Show me last year's financial report" during a meeting.

[1535] Terminal: The voice "Show me last year's financial statement" is recorded with a microphone, digitized, compressed, and sent to the server.

[1536] Server: The speech recognition engine converts the request to "Show me last year's financial report," and the NLP engine analyzes it.

[1537] Server: Determines "relaxed" using emotion recognition engine. Searches for "last year's financial report" from the database and formats it with detailed explanations.

[1538] Server: The formatted results are returned to the terminal, and the terminal displays a link to "Last Year's Financial Report.pdf".

[1539] Users can click on the link provided to view the report.

[1540] Example 2: Excel work support

[1541] Consider the case where a user is working in Excel and says, "Tell me how to use the SUM function."

[1542] Terminal: Record the audio "Teach me how to use the SUM function," digitize it, compress it, and send it to the server.

[1543] Server: The speech recognition engine converts the request to "Please tell me how to use the SUM function," and the NLP engine analyzes it.

[1544] Server: The emotion recognition engine determines that the person is in a hurry. It searches the database for ways to use the SUM function and formats it to emphasize the main points.

[1545] Server: The formatted result is sent back to the terminal, and the terminal displays a link to "How to use the SUM function.pdf".

[1546] Users: Click the link provided to learn how to use it.

[1547] As described above, this system plays a specific role at each processing step, providing flexible responses while adapting to the user's emotional state, thereby significantly improving work efficiency and user experience.

[1548] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1549] Step 1:

[1550] Acquiring voice input

[1551] Users can make requests via voice input, such as "Show me this year's meeting materials."

[1552] The device uses a built-in microphone to record audio, and noise-canceling technology is used to capture clear audio data.

[1553] The input is the user's speech, and the output is recorded voice data.

[1554] Step 2:

[1555] Sending audio data

[1556] The device digitizes the acquired voice data and converts it into a file format.

[1557] The device compresses the digitized voice data and transmits it over the network to the server, encrypting the data for security reasons.

[1558] The input is recorded audio data, and the output is a compressed and encrypted audio file.

[1559] Step 3:

[1560] Analysis of audio data

[1561] The server decompresses the audio data received via the network and temporarily stores it.

[1562] The server converts the voice data into text data using a voice recognition engine (e.g., a general voice recognition API).

[1563] The server passes the converted text data to a natural language processing (NLP) engine (e.g., a general natural language processing model) to analyze the user's intent.

[1564] The input is a compressed and encrypted audio file, and the output is text data that represents the user's intent.

[1565] Step 4:

[1566] Emotion recognition

[1567] The server uses an emotion recognition engine (e.g., a general emotion recognition API) to analyze the user's emotional state from the text or voice data.

[1568] As a result of the analysis, the server identifies the user's emotions, such as excitement, impatience, or relaxation.

[1569] The input is text data and voice data, and the output is the analysis result of the user's emotional state.

[1570] Step 5:

[1571] Database search

[1572] The server searches for relevant information from an internal database (e.g., a general database system) based on the analysis results of the natural language processing engine and the emotion recognition results.

[1573] The server performs query optimization to deliver fast and accurate search results.

[1574] The input is text data and emotional state that reflects the user's intention, and the output is the search results for related information.

[1575] Step 6:

[1576] Adjusting the results

[1577] The server organizes the materials and information obtained as search results in an appropriate format according to the user's feelings.

[1578] For example, the server formats the results to highlight key points for a user who is in a hurry, or to include more detailed information for a user who is relaxed.

[1579] The input is the search results for related information and the user's emotional state, and the output is the formatted search results.

[1580] Step 7:

[1581] Returning search results

[1582] The server sends the formatted search results to the terminal.

[1583] The terminal displays the received search results to the user.

[1584] For example, the device will display a file name such as "2023_Conference Materials.pdf" in the form of a link, allowing the user to access the document directly by clicking on it.

[1585] The input is the formatted search results, and the output is the resource links displayed to the user.

[1586] (Application example 2)

[1587] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1588] While conventional voice input systems can properly understand a user's intentions and provide necessary information, they do not respond to the user's emotional state. As a result, they are unable to respond flexibly to situations, such as when the user is in a hurry or relaxed, which can lead to a poor user experience. Furthermore, in workplaces such as factories, robots are required to efficiently understand users' voice instructions and provide appropriate responses according to their emotional state.

[1589] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, means for recognizing the user's emotion, and means for adjusting search results in a format according to the emotion. This makes it possible to accurately understand the user's intention and provide appropriate information according to the user's emotional state.

[1590] The "voice input means" is a device for receiving the user's voice and recognizing it as digital voice data.

[1591] The "means for transmitting voice data to a server" is a function for transferring acquired voice data to a server via a network.

[1592] The "means for converting voice data into text data" is a process for converting voice data into linguistic text data using voice recognition technology.

[1593] "Means for analyzing text data to understand user intent" refers to a method that uses a natural language processing (NLP) engine to analyze the meaning of text data and understand what the user is looking for.

[1594] "Means for searching for related information from a database based on the analysis results" is a function for searching for related information from a database according to the intent analyzed by the NLP engine.

[1595] "Means for returning search results to the user terminal" refers to a method for transmitting data to the terminal in order to display the searched information or materials to the user.

[1596] "Means for recognizing user emotions" refers to technology for detecting the user's emotional state (for example, relaxed, anxious, excited, etc.) from voice data or text data.

[1597] The "means for adjusting search results in a format according to emotions" is a function for adjusting and providing information in a format or presentation method according to the recognized emotional state of the user.

[1598] The present invention relates to a system that uses voice input to efficiently search for information during work, and further recognizes the user's emotions and provides appropriate responses. This system is composed of the following elements:

[1599] Overall system configuration

[1600] 1. Voice input method:

[1601] A device for user voice input. This device can be integrated into a smartphone with a microphone, smart glasses, a head-mounted display, or a factory robot. This means is used to recognize the user's voice as digital audio data.

[1602] 2. How to send audio data to the server:

[1603] The voice data acquired by the voice input means has a function to transmit it to the server via the network. This means is important for transferring the voice data to the server quickly and accurately.

[1604] 3. How to convert audio data to text data:

[1605] The server converts the acquired voice data into text data using a voice recognition engine (e.g., Google API). Through this process, the voice data is interpreted as language text.

[1606] 4. Means of analyzing text data to understand user intent:

[1607] The server analyzes the text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, it clarifies what the user is looking for.

[1608] 5. How to recognize user emotions:

[1609] The server recognizes the user's emotional state from the analyzed text and voice data using an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tools). Emotional states such as "relaxed," "anxious," and "excited" are identified.

[1610] 6. How to tailor search results based on sentiment:

[1611] The server retrieves relevant information and tailors it to the user's emotional state, for example, returning information in a concise format that emphasizes key points if the user is in a hurry.

[1612] 7. Means for returning search results to the user's device:

[1613] The server sends the adjusted search results to the user's device, allowing the device to display the information the user needs in an appropriate format.

[1614] Specific examples

[1615] 1. Example during a meeting:

[1616] If a user speaks during a meeting, "Show me last year's financial report," the system operates as follows:

[1617] Device: Records audio and sends it to the server.

[1618] Server: Converts voice data into text data and analyzes the user's intent.

[1619] Server: Recognizes the user's emotional state, determining, for example, whether they are relaxed.

[1620] Server: Searches the database for the relevant financial statements and returns them in a detailed explanatory format.

[1621] Device: View search results.

[1622] 2. Example of program code:

[1623] Example prompt sentence:

[1624] User: "Show me last year's financial statements."

[1625] System: "Last year's financial report can be found at: Meeting Materials / 2023 / Financial Report.pdf."

[1626] or

[1627] User: "How do I use the SUM function?"

[1628] System: "(Key point) The SUM function calculates the sum of a range of numbers."

[1629] This system can provide necessary information quickly and appropriately based on the user's voice input and emotional state, which is expected to significantly improve user experience and work efficiency.

[1630] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1631] Step 1:

[1632] The user gives a voice command (e.g., "Show me last year's financial statement") through the voice input means. This voice input is recorded by the microphone of the terminal. The input is taken into the system as voice data. The output is the recorded voice data.

[1633] Step 2:

[1634] The device converts the captured voice data into a digital format and sends it to the server over the network. This step involves digitizing and transferring the voice data. The input is the recorded voice data, and the output is the digital voice data sent to the server.

[1635] Step 3:

[1636] The server converts the received voice data into text data using a speech recognition engine (e.g., Google API). This conversion is the process of converting voice signals into text information. The input is digital voice data, and the output is text data.

[1637] Step 4:

[1638] The server analyzes the generated text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, the text data is processed to analyze its grammar and meaning. The input is the text data, and the output is the analysis result (identification of the user's intent).

[1639] Step 5:

[1640] The server uses an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tool) to recognize the user's emotional state from the text data and characteristics specific to the voice. Here, the user's feeling tendency is analyzed. The input is text data, and the output is the user's emotional state (e.g., relaxed, anxious).

[1641] Step 6:

[1642] The server searches for relevant information from a database based on the NLP analysis results and emotion recognition results. Specifically, it extracts relevant database entries based on the user's instructions (e.g., "last year's financial report"). The input is the NLP analysis results and emotion recognition results, and the output is a list of relevant information.

[1643] Step 7:

[1644] The server tailors search results to reflect the user's emotional state. For example, if the user is in a hurry, the server modifies the information to emphasize key points and provide a concise format. The input is the user's emotional state and a list of related information, and the output is the tailored search results.

[1645] Step 8:

[1646] The server sends the adjusted search results to the terminal, which then displays the information the user needs in an appropriate format. The input is the adjusted search results, and the output is what is displayed to the user.

[1647] Step 9:

[1648] The device helps the user prepare for the next action based on the displayed information. The input is the user's action, and the output is preparation for the next step.

[1649] This system allows users to efficiently search for information using voice and receive information in the most appropriate format depending on their emotional state.

[1650] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1651] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1652] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1653] [Fourth embodiment]

[1654] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1655] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1656] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1657] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1658] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1659] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1660] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1661] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1662] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1663] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1664] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1665] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1666] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1667] The present invention relates to a system for efficiently searching for documents and information during work using voice input. This system improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[1668] Overall system configuration

[1669] This system mainly consists of the following elements:

[1670] A device that receives user voice input

[1671] Server that processes received voice data

[1672] Speech Recognition Engine

[1673] Natural Language Processing (NLP) Engine

[1674] Database

[1675] Specific processing

[1676] In this system, when the user inputs voice, documents and information are searched and the results are returned to the user. The specific process is explained below.

[1677] 1. Acquiring voice input

[1678] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1679] Device: Records audio through a microphone and acquires it as audio data in real time.

[1680] 2. Sending audio data

[1681] Terminal: The acquired voice data is digitized and sent to the server via the network.

[1682] 3. Analysis of audio data

[1683] Server: Receives the voice data and converts it into text using a speech recognition engine.

[1684] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[1685] 4. Database Search

[1686] Server: Based on the analysis results of the NLP engine, it searches for relevant materials and information from the company's internal database.

[1687] 5. Returning search results

[1688] Server: Returns the materials and information found as search results to the device as text data.

[1689] Terminal: Displays the received search results to the user.

[1690] Specific examples

[1691] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[1692] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[1693] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[1694] Server: Search the database for files that correspond to "last year's financial statement."

[1695] Server: Returns "2022_Financial Report.pdf" to the terminal as the search result.

[1696] Terminal: Displays the report of findings to the user.

[1697] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[1698] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[1699] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[1700] Server: Retrieves information from a database about how to use the SUM function.

[1701] Server: Returns specific usage instructions and examples to the device as search results.

[1702] Terminal: Display the found information to the user.

[1703] In this way, this system uses voice input to quickly and accurately provide the materials and information the user desires, greatly improving work efficiency.

[1704] The processing flow will be explained below.

[1705] Step 1:

[1706] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[1707] Step 2:

[1708] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[1709] Step 3:

[1710] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[1711] Step 4:

[1712] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[1713] Step 5:

[1714] The server searches the company's internal database based on the analysis results, and the NLP engine identifies files and information related to "this year's conference materials."

[1715] Step 6:

[1716] The server compiles the documents and information found as search results into text data and returns it to the device. For example, a file name or link such as "2023_ConferenceMaterials.pdf" is sent to the device.

[1717] Step 7:

[1718] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[1719] As a specific example, the process when the user inputs "Teach me how to use the SUM function" by voice will be described.

[1720] Step 1:

[1721] The user speaks, "Tell me how to use the SUM function." The device records this speech.

[1722] Step 2:

[1723] The device digitizes the recorded audio data and sends it to the server.

[1724] Step 3:

[1725] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[1726] Step 4:

[1727] The server analyzes the text data using an NLP engine to understand the user's intent. It identifies the phrase "how to use the SUM function" and determines that the user is looking for information on how to use the function.

[1728] Step 5:

[1729] The server searches a database based on the analysis results to identify information about the specific use of the SUM function.

[1730] Step 6:

[1731] The server compiles the usage methods and specific examples found as search results into text data and returns it to the terminal, including information on specific procedures and examples.

[1732] Step 7:

[1733] The terminal displays the information received to the user. Specific instructions and procedures for using the SUM function are displayed on the screen so that the user can refer to the information.

[1734] In this way, information that meets the user's request is provided through specific steps.

[1735] Example 1

[1736] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1737] In today's information society, it is extremely important for users to be able to quickly search for the information they need from vast amounts of documents and databases, thereby improving work efficiency. Furthermore, if users could search for information by voice input without using their hands during meetings or while working, convenience for users would be greatly improved. However, conventional systems lack the precision and speed of voice-input searches, making it difficult to accurately understand the user's intent and provide appropriate information.

[1738] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1739] In this invention, the server includes a voice input means, a means for digitizing voice data and transmitting it to the server, a voice recognition means for converting the voice data into text data, a natural language processing means for analyzing the text data and understanding the user's intention, a means for searching a database for related information based on the analysis results, and a means for returning the search results to the terminal and displaying them to the user. This enables the user to quickly search for materials and information using voice input and obtain the information they need efficiently and accurately.

[1740] The "voice input means" is a device or function that picks up the user's voice and acquires it as digital voice data.

[1741] The "means for digitizing audio data and transmitting it to a server" is a process or method for converting analog audio data into a digital signal and transmitting it to a server over a network.

[1742] "Speech recognition means" refers to a technique or device for analyzing voice data and converting it into text data.

[1743] A "natural language processing means" is a technology or device that analyzes acquired text data, understands the context and meaning, and interprets the user's intentions.

[1744] A "means for retrieving relevant information from a database" is a process or method for retrieving relevant information in a database using an automatically generated query.

[1745] "Means for returning search results to the terminal for display to the user" means the process or method by which search results are organized, transmitted to the terminal, and presented to the user in a visual or other format.

[1746] The present invention relates to a system that uses voice input to efficiently search for materials and information needed while a user is working. This system significantly improves the user's work efficiency through voice input, voice recognition, natural language processing, database search, and result feedback.

[1747] Overall system configuration

[1748] The system mainly consists of the following elements:

[1749] A device that receives user voice input

[1750] Server that processes received voice data

[1751] Speech Recognition Engine

[1752] Natural Language Processing (NLP) Engine

[1753] Database

[1754] Voice input and data transmission

[1755] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1756] Device: Records audio through a built-in microphone or a connected microphone, and acquires it as audio data in real time. This audio data is first converted into a digital signal and then transmitted to a server via a network.

[1757] Analysis of audio data

[1758] Server: The received voice data is stored in storage and converted into text data using a speech recognition engine such as the Google Speech-to-Text API.The text data is then analyzed using a natural language processing (NLP) engine such as SpaCy or NLTK to understand the user's intent.

[1759] Database search

[1760] Server: Based on the user request analyzed by the NLP engine, generates SQL queries and other search queries to search for relevant materials and information from internal databases (e.g., MySQL, PostgreSQL).

[1761] Returning and displaying search results

[1762] Server: Organizes the search results, converts them into a format that is easy for the user to understand, and sends them back to the device.

[1763] Terminal: Displays the received search results on a user interface (UI), for example, in a browser window or a dedicated app.

[1764] Specific examples

[1765] Here is a concrete example of how the system works:

[1766] Searching for materials during a meeting

[1767] User: Says, "Show me last year's financial report."

[1768] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[1769] Server: The audio is converted to "Show me last year's financial report" using the Google Speech-to-Text API and analyzed using SpaCy.

[1770] Server: Run an SQL query against the MySQL database to find files that match "Last Year's Financial Report."

[1771] Server: Search for "2022_Financial Report.pdf" in the database, generate a link, and send it to the device.

[1772] On the device: Opens the received link in a browser window and displays the PDF to the user.

[1773] Search for how to use Excel

[1774] User: Say "How do I use the SUM function?"

[1775] Terminal: Records audio, converts the audio data into 44.1kHz digital data, and sends it to the server.

[1776] Server: Convert the audio into "How do I use the SUM function?" using the Google Speech-to-Text API, and analyze it using NLTK.

[1777] Server: Run a SQL query against the PostgreSQL database to find information about how to use the SUM function.

[1778] Server: Searches the database for specific usage methods and examples of the SUM function and sends the text information to the terminal.

[1779] Device: The received text information is displayed in a dedicated app, providing the user with instructions on how to use the device.

[1780] In this way, the user can efficiently search for materials and information through voice input, and quickly and accurately obtain the information he or she needs.

[1781] Examples of prompt statements

[1782] Here are some examples of input prompts for a generative AI model:

[1783] Search for meeting materials

[1784] A user says, "Show me last year's financial report." Describe the process to convert this into text, search the database for the relevant documents, and display them.

[1785] Search for how to use Excel

[1786] A user speaks, "Tell me how to use the SUM function." Describe the process to convert this to text, search the database for the relevant information, and display it.

[1787] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1788] Step 1:

[1789] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1790] Input: User's voice

[1791] Output: Audio data

[1792] Specific operation: By speaking into the user's microphone, the audio is received through the device's built-in microphone or a connected microphone.

[1793] Step 2:

[1794] Device: Record audio in real time through the built-in microphone or an external microphone.

[1795] Input: Audio data

[1796] Output: Digital audio data

[1797] Specific operation: The recorded voice is converted into a digital signal by the terminal's voice input system and temporarily stored in memory.

[1798] Step 3:

[1799] Terminal: Transmits digitized voice data to a server via a network.

[1800] Input: Digital audio data

[1801] Output: Transmitted digital audio data

[1802] How it works: The device compresses the digital audio data and sends it over the Internet to a server using either HTTP or HTTPS.

[1803] Step 4:

[1804] Server: The received voice data is stored in storage and passed to the voice recognition engine.

[1805] Input: Transmitted digital audio data

[1806] Output: Saved audio and text data

[1807] Specific operation: The server temporarily stores the received voice data in storage, then sends it to a speech recognition engine and converts it into text data. This process is performed using, for example, the Google Speech-to-Text API.

[1808] Step 5:

[1809] Server: Converts voice data into text data using a speech recognition engine.

[1810] Input: Saved audio data

[1811] Output: Text data

[1812] Specific operation: Analyzes received voice data and converts it into corresponding text data. This is the process of converting spoken words into written information.

[1813] Step 6:

[1814] Server: Analyzes text data using a natural language processing (NLP) engine to understand the user's intent.

[1815] Input: Text data

[1816] Output: Parsed intent data

[1817] How it works: The server sends the text data to an NLP engine (e.g., SpaCy or NLTK) for contextual analysis and intent estimation, which identifies the information or resource the user is looking for.

[1818] Step 7:

[1819] Server: Searches for relevant materials and information from the database based on the user's request analyzed by the NLP engine.

[1820] Input: Parsed intent data

[1821] Output: Search result data

[1822] Specific operation: Based on the analysis results, the generated SQL query is sent to a database (e.g., MySQL, PostgreSQL) to perform a search. Related file names and information are identified.

[1823] Step 8:

[1824] Server: Organizes the search results and converts them into a format that is easy for the user to understand.

[1825] Input: Search result data

[1826] Output: Formatted data

[1827] Specific operation: Search results are converted into a data format such as JSON or XML, and formatted to be user-friendly, such as a file link or text information.

[1828] Step 9:

[1829] Server: Returns the formatted search results to the terminal via the network.

[1830] Input: Formatted data

[1831] Output: Search result data sent

[1832] Specific operation: The formatted data is returned to the terminal and communicated using the HTTP or HTTPS protocol.

[1833] Step 10:

[1834] Terminal: Displays the received search results on a user interface (UI).

[1835] Input: Submitted search result data

[1836] Output: Displayed information

[1837] What it does: It displays search results in a browser or dedicated app, allowing users to visually access information. For example, they can click links to open files or read text information.

[1838] (Application example 1)

[1839] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1840] Conventional voice-activated information search systems have been primarily used for office work and document search during meetings. However, in factories, there are many situations where workers cannot use their hands, so there is a need for a system that can easily check the location of parts and inventory information. In particular, in large factories, where there are many parts, manually searching for information is inefficient, making it difficult to improve work efficiency.

[1841] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1842] In this invention, the server includes a voice input means, a means for transmitting voice data to the server, a means for converting the voice data into text data, a means for searching a database for related information based on the analysis results, a means for returning the search results to a user terminal, and a means for issuing voice instructions to a factory robot to search for parts lists and inventory information. This makes it possible to quickly search for parts lists and inventory information using voice instructions within the factory, greatly improving work efficiency.

[1843] The "voice input means" refers to a device or software that receives a user's voice instruction and acquires it as voice data.

[1844] "Means for transmitting voice data to a server" refers to a method or technology for digitizing the acquired voice data and transmitting it to a server via a network.

[1845] "Means for converting voice data into text data" refers to software or algorithms that use voice recognition technology to convert voice data into text information.

[1846] "Means for analyzing text data to understand user intent" refers to a system or method that uses natural language processing technology to extract user requests and intent from text data.

[1847] "Means for searching for related information from a database based on the analysis results" refers to a technique or method for querying an internal database for relevant information based on the analysis results and obtaining the necessary data.

[1848] "Means for returning search results to the user terminal" refers to a system or protocol for sending the acquired data to the user terminal and notifying the user by display or voice.

[1849] "Means for giving voice instructions to factory robots to search for parts lists and inventory information" refers to a system or method for issuing voice commands to robots in a factory and searching for parts lists and inventory information based on those commands.

[1850] The present invention is a system for quickly searching for parts lists and inventory information within a factory. A specific embodiment of this system is shown below.

[1851] System configuration

[1852] This system consists of the following elements:

[1853] Voice input means

[1854] A means of sending audio data to the server

[1855] A means of converting audio data into text data

[1856] A means of analyzing text data to understand user intent

[1857] A means of searching for related information from a database based on the analysis results

[1858] A means for returning search results to the user's device

[1859] A way to give voice commands to factory robots to retrieve parts lists and inventory information

[1860] Hardware and software used

[1861] 1. Voice input method

[1862] Hardware: Microphone

[1863] Software: Voice input module (e.g. Google Cloud Speech-to-Text API)

[1864] 2. A method for sending audio data to the server

[1865] Hardware: The robot's processor

[1866] Software: Data transmission module

[1867] 3. Means of converting audio data into text data

[1868] Hardware: Server

[1869] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[1870] 4. A means of analyzing text data to understand user intent

[1871] Hardware: Server

[1872] Software: Natural Language Processing (NLP) engines (e.g., spaCy, OpenAI GPT-4)

[1873] 5. A means of searching databases for relevant information

[1874] Hardware: Server

[1875] Software: Database management system (e.g., MySQL, PostgreSQL)

[1876] 6. Means of returning search results to the user's device

[1877] Hardware: Server

[1878] Software: Data return module

[1879] 7. A way to give voice commands to factory robots to retrieve parts lists and inventory information.

[1880] Hardware: Factory robots

[1881] Software: Robot control system

[1882] Process Overview

[1883] This system allows users to quickly search for parts lists and inventory information within a factory by giving verbal instructions. When a user gives voice input, the voice data is picked up through a microphone, digitized, and sent to a server. On the server, the voice data is converted into text data using a speech recognition engine. A natural language processing (NLP) engine then analyzes the text data to understand the user's intent. Based on the results of the analysis, relevant parts lists and inventory information are searched for in the database, and this information is then sent back from the server to the user's device, specifically the robot. The robot can display the results on a screen or provide verbal feedback using a text-to-speech engine.

[1884] Specific examples

[1885] For example, consider the case where a worker voice-inputs, "Tell me the location of part B." The system operates as follows:

[1886] 1. The microphone picks up the voice message "Tell me the location of part B" and sends it to the server.

[1887] 2. The server's speech recognition engine converts this speech into text data such as "Tell me the location of part B."

[1888] 3. The NLP engine analyzes the text data and extracts the user's intent, such as "I want to know the location of part B."

[1889] 4. The server searches the database for the "location of part B" information and retrieves the result "Location: Shelf number A3."

[1890] 5. The result is sent back to the robot, which notifies the worker via the robot's display and speaker. A voice message is output saying, "Part B is located on shelf number A3."

[1891] Prompt Sentence Examples

[1892] Below is an example of a prompt to input to a generative AI model for speech analysis (e.g., OpenAI GPT-4):

[1893] Convert the user's voice input into text and analyze its intent. Analyze the following text, extract the user's intent and request, and generate a response.

[1894] Text: "What is the stock of part A?"

[1895] In this way, workers can instantly obtain information using voice instructions, greatly improving work efficiency within the factory.

[1896] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1897] Step 1:

[1898] The user inputs voice data using a voice input means (microphone), such as "Please tell me the stock of part A."

[1899] Input: User's voice command

[1900] Output: Audio data

[1901] Specific behavior: A user speaks into a microphone, "Tell me the inventory of part A." The microphone captures the voice signal.

[1902] Step 2:

[1903] The terminal digitizes the voice data for transmission to the server, and then transmits it to the server via the network using a data transmission module.

[1904] Input: Audio data

[1905] Output: Digitized audio data

[1906] What it does: Digitizes audio data and sends it to a server over the Internet or a local network.

[1907] Step 3:

[1908] The server receives the voice data and converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[1909] Input: Digitized audio data

[1910] Output: Text data

[1911] Specific operation: The server analyzes the voice data and converts it into text such as "Please tell me the stock of part A."

[1912] Step 4:

[1913] The server analyzes the text data using a natural language processing (NLP) engine (e.g., spaCy, OpenAI GPT-4) to understand the user's intent.

[1914] Input: Text data

[1915] Output: Analysis results including user intent

[1916] Specific operation: The NLP engine extracts the user's intent, such as "I want to know the inventory of part A."

[1917] Step 5:

[1918] Based on the analysis results, the server uses a database management system (e.g., MySQL, PostgreSQL) to search for relevant information from a database.

[1919] Input: Analysis results including user intent

[1920] Output: Search results (e.g., inventory information for part A)

[1921] Specific operation: The server searches the database for inventory information corresponding to "Part A" and obtains the necessary information (e.g., inventory quantity).

[1922] Step 6:

[1923] The server returns the search results to the user's terminal, and the data return module is used to deliver the results to the robot.

[1924] Input: Search results (e.g., inventory information for part A)

[1925] Output: Displayable data (text and audio formats)

[1926] Specific actions: Organize search results and return them to the robot as text data, including information for converting the text to speech.

[1927] Step 7:

[1928] The terminal (factory robot) receives the search results and displays them on a screen or provides audio feedback using a text-to-speech engine (e.g., Google Text-to-Speech API).

[1929] Input: Displayable data (text or audio format)

[1930] Output: Feedback to the user (visual or audio output)

[1931] Specific operation: The robot will announce "There are 30 units of part A in stock" by voice and display the stock information on the screen.

[1932] In this way, a system is realized that specifically describes how voice data is processed at each step and can quickly provide related information based on the user's voice instructions.

[1933] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1934] The present invention relates to a system that uses voice input to efficiently search for materials and information during work, and further recognizes the user's emotions and provides appropriate responses. This system aims to improve the user's work efficiency and user experience through voice input, voice recognition, natural language processing, database search, emotion recognition engine, and result feedback.

[1935] Overall system configuration

[1936] This system mainly consists of the following elements:

[1937] A device that receives user voice input

[1938] Server that processes received voice data

[1939] Speech Recognition Engine

[1940] Natural Language Processing (NLP) Engine

[1941] Database

[1942] Emotion Recognition Engine

[1943] Specific processing

[1944] In this system, when the user inputs voice, materials and information are searched for and an appropriate response is provided according to the user's emotions. The specific processing is explained below.

[1945] 1. Acquiring voice input

[1946] User: Uses voice input to make a request such as "Show me this year's meeting materials."

[1947] Device: Records audio through a microphone and acquires it as audio data in real time.

[1948] 2. Sending audio data

[1949] Terminal: The acquired voice data is digitized and sent to the server via the network.

[1950] 3. Analysis of audio data

[1951] Server: Receives the voice data and converts it into text using a speech recognition engine.

[1952] Server: The converted text data is analyzed using a natural language processing (NLP) engine to understand the user's intent.

[1953] 4. Emotional Recognition

[1954] Server: Uses an emotion recognition engine to analyze the user's emotional state from the voice data.

[1955] Server: As a result, identify the user's emotions, such as excited, anxious, relaxed, etc.

[1956] 5. Database Search

[1957] Server: Based on the analysis results of the NLP engine and emotion recognition, it searches for relevant materials and information from the company's internal database.

[1958] 6. Adjusting the results

[1959] Server: The server organizes the materials and information found as search results into an appropriate format based on the user's emotions and returns it to the device. For example, if the user is feeling anxious, the server may return the information in a format that emphasizes the main points.

[1960] 7. Returning search results

[1961] Server: Sends the compiled search results to the device. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf".

[1962] Terminal: Displays the received search results to the user.

[1963] Specific examples

[1964] For example, consider the case where a user speaks during a meeting and says, "Show me last year's financial report." The system operates as follows.

[1965] Device: Record the voice "Show me last year's financial statement" and send it to the server.

[1966] Server: The speech is converted into "Show me last year's financial report" using a speech recognition engine, and then analyzed using an NLP engine.

[1967] Server: The emotion recognition engine analyzes the emotions from the user's voice and determines, for example, that the user is relaxed.

[1968] Server: Search the database for files that correspond to "last year's financial statement."

[1969] Server: Returns search results in a format that includes detailed descriptions depending on the user's relaxed state.

[1970] Terminal: Display the found financial statements to the user.

[1971] The same process is also performed if a user voice-types "Tell me how to use the SUM function" while working in Excel.

[1972] Device: Record the voice "Tell me how to use the SUM function" and send it to the server.

[1973] Server: The speech is converted into "Please tell me how to use the SUM function" using a speech recognition engine, and then analyzed using an NLP engine.

[1974] Server: The emotion recognition engine determines that the user is anxious.

[1975] Server: Retrieves information from a database about the specific use of the SUM function.

[1976] Server: Return search results in a concise format that emphasizes key points and is tailored to impatient users.

[1977] Terminal: Display the found information to the user.

[1978] In this way, by combining it with an emotion recognition engine, flexible responses that adapt to the user's emotional state become possible, greatly improving work efficiency and user experience.

[1979] The processing flow will be explained below.

[1980] Step 1:

[1981] The user inputs voice, for example, "Show me this year's meeting materials." The device records this voice through a microphone.

[1982] Step 2:

[1983] The device digitizes the recorded voice data and sends it to a server, which transmits the digital data in real time over a network.

[1984] Step 3:

[1985] The server receives the voice data and converts it into text data using a speech recognition engine, such as "Show me the materials for this year's conference."

[1986] Step 4:

[1987] The server analyzes the text data using a natural language processing (NLP) engine to understand the user's intent. For example, it identifies the phrase "conference materials" and determines what information the user is specifically seeking.

[1988] Step 5:

[1989] The server uses an emotion recognition engine to analyze the user's emotional state from the voice data, analyzing the tone, speed, rhythm, etc. of the voice to identify emotions such as "excited," "anxious," or "relaxed."

[1990] Step 6:

[1991] The server searches the company database based on the analysis results of the NLP engine and emotion recognition, and identifies files and information related to "this year's conference materials."

[1992] Step 7:

[1993] The server summarizes the documents and information found as search results in an appropriate format depending on the user's emotional state. For example, if a user is in a hurry, the server summarizes the information in a concise format that emphasizes the main points.

[1994] Step 8:

[1995] The server sends the search results compiled by the server to the device as text data. For example, it sends a file name or link such as "2023_ConferenceMaterials.pdf."

[1996] Step 9:

[1997] The terminal displays the search results received to the user. The file names and links obtained as search results are displayed on the screen so that the user can easily access them.

[1998] Specific examples

[1999] Consider the case where a user speaks, "Show me last year's financial statement."

[2000] Step 1:

[2001] The user inputs voice, and the terminal records the voice.

[2002] Step 2:

[2003] The device digitizes the recorded audio and sends it to the server.

[2004] Step 3:

[2005] The server receives the voice data and converts it into "Show me last year's financial statement" using a voice recognition engine.

[2006] Step 4:

[2007] The server analyzes the text data using an NLP engine and identifies the phrase "last year's financial report."

[2008] Step 5:

[2009] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is relaxed.

[2010] Step 6:

[2011] Based on the analysis results, the server searches the database for "last year's financial statement."

[2012] Step 7:

[2013] The server compiles the search results in a format that includes detailed descriptions tailored to the user who is relaxing.

[2014] Step 8:

[2015] The server sends the search results compiled to the terminal.

[2016] Step 9:

[2017] The terminal displays the received search results to the user.

[2018] Similarly, if the user says "Tell me how to use the SUM function," the following will happen:

[2019] Step 1:

[2020] The user gives voice input, and the device records the voice.

[2021] Step 2:

[2022] The device digitizes the recorded audio and sends it to the server.

[2023] Step 3:

[2024] The server receives the voice data and converts it into "Tell me how to use the SUM function" using a voice recognition engine.

[2025] Step 4:

[2026] The server analyzes the text data using an NLP engine and identifies the phrase "How to use the SUM function."

[2027] Step 5:

[2028] The server uses an emotion recognition engine to analyze the user's emotions from the voice and determines that the user is anxious.

[2029] Step 6:

[2030] The server searches the database for how to use the SUM function based on the analysis results.

[2031] Step 7:

[2032] The server summarizes the information in a concise format that emphasizes key points.

[2033] Step 8:

[2034] The server sends the compiled information to the terminal.

[2035] Step 9:

[2036] The terminal displays the received information to the user.

[2037] In this way, through specific steps, information according to the user's request is provided, and the emotion engine makes it possible to respond according to the user's emotions.

[2038] Example 2

[2039] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2040] While conventional speech recognition systems allow users to search for information through voice input, they are unable to adjust responses based on the user's emotional state, resulting in a limited user experience and low effectiveness, especially in stressful situations. Furthermore, searches using only speech recognition and natural language processing have difficulty fully understanding the user's intent, resulting in the problem of displaying inappropriate results.

[2041] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2042] In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, and means for recognizing the user's emotional state, which makes it possible to present information in a format that is adapted to the user's emotions, thereby significantly improving work efficiency and the user experience.

[2043] The "voice input means" is a means for acquiring voice information uttered by the user.

[2044] The "means for transmitting voice data to a server" refers to a means for transmitting the acquired voice data to a server via a network.

[2045] The "means for converting voice data into text data" refers to a means for converting voice data into text data expressed as a character string.

[2046] "Means for analyzing text data to understand user intent" refers to means for processing text data and understanding the content of a user's requests or questions.

[2047] The "means for searching a database for related information based on the analysis results" refers to a means for searching a database for related information based on the user's intentions.

[2048] The "means for returning search results to the user terminal" refers to a means for transmitting search results obtained from the database to the user terminal.

[2049] The "means for recognizing the user's emotional state" is a means for determining the user's current emotions from the user's voice and other information.

[2050] The "means for adjusting search results according to the user's emotions" is a means for adjusting the display format and content of search results based on the recognized emotional state of the user.

[2051] This invention relates to a system that allows users to efficiently search for materials and information through voice input, and also recognizes the user's emotions and provides appropriate responses. The system aims to improve the user's work efficiency and experience through voice input, voice recognition, natural language processing, database search, an emotion recognition engine, and feedback of the results.

[2052] Overall system configuration

[2053] This system mainly consists of the following elements:

[2054] A device that receives user voice input

[2055] Server that processes received voice data

[2056] Speech recognition engine (e.g. Google Speech-to-Text API)

[2057] Natural Language Processing (NLP) engines (e.g., OpenAI's GPT-4)

[2058] Database (e.g. Microsoft SQL Server)

[2059] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[2060] Voice input and data processing flow

[2061] 1. Acquiring voice input

[2062] Users can make requests via voice input, such as "Show me this year's meeting materials."

[2063] The device records audio through a built-in microphone and converts the audio data into a digital format in real time.

[2064] 2. Sending audio data

[2065] The terminal compresses the digitized voice data and transmits it over the network to the server, where it also encrypts the data to ensure security.

[2066] 3. Analysis of audio data

[2067] The server receives the voice data and converts it into text using a speech recognition engine, which then analyzes it with a natural language processing (NLP) engine to understand the user's intent.

[2068] 4. Emotional Recognition

[2069] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, and as a result, identifies emotions such as excitement, impatience, or relaxation.

[2070] 5. Database Search

[2071] The server searches for relevant information from the company's internal database based on the analysis results of the natural language processing engine and the emotion recognition results.

[2072] 6. Adjusting the results

[2073] The server then organizes the search results into a format appropriate for the user's emotions, for example, highlighting key points for a user who is in a hurry, and including more detailed information for a user who is relaxed.

[2074] 7. Returning search results

[2075] The server sends the formatted search results to the terminal, which then displays the received search results to the user. For example, it displays a file name such as "2023_ConferenceMaterials.pdf" as a link so that the user can click it to access the document directly.

[2076] Specific examples

[2077] Example 1: Searching for documents during a meeting

[2078] Consider a case where a user voice-inputs "Show me last year's financial report" during a meeting.

[2079] Terminal: The voice "Show me last year's financial statement" is recorded with a microphone, digitized, compressed, and sent to the server.

[2080] Server: The speech recognition engine converts the request to "Show me last year's financial report," and the NLP engine analyzes it.

[2081] Server: Determines "relaxed" using emotion recognition engine. Searches for "last year's financial report" from the database and formats it with detailed explanations.

[2082] Server: The formatted results are returned to the terminal, and the terminal displays a link to "Last Year's Financial Report.pdf".

[2083] Users can click on the link provided to view the report.

[2084] Example 2: Excel work support

[2085] Consider the case where a user is working in Excel and says, "Tell me how to use the SUM function."

[2086] Terminal: Record the audio "Teach me how to use the SUM function," digitize it, compress it, and send it to the server.

[2087] Server: The speech recognition engine converts the request to "Please tell me how to use the SUM function," and the NLP engine analyzes it.

[2088] Server: The emotion recognition engine determines that the person is in a hurry. It searches the database for ways to use the SUM function and formats it to emphasize the main points.

[2089] Server: The formatted result is sent back to the terminal, and the terminal displays a link to "How to use the SUM function.pdf".

[2090] Users: Click the link provided to learn how to use it.

[2091] As described above, this system plays a specific role at each processing step, providing flexible responses while adapting to the user's emotional state, thereby significantly improving work efficiency and user experience.

[2092] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2093] Step 1:

[2094] Acquiring voice input

[2095] Users can make requests via voice input, such as "Show me this year's meeting materials."

[2096] The device uses a built-in microphone to record audio, and noise-canceling technology is used to capture clear audio data.

[2097] The input is the user's speech, and the output is recorded voice data.

[2098] Step 2:

[2099] Sending audio data

[2100] The device digitizes the acquired voice data and converts it into a file format.

[2101] The device compresses the digitized voice data and transmits it over the network to the server, encrypting the data for security reasons.

[2102] The input is recorded audio data, and the output is a compressed and encrypted audio file.

[2103] Step 3:

[2104] Analysis of audio data

[2105] The server decompresses the audio data received via the network and temporarily stores it.

[2106] The server converts the voice data into text data using a voice recognition engine (e.g., a general voice recognition API).

[2107] The server passes the converted text data to a natural language processing (NLP) engine (e.g., a general natural language processing model) to analyze the user's intent.

[2108] The input is a compressed and encrypted audio file, and the output is text data that represents the user's intent.

[2109] Step 4:

[2110] Emotion recognition

[2111] The server uses an emotion recognition engine (e.g., a general emotion recognition API) to analyze the user's emotional state from the text or voice data.

[2112] As a result of the analysis, the server identifies the user's emotions, such as excitement, impatience, or relaxation.

[2113] The input is text data and voice data, and the output is the analysis result of the user's emotional state.

[2114] Step 5:

[2115] Database search

[2116] The server searches for relevant information from an internal database (e.g., a general database system) based on the analysis results of the natural language processing engine and the emotion recognition results.

[2117] The server performs query optimization to deliver fast and accurate search results.

[2118] The input is text data and emotional state that reflects the user's intention, and the output is the search results for related information.

[2119] Step 6:

[2120] Adjusting the results

[2121] The server organizes the materials and information obtained as search results in an appropriate format according to the user's feelings.

[2122] For example, the server formats the results to highlight key points for a user who is in a hurry, or to include more detailed information for a user who is relaxed.

[2123] The input is the search results for related information and the user's emotional state, and the output is the formatted search results.

[2124] Step 7:

[2125] Returning search results

[2126] The server sends the formatted search results to the terminal.

[2127] The terminal displays the received search results to the user.

[2128] For example, the device will display a file name such as "2023_Conference Materials.pdf" in the form of a link, allowing the user to access the document directly by clicking on it.

[2129] The input is the formatted search results, and the output is the resource links displayed to the user.

[2130] (Application example 2)

[2131] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2132] While conventional voice input systems can properly understand a user's intentions and provide necessary information, they do not respond to the user's emotional state. As a result, they are unable to respond flexibly to situations, such as when the user is in a hurry or relaxed, which can lead to a poor user experience. Furthermore, in workplaces such as factories, robots are required to efficiently understand users' voice instructions and provide appropriate responses according to their emotional state.

[2133] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for converting voice data into text data, means for analyzing the text data to understand the user's intention, means for recognizing the user's emotion, and means for adjusting search results in a format according to the emotion. This makes it possible to accurately understand the user's intention and provide appropriate information according to the user's emotional state.

[2134] The "voice input means" is a device for receiving the user's voice and recognizing it as digital voice data.

[2135] The "means for transmitting voice data to a server" is a function for transferring acquired voice data to a server via a network.

[2136] The "means for converting voice data into text data" is a process for converting voice data into linguistic text data using voice recognition technology.

[2137] "Means for analyzing text data to understand user intent" refers to a method that uses a natural language processing (NLP) engine to analyze the meaning of text data and understand what the user is looking for.

[2138] "Means for searching for related information from a database based on the analysis results" is a function for searching for related information from a database according to the intent analyzed by the NLP engine.

[2139] "Means for returning search results to the user terminal" refers to a method for transmitting data to the terminal in order to display the searched information or materials to the user.

[2140] "Means for recognizing user emotions" refers to technology for detecting the user's emotional state (for example, relaxed, anxious, excited, etc.) from voice data or text data.

[2141] The "means for adjusting search results in a format according to emotions" is a function for adjusting and providing information in a format or presentation method according to the recognized emotional state of the user.

[2142] The present invention relates to a system that uses voice input to efficiently search for information during work, and further recognizes the user's emotions and provides appropriate responses. This system is composed of the following elements:

[2143] Overall system configuration

[2144] 1. Voice input method:

[2145] A device for user voice input. This device can be integrated into a smartphone with a microphone, smart glasses, a head-mounted display, or a factory robot. This means is used to recognize the user's voice as digital audio data.

[2146] 2. How to send audio data to the server:

[2147] The voice data acquired by the voice input means has a function to transmit it to the server via the network. This means is important for transferring the voice data to the server quickly and accurately.

[2148] 3. How to convert audio data to text data:

[2149] The server converts the acquired voice data into text data using a voice recognition engine (e.g., Google API). Through this process, the voice data is interpreted as language text.

[2150] 4. Means of analyzing text data to understand user intent:

[2151] The server analyzes the text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, it clarifies what the user is looking for.

[2152] 5. How to recognize user emotions:

[2153] The server recognizes the user's emotional state from the analyzed text and voice data using an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tools). Emotional states such as "relaxed," "anxious," and "excited" are identified.

[2154] 6. How to tailor search results based on sentiment:

[2155] The server retrieves relevant information and tailors it to the user's emotional state, for example, returning information in a concise format that emphasizes key points if the user is in a hurry.

[2156] 7. Means for returning search results to the user's device:

[2157] The server sends the adjusted search results to the user's device, allowing the device to display the information the user needs in an appropriate format.

[2158] Specific examples

[2159] 1. Example during a meeting:

[2160] If a user speaks during a meeting, "Show me last year's financial report," the system operates as follows:

[2161] Device: Records audio and sends it to the server.

[2162] Server: Converts voice data into text data and analyzes the user's intent.

[2163] Server: Recognizes the user's emotional state, determining, for example, whether they are relaxed.

[2164] Server: Searches the database for the relevant financial statements and returns them in a detailed explanatory format.

[2165] Device: View search results.

[2166] 2. Example of program code:

[2167] Example prompt sentence:

[2168] User: "Show me last year's financial statements."

[2169] System: "Last year's financial report can be found at: Meeting Materials / 2023 / Financial Report.pdf."

[2170] or

[2171] User: "How do I use the SUM function?"

[2172] System: "(Key point) The SUM function calculates the sum of a range of numbers."

[2173] This system can provide necessary information quickly and appropriately based on the user's voice input and emotional state, which is expected to significantly improve user experience and work efficiency.

[2174] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2175] Step 1:

[2176] The user gives a voice command (e.g., "Show me last year's financial statement") through the voice input means. This voice input is recorded by the microphone of the terminal. The input is taken into the system as voice data. The output is the recorded voice data.

[2177] Step 2:

[2178] The device converts the captured voice data into a digital format and sends it to the server over the network. This step involves digitizing and transferring the voice data. The input is the recorded voice data, and the output is the digital voice data sent to the server.

[2179] Step 3:

[2180] The server converts the received voice data into text data using a speech recognition engine (e.g., Google API). This conversion is the process of converting voice signals into text information. The input is digital voice data, and the output is text data.

[2181] Step 4:

[2182] The server analyzes the generated text data using a natural language processing (NLP) engine (e.g., SpaCy or NLTK) to understand the user's intent. At this stage, the text data is processed to analyze its grammar and meaning. The input is the text data, and the output is the analysis result (identification of the user's intent).

[2183] Step 5:

[2184] The server uses an emotion recognition engine (e.g., TextBlob or Sentiment Analysis tool) to recognize the user's emotional state from the text data and characteristics specific to the voice. Here, the user's feeling tendency is analyzed. The input is text data, and the output is the user's emotional state (e.g., relaxed, anxious).

[2185] Step 6:

[2186] The server searches for relevant information from a database based on the NLP analysis results and emotion recognition results. Specifically, it extracts relevant database entries based on the user's instructions (e.g., "last year's financial report"). The input is the NLP analysis results and emotion recognition results, and the output is a list of relevant information.

[2187] Step 7:

[2188] The server tailors search results to reflect the user's emotional state. For example, if the user is in a hurry, the server modifies the information to emphasize key points and provide a concise format. The input is the user's emotional state and a list of related information, and the output is the tailored search results.

[2189] Step 8:

[2190] The server sends the adjusted search results to the terminal, which then displays the information the user needs in an appropriate format. The input is the adjusted search results, and the output is what is displayed to the user.

[2191] Step 9:

[2192] The device helps the user prepare for the next action based on the displayed information. The input is the user's action, and the output is preparation for the next step.

[2193] This system allows users to efficiently search for information using voice and receive information in the most appropriate format depending on their emotional state.

[2194] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2195] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2196] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2197] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2198] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2199] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2200] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2201] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2202] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2203] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2204] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2205] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2206] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2207] 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.

[2208] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2209] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2210] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2211] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2212] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2213] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2214] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2215] The following is further disclosed regarding the above embodiment.

[2216] (Claim 1)

[2217] A voice input means;

[2218] means for transmitting audio data to a server;

[2219] means for converting voice data into text data;

[2220] A means of analyzing text data to understand user intent;

[2221] A means for searching a database for relevant information based on the analysis results;

[2222] The system includes means for returning search results to the user terminal.

[2223] (Claim 2)

[2224] A means for searching for file names by voice input during a meeting;

[2225] A means to search for materials by voice command while working on a PC,

[2226] A means to search for tools and functions by voice command while using the software;

[2227] 2. The system according to claim 1, which provides appropriate information according to the user's intention.

[2228] (Claim 3)

[2229] 2. The system according to claim 1, further comprising means for analyzing the voice data in real time and promptly presenting corresponding information to a user.

[2230] "Example 1"

[2231] (Claim 1)

[2232] A voice input means;

[2233] means for digitizing the voice data and transmitting it to a server;

[2234] a speech recognition means for converting speech data into text data;

[2235] natural language processing means for analyzing text data to understand user intent;

[2236] A means for searching a database for relevant information based on the analysis results;

[2237] The system includes means for returning search results to the terminal for display to the user.

[2238] (Claim 2)

[2239] A means for searching for documents by voice input during a meeting;

[2240] A means for searching for materials and information by voice command while working;

[2241] A means to find tools and features by voice prompts while using the software;

[2242] 2. The system according to claim 1, which provides appropriate information according to the user's intention.

[2243] (Claim 3)

[2244] 2. The system according to claim 1, further comprising means for analyzing the voice data in real time and immediately presenting corresponding information to a user.

[2245] "Application Example 1"

[2246] (Claim 1)

[2247] A voice input means;

[2248] means for transmitting audio data to a server;

[2249] means for converting voice data into text data;

[2250] A means of analyzing text data to understand user intent;

[2251] A means for searching a database for relevant information based on the analysis results;

[2252] means for returning search results to the user terminal;

[2253] A system that includes a means to give voice instructions to factory robots to retrieve parts lists and inventory information.

[2254] (Claim 2)

[2255] A means for searching for file names by voice input during a meeting;

[2256] A means to search for materials by voice command while working on a PC,

[2257] A means to search for tools and functions by voice command while using the software;

[2258] Quickly search for parts locations and inventory information using voice commands within the factory.

[2259] Provide a means for notifying the results by voice or text,

[2260] 2. The system according to claim 1, which provides appropriate information according to the user's intention.

[2261] (Claim 3)

[2262] 2. The system according to claim 1, further comprising means for analyzing the voice data in real time and promptly presenting information about parts in the factory to the user.

[2263] "Example 2: Combining Emotion Engines"

[2264] (Claim 1)

[2265] A voice input means;

[2266] means for transmitting audio data to a server;

[2267] means for converting voice data into text data;

[2268] A means of analyzing text data to understand user intent;

[2269] A means for searching a database for relevant information based on the analysis results;

[2270] means for returning search results to the user terminal;

[2271] means for recognizing the emotional state of a user;

[2272] A system including means for adjusting search results according to user sentiment.

[2273] (Claim 2)

[2274] The system of claim 1 includes means for searching for file names by voice input during a meeting, means for searching for materials by voice instructions while working on a PC, means for searching for tools and functions by voice instructions while using software, and means for providing appropriate information according to the user's intentions and emotions.

[2275] (Claim 3)

[2276] 2. The system according to claim 1, further comprising: means for analyzing the voice data in real time, and promptly presenting corresponding information to the user, and means for presenting the information in a format adapted to the user's emotions.

[2277] "Application example 2 when combining emotion engines"

[2278] (Claim 1)

[2279] A voice input means;

[2280] means for transmitting audio data to a server;

[2281] means for converting voice data into text data;

[2282] A means of analyzing text data to understand user intent;

[2283] A means for searching a database for relevant information based on the analysis results;

[2284] means for returning search results to the user terminal;

[2285] means for recognizing a user's emotion;

[2286] A system including a means for tailoring search results in a sentiment-sensitive format.

[2287] (Claim 2)

[2288] A means for searching for file names by voice input during a meeting;

[2289] A means to search for materials by voice command while working on a PC,

[2290] A means to search for tools and functions by voice command while using the software;

[2291] 2. The system according to claim 1, which provides appropriate information according to the user's intention.

[2292] (Claim 3)

[2293] means for analyzing the voice data in real time and promptly presenting corresponding information to a user;

[2294] 10. The system of claim 1, further comprising means for providing search results that are tailored according to the emotional state of the user. [Explanation of symbols]

[2295] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A voice input means; means for transmitting audio data to a server; means for converting voice data into text data; A means of analyzing text data to understand user intent; A means for searching a database for relevant information based on the analysis results; The system includes means for returning search results to the user terminal.

2. A means for searching for file names by voice input during a meeting; A means to search for materials by voice command while working on a PC, A means to search for tools and functions by voice command while using the software; 2. The system according to claim 1, wherein appropriate information is provided in accordance with the user's intention.

3. 2. The system according to claim 1, further comprising means for analyzing the voice data in real time and promptly presenting corresponding information to the user.

Images