system

Abstract

We provide the system. [Solution] A means for receiving a question entered by the user, A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions, A means for querying a database based on the aforementioned divided questions and obtaining corresponding information, A means for integrating the divided questions and corresponding information to generate a final answer, A means of providing the user with the aforementioned final answer, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern artificial intelligence systems and chatbots, when the questions input by users are ambiguous or multiple questions are mixed, there is a problem that it is difficult for these systems to provide accurate answers. Also, in order to improve the accuracy of information, access to a wide range of databases is required, but since many systems rely on limited databases, the accuracy of answers may decrease. As a result, users cannot obtain the information they need, resulting in a problem of low satisfaction.

Means for Solving the Problems

[0005] This invention provides a system that receives a question entered by a user, analyzes it using natural language processing technology, and converts it into multiple segmented questions. This system includes means for querying a database based on the segmented questions, retrieving corresponding information, and integrating the obtained information with the original question to generate a final answer. Furthermore, by accessing an extensive English-language database, it can obtain detailed and highly accurate information. This allows users to obtain appropriate information even from a single prompt, improving the system's usability and the accuracy of its answers.

[0006] A "user" is an individual or legal entity that uses this system to input questions and seek answers.

[0007] A "device" is a device used by a user to input questions and receive answers, and includes personal computers, smartphones, tablets, and other similar devices.

[0008] A "server" is a central computing system that analyzes, segments, queries databases, and generates final answers to questions received from users.

[0009] A "prompt" is the text data of a question or inquiry that a user enters into the device.

[0010] "Natural language processing" is a general term for the technologies and methods used by computers to understand, analyze, and generate human language.

[0011] A "divided question" is a prompt that has been analyzed using natural language processing and converted into multiple independent questions.

[0012] A "database" is a digital system for systematically organizing and storing information, and in this invention, it serves as a source of information in response to inquiries.

[0013] An "English-language database" is a database containing a wide range of information, primarily written in English, and is referenced to improve the accuracy of answers.

[0014] "Integration" is the process of combining divided questions and corresponding information into a single structure, forming a final answer.

[0015] The "final answer" is the result of providing the final information in response to the user's prompts, and is generated through analysis, segmentation, information retrieval, and integration.

[0016] "Providing" refers to the act of displaying or sending the final response generated by the server to the user via the terminal. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be described. <00,00106> In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[0039] Receiving a prompt

[0040] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[0041] Prompt analysis and segmentation

[0042] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[0043] Database query

[0044] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, especially the English version, to obtain detailed and accurate information.

[0045] Integration and purification

[0046] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[0047] Provision to users

[0048] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[0049] Specific example

[0050] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history."

[0051] 1. Terminal: The user submits the input content.

[0052] 2. Server: The server analyzes the received query and divides it as follows:

[0053] "What is artificial intelligence?"

[0054] "Please tell me about its history as well."

[0055] 3. Server: Access the English version of the database to retrieve additional information:

[0056] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0057] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0058] 4. Server: Integrates the divided questions and acquired information to generate the final answer:

[0059] "What is artificial intelligence?"

[0060] "Additional information: Artificial Intelligence is the field of study..."

[0061] "Please tell me about its history as well."

[0062] "Additional information: The history of AI dates back to the mid-20th century..."

[0063] 5. Terminal: Provides the final answer to the user.

[0064] "What is artificial intelligence?"

[0065] "Additional information: Artificial Intelligence is the field of study..."

[0066] "Please tell me about its history as well."

[0067] "Additional information: The history of AI dates back to the mid-20th century..."

[0068] Such a system allows users to obtain detailed and comprehensive information with a single question input, improving both the system's usability and the accuracy of the answers.

[0069] The following describes the processing flow.

[0070] Step 1: The user enters the question and presses the submit button.

[0071] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on the device and presses the send button.

[0072] Step 2: The device sends the user's query to the server.

[0073] The terminal sends the user's input to the server. This data is sent as text.

[0074] Step 3: The server receives and analyzes the query.

[0075] The server analyzes the questions received from the terminal. First, it uses natural language processing techniques to break down the questions into sentences and convert them into multiple specific questions.

[0076] Step 4: The server queries the database with the divided queries.

[0077] The server queries the database based on each segmented question and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves a wide range of information such as "Artificial Intelligence is the field of study...".

[0078] Step 5: The server also accesses the English version of the database.

[0079] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[0080] Step 6: Integrate the information obtained by the server with the original question.

[0081] The server integrates the acquired information with the original segmented questions to generate a final answer. For example, it might connect "What is artificial intelligence?" with "Artificial Intelligence is the field of study...".

[0082] Step 7: The server sends the final response to the terminal.

[0083] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[0084] Step 8: The device displays the final answer to the user.

[0085] The device displays the final received response to the user. The user can instantly see a comprehensive answer to the question.

[0086] (Example 1)

[0087] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] Conventional information retrieval systems have struggled to provide appropriate answers to user-inputted questions, and generating consistent and comprehensive responses, especially for complex questions, has been a challenge. Furthermore, there has been a need for systems that can access extensive databases spanning multiple languages ​​and possess high-precision analysis capabilities using natural language processing.

[0089] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0090] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a data storage device based on the segmented questions and obtaining corresponding information, means for integrating the segmented questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for performing tokenization and dependency analysis based on natural language processing and segmenting the question into sentence units, means for querying an external information provider for the generated questions and analyzing the obtained information, and means for generating a consistent answer using a generative model based on the obtained information. This makes it possible to provide complex and comprehensive information in response to a user's question with high accuracy.

[0091] A "user" is a person who uses the system to input and submit questions.

[0092] "Means of receiving" refers to the function of sending the entered question to the server via the network.

[0093] "Natural language processing" refers to the technology that enables computers to understand, analyze, and generate human language.

[0094] "Analysis" is the process of understanding the content of a question and grasping its meaning.

[0095] A "divided question" refers to multiple specific questions derived from analyzing the initial question.

[0096] A "data storage device" is a part of a system that stores and provides information, and often refers to a database or an external API.

[0097] "Means of querying and obtaining information" refers to the process of obtaining information corresponding to divided questions from a data storage device.

[0098] "Means of integrating to generate a final answer" refers to the process of integrating acquired information to create a consistent answer.

[0099] "Means of providing" refers to the function of displaying or sending the final answer to the user.

[0100] "Tokenization" is the process of dividing a text into units such as words or phrases.

[0101] "Dependency analysis" is the process of analyzing how words in a sentence are related to each other.

[0102] "Splitting into sentences" refers to the process of dividing a prompt message into multiple sentences.

[0103] An "external information provider" refers to an external data source that a server accesses to retrieve information.

[0104] A "generative model" is an AI technology used to generate new text or answers based on input data.

[0105] A "consistent answer" is one that is free from contradictions and has a unified logical structure.

[0106] The system of this invention receives a question entered by the user, analyzes and divides it, queries a data storage device to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[0107] Receiving a prompt

[0108] User: The user enters the question into the input field on the terminal and presses the submit button.

[0109] Terminal: The terminal sends this input to the server. This communication uses an HTTP POST request.

[0110] Prompt analysis and segmentation

[0111] Server: The server uses the Python®-based natural language processing tool "Open Source Natural Language Processing Toolkit" to parse the received prompts. Specifically, it performs the following processes:

[0112] Tokenization: Dividing a prompt into units of words or phrases.

[0113] Dependency analysis: Analyzes how words in a sentence are related to each other.

[0114] Split into sentences: Divide the prompt message into multiple sentences.

[0115] Convert into individual questions as needed.

[0116] Database query

[0117] Server: The server queries external information providers based on each segmented query. The following APIs are used for this:

[0118] A "general-purpose knowledge base API" for retrieving general information.

[0119] A "scientific data API" is used to obtain scientific data and facts.

[0120] The server sends an HTTP GET request to each API and receives data in JSON format.

[0121] Integration and purification

[0122] Server: The server integrates the acquired information and the segmented questions to generate the final answer. This process uses a generative AI model, the "Generative AI Engine." The specific steps are as follows:

[0123] The acquired JSON data is analyzed, and candidate answers are extracted.

[0124] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[0125] Regenerate the output as needed and select the optimal answer.

[0126] Provision to users

[0127] Server: The server sends the final generated response to the user's terminal.

[0128] Terminal: The terminal displays the received response to the user. This received data is in HTML format and is rendered correctly in the browser.

[0129] Specific example

[0130] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." The process in this case would be as follows:

[0131] 1. User: The user enters "What is artificial intelligence?" into the input field on the device and presses the send button.

[0132] 2. Terminal: The terminal sends data including this prompt to the server as an HTTP POST request.

[0133] 3. Server: The server analyzes the received query using a natural language processing toolkit and divides it as follows:

[0134] "What is artificial intelligence?"

[0135] "Please tell me about its history as well."

[0136] 4. Server: Access the General Knowledge Base API and Scientific Data API to retrieve additional information:

[0137] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0138] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0139] 5. Server: Inputs the acquired information into the AI ​​engine to generate consistent responses:

[0140] "What is artificial intelligence?" -> "Additional information: Artificial intelligence is the field of study..."

[0141] "Please also tell me about its history." -> "Additional information: The history of AI dates back to the mid-20th century..."

[0142] 6. Server: Converts the generated response into HTML format and sends it to the user's device.

[0143] 7. Terminal: The terminal displays the received HTML data in a browser and shows it to the user in the following format: "What is artificial intelligence?", "Additional information: Artificial Intelligence is the field of study...", "Please also tell me about its history.", "Additional information: The history of AI dates back to the mid-20th century...".

[0144] In this way, the system can provide accurate and comprehensive information in response to user inquiries.

[0145] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0146] Step 1: Receiving the prompt

[0147] User: The user enters a question into the input field on the terminal and presses the submit button.

[0148] Specific action: The user types, for example, "What is artificial intelligence?" and presses the submit button.

[0149] Input: The user entered the question, "What is artificial intelligence?".

[0150] Terminal: The terminal sends this input to the server. It uses an HTTP POST request for communication.

[0151] Output: Input data sent to the server.

[0152] Step 2: Prompt analysis and splitting

[0153] Server: The server utilizes a Python-based open-source natural language processing toolkit to parse the received prompts.

[0154] Specific actions:

[0155] Tokenization: Dividing a sentence into words or phrases. For example, dividing it into "artificial intelligence," "what is," and "what is it?".

[0156] Dependency analysis: This analyzes how words in a sentence relate to each other. For example, it identifies that "artificial intelligence" is the subject, "what is" is the predicate, and "what is it?" is the complement.

[0157] Split into sentences: Process each prompt statement as a single sentence.

[0158] Input: Received prompt message: "What is artificial intelligence?"

[0159] Output: The question, broken down into sentence units, obtained as a result of the analysis, for example, "What is artificial intelligence?".

[0160] Step 3: Query the database

[0161] Server: The server queries external information providers based on the questions generated through analysis.

[0162] Specific actions:

[0163] Send the query "What is AI?" to a general-purpose knowledge base API.

[0164] Send the query "What is AI?" to the scientific data API.

[0165] Receive data in JSON format from the API.

[0166] Input: Divided question "What is AI?".

[0167] Output: Retrieved response data in JSON format.

[0168] Step 4: Integration and Purification

[0169] Server: The server integrates the acquired information and the segmented questions to generate the final answer.

[0170] Specific actions:

[0171] The acquired JSON data is analyzed to extract potential answers. For example, information such as "Artificial Intelligence is the field of study..."

[0172] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[0173] If necessary, the AI ​​generation engine will regenerate the answer and select the most suitable response.

[0174] Input: Retrieved response data in JSON format.

[0175] Output: The final, integrated answer.

[0176] Step 5: Provision to users

[0177] Server: The server sends the final generated response to the user's terminal.

[0178] Terminal: The terminal displays the received response to the user.

[0179] Specific operation: The server sends HTML-formatted data to the user's device, and the device displays that data in its browser.

[0180] Input: The server's final generated response: "Artificial Intelligence is the field of study..."

[0181] Output: The final answer displayed to the user.

[0182] In this way, the system provides accurate and comprehensive information in response to user inquiries.

[0183] (Application Example 1)

[0184] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0185] Traditional systems that accept inquiries and provide information have struggled to provide optimal real-time responses to user-inputted instructions and questions. Furthermore, especially in autonomous vehicles, the immediate provision of traffic and navigation information is crucial, and the lack of systems capable of handling this has been a problem. Therefore, a new system is needed that enables real-time and detailed information provision, thereby improving user convenience.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0187] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into a plurality of divided questions, means for querying a database based on the divided questions and obtaining corresponding information, means for integrating the divided questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for the user to input instructions by voice or text, analyzing them and dividing them into specific questions, and means for generating and providing the optimal answer in real time based on the acquired information. This enables real-time and detailed information provision even in autonomous vehicles, improving user convenience and safety.

[0188] A "user" is someone who uses the system and inputs questions or instructions.

[0189] A "question" refers to a question or instruction that a user enters into the system, and it is a request for information or advice.

[0190] "Natural language processing" is a technology that enables computers to understand, analyze, and process human language.

[0191] A "divided question" is a question that has been analyzed using natural language processing and transformed into multiple specific questions.

[0192] A "database" is a system where information is stored and provides information that responds to user inquiries.

[0193] The "final answer" is the answer provided to the user, generated by integrating the divided questions and the corresponding information.

[0194] "Real-time" means that processing and information are provided almost instantly.

[0195] "Voice or text" refers to the method by which a user inputs a question to the system, and includes voice input and text input.

[0196] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments are described below.

[0197] 1. System Overview

[0198] Receiving a prompt

[0199] Terminal: The user enters and submits the question in voice or text format. The terminal sends this input to the server.

[0200] Prompt analysis and segmentation

[0201] Server: Upon receiving a prompt, the server analyzes the question using natural language processing techniques. The analysis process divides the question into sentences and, if necessary, converts them into more specific questions. This generates multiple specific questions.

[0202] Database query

[0203] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, especially the English version, to obtain detailed and accurate information.

[0204] Integration and purification

[0205] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[0206] Provision to users

[0207] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[0208] 2. Hardware and software used

[0209] hardware

[0210] Microphone and speaker: A device for users to input instructions by voice and receive responses by voice.

[0211] Terminal (smartphone, in-car display, etc.): A device used by the user to input questions and receive answers.

[0212] software

[0213] Natural Language Processing: A technique used to analyze a question and break it down into more specific questions. A concrete example is the Python Natural Language Toolkit (nltk) library.

[0214] Database access: A tool for querying a database and retrieving corresponding information. Examples include SQL databases and NoSQL databases.

[0215] Integration and Refinement: Logic for integrating acquired information and generating the final answer. Programming languages ​​such as Python or Ruby can be used.

[0216] 3. Specific examples

[0217] For example, let's look at a specific case where a user inputs a question via voice, such as, "Tell me about traffic congestion ahead."

[0218] Example of a prompt

[0219] "Please tell me about the traffic conditions ahead."

[0220] Execution process

[0221] 1. Terminal: The user provides voice input, which the system converts into text data. Alternatively, the user may have already entered the question in text format.

[0222] 2. Server: The server analyzes the received query using natural language processing technology and divides it into "traffic information" and "what's ahead".

[0223] 3. Server: Retrieves real-time data related to "traffic congestion information" from the database, and simultaneously retrieves location information related to "what's ahead".

[0224] 4. Server: Integrates the acquired information and generates a final response (e.g., "There is traffic congestion 5km ahead. The recommended detour is here.").

[0225] 5. Device: Provide this final answer to the user. It will be displayed via voice or on the screen.

[0226] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0227] Step 1:

[0228] Input: The user enters the question via voice or text.

[0229] Operation: In the case of voice input, the device uses the microphone to capture voice data and converts it to text using speech recognition software (e.g., Google® Speech Recognition API).

[0230] Output: Sends a question in text format to the server.

[0231] Step 2:

[0232] Input: The server receives the user's query in text format.

[0233] Operation: The server analyzes the question using natural language processing (NLP) techniques. Specifically, it uses Python's Natural Language Toolkit (nltk) and the spaCy API to break down the question into sentences and convert them into more specific, subdivided questions.

[0234] Output: Generates a list of specific questions broken down into segments.

[0235] Step 3:

[0236] Input: A list of specific questions divided into sections.

[0237] Operation: The server queries the database based on each segmented query. It references SQL and NoSQL databases to retrieve corresponding information in real time.

[0238] Output: Generates a list of corresponding information for each question.

[0239] Step 4:

[0240] Input: A list of divided questions and a list of corresponding information.

[0241] Operation: The server integrates the acquired information and generates the final answer using natural language generation (NLG) technology. It constructs the sentence into a natural form using programs such as Python or Ruby.

[0242] Output: Generates the final answer and outputs it in text format.

[0243] Step 5:

[0244] Input: Final response generated by the server.

[0245] Operation: The device displays the response received from the server. If audio output is required, it converts it to speech using a Text-to-Speech (TTS) engine (e.g., Google Text-to-Speech API) and outputs it through the speaker.

[0246] Output: Provides the user with the final answer in text and audio formats.

[0247] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0248] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[0249] Receiving a prompt

[0250] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[0251] Prompt analysis and segmentation

[0252] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[0253] Emotion recognition by an emotion engine

[0254] Server: Next, the server uses an emotion engine to recognize emotions from the questions entered by the user. The emotion engine extracts and analyzes emotional information from the user's text. This emotional information includes various emotions such as anger, sadness, and joy.

[0255] Database query

[0256] Server: Based on each generated query, the server queries the database and retrieves the corresponding information. This database is multilingual, and can access a particularly extensive English version of the database to obtain detailed and accurate information. Based on the sentiment information obtained by the sentiment engine, it selects information that is appropriate to the emotion.

[0257] Integration and purification

[0258] Server: Integrates acquired information, segmented questions, and sentiment information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent answer. By adding sentiment information, it provides answers that are easier for users to understand and empathize with.

[0259] Provision to users

[0260] Terminal: The final answers generated by the server are sent to the user's terminal. The terminal displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[0261] Specific example

[0262] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would handle the situation if it detects that the user's question contains feelings of anger.

[0263] 1. Terminal: The user submits the input content.

[0264] 2. Server: The server analyzes the received query and divides it as follows:

[0265] "What is artificial intelligence?"

[0266] "Please tell me about its history as well."

[0267] 3. Server: Analyzes user emotions using an emotion engine:

[0268] The user's question contains feelings of anger.

[0269] 4. Server: Access the English version of the database to retrieve additional information:

[0270] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0271] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0272] 5. Server: Integrates the segmented questions, acquired information, and sentiment information to generate the final answer:

[0273] "What is artificial intelligence?"

[0274] "Additional information: Artificial Intelligence is the field of study..."

[0275] "To answer your questions, we will provide you with more detailed information, so please let us know."

[0276] "Please tell me about its history as well."

[0277] "Additional information: The history of AI dates back to the mid-20th century..."

[0278] "If you'd like to delve deeper into history, we also have textbook-style materials available."

[0279] 6. Terminal: Provides the final answer to the user.

[0280] Such a system allows users to obtain detailed and comprehensive information with a single question input, while simultaneously improving the user experience by enabling the system to respond in a way that is sensitive to the user's emotions.

[0281] The following describes the processing flow.

[0282] Step 1: The user enters a question and presses the send button.

[0283] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." in the input field of the terminal. Then, the user presses the send button to send the question.

[0284] Step 2: The terminal sends the user's question to the server.

[0285] The terminal sends the question entered by the user to the server. At this time, the input text data is sent to the server.

[0286] Step 3: The server receives and analyzes the question.

[0287] The server analyzes the received question. First, it uses natural language processing technology to split the question into sentence units and convert it into individual questions that are refined as needed. For example, a question like "What is artificial intelligence? Please also tell me about its history." is split into "What is artificial intelligence?" and "Please also tell me about its history."

[0288] Step 4: The server recognizes the user's sentiment.

[0289] The server uses a sentiment engine to recognize the sentiment from the user's question. The sentiment engine analyzes the text data of the question and detects the user's sentiment (such as anger, sadness, joy, etc.). For example, it is determined that the user's question contains a somewhat angry sentiment.

[0290] Step 5: The server queries the database with the split questions.

[0291] Next, the server queries the database based on each of the divided questions and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves information such as "Artificial Intelligence is the field of study...", and in response to "Please also tell me about its history," it retrieves information such as "The history of AI dates back to the mid-20th century...".

[0292] Step 6: The server also accesses the English version of the database.

[0293] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[0294] Step 7: Integrate the information obtained by the server with the original question.

[0295] The server integrates the acquired information, segmented questions, and emotional information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent response. Adding emotional information provides answers that are easier for users to understand and empathize with.

[0296] Step 8: The server sends the final response to the terminal.

[0297] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[0298] Step 9: The device displays the final answer to the user.

[0299] The device displays the final received answer to the user. The user can instantly see a comprehensive answer to their question. For example, in response to the question, "What is artificial intelligence?", it will display, "Artificial Intelligence is the field of study... Please let us know if you would like more information to answer your question." Also, in response to "Please tell me about its history," it will display, "The history of AI dates back to the mid-20th century... If you would like to delve deeper into its history, we also have textbook-style materials available."

[0300] In this way, users can obtain comprehensive information with a single question input, and receive highly relevant answers that reflect their emotions at the time of input, thus improving the user experience.

[0301] (Example 2)

[0302] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0303] Conventional question-answering systems have a problem in that the process of receiving user-entered questions and providing corresponding answers is not properly handled, making it difficult to obtain satisfactory answers, especially for complex or emotionally charged questions. Furthermore, there was a lack of means to quickly retrieve detailed information from multilingual databases and present it to users in an easily understandable way. In addition, the ability to generate optimal answers that take into account the user's emotions was insufficient.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an inquiry input by a user, means for analyzing the inquiry using natural language processing and converting it into a plurality of divided inquiries, means for querying a database based on the divided inquiries and obtaining corresponding information, means for integrating sentiment information in addition to the divided inquiries and the corresponding information to generate a final answer, and means for providing the final answer to the user. Thereby, the user can quickly obtain detailed and consistent information, and further the system can provide an optimal answer according to the user's sentiment. Also, by using a multilingual database, it is possible to provide richer information.

[0305] A "user" refers to an individual or group that uses the system.

[0306] An "input" refers to information or an inquiry provided by a user to the system.

[0307] An "inquiry" refers to a question asked by a user to the system.

[0308] "Natural language processing" is a technology for a computer to understand, analyze, and generate human language.

[0309] [[ID=I9]] "Analysis" is a process for the system to understand the input inquiry and grasp its meaning.

[0310] "Division" is a process of converting the input inquiry into a plurality of specific inquiries.

[0311] A "database" is a system that organizes and stores information and can be searched and retrieved as needed.

[0312] A "query" is a process of requesting specific information from a database.

[0313] "Information" refers to the data and knowledge necessary to provide an answer, which are retrieved from a database.

[0314] "Emotional information" refers to data obtained by analyzing and identifying the emotions contained in the user's questions.

[0315] An "answer" is the system's response to a user's question.

[0316] "Integration" is the process of combining multiple pieces of information and data to form a consistent answer as a whole.

[0317] "Multilingual support" refers to the ability to handle and process information written in different languages.

[0318] "Means" refer to the specific methods and techniques used to achieve an objective.

[0319] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[0320] Receiving a prompt

[0321] The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server. The terminal sends the user's input to the server using the HTTP POST method.

[0322] Prompt analysis and segmentation

[0323] The server analyzes the received questions using natural language processing (NLP) techniques. Specifically, it uses the Python NLTK library to break down the questions into sentences and, if necessary, convert them into individual, subdivided questions. This process involves tokenization, morphological analysis, and grammatical analysis.

[0324] Emotion recognition by an emotion engine

[0325] The server uses an emotion engine to recognize emotions from the user's questions. This emotion engine uses a general emotion analysis system to extract and analyze emotional information from the user's text. Emotional information includes various emotions such as anger, sadness, and joy.

[0326] Database query

[0327] Based on each generated query, the server queries the database using a standard database management system to retrieve the corresponding information. The database is multilingual, and can access extensive databases, particularly in English, to obtain detailed and accurate information.

[0328] Integration and purification

[0329] The server integrates the acquired information, segmented questions, and sentiment information to generate a final answer. Using the Python Pandas library, it appropriately integrates the information corresponding to each question to form a consistent answer.

[0330] Provision to users

[0331] The final answers generated by the server are sent to the user's device. The device displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[0332] Specific example

[0333] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would process the situation if it detects that the user's question contains the emotion of "anger."

[0334] 1. The user submits their input.

[0335] 2. The server analyzes the received query and divides it as follows:

[0336] "What is artificial intelligence?"

[0337] "Please tell me about its history as well."

[0338] 3. The server uses an emotion engine to analyze the user's emotions and recognizes the emotion of "anger."

[0339] 4. The server accesses a multilingual database to retrieve additional information. Example:

[0340] "Artificial Intelligence is the field of study..."

[0341] "The history of AI dates back to the mid-20th century..."

[0342] 5. The server integrates the segmented questions, acquired information, and sentiment information to generate the final answer. Example:

[0343] "What is artificial intelligence?"

[0344] "Artificial Intelligence is the field of study..."

[0345] "If you tell us why you're angry, we can provide you with more detailed information."

[0346] "Please tell me about its history as well."

[0347] "The history of AI dates back to the mid-20th century..."

[0348] "If you'd like to delve deeper into the history, please feel free to contact us."

[0349] 6. The final answer is provided to the user.

[0350] This system allows users to obtain detailed and comprehensive information with a single question input, and the system responds to the user's emotions, thus improving the user experience.

[0351] Example of a prompt

[0352] "What is machine learning? Please explain it in a way that's easy for beginners to understand."

[0353] "How do I install Python?"

[0354] "I'd like to learn about career paths in data science."

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1: Receiving the prompt

[0357] The user enters a question into the terminal's input field and presses the submit button. The terminal sends the input to the server using the HTTP POST method. The input is the text entered by the user, and the output is JSON data sent to the server. The terminal sends the input text to the appropriate API endpoint.

[0358] Step 2: Prompt analysis and splitting

[0359] The server parses the JSON data received from the terminal and extracts the questions. The input is text data containing the questions received from the terminal, and the output is multiple specific questions that have been divided. The server uses Python's NLTK library to divide the questions into sentences and convert each sentence into a separate question. Specifically, the `sent_tokenize` function is used to divide the data into sentences.

[0360] Step 3: Emotion recognition by the emotion engine

[0361] The server extracts sentiment information from each question that has been analyzed and segmented. The input is a list of segmented questions, and the output is data containing the corresponding sentiment information. The server uses a sentiment analysis engine (e.g., a general sentiment analysis system) to identify the sentiment for each question. Specifically, it uses the tone_analyzer.tone method to obtain a sentiment score and adds it to the data.

[0362] Step 4: Query the database

[0363] The server queries the database based on the segmented questions. The input is data containing each question and sentiment information, and the output is the corresponding information retrieved from the database. The server uses a database management system (e.g., a general database management system) to execute the queries and retrieve the necessary information. Specifically, it constructs SQL queries, executes them against the database, and retrieves the results.

[0364] Step 5: Integration and Purification

[0365] The server integrates information retrieved from the database with segmented questions and sentiment information to generate a final answer. The input is data containing segmented questions, retrieved information, and sentiment information, and the output is the final answer provided to the user. The server uses the Python Pandas library to integrate various data and form a consistent answer. Specifically, it uses Pandas' DataFrame functionality to organize and combine data to create a consistently meaningful answer.

[0366] Step 6: Provision to users

[0367] The server sends the final generated response to the user's device. The input is the final response generated by the server, and the output is the text displayed on the user's device. The server sends the final response to the device as an HTTP response, and the device displays the received response in a user-friendly format.

[0368] This specific processing allows users to quickly obtain detailed and consistent information with a single question input. Furthermore, the system provides responses that are sensitive to the user's emotions, improving the user experience.

[0369] (Application Example 2)

[0370] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0371] Modern consumers ask a variety of questions in physical stores and expect quick and appropriate answers, but traditional systems struggle to provide sufficient information immediately and respond flexibly to customer emotions. To solve these problems, technology is needed that analyzes user questions and provides optimal answers while considering emotions. In particular, multilingual support and information provision that takes emotions into account are required.

[0372] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0373] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for adjusting the answer in a way that takes the user's emotions into account using an emotion engine, and means for displaying the final answer on a mobile information terminal used in a physical store. This enables quick and appropriate responses to customer questions in physical stores and the provision of highly satisfying services tailored to the customer's emotions.

[0374] A "user" refers to a person who uses a system or service.

[0375] A "terminal" refers to an electronic device that a user can operate.

[0376] A "question" refers to a question or request that a user enters into the system.

[0377] "Natural language processing" is a technology that analyzes natural language spoken by humans and processes it using computers.

[0378] "Analysis" refers to the process of understanding a given question based on its meaning and structure.

[0379] A "divided question" refers to the original question that has been transformed into multiple specific questions.

[0380] A "database" is a system in which information is systematically stored.

[0381] "Inquiry" refers to the act of accessing a database to retrieve information.

[0382] "Information" refers to answers and data obtained from a database.

[0383] "Integration" refers to the act of bringing together multiple pieces of information in a consistent manner.

[0384] The "final answer" refers to the answer generated based on integrated information.

[0385] An "emotion engine" is a program that analyzes a user's emotions and adjusts the information provided based on those emotions.

[0386] A "multilingual database" is a database that can provide information in multiple languages.

[0387] A "physical store" refers to a store that has a physical presence.

[0388] "Personal information terminals" refer to portable electronic devices such as mobile phones, smartphones, and tablets.

[0389] This invention is a system that receives questions from users in physical stores and provides quick and appropriate answers using natural language processing and an emotion engine. The specific implementation of this system is described below.

[0390] First, this system will be implemented using a portable information terminal such as smart glasses. The terminal is equipped with a microphone that can receive the user's voice input. Once voice input is received, the data is sent to a server.

[0391] The server first uses a speech recognition engine to convert the audio data into text. This transcribed data represents the question in the system, which is then analyzed by natural language processing (NLP). This analysis breaks down the question into multiple specific questions.

[0392] Next, the server uses an emotion engine to determine the user's emotions. This emotion determination extracts emotional information from the user's text and recognizes the emotions behind the question (e.g., joy, anger, sadness, etc.).

[0393] The segmented questions and sentiment information are stored on the server, and queries are then sent to the database based on this information. The database is multilingual and can access a wide range of databases, particularly in English. Therefore, detailed and highly accurate information can be obtained.

[0394] The system integrates acquired information with emotional data to generate a final response that takes emotions into consideration. Because the response is adjusted to reflect the user's emotions, the user experience is improved.

[0395] The final response is sent to the device and displayed on the screen. This allows in-store staff to provide customers with quick and emotionally sensitive answers.

[0396] Hardware and software to use

[0397] Hardware: Portable information devices such as smart glasses equipped with a microphone.

[0398] Software: Speech recognition engine (e.g., speech_recognition library), natural language processing (e.g., transformers library), emotion engine, database access library (e.g., requests library).

[0399] Specific example

[0400] For example, if a customer speaks into the microphone built into the smart glasses and says, "Please tell me how to use this product," the system analyzes and breaks down the question, recognizes the customer's emotions, and provides the most appropriate answer.

[0401] Example of a prompt

[0402] If you are asked about the intended use of the product, please generate your answer using the following method:

[0403] 1. Analyze the question and divide it into individual sentences.

[0404] 2. Determine the emotions contained in the question.

[0405] 3. Query the database based on the question and sentiment to obtain the best answer.

[0406] 4. Integrate the divided questions and answers to generate sentiment-sensitive responses.

[0407] As a specific example, if a question is entered such as "How do I use this product?", we will provide links to detailed user instructions and related videos for that product.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The device receives the user's voice input. The user speaks into the microphone attached to the device, and voice data is collected. The input is the user's question, and the output is voice data.

[0411] Step 2:

[0412] The terminal sends audio data to the server. The audio data is converted to a digital format and transferred to the server. The input is audio data, and the output is the digital audio data sent to the server.

[0413] Step 3:

[0414] The server uses a speech recognition engine to convert the audio data into text. The converted text becomes the question. The input is digital audio data, and the output is converted text data.

[0415] Step 4:

[0416] The server uses a natural language processing engine to analyze the question. Through this analysis, the question is broken down into sentences. The input is text data, and the output is the multiple, divided questions.

[0417] Step 5:

[0418] The server uses an emotion engine to determine the user's emotions from segmented questions. Emotional information is extracted, and emotions such as joy, anger, and sadness are identified. The input is segmented questions, and the output is emotional information.

[0419] Step 6:

[0420] The server queries a database based on segmented questions and sentiment information to retrieve corresponding information. It also accesses multilingual databases to collect detailed and appropriate information. The input is segmented questions and sentiment information, and the output is the retrieved information.

[0421] Step 7:

[0422] The server integrates the acquired information with the segmented questions and sentiment information to generate the final answer. By incorporating sentiment information, the answer is refined to resonate with the user. The input is the acquired information and sentiment information, and the output is the final answer.

[0423] Step 8:

[0424] The server sends the final answer to the terminal. The terminal displays this final answer on its screen. The input is the final answer, and the output is the answer information sent to the terminal.

[0425] Step 9:

[0426] The device displays the response information to the user. The final response is displayed on the device's screen and can be viewed by the user. The input is the submitted response information, and the output is the response displayed on the screen.

[0427] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0428] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0429] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0430] [Second Embodiment]

[0431] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0432] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0433] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0434] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0435] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0436] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0437] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0438] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0439] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0440] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0441] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0442] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0443] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[0444] Receiving a prompt

[0445] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[0446] Prompt analysis and segmentation

[0447] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[0448] Database query

[0449] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, particularly the English version, to obtain detailed and accurate information.

[0450] Integration and purification

[0451] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[0452] Provision to users

[0453] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[0454] Specific example

[0455] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history."

[0456] 1. Terminal: The user submits the entered content.

[0457] 2. Server: The server analyzes the received query and divides it as follows:

[0458] "What is artificial intelligence?"

[0459] "Please tell me about its history as well."

[0460] 3. Server: Access the English version of the database to retrieve additional information:

[0461] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0462] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0463] 4. Server: Integrates the divided questions and acquired information to generate the final answer:

[0464] "What is artificial intelligence?"

[0465] "Additional information: Artificial Intelligence is the field of study..."

[0466] "Please tell me about its history as well."

[0467] "Additional information: The history of AI dates back to the mid-20th century..."

[0468] 5. Terminal: Provides the final answer to the user.

[0469] "What is artificial intelligence?"

[0470] "Additional information: Artificial Intelligence is the field of study..."

[0471] "Please tell me about its history as well."

[0472] "Additional information: The history of AI dates back to the mid-20th century..."

[0473] Such a system allows users to obtain detailed and comprehensive information with a single question input, improving both the system's usability and the accuracy of the answers.

[0474] The following describes the processing flow.

[0475] Step 1: The user enters the question and presses the submit button.

[0476] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on the device and presses the send button.

[0477] Step 2: The device sends the user's query to the server.

[0478] The terminal sends the user's input to the server. This data is sent as text.

[0479] Step 3: The server receives and analyzes the query.

[0480] The server analyzes the questions received from the terminal. First, it uses natural language processing techniques to break down the questions into sentences and convert them into multiple specific questions.

[0481] Step 4: The server queries the database with the divided queries.

[0482] The server queries the database based on each segmented question and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves a wide range of information such as "Artificial Intelligence is the field of study...".

[0483] Step 5: The server also accesses the English version of the database.

[0484] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[0485] Step 6: Integrate the information obtained by the server with the original question.

[0486] The server integrates the acquired information with the original segmented questions to generate a final answer. For example, it might connect "What is artificial intelligence?" with "Artificial Intelligence is the field of study...".

[0487] Step 7: The server sends the final response to the terminal.

[0488] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[0489] Step 8: The device displays the final answer to the user.

[0490] The device displays the final received response to the user. The user can instantly see a comprehensive answer to the question.

[0491] (Example 1)

[0492] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0493] Conventional information retrieval systems have struggled to provide appropriate answers to user-inputted questions, and generating consistent and comprehensive responses, especially for complex questions, has been a challenge. Furthermore, there has been a need for systems that can access extensive databases spanning multiple languages ​​and possess high-precision analysis capabilities using natural language processing.

[0494] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0495] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a data storage device based on the segmented questions and obtaining corresponding information, means for integrating the segmented questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for performing tokenization and dependency analysis based on natural language processing and segmenting the question into sentence units, means for querying an external information provider for the generated questions and analyzing the obtained information, and means for generating a consistent answer using a generative model based on the obtained information. This makes it possible to provide complex and comprehensive information in response to a user's question with high accuracy.

[0496] A "user" is a person who uses the system to input and submit questions.

[0497] "Means of receiving" refers to the function of sending the entered question to the server via the network.

[0498] "Natural language processing" refers to the technology that enables computers to understand, analyze, and generate human language.

[0499] "Analysis" is the process of understanding the content of a question and grasping its meaning.

[0500] A "divided question" refers to multiple specific questions derived from analyzing the initial question.

[0501] A "data storage device" is a part of a system that stores and provides information, and often refers to a database or an external API.

[0502] "Means of querying and obtaining information" refers to the process of obtaining information corresponding to divided questions from a data storage device.

[0503] "Means of integrating to generate a final answer" refers to the process of integrating acquired information to create a consistent answer.

[0504] "Means of providing" refers to the function of displaying or sending the final answer to the user.

[0505] "Tokenization" is the process of dividing a text into units such as words or phrases.

[0506] "Dependency analysis" is the process of analyzing how words in a sentence are related to each other.

[0507] "Splitting into sentences" refers to the process of dividing a prompt message into multiple sentences.

[0508] An "external information provider" refers to an external data source that a server accesses to retrieve information.

[0509] A "generative model" is an AI technology used to generate new text or answers based on input data.

[0510] A "consistent answer" is one that is free from contradictions and has a unified logical structure.

[0511] The system of this invention receives a question entered by the user, analyzes and divides it, queries a data storage device to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[0512] Receiving a prompt

[0513] User: The user enters the question into the input field on the terminal and presses the submit button.

[0514] Terminal: The terminal sends this input to the server. This communication uses an HTTP POST request.

[0515] Prompt analysis and segmentation

[0516] Server: The server uses the Python-based natural language processing tool "Open Source Natural Language Processing Toolkit" to parse the received prompt. Specifically, it performs the following processes:

[0517] Tokenization: Dividing a prompt into units of words or phrases.

[0518] Dependency analysis: Analyzes how words in a sentence are related to each other.

[0519] Split into sentences: Divide the prompt message into multiple sentences.

[0520] Convert into individual questions as needed.

[0521] Database query

[0522] Server: The server queries external information providers based on each segmented query. The following APIs are used for this:

[0523] A "general-purpose knowledge base API" for retrieving general information.

[0524] A "scientific data API" is used to obtain scientific data and facts.

[0525] The server sends an HTTP GET request to each API and receives data in JSON format.

[0526] Integration and purification

[0527] Server: The server integrates the acquired information and the segmented questions to generate the final answer. This process uses a generative AI model, the "Generative AI Engine." The specific steps are as follows:

[0528] The acquired JSON data is analyzed, and candidate answers are extracted.

[0529] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[0530] Regenerate the output as needed and select the optimal answer.

[0531] Provision to users

[0532] Server: The server sends the final generated response to the user's terminal.

[0533] Terminal: The terminal displays the received response to the user. This received data is in HTML format and is rendered correctly in the browser.

[0534] Specific example

[0535] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." The process in this case would be as follows:

[0536] 1. User: The user enters "What is artificial intelligence?" into the input field on the device and presses the send button.

[0537] 2. Terminal: The terminal sends data including this prompt to the server as an HTTP POST request.

[0538] 3. Server: The server analyzes the received query using a natural language processing toolkit and divides it as follows:

[0539] "What is artificial intelligence?"

[0540] "Please tell me about its history as well."

[0541] 4. Server: Access the General Knowledge Base API and Scientific Data API to retrieve additional information:

[0542] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0543] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0544] 5. Server: Inputs the acquired information into the AI ​​engine to generate consistent responses:

[0545] "What is artificial intelligence?" -> "Additional information: Artificial intelligence is the field of study..."

[0546] "Please also tell me about its history." -> "Additional information: The history of AI dates back to the mid-20th century..."

[0547] 6. Server: Converts the generated response into HTML format and sends it to the user's device.

[0548] 7. Terminal: The terminal displays the received HTML data in a browser and shows it to the user in the following format: "What is artificial intelligence?", "Additional information: Artificial Intelligence is the field of study...", "Please also tell me about its history.", "Additional information: The history of AI dates back to the mid-20th century...".

[0549] In this way, the system can provide accurate and comprehensive information in response to user inquiries.

[0550] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0551] Step 1: Receiving the prompt

[0552] User: The user enters a question into the input field on the terminal and presses the submit button.

[0553] Specific action: The user types, for example, "What is artificial intelligence?" and presses the submit button.

[0554] Input: The user entered the question, "What is artificial intelligence?".

[0555] Terminal: The terminal sends this input to the server. It uses an HTTP POST request for communication.

[0556] Output: Input data sent to the server.

[0557] Step 2: Prompt analysis and splitting

[0558] Server: The server utilizes a Python-based open-source natural language processing toolkit to parse the received prompts.

[0559] Specific actions:

[0560] Tokenization: Dividing a sentence into words or phrases. For example, dividing it into "artificial intelligence," "what is," and "what is it?".

[0561] Dependency analysis: This analyzes how words in a sentence relate to each other. For example, it identifies that "artificial intelligence" is the subject, "what is" is the predicate, and "what is it?" is the complement.

[0562] Split into sentences: Process each prompt statement as a single sentence.

[0563] Input: Received prompt message: "What is artificial intelligence?"

[0564] Output: The question, broken down into sentence units, obtained as a result of the analysis, for example, "What is artificial intelligence?".

[0565] Step 3: Query the database

[0566] Server: The server queries external information providers based on the questions generated through analysis.

[0567] Specific actions:

[0568] Send the query "What is AI?" to a general-purpose knowledge base API.

[0569] Send the query "What is AI?" to the scientific data API.

[0570] Receive data in JSON format from the API.

[0571] Input: Divided question "What is AI?".

[0572] Output: Retrieved response data in JSON format.

[0573] Step 4: Integration and Purification

[0574] Server: The server integrates the acquired information and the segmented questions to generate the final answer.

[0575] Specific actions:

[0576] The acquired JSON data is analyzed to extract potential answers. For example, information such as "Artificial Intelligence is the field of study..."

[0577] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[0578] If necessary, the AI ​​generation engine will regenerate the answer and select the most suitable response.

[0579] Input: Retrieved response data in JSON format.

[0580] Output: The final integrated answer.

[0581] Step 5: Providing to Users

[0582] Server: The server sends the final generated response to the user's terminal.

[0583] Terminal: The terminal displays the received response to the user.

[0584] Specific operation: The server sends HTML-formatted data to the user's device, and the device displays that data in its browser.

[0585] Input: The server's final generated response: "Artificial Intelligence is the field of study..."

[0586] Output: The final answer displayed to the user.

[0587] In this way, the system provides accurate and comprehensive information in response to user inquiries.

[0588] (Application Example 1)

[0589] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0590] Traditional systems that accept inquiries and provide information have struggled to provide optimal real-time responses to user-inputted instructions and questions. Furthermore, especially in autonomous vehicles, the immediate provision of traffic and navigation information is crucial, and the lack of systems capable of handling this has been a problem. Therefore, a new system is needed that enables real-time and detailed information provision, thereby improving user convenience.

[0591] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0592] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into a plurality of divided questions, means for querying a database based on the divided questions and obtaining corresponding information, means for integrating the divided questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for the user to input instructions by voice or text, analyzing them and dividing them into specific questions, and means for generating and providing the optimal answer in real time based on the acquired information. This enables real-time and detailed information provision even in autonomous vehicles, improving user convenience and safety.

[0593] A "user" is someone who uses the system and inputs questions or instructions.

[0594] A "question" refers to a question or instruction that a user enters into the system, and it is a request for information or advice.

[0595] "Natural language processing" is a technology that enables computers to understand, analyze, and process human language.

[0596] A "divided question" is a question that has been analyzed using natural language processing and transformed into multiple specific questions.

[0597] A "database" is a system where information is stored and provides information that responds to user inquiries.

[0598] The "final answer" is the answer provided to the user, generated by integrating the divided questions and the corresponding information.

[0599] "Real-time" means that processing and information are provided almost instantly.

[0600] "Voice or text" refers to the method by which a user inputs a question to the system, and includes voice input and text input.

[0601] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments are described below.

[0602] 1. System Overview

[0603] Receiving a prompt

[0604] Terminal: The user enters and submits the question in voice or text format. The terminal sends this input to the server.

[0605] Prompt analysis and segmentation

[0606] Server: Upon receiving a prompt, the server analyzes the question using natural language processing techniques. The analysis process divides the question into sentences and, if necessary, converts them into more specific questions. This generates multiple specific questions.

[0607] Database query

[0608] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, especially the English version, to obtain detailed and accurate information.

[0609] Integration and purification

[0610] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[0611] Provision to users

[0612] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[0613] 2. Hardware and software used

[0614] hardware

[0615] Microphone and speaker: A device for users to input instructions by voice and receive responses by voice.

[0616] Terminal (smartphone, in-car display, etc.): A device used by the user to input questions and receive answers.

[0617] software

[0618] Natural Language Processing: A technique used to analyze a question and break it down into more specific questions. A concrete example is the Python Natural Language Toolkit (nltk) library.

[0619] Database access: A tool for querying a database and retrieving corresponding information. Examples include SQL databases and NoSQL databases.

[0620] Integration and Refinement: Logic for integrating acquired information and generating the final answer. Programming languages ​​such as Python or Ruby can be used.

[0621] 3. Specific Examples

[0622] For example, let's look at a specific case where a user inputs a question via voice, such as, "Tell me about traffic congestion ahead."

[0623] Example of a prompt

[0624] "Please tell me about the traffic conditions ahead."

[0625] Execution process

[0626] 1. Terminal: The user provides voice input, which the system converts into text data. Alternatively, the user may have already entered the question in text format.

[0627] 2. Server: The server analyzes the received query using natural language processing technology and divides it into "traffic information" and "what's ahead".

[0628] 3. Server: Retrieves real-time data related to "traffic congestion information" from the database, and simultaneously retrieves location information related to "what's ahead".

[0629] 4. Server: Integrates the acquired information and generates a final response (e.g., "There is traffic congestion 5km ahead. The recommended detour is here.").

[0630] 5. Device: Provide this final answer to the user. It will be displayed via voice or on the screen.

[0631] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0632] Step 1:

[0633] Input: The user enters the question via voice or text.

[0634] Operation: In the case of voice input, the device uses the microphone to capture voice data and converts it to text using speech recognition software (e.g., Google Speech Recognition API).

[0635] Output: Sends a question in text format to the server.

[0636] Step 2:

[0637] Input: The server receives the user's query in text format.

[0638] Operation: The server analyzes the question using natural language processing (NLP) techniques. Specifically, it uses Python's Natural Language Toolkit (nltk) and the spaCy API to break down the question into sentences and convert them into more specific, subdivided questions.

[0639] Output: Generates a list of specific questions broken down into segments.

[0640] Step 3:

[0641] Input: A list of specific questions divided into sections.

[0642] Operation: The server queries the database based on each segmented query. It references SQL and NoSQL databases to retrieve corresponding information in real time.

[0643] Output: Generates a list of corresponding information for each question.

[0644] Step 4:

[0645] Input: A list of divided questions and a list of corresponding information.

[0646] Operation: The server integrates the acquired information and generates the final answer using natural language generation (NLG) technology. It constructs the sentence into a natural form using programs such as Python or Ruby.

[0647] Output: Generates the final answer and outputs it in text format.

[0648] Step 5:

[0649] Input: Final response generated by the server.

[0650] Operation: The device displays the response received from the server. If audio output is required, it converts it to speech using a Text-to-Speech (TTS) engine (e.g., Google Text-to-Speech API) and outputs it through the speaker.

[0651] Output: Provides the user with the final answer in text and audio formats.

[0652] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0653] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[0654] Receiving a prompt

[0655] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[0656] Prompt analysis and segmentation

[0657] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[0658] Emotion recognition by an emotion engine

[0659] Server: Next, the server uses an emotion engine to recognize emotions from the questions entered by the user. The emotion engine extracts and analyzes emotional information from the user's text. This emotional information includes various emotions such as anger, sadness, and joy.

[0660] Database query

[0661] Server: Based on each generated query, the server queries the database and retrieves the corresponding information. This database is multilingual, and can access a particularly extensive English version of the database to obtain detailed and accurate information. Based on the sentiment information obtained by the sentiment engine, it selects information that is appropriate to the emotion.

[0662] Integration and purification

[0663] Server: Integrates acquired information, segmented questions, and sentiment information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent answer. By adding sentiment information, it provides answers that are easier for users to understand and empathize with.

[0664] Provision to users

[0665] Terminal: The final answers generated by the server are sent to the user's terminal. The terminal displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[0666] Specific example

[0667] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would handle the situation if it detects that the user's question contains feelings of anger.

[0668] 1. Terminal: The user submits the input content.

[0669] 2. Server: The server analyzes the received query and divides it as follows:

[0670] "What is artificial intelligence?"

[0671] "Please tell me about its history as well."

[0672] 3. Server: Analyzes user emotions using an emotion engine:

[0673] The user's question contains feelings of anger.

[0674] 4. Server: Access the English version of the database to retrieve additional information:

[0675] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0676] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0677] 5. Server: Integrates the segmented questions, acquired information, and sentiment information to generate the final answer:

[0678] "What is artificial intelligence?"

[0679] "Additional information: Artificial Intelligence is the field of study..."

[0680] "To answer your questions, we will provide you with more detailed information, so please let us know."

[0681] "Please tell me about its history as well."

[0682] "Additional information: The history of AI dates back to the mid-20th century..."

[0683] "If you'd like to delve deeper into history, we also have textbook-style materials available."

[0684] 6. Terminal: Provides the final answer to the user.

[0685] Such a system allows users to obtain detailed and comprehensive information with a single question input, while simultaneously improving the user experience by enabling the system to respond in a way that is sensitive to the user's emotions.

[0686] The following describes the processing flow.

[0687] Step 1: The user enters the question and presses the submit button.

[0688] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on their device. Then, they press the send button to submit the question.

[0689] Step 2: The device sends the user's query to the server.

[0690] The terminal sends the user's input to the server. At this time, the entered text data is sent to the server.

[0691] Step 3: The server receives and analyzes the query.

[0692] The server analyzes the received question. First, it uses natural language processing techniques to break down the question into sentences and, if necessary, converts them into individual questions. For example, the question "What is artificial intelligence? Please also tell me about its history." is split into "What is artificial intelligence?" and "Please also tell me about its history."

[0693] Step 4: The server recognizes the user's emotions.

[0694] The server uses an emotion engine to recognize emotions from the user's question. The emotion engine analyzes the text data of the question and detects the user's emotions (e.g., anger, sadness, joy). For example, it might determine that the user's question contains some anger.

[0695] Step 5: The server queries the database with the divided queries.

[0696] Next, the server queries the database based on each of the divided questions and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves information such as "Artificial Intelligence is the field of study...", and in response to "Please also tell me about its history," it retrieves information such as "The history of AI dates back to the mid-20th century...".

[0697] Step 6: The server also accesses the English version of the database.

[0698] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[0699] Step 7: Integrate the information obtained by the server with the original question.

[0700] The server integrates the acquired information, segmented questions, and emotional information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent response. Adding emotional information provides answers that are easier for users to understand and empathize with.

[0701] Step 8: The server sends the final response to the terminal.

[0702] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[0703] Step 9: The device displays the final answer to the user.

[0704] The device displays the final received answer to the user. The user can instantly see a comprehensive answer to their question. For example, in response to the question, "What is artificial intelligence?", it will display, "Artificial Intelligence is the field of study... Please let us know if you would like more information to answer your question." Also, in response to "Please tell me about its history," it will display, "The history of AI dates back to the mid-20th century... If you would like to delve deeper into its history, we also have textbook-style materials available."

[0705] In this way, users can obtain comprehensive information with a single question input, and receive highly relevant answers that reflect their emotions at the time of input, thus improving the user experience.

[0706] (Example 2)

[0707] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0708] Conventional question-answering systems have a problem in that the process of receiving user-entered questions and providing corresponding answers is not properly handled, making it difficult to obtain satisfactory answers, especially for complex or emotionally charged questions. Furthermore, there was a lack of means to quickly retrieve detailed information from multilingual databases and present it to users in an easily understandable way. In addition, the ability to generate optimal answers that take into account the user's emotions was insufficient.

[0709] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question entered by the user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for integrating sentiment information in addition to the segmented questions and corresponding information to generate a final answer, and means for providing the final answer to the user. As a result, the user can quickly obtain detailed and consistent information, and the system can provide the optimal answer according to the user's sentiment. Furthermore, by using a multilingual database, it becomes possible to provide even richer information.

[0710] A "user" is an individual or group that uses the system.

[0711] "Input" refers to the information or questions that a user provides to the system.

[0712] A "question" is a question that a user asks the system.

[0713] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0714] "Analysis" is the process by which a system understands the input question and grasps its meaning.

[0715] "Splitting" is the process of converting an input question into multiple specific questions.

[0716] A "database" is a system that organizes and stores information, making it searchable and retrievable as needed.

[0717] A "query" is the process of requesting specific information from a database.

[0718] "Information" refers to the data and knowledge necessary to provide an answer, which are retrieved from a database.

[0719] "Emotional information" refers to data obtained by analyzing and identifying the emotions contained in the user's questions.

[0720] An "answer" is the system's response to a user's question.

[0721] "Integration" is the process of combining multiple pieces of information and data to form a consistent answer as a whole.

[0722] "Multilingual support" refers to the ability to handle and process information written in different languages.

[0723] "Means" refer to the specific methods and techniques used to achieve an objective.

[0724] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[0725] Receiving a prompt

[0726] The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server. The terminal sends the user's input to the server using the HTTP POST method.

[0727] Prompt analysis and segmentation

[0728] The server analyzes the received questions using natural language processing (NLP) techniques. Specifically, it uses the Python NLTK library to break down the questions into sentences and, if necessary, convert them into individual, subdivided questions. This process involves tokenization, morphological analysis, and grammatical analysis.

[0729] Emotion recognition by an emotion engine

[0730] The server uses an emotion engine to recognize emotions from the user's questions. This emotion engine uses a general emotion analysis system to extract and analyze emotional information from the user's text. Emotional information includes various emotions such as anger, sadness, and joy.

[0731] Database query

[0732] Based on each generated query, the server queries the database using a standard database management system to retrieve the corresponding information. The database is multilingual, and can access extensive databases, particularly in English, to obtain detailed and accurate information.

[0733] Integration and purification

[0734] The server integrates the acquired information, segmented questions, and sentiment information to generate a final answer. Using the Python Pandas library, it appropriately integrates the information corresponding to each question to form a consistent answer.

[0735] Provision to users

[0736] The final answers generated by the server are sent to the user's device. The device displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[0737] Specific example

[0738] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would process the situation if it detected that the user's question contained the emotion of "anger."

[0739] 1. The user submits their input.

[0740] 2. The server analyzes the received query and divides it as follows:

[0741] "What is artificial intelligence?"

[0742] "Please tell me about its history as well."

[0743] 3. The server uses an emotion engine to analyze the user's emotions and recognizes the emotion of "anger."

[0744] 4. The server accesses a multilingual database to retrieve additional information. Example:

[0745] "Artificial Intelligence is the field of study..."

[0746] "The history of AI dates back to the mid-20th century..."

[0747] 5. The server integrates the segmented questions, acquired information, and sentiment information to generate the final answer. Example:

[0748] "What is artificial intelligence?"

[0749] "Artificial Intelligence is the field of study..."

[0750] "If you tell us why you're angry, we can provide you with more detailed information."

[0751] "Please tell me about its history as well."

[0752] "The history of AI dates back to the mid-20th century..."

[0753] "If you'd like to delve deeper into the history, please feel free to contact us."

[0754] 6. The final answer is provided to the user.

[0755] This system allows users to obtain detailed and comprehensive information with a single question input, and the system responds to the user's emotions, thus improving the user experience.

[0756] Example of a prompt

[0757] "What is machine learning? Please explain it in a way that's easy for beginners to understand."

[0758] "How do I install Python?"

[0759] "I'd like to learn about career paths in data science."

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1: Receiving the prompt

[0762] The user enters a question into the terminal's input field and presses the submit button. The terminal sends the input to the server using the HTTP POST method. The input is the text entered by the user, and the output is JSON data sent to the server. The terminal sends the input text to the appropriate API endpoint.

[0763] Step 2: Prompt analysis and splitting

[0764] The server parses the JSON data received from the terminal and extracts the questions. The input is text data containing the questions received from the terminal, and the output is multiple specific questions that have been divided. The server uses Python's NLTK library to divide the questions into sentences and convert each sentence into a separate question. Specifically, the `sent_tokenize` function is used to divide the data into sentences.

[0765] Step 3: Emotion recognition by the emotion engine

[0766] The server extracts sentiment information from each question that has been analyzed and segmented. The input is a list of segmented questions, and the output is data containing the corresponding sentiment information. The server uses a sentiment analysis engine (e.g., a general sentiment analysis system) to identify the sentiment for each question. Specifically, it uses the tone_analyzer.tone method to obtain a sentiment score and adds it to the data.

[0767] Step 4: Query the database

[0768] The server queries the database based on the segmented questions. The input is data containing each question and sentiment information, and the output is the corresponding information retrieved from the database. The server uses a database management system (e.g., a general database management system) to execute the queries and retrieve the necessary information. Specifically, it constructs SQL queries, executes them against the database, and retrieves the results.

[0769] Step 5: Integration and Purification

[0770] The server integrates information retrieved from the database with segmented questions and sentiment information to generate a final answer. The input is data containing segmented questions, retrieved information, and sentiment information, and the output is the final answer provided to the user. The server uses the Python Pandas library to integrate various data and form a consistent answer. Specifically, it uses Pandas' DataFrame functionality to organize and combine data to create a consistently meaningful answer.

[0771] Step 6: Provision to users

[0772] The server sends the final generated response to the user's device. The input is the final response generated by the server, and the output is the text displayed on the user's device. The server sends the final response to the device as an HTTP response, and the device displays the received response in a user-friendly format.

[0773] This specific processing allows users to quickly obtain detailed and consistent information with a single question input. Furthermore, the system provides responses that are sensitive to the user's emotions, improving the user experience.

[0774] (Application Example 2)

[0775] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0776] Modern consumers ask a variety of questions in physical stores and expect quick and appropriate answers, but traditional systems struggle to provide sufficient information immediately and respond flexibly to customer emotions. To solve these problems, technology is needed that analyzes user questions and provides optimal answers while considering emotions. In particular, multilingual support and information provision that takes emotions into account are required.

[0777] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0778] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for adjusting the answer in a way that takes the user's emotions into account using an emotion engine, and means for displaying the final answer on a mobile information terminal used in a physical store. This enables quick and appropriate responses to customer questions in physical stores and the provision of highly satisfying services tailored to the customer's emotions.

[0779] A "user" refers to a person who uses a system or service.

[0780] A "terminal" refers to an electronic device that a user can operate.

[0781] A "question" refers to a question or request that a user enters into the system.

[0782] "Natural language processing" is a technology that analyzes natural language spoken by humans and processes it using computers.

[0783] "Analysis" refers to the process of understanding a given question based on its meaning and structure.

[0784] A "divided question" refers to the original question that has been transformed into multiple specific questions.

[0785] A "database" is a system in which information is systematically stored.

[0786] "Inquiry" refers to the act of accessing a database to retrieve information.

[0787] "Information" refers to answers and data obtained from a database.

[0788] "Integration" refers to the act of bringing together multiple pieces of information in a consistent manner.

[0789] The "final answer" refers to the answer generated based on integrated information.

[0790] An "emotion engine" is a program that analyzes a user's emotions and adjusts the information provided based on those emotions.

[0791] A "multilingual database" is a database that can provide information in multiple languages.

[0792] A "physical store" refers to a store that has a physical presence.

[0793] "Personal information terminals" refer to portable electronic devices such as mobile phones, smartphones, and tablets.

[0794] This invention is a system that receives questions from users in physical stores and provides quick and appropriate answers using natural language processing and an emotion engine. The specific implementation of this system is described below.

[0795] First, this system will be implemented using a portable information terminal such as smart glasses. The terminal is equipped with a microphone that can receive voice input from the user. Once voice input is received, the data is sent to a server.

[0796] The server first uses a speech recognition engine to convert the audio data into text. This transcribed data represents the question in the system, which is then analyzed by natural language processing (NLP). This analysis breaks down the question into multiple specific questions.

[0797] Next, the server uses an emotion engine to determine the user's emotions. This emotion determination extracts emotional information from the user's text and recognizes the emotions behind the question (e.g., joy, anger, sadness, etc.).

[0798] The segmented questions and sentiment information are stored on the server, and queries are then sent to the database based on this information. The database is multilingual and can access a wide range of databases, particularly in English. Therefore, detailed and highly accurate information can be obtained.

[0799] The system integrates acquired information with emotional data to generate a final response that takes emotions into consideration. Because the response is adjusted to reflect the user's emotions, the user experience is improved.

[0800] The final response is sent to the device and displayed on the screen. This allows in-store staff to provide customers with quick and emotionally sensitive answers.

[0801] Hardware and software to use

[0802] Hardware: Portable information devices such as smart glasses equipped with a microphone.

[0803] Software: Speech recognition engine (e.g., speech_recognition library), natural language processing (e.g., transformers library), emotion engine, database access library (e.g., requests library).

[0804] Specific example

[0805] For example, if a customer speaks into the microphone built into the smart glasses and says, "Please tell me how to use this product," the system analyzes and breaks down the question, recognizes the customer's emotions, and provides the most appropriate answer.

[0806] Example of a prompt

[0807] If you are asked about the intended use of the product, please generate your answer using the following method:

[0808] 1. Analyze the question and divide it into individual sentences.

[0809] 2. Determine the emotions contained in the question.

[0810] 3. Query the database based on the question and sentiment to obtain the best answer.

[0811] 4. Integrate the divided questions and answers to generate sentiment-sensitive responses.

[0812] As a specific example, if a question is entered such as "How do I use this product?", we will provide links to detailed user instructions and related videos for that product.

[0813] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0814] Step 1:

[0815] The device receives the user's voice input. The user speaks into the microphone attached to the device, and voice data is collected. The input is the user's question, and the output is voice data.

[0816] Step 2:

[0817] The terminal sends audio data to the server. The audio data is converted to a digital format and transferred to the server. The input is audio data, and the output is the digital audio data sent to the server.

[0818] Step 3:

[0819] The server uses a speech recognition engine to convert the audio data into text. The converted text becomes the question. The input is digital audio data, and the output is converted text data.

[0820] Step 4:

[0821] The server uses a natural language processing engine to analyze the question. Through this analysis, the question is broken down into sentences. The input is text data, and the output is the multiple, divided questions.

[0822] Step 5:

[0823] The server uses an emotion engine to determine the user's emotions from segmented questions. Emotional information is extracted, and emotions such as joy, anger, and sadness are identified. The input is segmented questions, and the output is emotional information.

[0824] Step 6:

[0825] The server queries a database based on segmented questions and sentiment information to retrieve corresponding information. It also accesses multilingual databases to collect detailed and appropriate information. The input is segmented questions and sentiment information, and the output is the retrieved information.

[0826] Step 7:

[0827] The server integrates the acquired information with the segmented questions and sentiment information to generate the final answer. By incorporating sentiment information, the answer is refined to resonate with the user. The input is the acquired information and sentiment information, and the output is the final answer.

[0828] Step 8:

[0829] The server sends the final answer to the terminal. The terminal displays this final answer on its screen. The input is the final answer, and the output is the answer information sent to the terminal.

[0830] Step 9:

[0831] The device displays the response information to the user. The final response is displayed on the device's screen and can be viewed by the user. The input is the submitted response information, and the output is the response displayed on the screen.

[0832] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0833] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0834] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0835] [Third Embodiment]

[0836] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0837] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0838] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0839] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0840] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0841] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0842] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0843] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0844] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0845] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0846] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0847] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0848] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[0849] Receiving a prompt

[0850] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[0851] Prompt analysis and segmentation

[0852] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[0853] Database query

[0854] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, particularly the English version, to obtain detailed and accurate information.

[0855] Integration and purification

[0856] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[0857] Provision to users

[0858] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[0859] Specific example

[0860] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history."

[0861] 1. Terminal: The user submits the entered content.

[0862] 2. Server: The server analyzes the received query and divides it as follows:

[0863] "What is artificial intelligence?"

[0864] "Please tell me about its history as well."

[0865] 3. Server: Access the English version of the database to retrieve additional information:

[0866] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0867] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0868] 4. Server: Integrates the divided questions and acquired information to generate the final answer:

[0869] "What is artificial intelligence?"

[0870] "Additional information: Artificial Intelligence is the field of study..."

[0871] "Please tell me about its history as well."

[0872] "Additional information: The history of AI dates back to the mid-20th century..."

[0873] 5. Terminal: Provides the final answer to the user.

[0874] "What is artificial intelligence?"

[0875] "Additional information: Artificial Intelligence is the field of study..."

[0876] "Please tell me about its history as well."

[0877] "Additional information: The history of AI dates back to the mid-20th century..."

[0878] Such a system allows users to obtain detailed and comprehensive information with a single question input, improving both the system's usability and the accuracy of the answers.

[0879] The following describes the processing flow.

[0880] Step 1: The user enters the question and presses the submit button.

[0881] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on the device and presses the send button.

[0882] Step 2: The device sends the user's query to the server.

[0883] The terminal sends the user's input to the server. This data is sent as text.

[0884] Step 3: The server receives and analyzes the query.

[0885] The server analyzes the questions received from the terminal. First, it uses natural language processing techniques to break down the questions into sentences and convert them into multiple specific questions.

[0886] Step 4: The server queries the database with the divided queries.

[0887] The server queries the database based on each segmented question and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves a wide range of information such as "Artificial Intelligence is the field of study...".

[0888] Step 5: The server also accesses the English version of the database.

[0889] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[0890] Step 6: Integrate the information obtained by the server with the original question.

[0891] The server integrates the acquired information with the original segmented questions to generate a final answer. For example, it might connect "What is artificial intelligence?" with "Artificial Intelligence is the field of study...".

[0892] Step 7: The server sends the final response to the terminal.

[0893] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[0894] Step 8: The device displays the final answer to the user.

[0895] The device displays the final received response to the user. The user can instantly see a comprehensive answer to the question.

[0896] (Example 1)

[0897] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0898] Conventional information retrieval systems have struggled to provide appropriate answers to user-inputted questions, and generating consistent and comprehensive responses, especially for complex questions, has been a challenge. Furthermore, there has been a need for systems that can access extensive databases spanning multiple languages ​​and possess high-precision analysis capabilities using natural language processing.

[0899] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0900] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a data storage device based on the segmented questions and obtaining corresponding information, means for integrating the segmented questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for performing tokenization and dependency analysis based on natural language processing and segmenting the question into sentence units, means for querying an external information provider for the generated questions and analyzing the obtained information, and means for generating a consistent answer using a generative model based on the obtained information. This makes it possible to provide complex and comprehensive information in response to a user's question with high accuracy.

[0901] A "user" is a person who uses the system to input and submit questions.

[0902] "Means of receiving" refers to the function of sending the entered question to the server via the network.

[0903] "Natural language processing" refers to the technology that enables computers to understand, analyze, and generate human language.

[0904] "Analysis" is the process of understanding the content of a question and grasping its meaning.

[0905] A "divided question" refers to multiple specific questions derived from analyzing the initial question.

[0906] A "data storage device" is a part of a system that stores and provides information, and often refers to a database or an external API.

[0907] "Means of querying and obtaining information" refers to the process of obtaining information corresponding to divided questions from a data storage device.

[0908] "Means of integrating to generate a final answer" refers to the process of integrating acquired information to create a consistent answer.

[0909] "Means of providing" refers to the function of displaying or sending the final answer to the user.

[0910] "Tokenization" is the process of dividing a text into units such as words or phrases.

[0911] "Dependency analysis" is the process of analyzing how words in a sentence are related to each other.

[0912] "Splitting into sentences" refers to the process of dividing a prompt message into multiple sentences.

[0913] An "external information provider" refers to an external data source that a server accesses to retrieve information.

[0914] A "generative model" is an AI technology used to generate new text or answers based on input data.

[0915] A "consistent answer" is one that is free from contradictions and has a unified logical structure.

[0916] The system of this invention receives a question entered by the user, analyzes and divides it, queries a data storage device to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[0917] Receiving a prompt

[0918] User: The user enters the question into the input field on the terminal and presses the submit button.

[0919] Terminal: The terminal sends this input to the server. This communication uses an HTTP POST request.

[0920] Prompt analysis and segmentation

[0921] Server: The server uses the Python-based natural language processing tool "Open Source Natural Language Processing Toolkit" to parse the received prompt. Specifically, it performs the following processes:

[0922] Tokenization: Dividing a prompt into units of words or phrases.

[0923] Dependency analysis: Analyzes how words in a sentence are related to each other.

[0924] Split into sentences: Divide the prompt message into multiple sentences.

[0925] Convert into individual questions as needed.

[0926] Database query

[0927] Server: The server queries external information providers based on each segmented query. The following APIs are used for this:

[0928] A "general-purpose knowledge base API" for retrieving general information.

[0929] A "scientific data API" is used to obtain scientific data and facts.

[0930] The server sends an HTTP GET request to each API and receives data in JSON format.

[0931] Integration and purification

[0932] Server: The server integrates the acquired information and the segmented questions to generate the final answer. This process uses a generative AI model, the "Generative AI Engine." The specific steps are as follows:

[0933] The acquired JSON data is analyzed, and candidate answers are extracted.

[0934] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[0935] Regenerate the output as needed and select the optimal answer.

[0936] Provision to users

[0937] Server: The server sends the final generated response to the user's terminal.

[0938] Terminal: The terminal displays the received response to the user. This received data is in HTML format and is rendered correctly in the browser.

[0939] Specific example

[0940] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." The process in this case would be as follows:

[0941] 1. User: The user enters "What is artificial intelligence?" into the input field on the device and presses the send button.

[0942] 2. Terminal: The terminal sends data including this prompt to the server as an HTTP POST request.

[0943] 3. Server: The server analyzes the received query using a natural language processing toolkit and divides it as follows:

[0944] "What is artificial intelligence?"

[0945] "Please tell me about its history as well."

[0946] 4. Server: Access the General Knowledge Base API and Scientific Data API to retrieve additional information:

[0947] "What is AI?" -> "Artificial Intelligence is the field of study..."

[0948] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[0949] 5. Server: Inputs the acquired information into the AI ​​engine to generate consistent responses:

[0950] "What is artificial intelligence?" -> "Additional information: Artificial intelligence is the field of study..."

[0951] "Please also tell me about its history." -> "Additional information: The history of AI dates back to the mid-20th century..."

[0952] 6. Server: Converts the generated response into HTML format and sends it to the user's device.

[0953] 7. Terminal: The terminal displays the received HTML data in a browser and shows it to the user in the following format: "What is artificial intelligence?", "Additional information: Artificial Intelligence is the field of study...", "Please also tell me about its history.", "Additional information: The history of AI dates back to the mid-20th century...".

[0954] In this way, the system can provide accurate and comprehensive information in response to user inquiries.

[0955] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0956] Step 1: Receiving the prompt

[0957] User: The user enters a question into the input field on the terminal and presses the submit button.

[0958] Specific action: The user types, for example, "What is artificial intelligence?" and presses the submit button.

[0959] Input: The user entered the question, "What is artificial intelligence?".

[0960] Terminal: The terminal sends this input to the server. It uses an HTTP POST request for communication.

[0961] Output: Input data sent to the server.

[0962] Step 2: Prompt analysis and splitting

[0963] Server: The server utilizes a Python-based open-source natural language processing toolkit to parse the received prompts.

[0964] Specific actions:

[0965] Tokenization: Dividing a sentence into words or phrases. For example, dividing it into "artificial intelligence," "what is," and "what is it?".

[0966] Dependency analysis: This analyzes how words in a sentence relate to each other. For example, it identifies that "artificial intelligence" is the subject, "what is" is the predicate, and "what is?" is the complement.

[0967] Split into sentences: Process each prompt statement as a single sentence.

[0968] Input: Received prompt message: "What is artificial intelligence?"

[0969] Output: The question, broken down into sentence units, obtained as a result of the analysis, for example, "What is artificial intelligence?".

[0970] Step 3: Query the database

[0971] Server: The server queries external information providers based on the questions generated through analysis.

[0972] Specific actions:

[0973] Send the query "What is AI?" to a general-purpose knowledge base API.

[0974] Send the query "What is AI?" to the scientific data API.

[0975] Receive data in JSON format from the API.

[0976] Input: Divided question "What is AI?".

[0977] Output: Retrieved response data in JSON format.

[0978] Step 4: Integration and Purification

[0979] Server: The server integrates the acquired information and the segmented questions to generate the final answer.

[0980] Specific actions:

[0981] The acquired JSON data is analyzed to extract potential answers. For example, information such as "Artificial Intelligence is the field of study..."

[0982] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[0983] If necessary, the AI ​​generation engine will regenerate the answer and select the most suitable response.

[0984] Input: Retrieved response data in JSON format.

[0985] Output: The final integrated answer.

[0986] Step 5: Providing to Users

[0987] Server: The server sends the final generated response to the user's terminal.

[0988] Terminal: The terminal displays the received response to the user.

[0989] Specific operation: The server sends HTML-formatted data to the user's device, and the device displays that data in its browser.

[0990] Input: The server's final generated response: "Artificial Intelligence is the field of study..."

[0991] Output: The final answer displayed to the user.

[0992] In this way, the system provides accurate and comprehensive information in response to user inquiries.

[0993] (Application Example 1)

[0994] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0995] Traditional systems that accept inquiries and provide information have struggled to provide optimal real-time responses to user-inputted instructions and questions. Furthermore, especially in autonomous vehicles, the immediate provision of traffic and navigation information is crucial, and the lack of systems capable of handling this has been a problem. Therefore, a new system is needed that enables real-time and detailed information provision, thereby improving user convenience.

[0996] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0997] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into a plurality of divided questions, means for querying a database based on the divided questions and obtaining corresponding information, means for integrating the divided questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for the user to input instructions by voice or text, analyzing them and dividing them into specific questions, and means for generating and providing the optimal answer in real time based on the acquired information. This enables real-time and detailed information provision even in autonomous vehicles, improving user convenience and safety.

[0998] A "user" is someone who uses the system and inputs questions or instructions.

[0999] A "question" refers to a question or instruction that a user enters into the system, and it is a request for information or advice.

[1000] "Natural language processing" is a technology that enables computers to understand, analyze, and process human language.

[1001] A "divided question" is a question that has been analyzed using natural language processing and transformed into multiple specific questions.

[1002] A "database" is a system where information is stored and provides information that responds to user inquiries.

[1003] The "final answer" is the answer provided to the user, generated by integrating the divided questions and the corresponding information.

[1004] "Real-time" means that processing and information are provided almost instantly.

[1005] "Voice or text" refers to the method by which a user inputs a question to the system, and includes voice input and text input.

[1006] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments are described below.

[1007] 1. System Overview

[1008] Receiving a prompt

[1009] Terminal: The user enters and submits the question in voice or text format. The terminal sends this input to the server.

[1010] Prompt analysis and segmentation

[1011] Server: Upon receiving a prompt, the server analyzes the question using natural language processing techniques. The analysis process divides the question into sentences and, if necessary, converts them into more specific questions. This generates multiple specific questions.

[1012] Database query

[1013] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, especially the English version, to obtain detailed and accurate information.

[1014] Integration and purification

[1015] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[1016] Provision to users

[1017] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[1018] 2. Hardware and software used

[1019] hardware

[1020] Microphone and speaker: A device for users to input instructions by voice and receive responses by voice.

[1021] Terminal (smartphone, in-car display, etc.): A device used by the user to input questions and receive answers.

[1022] software

[1023] Natural Language Processing: A technique used to analyze a question and break it down into more specific questions. A concrete example is the Python Natural Language Toolkit (nltk) library.

[1024] Database access: A tool for querying a database and retrieving corresponding information. Examples include SQL databases and NoSQL databases.

[1025] Integration and Refinement: Logic for integrating acquired information and generating the final answer. Programming languages ​​such as Python or Ruby can be used.

[1026] 3. Specific Examples

[1027] For example, let's look at a specific case where a user inputs a question via voice, such as, "Tell me about traffic congestion ahead."

[1028] Example of a prompt

[1029] "Please tell me about the traffic conditions ahead."

[1030] Execution process

[1031] 1. Terminal: The user provides voice input, which the system then converts into text data. Alternatively, the user may have already entered the question in text format.

[1032] 2. Server: The server analyzes the received query using natural language processing technology and divides it into "traffic information" and "what's ahead".

[1033] 3. Server: Retrieves real-time data related to "traffic congestion information" from the database, and simultaneously retrieves location information related to "what's ahead".

[1034] 4. Server: Integrates the acquired information and generates a final response (e.g., "There is traffic congestion 5km ahead. The recommended detour is here.").

[1035] 5. Device: Provide this final answer to the user. It will be displayed via voice or on the screen.

[1036] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1037] Step 1:

[1038] Input: The user enters the question via voice or text.

[1039] Operation: In the case of voice input, the device uses the microphone to capture voice data and converts it to text using speech recognition software (e.g., Google Speech Recognition API).

[1040] Output: Sends a question in text format to the server.

[1041] Step 2:

[1042] Input: The server receives the user's query in text format.

[1043] Operation: The server analyzes the question using natural language processing (NLP) techniques. Specifically, it uses Python's Natural Language Toolkit (nltk) and the spaCy API to break down the question into sentences and convert them into more specific, subdivided questions.

[1044] Output: Generates a list of specific questions broken down into segments.

[1045] Step 3:

[1046] Input: A list of specific questions divided into sections.

[1047] Operation: The server queries the database based on each segmented query. It references SQL and NoSQL databases to retrieve corresponding information in real time.

[1048] Output: Generates a list of corresponding information for each question.

[1049] Step 4:

[1050] Input: A list of divided questions and a list of corresponding information.

[1051] Operation: The server integrates the acquired information and generates the final answer using natural language generation (NLG) technology. It constructs the sentence into a natural form using programs such as Python or Ruby.

[1052] Output: Generates the final answer and outputs it in text format.

[1053] Step 5:

[1054] Input: Final response generated by the server.

[1055] Operation: The device displays the response received from the server. If audio output is required, it uses a Text-to-Speech (TTS) engine (e.g., Google Text-to-Speech API) to convert it to speech and output it through the speaker.

[1056] Output: Provides the user with the final answer in text and audio formats.

[1057] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1058] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[1059] Receiving a prompt

[1060] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[1061] Prompt analysis and segmentation

[1062] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[1063] Emotion recognition by an emotion engine

[1064] Server: Next, the server uses an emotion engine to recognize emotions from the questions entered by the user. The emotion engine extracts and analyzes emotional information from the user's text. This emotional information includes various emotions such as anger, sadness, and joy.

[1065] Database query

[1066] Server: Based on each generated query, the server queries the database and retrieves the corresponding information. This database is multilingual, and can access a particularly extensive English version of the database to obtain detailed and accurate information. Based on the sentiment information obtained by the sentiment engine, it selects information that is appropriate to the emotion.

[1067] Integration and purification

[1068] Server: Integrates acquired information, segmented questions, and sentiment information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent answer. By adding sentiment information, it provides answers that are easier for users to understand and empathize with.

[1069] Provision to users

[1070] Terminal: The final answers generated by the server are sent to the user's terminal. The terminal displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[1071] Specific example

[1072] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would handle the situation if it detects that the user's question contains feelings of anger.

[1073] 1. Terminal: The user submits the input content.

[1074] 2. Server: The server analyzes the received query and divides it as follows:

[1075] "What is artificial intelligence?"

[1076] "Please tell me about its history as well."

[1077] 3. Server: Analyzes user emotions using an emotion engine:

[1078] The user's question contains feelings of anger.

[1079] 4. Server: Access the English version of the database to retrieve additional information:

[1080] "What is AI?" -> "Artificial Intelligence is the field of study..."

[1081] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[1082] 5. Server: Integrates the segmented questions, acquired information, and sentiment information to generate the final answer:

[1083] "What is artificial intelligence?"

[1084] "Additional information: Artificial Intelligence is the field of study..."

[1085] "To answer your questions, we will provide you with more detailed information, so please let us know."

[1086] "Please tell me about its history as well."

[1087] "Additional information: The history of AI dates back to the mid-20th century..."

[1088] "If you'd like to delve deeper into history, we also have textbook-style materials available."

[1089] 6. Terminal: Provides the final answer to the user.

[1090] Such a system allows users to obtain detailed and comprehensive information with a single question input, while simultaneously improving the user experience by enabling the system to respond in a way that is sensitive to the user's emotions.

[1091] The following describes the processing flow.

[1092] Step 1: The user enters the question and presses the submit button.

[1093] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on their device. Then, they press the send button to submit the question.

[1094] Step 2: The device sends the user's query to the server.

[1095] The terminal sends the user's input to the server. At this time, the entered text data is sent to the server.

[1096] Step 3: The server receives and analyzes the query.

[1097] The server analyzes the received question. First, it uses natural language processing techniques to break down the question into sentences and, if necessary, converts them into individual questions. For example, the question "What is artificial intelligence? Please also tell me about its history." is split into "What is artificial intelligence?" and "Please also tell me about its history."

[1098] Step 4: The server recognizes the user's emotions.

[1099] The server uses an emotion engine to recognize emotions from the user's question. The emotion engine analyzes the text data of the question and detects the user's emotions (e.g., anger, sadness, joy). For example, it might determine that the user's question contains some anger.

[1100] Step 5: The server queries the database with the divided queries.

[1101] Next, the server queries the database based on each of the divided questions and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves information such as "Artificial Intelligence is the field of study...", and in response to "Please also tell me about its history," it retrieves information such as "The history of AI dates back to the mid-20th century...".

[1102] Step 6: The server also accesses the English version of the database.

[1103] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[1104] Step 7: Integrate the information obtained by the server with the original question.

[1105] The server integrates the acquired information, segmented questions, and emotional information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent response. Adding emotional information provides answers that are easier for users to understand and empathize with.

[1106] Step 8: The server sends the final response to the terminal.

[1107] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[1108] Step 9: The device displays the final answer to the user.

[1109] The device displays the final received answer to the user. The user can instantly see a comprehensive answer to their question. For example, in response to the question, "What is artificial intelligence?", it will display, "Artificial Intelligence is the field of study... Please let us know if you would like more information to answer your question." Also, in response to "Please tell me about its history," it will display, "The history of AI dates back to the mid-20th century... If you would like to delve deeper into its history, we also have textbook-style materials available."

[1110] In this way, users can obtain comprehensive information with a single question input, and receive highly relevant answers that reflect their emotions at the time of input, thus improving the user experience.

[1111] (Example 2)

[1112] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1113] Conventional question-answering systems have a problem in that the process of receiving user-entered questions and providing corresponding answers is not properly handled, making it difficult to obtain satisfactory answers, especially for complex or emotionally charged questions. Furthermore, there was a lack of means to quickly retrieve detailed information from multilingual databases and present it to users in an easily understandable way. In addition, the ability to generate optimal answers that take into account the user's emotions was insufficient.

[1114] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question entered by the user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for integrating sentiment information in addition to the segmented questions and corresponding information to generate a final answer, and means for providing the final answer to the user. As a result, the user can quickly obtain detailed and consistent information, and the system can provide the optimal answer according to the user's sentiment. Furthermore, by using a multilingual database, it becomes possible to provide even richer information.

[1115] A "user" is an individual or group that uses the system.

[1116] "Input" refers to the information or questions that a user provides to the system.

[1117] A "question" is a question that a user asks the system.

[1118] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[1119] "Analysis" is the process by which a system understands the input question and grasps its meaning.

[1120] "Splitting" is the process of converting an input question into multiple specific questions.

[1121] A "database" is a system that organizes and stores information, making it searchable and retrievable as needed.

[1122] A "query" is the process of requesting specific information from a database.

[1123] "Information" refers to the data and knowledge necessary to provide an answer, which are retrieved from a database.

[1124] "Emotional information" refers to data obtained by analyzing and identifying the emotions contained in the user's questions.

[1125] An "answer" is the system's response to a user's question.

[1126] "Integration" is the process of combining multiple pieces of information and data to form a consistent answer as a whole.

[1127] "Multilingual support" refers to the ability to handle and process information written in different languages.

[1128] "Means" refer to the specific methods and techniques used to achieve an objective.

[1129] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[1130] Receiving a prompt

[1131] The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server. The terminal sends the user's input to the server using the HTTP POST method.

[1132] Prompt analysis and segmentation

[1133] The server analyzes the received questions using natural language processing (NLP) techniques. Specifically, it uses the Python NLTK library to break down the questions into sentences and, if necessary, convert them into individual, subdivided questions. This process involves tokenization, morphological analysis, and grammatical analysis.

[1134] Emotion recognition by an emotion engine

[1135] The server uses an emotion engine to recognize emotions from the user's questions. This emotion engine uses a general emotion analysis system to extract and analyze emotional information from the user's text. Emotional information includes various emotions such as anger, sadness, and joy.

[1136] Database query

[1137] Based on each generated query, the server queries the database using a standard database management system to retrieve the corresponding information. The database is multilingual, and can access extensive databases, particularly in English, to obtain detailed and accurate information.

[1138] Integration and purification

[1139] The server integrates the acquired information, segmented questions, and sentiment information to generate a final answer. Using the Python Pandas library, it appropriately integrates the information corresponding to each question to form a consistent answer.

[1140] Provision to users

[1141] The final answers generated by the server are sent to the user's device. The device displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[1142] Specific example

[1143] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would process the situation if it detects that the user's question contains the emotion of "anger."

[1144] 1. The user submits their input.

[1145] 2. The server analyzes the received query and divides it as follows:

[1146] "What is artificial intelligence?"

[1147] "Please tell me about its history as well."

[1148] 3. The server uses an emotion engine to analyze the user's emotions and recognizes the emotion of "anger."

[1149] 4. The server accesses a multilingual database to retrieve additional information. Example:

[1150] "Artificial Intelligence is the field of study..."

[1151] "The history of AI dates back to the mid-20th century..."

[1152] 5. The server integrates the segmented questions, acquired information, and sentiment information to generate the final answer. Example:

[1153] "What is artificial intelligence?"

[1154] "Artificial Intelligence is the field of study..."

[1155] "If you tell us why you're angry, we can provide you with more detailed information."

[1156] "Please tell me about its history as well."

[1157] "The history of AI dates back to the mid-20th century..."

[1158] "If you'd like to delve deeper into the history, please feel free to contact us."

[1159] 6. The final answer is provided to the user.

[1160] This system allows users to obtain detailed and comprehensive information with a single question input, and the system responds to the user's emotions, thus improving the user experience.

[1161] Example of a prompt

[1162] "What is machine learning? Please explain it in a way that's easy for beginners to understand."

[1163] "How do I install Python?"

[1164] "I'd like to learn about career paths in data science."

[1165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1166] Step 1: Receiving the prompt

[1167] The user enters a question into the terminal's input field and presses the submit button. The terminal sends the input to the server using the HTTP POST method. The input is the text entered by the user, and the output is JSON data sent to the server. The terminal sends the input text to the appropriate API endpoint.

[1168] Step 2: Prompt analysis and splitting

[1169] The server parses the JSON data received from the terminal and extracts the questions. The input is text data containing the questions received from the terminal, and the output is multiple specific questions that have been divided. The server uses Python's NLTK library to divide the questions into sentences and convert each sentence into a separate question. Specifically, the `sent_tokenize` function is used to divide the data into sentences.

[1170] Step 3: Emotion recognition by the emotion engine

[1171] The server extracts sentiment information from each question that has been analyzed and segmented. The input is a list of segmented questions, and the output is data containing the corresponding sentiment information. The server uses a sentiment analysis engine (e.g., a general sentiment analysis system) to identify the sentiment for each question. Specifically, it uses the tone_analyzer.tone method to obtain a sentiment score and adds it to the data.

[1172] Step 4: Query the database

[1173] The server queries the database based on the segmented questions. The input is data containing each question and sentiment information, and the output is the corresponding information retrieved from the database. The server uses a database management system (e.g., a general database management system) to execute the queries and retrieve the necessary information. Specifically, it constructs SQL queries, executes them against the database, and retrieves the results.

[1174] Step 5: Integration and Purification

[1175] The server integrates information retrieved from the database with segmented questions and sentiment information to generate a final answer. The input is data containing segmented questions, retrieved information, and sentiment information, and the output is the final answer provided to the user. The server uses the Python Pandas library to integrate various data and form a consistent answer. Specifically, it uses Pandas' DataFrame functionality to organize and combine data to create a consistently meaningful answer.

[1176] Step 6: Provision to users

[1177] The server sends the final generated response to the user's device. The input is the final response generated by the server, and the output is the text displayed on the user's device. The server sends the final response to the device as an HTTP response, and the device displays the received response in a user-friendly format.

[1178] This specific processing allows users to quickly obtain detailed and consistent information with a single question input. Furthermore, the system provides responses that are sensitive to the user's emotions, improving the user experience.

[1179] (Application Example 2)

[1180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1181] Modern consumers ask a variety of questions in physical stores and expect quick and appropriate answers, but traditional systems struggle to provide sufficient information immediately and respond flexibly to customer emotions. To solve these problems, technology is needed that analyzes user questions and provides optimal answers while considering emotions. In particular, multilingual support and information provision that takes emotions into account are required.

[1182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1183] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for adjusting the answer in a way that takes the user's emotions into account using an emotion engine, and means for displaying the final answer on a mobile information terminal used in a physical store. This enables quick and appropriate responses to customer questions in physical stores and the provision of highly satisfying services tailored to the customer's emotions.

[1184] A "user" refers to a person who uses a system or service.

[1185] A "terminal" refers to an electronic device that a user can operate.

[1186] A "question" refers to a question or request that a user enters into the system.

[1187] "Natural language processing" is a technology that analyzes natural language spoken by humans and processes it using computers.

[1188] "Analysis" refers to the process of understanding a given question based on its meaning and structure.

[1189] A "divided question" refers to the original question that has been transformed into multiple specific questions.

[1190] A "database" is a system in which information is systematically stored.

[1191] "Inquiry" refers to the act of accessing a database to retrieve information.

[1192] "Information" refers to answers and data obtained from a database.

[1193] "Integration" refers to the act of bringing together multiple pieces of information in a consistent manner.

[1194] The "final answer" refers to the answer generated based on integrated information.

[1195] An "emotion engine" is a program that analyzes a user's emotions and adjusts the information provided based on those emotions.

[1196] A "multilingual database" is a database that can provide information in multiple languages.

[1197] A "physical store" refers to a store that has a physical presence.

[1198] "Personal information terminals" refer to portable electronic devices such as mobile phones, smartphones, and tablets.

[1199] This invention is a system that receives questions from users in physical stores and provides quick and appropriate answers using natural language processing and an emotion engine. The specific implementation of this system is described below.

[1200] First, this system will be implemented using a portable information terminal such as smart glasses. The terminal is equipped with a microphone that can receive voice input from the user. Once voice input is received, the data is sent to a server.

[1201] The server first uses a speech recognition engine to convert the audio data into text. This transcribed data represents the question in the system, which is then analyzed by natural language processing (NLP). This analysis breaks down the question into multiple specific questions.

[1202] Next, the server uses an emotion engine to determine the user's emotions. This emotion determination extracts emotional information from the user's text and recognizes the emotions behind the question (e.g., joy, anger, sadness, etc.).

[1203] The segmented questions and sentiment information are stored on the server, and queries are then sent to the database based on this information. The database is multilingual and can access a wide range of databases, particularly in English. Therefore, detailed and highly accurate information can be obtained.

[1204] The system integrates acquired information with emotional data to generate a final response that takes emotions into consideration. Because the response is adjusted to reflect the user's emotions, the user experience is improved.

[1205] The final response is sent to the device and displayed on the screen. This allows in-store staff to provide customers with quick and emotionally sensitive answers.

[1206] Hardware and software to use

[1207] Hardware: Portable information devices such as smart glasses equipped with a microphone.

[1208] Software: Speech recognition engine (e.g., speech_recognition library), natural language processing (e.g., transformers library), emotion engine, database access library (e.g., requests library).

[1209] Specific example

[1210] For example, if a customer speaks into the microphone built into the smart glasses and says, "Please tell me how to use this product," the system analyzes and breaks down the question, recognizes the customer's emotions, and provides the most appropriate answer.

[1211] Example of a prompt

[1212] If you are asked about the intended use of the product, please generate your answer using the following method:

[1213] 1. Analyze the question and divide it into individual sentences.

[1214] 2. Determine the emotions contained in the question.

[1215] 3. Query the database based on the question and sentiment to obtain the best answer.

[1216] 4. Integrate the divided questions and answers to generate sentiment-sensitive responses.

[1217] As a specific example, if a question is entered such as "How do I use this product?", we will provide links to detailed user instructions and related videos for that product.

[1218] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1219] Step 1:

[1220] The device receives the user's voice input. The user speaks into the microphone attached to the device, and voice data is collected. The input is the user's question, and the output is voice data.

[1221] Step 2:

[1222] The terminal sends audio data to the server. The audio data is converted to a digital format and transferred to the server. The input is audio data, and the output is the digital audio data sent to the server.

[1223] Step 3:

[1224] The server uses a speech recognition engine to convert the audio data into text. The converted text becomes the question. The input is digital audio data, and the output is converted text data.

[1225] Step 4:

[1226] The server uses a natural language processing engine to analyze the question. Through this analysis, the question is broken down into sentences. The input is text data, and the output is the multiple, divided questions.

[1227] Step 5:

[1228] The server uses an emotion engine to determine the user's emotions from segmented questions. Emotional information is extracted, and emotions such as joy, anger, and sadness are identified. The input is segmented questions, and the output is emotional information.

[1229] Step 6:

[1230] The server queries a database based on segmented questions and sentiment information to retrieve corresponding information. It also accesses multilingual databases to collect detailed and appropriate information. The input is segmented questions and sentiment information, and the output is the retrieved information.

[1231] Step 7:

[1232] The server integrates the acquired information with the segmented questions and sentiment information to generate the final answer. By incorporating sentiment information, the answer is refined to resonate with the user. The input is the acquired information and sentiment information, and the output is the final answer.

[1233] Step 8:

[1234] The server sends the final answer to the terminal. The terminal displays this final answer on its screen. The input is the final answer, and the output is the answer information sent to the terminal.

[1235] Step 9:

[1236] The device displays the response information to the user. The final response is displayed on the device's screen and can be viewed by the user. The input is the submitted response information, and the output is the response displayed on the screen.

[1237] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1238] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1239] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1240] [Fourth Embodiment]

[1241] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1242] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1243] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1244] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1245] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1246] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1247] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1248] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1249] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1250] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1251] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1252] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1253] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1254] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[1255] Receiving a prompt

[1256] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[1257] Prompt analysis and segmentation

[1258] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[1259] Database query

[1260] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, especially the English version, to obtain detailed and accurate information.

[1261] Integration and purification

[1262] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[1263] Provision to users

[1264] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[1265] Specific example

[1266] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history."

[1267] 1. Terminal: The user submits the entered content.

[1268] 2. Server: The server analyzes the received query and divides it as follows:

[1269] "What is artificial intelligence?"

[1270] "Please tell me about its history as well."

[1271] 3. Server: Access the English version of the database to retrieve additional information:

[1272] "What is AI?" -> "Artificial Intelligence is the field of study..."

[1273] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[1274] 4. Server: Integrates the divided questions and acquired information to generate the final answer:

[1275] "What is artificial intelligence?"

[1276] "Additional information: Artificial Intelligence is the field of study..."

[1277] "Please tell me about its history as well."

[1278] "Additional information: The history of AI dates back to the mid-20th century..."

[1279] 5. Terminal: Provides the final answer to the user.

[1280] "What is artificial intelligence?"

[1281] "Additional information: Artificial Intelligence is the field of study..."

[1282] "Please tell me about its history as well."

[1283] "Additional information: The history of AI dates back to the mid-20th century..."

[1284] Such a system allows users to obtain detailed and comprehensive information with a single question input, improving both the system's usability and the accuracy of the answers.

[1285] The following describes the processing flow.

[1286] Step 1: The user enters the question and presses the submit button.

[1287] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on the device and presses the send button.

[1288] Step 2: The device sends the user's query to the server.

[1289] The terminal sends the user's input to the server. This data is sent as text.

[1290] Step 3: The server receives and analyzes the query.

[1291] The server analyzes the questions received from the terminal. First, it uses natural language processing techniques to break down the questions into sentences and convert them into multiple specific questions.

[1292] Step 4: The server queries the database with the divided queries.

[1293] The server queries the database based on each segmented question and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves a wide range of information such as "Artificial Intelligence is the field of study...".

[1294] Step 5: The server also accesses the English version of the database.

[1295] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[1296] Step 6: Integrate the information obtained by the server with the original question.

[1297] The server integrates the acquired information with the original segmented questions to generate a final answer. For example, it might connect "What is artificial intelligence?" with "Artificial Intelligence is the field of study...".

[1298] Step 7: The server sends the final response to the terminal.

[1299] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[1300] Step 8: The device displays the final answer to the user.

[1301] The device displays the final received response to the user. The user can instantly see a comprehensive answer to the question.

[1302] (Example 1)

[1303] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1304] Conventional information retrieval systems have struggled to provide appropriate answers to user-inputted questions, and generating consistent and comprehensive responses, especially for complex questions, has been a challenge. Furthermore, there has been a need for systems that can access extensive databases spanning multiple languages ​​and possess high-precision analysis capabilities using natural language processing.

[1305] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1306] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a data storage device based on the segmented questions and obtaining corresponding information, means for integrating the segmented questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for performing tokenization and dependency analysis based on natural language processing and segmenting the question into sentence units, means for querying an external information provider for the generated questions and analyzing the obtained information, and means for generating a consistent answer using a generative model based on the obtained information. This makes it possible to provide complex and comprehensive information in response to a user's question with high accuracy.

[1307] A "user" is a person who uses the system to input and submit questions.

[1308] "Means of receiving" refers to the function of sending the entered question to the server via the network.

[1309] "Natural language processing" refers to the technology that enables computers to understand, analyze, and generate human language.

[1310] "Analysis" is the process of understanding the content of a question and grasping its meaning.

[1311] A "divided question" refers to multiple specific questions derived from analyzing the initial question.

[1312] A "data storage device" is a part of a system that stores and provides information, and often refers to a database or an external API.

[1313] "Means of querying and obtaining information" refers to the process of obtaining information corresponding to divided questions from a data storage device.

[1314] "Means of integrating to generate a final answer" refers to the process of integrating acquired information to create a consistent answer.

[1315] "Means of providing" refers to the function of displaying or sending the final answer to the user.

[1316] "Tokenization" is the process of dividing a text into units such as words or phrases.

[1317] "Dependency analysis" is the process of analyzing how words in a sentence are related to each other.

[1318] "Splitting into sentences" refers to the process of dividing a prompt message into multiple sentences.

[1319] An "external information provider" refers to an external data source that a server accesses to retrieve information.

[1320] A "generative model" is an AI technology used to generate new text or answers based on input data.

[1321] A "consistent answer" is one that is free from contradictions and has a unified logical structure.

[1322] The system of this invention receives a question entered by the user, analyzes and divides it, queries a data storage device to generate the optimal answer, and provides it to the user. Specific embodiments of the system are described below.

[1323] Receiving a prompt

[1324] User: The user enters the question into the input field on the terminal and presses the submit button.

[1325] Terminal: The terminal sends this input to the server. This communication uses an HTTP POST request.

[1326] Prompt analysis and segmentation

[1327] Server: The server uses the Python-based natural language processing tool "Open Source Natural Language Processing Toolkit" to parse the received prompt. Specifically, it performs the following processes:

[1328] Tokenization: Dividing a prompt into units of words or phrases.

[1329] Dependency analysis: Analyzes how words in a sentence are related to each other.

[1330] Split into sentences: Divide the prompt message into multiple sentences.

[1331] Convert into individual questions as needed.

[1332] Database query

[1333] Server: The server queries external information providers based on each segmented query. The following APIs are used for this:

[1334] A "general-purpose knowledge base API" for retrieving general information.

[1335] A "scientific data API" is used to obtain scientific data and facts.

[1336] The server sends an HTTP GET request to each API and receives data in JSON format.

[1337] Integration and purification

[1338] Server: The server integrates the acquired information and the segmented questions to generate the final answer. This process uses a generative AI model, the "Generative AI Engine." The specific steps are as follows:

[1339] The acquired JSON data is analyzed, and candidate answers are extracted.

[1340] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[1341] Regenerate the output as needed and select the optimal answer.

[1342] Provision to users

[1343] Server: The server sends the final generated response to the user's terminal.

[1344] Terminal: The terminal displays the received response to the user. This received data is in HTML format and is rendered correctly in the browser.

[1345] Specific example

[1346] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." The process in this case would be as follows:

[1347] 1. User: The user enters "What is artificial intelligence?" into the input field on the device and presses the send button.

[1348] 2. Terminal: The terminal sends data including this prompt to the server as an HTTP POST request.

[1349] 3. Server: The server analyzes the received query using a natural language processing toolkit and divides it as follows:

[1350] "What is artificial intelligence?"

[1351] "Please tell me about its history as well."

[1352] 4. Server: Access the General Knowledge Base API and Scientific Data API to retrieve additional information:

[1353] "What is AI?" -> "Artificial Intelligence is the field of study..."

[1354] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[1355] 5. Server: Inputs the acquired information into the AI ​​engine to generate consistent responses:

[1356] "What is artificial intelligence?" -> "Additional information: Artificial intelligence is the field of study..."

[1357] "Please also tell me about its history." -> "Additional information: The history of AI dates back to the mid-20th century..."

[1358] 6. Server: Converts the generated response into HTML format and sends it to the user's device.

[1359] 7. Terminal: The terminal displays the received HTML data in a browser and shows it to the user in the following format: "What is artificial intelligence?", "Additional information: Artificial Intelligence is the field of study...", "Please also tell me about its history.", "Additional information: The history of AI dates back to the mid-20th century...".

[1360] In this way, the system can provide accurate and comprehensive information in response to user inquiries.

[1361] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1362] Step 1: Receiving the prompt

[1363] User: The user enters a question into the input field on the terminal and presses the submit button.

[1364] Specific action: The user types, for example, "What is artificial intelligence?" and presses the submit button.

[1365] Input: The user entered the question, "What is artificial intelligence?".

[1366] Terminal: The terminal sends this input to the server. It uses an HTTP POST request for communication.

[1367] Output: Input data sent to the server.

[1368] Step 2: Prompt analysis and splitting

[1369] Server: The server utilizes a Python-based open-source natural language processing toolkit to parse the received prompts.

[1370] Specific actions:

[1371] Tokenization: Dividing a sentence into words or phrases. For example, dividing it into "artificial intelligence," "what is," and "what is it?".

[1372] Dependency analysis: This analyzes how words in a sentence relate to each other. For example, it identifies that "artificial intelligence" is the subject, "what is" is the predicate, and "what is?" is the complement.

[1373] Split into sentences: Process each prompt statement as a single sentence.

[1374] Input: Received prompt message: "What is artificial intelligence?"

[1375] Output: The question, broken down into sentence units, obtained as a result of the analysis, for example, "What is artificial intelligence?".

[1376] Step 3: Query the database

[1377] Server: The server queries external information providers based on the questions generated through analysis.

[1378] Specific actions:

[1379] Send the query "What is AI?" to a general-purpose knowledge base API.

[1380] Send the query "What is AI?" to the scientific data API.

[1381] Receive data in JSON format from the API.

[1382] Input: Divided question "What is AI?".

[1383] Output: Retrieved response data in JSON format.

[1384] Step 4: Integration and Purification

[1385] Server: The server integrates the acquired information and the segmented questions to generate the final answer.

[1386] Specific actions:

[1387] The acquired JSON data is analyzed to extract potential answers. For example, information such as "Artificial Intelligence is the field of study..."

[1388] The AI ​​engine generates a consistent answer by inputting candidate answers corresponding to each question.

[1389] If necessary, the AI ​​generation engine will regenerate the answer and select the most suitable response.

[1390] Input: Retrieved response data in JSON format.

[1391] Output: The final, integrated answer.

[1392] Step 5: Provision to users

[1393] Server: The server sends the final generated response to the user's terminal.

[1394] Terminal: The terminal displays the received response to the user.

[1395] Specific operation: The server sends HTML-formatted data to the user's device, and the device displays that data in its browser.

[1396] Input: The server's final generated response: "Artificial Intelligence is the field of study..."

[1397] Output: The final answer displayed to the user.

[1398] In this way, the system provides accurate and comprehensive information in response to user inquiries.

[1399] (Application Example 1)

[1400] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1401] Traditional systems that accept inquiries and provide information have struggled to provide optimal real-time responses to user-inputted instructions and questions. Furthermore, especially in autonomous vehicles, the immediate provision of traffic and navigation information is crucial, and the lack of systems capable of handling this has been a problem. Therefore, a new system is needed that enables real-time and detailed information provision, thereby improving user convenience.

[1402] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1403] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into a plurality of divided questions, means for querying a database based on the divided questions and obtaining corresponding information, means for integrating the divided questions and corresponding information to generate a final answer, means for providing the final answer to the user, means for the user to input instructions by voice or text, analyzing them and dividing them into specific questions, and means for generating and providing the optimal answer in real time based on the acquired information. This enables real-time and detailed information provision even in autonomous vehicles, improving user convenience and safety.

[1404] A "user" is someone who uses the system and inputs questions or instructions.

[1405] A "question" refers to a question or instruction that a user enters into the system, and it is a request for information or advice.

[1406] "Natural language processing" is a technology that enables computers to understand, analyze, and process human language.

[1407] A "divided question" is a question that has been analyzed using natural language processing and transformed into multiple specific questions.

[1408] A "database" is a system where information is stored and provides information that responds to user inquiries.

[1409] The "final answer" is the answer provided to the user, generated by integrating the divided questions and the corresponding information.

[1410] "Real-time" means that processing and information are provided almost instantly.

[1411] "Voice or text" refers to the method by which a user inputs a question to the system, and includes voice input and text input.

[1412] This invention is a system that receives a question entered by a user, analyzes and divides it, queries a database to generate the optimal answer, and provides it to the user. Specific embodiments are described below.

[1413] 1. System Overview

[1414] Receiving a prompt

[1415] Terminal: The user enters and submits the question in voice or text format. The terminal sends this input to the server.

[1416] Prompt analysis and segmentation

[1417] Server: Upon receiving a prompt, the server analyzes the question using natural language processing techniques. The analysis process divides the question into sentences and, if necessary, converts them into more specific questions. This generates multiple specific questions.

[1418] Database query

[1419] Server: Next, the server queries the database based on each generated question and retrieves the corresponding information. This database is multilingual, and can access an extensive database, especially the English version, to obtain detailed and accurate information.

[1420] Integration and purification

[1421] Server: Integrates the acquired information and segmented questions to generate the final answer. This process appropriately integrates the information corresponding to each question to form a consistent answer.

[1422] Provision to users

[1423] Terminal: The final answer generated by the server is sent to the user's terminal. The terminal displays the received answer to the user. At this time, the divided questions and their corresponding additional information are displayed together, providing the user with comprehensive information they are looking for.

[1424] 2. Hardware and software used

[1425] hardware

[1426] Microphone and speaker: A device for users to input instructions by voice and receive responses by voice.

[1427] Terminal (smartphone, in-car display, etc.): A device used by the user to input questions and receive answers.

[1428] software

[1429] Natural Language Processing: A technique used to analyze a question and break it down into more specific questions. A concrete example is the Python Natural Language Toolkit (nltk) library.

[1430] Database access: A tool for querying a database and retrieving corresponding information. Examples include SQL databases and NoSQL databases.

[1431] Integration and Refinement: Logic for integrating acquired information and generating the final answer. Programming languages ​​such as Python or Ruby can be used.

[1432] 3. Specific Examples

[1433] For example, let's look at a specific case where a user inputs a question via voice, such as, "Tell me about traffic congestion ahead."

[1434] Example of a prompt

[1435] "Please tell me about the traffic conditions ahead."

[1436] Execution process

[1437] 1. Terminal: The user provides voice input, which the system converts into text data. Alternatively, the user may have already entered the question in text format.

[1438] 2. Server: The server analyzes the received query using natural language processing technology and divides it into "traffic information" and "what's ahead".

[1439] 3. Server: Retrieves real-time data related to "traffic congestion information" from the database, and simultaneously retrieves location information related to "what's ahead".

[1440] 4. Server: Integrates the acquired information and generates a final response (e.g., "There is traffic congestion 5km ahead. The recommended detour is here.").

[1441] 5. Device: Provide this final answer to the user. It will be displayed via voice or on the screen.

[1442] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1443] Step 1:

[1444] Input: The user enters the question via voice or text.

[1445] Operation: In the case of voice input, the device uses the microphone to capture voice data and converts it to text using speech recognition software (e.g., Google Speech Recognition API).

[1446] Output: Sends a question in text format to the server.

[1447] Step 2:

[1448] Input: The server receives the user's query in text format.

[1449] Operation: The server analyzes the question using natural language processing (NLP) techniques. Specifically, it uses Python's Natural Language Toolkit (nltk) and the spaCy API to break down the question into sentences and convert them into more specific, subdivided questions.

[1450] Output: Generates a list of specific questions broken down into segments.

[1451] Step 3:

[1452] Input: A list of specific questions divided into sections.

[1453] Operation: The server queries the database based on each segmented query. It references SQL and NoSQL databases to retrieve corresponding information in real time.

[1454] Output: Generates a list of corresponding information for each question.

[1455] Step 4:

[1456] Input: A list of divided questions and a list of corresponding information.

[1457] Operation: The server integrates the acquired information and generates the final answer using natural language generation (NLG) technology. It constructs the sentence into a natural form using programs such as Python or Ruby.

[1458] Output: Generates the final answer and outputs it in text format.

[1459] Step 5:

[1460] Input: Final response generated by the server.

[1461] Operation: The device displays the response received from the server. If audio output is required, it converts it to speech using a Text-to-Speech (TTS) engine (e.g., Google Text-to-Speech API) and outputs it through the speaker.

[1462] Output: Provides the user with the final answer in text and audio formats.

[1463] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1464] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[1465] Receiving a prompt

[1466] Terminal: The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server.

[1467] Prompt analysis and segmentation

[1468] Server: Upon receiving the prompt, the server first analyzes the question using natural language processing. As part of the analysis, the server divides the question into sentences and, if necessary, converts them into individual, subdivided questions. This generates multiple specific questions.

[1469] Emotion recognition by an emotion engine

[1470] Server: Next, the server uses an emotion engine to recognize emotions from the questions entered by the user. The emotion engine extracts and analyzes emotional information from the user's text. This emotional information includes various emotions such as anger, sadness, and joy.

[1471] Database query

[1472] Server: Based on each generated query, the server queries the database and retrieves the corresponding information. This database is multilingual, and can access a particularly extensive English version of the database to obtain detailed and accurate information. Based on the sentiment information obtained by the sentiment engine, it selects information that is appropriate to the emotion.

[1473] Integration and purification

[1474] Server: Integrates acquired information, segmented questions, and sentiment information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent answer. By adding sentiment information, it provides answers that are easier for users to understand and empathize with.

[1475] Provision to users

[1476] Terminal: The final answers generated by the server are sent to the user's terminal. The terminal displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[1477] Specific example

[1478] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would handle the situation if it detects that the user's question contains feelings of anger.

[1479] 1. Terminal: The user submits the input content.

[1480] 2. Server: The server analyzes the received query and divides it as follows:

[1481] "What is artificial intelligence?"

[1482] "Please tell me about its history as well."

[1483] 3. Server: Analyzes user emotions using an emotion engine:

[1484] The user's question contains feelings of anger.

[1485] 4. Server: Access the English version of the database to retrieve additional information:

[1486] "What is AI?" -> "Artificial Intelligence is the field of study..."

[1487] "Tell me about its history." -> "The history of AI dates back to the mid-20th century ..."

[1488] 5. Server: Integrates the segmented questions, acquired information, and sentiment information to generate the final answer:

[1489] "What is artificial intelligence?"

[1490] "Additional information: Artificial Intelligence is the field of study..."

[1491] "To answer your questions, we will provide you with more detailed information, so please let us know."

[1492] "Please tell me about its history as well."

[1493] "Additional information: The history of AI dates back to the mid-20th century..."

[1494] "If you'd like to delve deeper into history, we also have textbook-style materials available."

[1495] 6. Terminal: Provides the final answer to the user.

[1496] Such a system allows users to obtain detailed and comprehensive information with a single question input, while simultaneously improving the user experience by enabling the system to respond in a way that is sensitive to the user's emotions.

[1497] The following describes the processing flow.

[1498] Step 1: The user enters the question and presses the submit button.

[1499] The user enters a question such as "What is artificial intelligence? Please also tell me about its history." into the input field on their device. Then, they press the send button to submit the question.

[1500] Step 2: The device sends the user's query to the server.

[1501] The terminal sends the user's input to the server. At this time, the entered text data is sent to the server.

[1502] Step 3: The server receives and analyzes the query.

[1503] The server analyzes the received question. First, it uses natural language processing techniques to break down the question into sentences and, if necessary, converts them into individual questions. For example, the question "What is artificial intelligence? Please also tell me about its history." is split into "What is artificial intelligence?" and "Please also tell me about its history."

[1504] Step 4: The server recognizes the user's emotions.

[1505] The server uses an emotion engine to recognize emotions from the user's question. The emotion engine analyzes the text data of the question and detects the user's emotions (e.g., anger, sadness, joy). For example, it might determine that the user's question contains some anger.

[1506] Step 5: The server queries the database with the divided queries.

[1507] Next, the server queries the database based on each of the divided questions and retrieves the corresponding information. For example, in response to "What is artificial intelligence?", it retrieves information such as "Artificial Intelligence is the field of study...", and in response to "Please also tell me about its history," it retrieves information such as "The history of AI dates back to the mid-20th century...".

[1508] Step 6: The server also accesses the English version of the database.

[1509] The server also accesses extensive English-language databases to obtain more detailed information. This allows for the acquisition of more comprehensive and accurate data.

[1510] Step 7: Integrate the information obtained by the server with the original question.

[1511] The server integrates the acquired information, segmented questions, and emotional information to generate the final answer. This process appropriately integrates information corresponding to each question to form a consistent response. Adding emotional information provides answers that are easier for users to understand and empathize with.

[1512] Step 8: The server sends the final response to the terminal.

[1513] The generated final response is sent from the server to the terminal. At this time, the information is transmitted in an integrated form.

[1514] Step 9: The device displays the final answer to the user.

[1515] The device displays the final received answer to the user. The user can instantly see a comprehensive answer to their question. For example, in response to the question, "What is artificial intelligence?", it will display, "Artificial Intelligence is the field of study... Please let us know if you would like more information to answer your question." Also, in response to "Please tell me about its history," it will display, "The history of AI dates back to the mid-20th century... If you would like to delve deeper into its history, we also have textbook-style materials available."

[1516] In this way, users can obtain comprehensive information with a single question input, and receive highly relevant answers that reflect their emotions at the time of input, thus improving the user experience.

[1517] (Example 2)

[1518] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1519] Conventional question-answering systems have a problem in that the process of receiving user-entered questions and providing corresponding answers is not properly handled, making it difficult to obtain satisfactory answers, especially for complex or emotionally charged questions. Furthermore, there was a lack of means to quickly retrieve detailed information from multilingual databases and present it to users in an easily understandable way. In addition, the ability to generate optimal answers that take into account the user's emotions was insufficient.

[1520] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question entered by the user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for integrating sentiment information in addition to the segmented questions and corresponding information to generate a final answer, and means for providing the final answer to the user. As a result, the user can quickly obtain detailed and consistent information, and the system can provide the optimal answer according to the user's sentiment. Furthermore, by using a multilingual database, it becomes possible to provide even richer information.

[1521] A "user" is an individual or group that uses the system.

[1522] "Input" refers to the information or questions that a user provides to the system.

[1523] A "question" is a question that a user asks the system.

[1524] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[1525] "Analysis" is the process by which a system understands the input question and grasps its meaning.

[1526] "Splitting" is the process of converting an input question into multiple specific questions.

[1527] A "database" is a system that organizes and stores information, making it searchable and retrievable as needed.

[1528] A "query" is the process of requesting specific information from a database.

[1529] "Information" refers to the data and knowledge necessary to provide an answer, which are retrieved from a database.

[1530] "Emotional information" refers to data obtained by analyzing and identifying the emotions contained in the user's questions.

[1531] An "answer" is the system's response to a user's question.

[1532] "Integration" is the process of combining multiple pieces of information and data to form a consistent answer as a whole.

[1533] "Multilingual support" refers to the ability to handle and process information written in different languages.

[1534] "Means" refer to the specific methods and techniques used to achieve an objective.

[1535] This invention is a system that receives a question entered by a user, analyzes and segments it, queries a database to generate the optimal answer, and provides it to the user while also considering the user's emotions using an emotion engine. A specific embodiment of the system is described below.

[1536] Receiving a prompt

[1537] The user enters a question into the terminal's input field and presses the submit button. The terminal sends this input to the server. The terminal sends the user's input to the server using the HTTP POST method.

[1538] Prompt analysis and segmentation

[1539] The server analyzes the received questions using natural language processing (NLP) techniques. Specifically, it uses the Python NLTK library to break down the questions into sentences and, if necessary, convert them into individual, subdivided questions. This process involves tokenization, morphological analysis, and grammatical analysis.

[1540] Emotion recognition by an emotion engine

[1541] The server uses an emotion engine to recognize emotions from the user's questions. This emotion engine uses a general emotion analysis system to extract and analyze emotional information from the user's text. Emotional information includes various emotions such as anger, sadness, and joy.

[1542] Database query

[1543] Based on each generated query, the server queries the database using a standard database management system to retrieve the corresponding information. The database is multilingual, and can access extensive databases, particularly in English, to obtain detailed and accurate information.

[1544] Integration and purification

[1545] The server integrates the acquired information, segmented questions, and sentiment information to generate a final answer. Using the Python Pandas library, it appropriately integrates the information corresponding to each question to form a consistent answer.

[1546] Provision to users

[1547] The final answers generated by the server are sent to the user's device. The device displays the received answers to the user. At this time, the divided questions, corresponding additional information, and sentiment-based feedback are displayed together.

[1548] Specific example

[1549] For example, suppose a user enters the question, "What is artificial intelligence? Please also tell me about its history." Furthermore, the following shows how the emotion engine would process the situation if it detected that the user's question contained the emotion of "anger."

[1550] 1. The user submits their input.

[1551] 2. The server analyzes the received query and divides it as follows:

[1552] "What is artificial intelligence?"

[1553] "Please tell me about its history as well."

[1554] 3. The server uses an emotion engine to analyze the user's emotions and recognizes the emotion of "anger."

[1555] 4. The server accesses a multilingual database to retrieve additional information. Example:

[1556] "Artificial Intelligence is the field of study..."

[1557] "The history of AI dates back to the mid-20th century..."

[1558] 5. The server integrates the segmented questions, acquired information, and sentiment information to generate the final answer. Example:

[1559] "What is artificial intelligence?"

[1560] "Artificial Intelligence is the field of study..."

[1561] "If you tell us why you're angry, we can provide you with more detailed information."

[1562] "Please tell me about its history as well."

[1563] "The history of AI dates back to the mid-20th century..."

[1564] "If you'd like to delve deeper into the history, please feel free to contact us."

[1565] 6. The final answer is provided to the user.

[1566] This system allows users to obtain detailed and comprehensive information with a single question input, and the system responds to the user's emotions, thus improving the user experience.

[1567] Example of a prompt

[1568] "What is machine learning? Please explain it in a way that's easy for beginners to understand."

[1569] "How do I install Python?"

[1570] "I'd like to learn about career paths in data science."

[1571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1572] Step 1: Receiving the prompt

[1573] The user enters a question into the terminal's input field and presses the submit button. The terminal sends the input to the server using the HTTP POST method. The input is the text entered by the user, and the output is JSON data sent to the server. The terminal sends the input text to the appropriate API endpoint.

[1574] Step 2: Prompt analysis and splitting

[1575] The server parses the JSON data received from the terminal and extracts the questions. The input is text data containing the questions received from the terminal, and the output is multiple specific questions that have been divided. The server uses Python's NLTK library to divide the questions into sentences and convert each sentence into a separate question. Specifically, the `sent_tokenize` function is used to divide the data into sentences.

[1576] Step 3: Emotion recognition by the emotion engine

[1577] The server extracts sentiment information from each question that has been analyzed and segmented. The input is a list of segmented questions, and the output is data containing the corresponding sentiment information. The server uses a sentiment analysis engine (e.g., a general sentiment analysis system) to identify the sentiment for each question. Specifically, it uses the tone_analyzer.tone method to obtain a sentiment score and adds it to the data.

[1578] Step 4: Query the database

[1579] The server queries the database based on the segmented questions. The input is data containing each question and sentiment information, and the output is the corresponding information retrieved from the database. The server uses a database management system (e.g., a general database management system) to execute the queries and retrieve the necessary information. Specifically, it constructs SQL queries, executes them against the database, and retrieves the results.

[1580] Step 5: Integration and Purification

[1581] The server integrates information retrieved from the database with segmented questions and sentiment information to generate a final answer. The input is data containing segmented questions, retrieved information, and sentiment information, and the output is the final answer provided to the user. The server uses the Python Pandas library to integrate various data and form a consistent answer. Specifically, it uses Pandas' DataFrame functionality to organize and combine data to create a consistently meaningful answer.

[1582] Step 6: Provision to users

[1583] The server sends the final generated response to the user's device. The input is the final response generated by the server, and the output is the text displayed on the user's device. The server sends the final response to the device as an HTTP response, and the device displays the received response in a user-friendly format.

[1584] This specific processing allows users to quickly obtain detailed and consistent information with a single question input. Furthermore, the system provides responses that are sensitive to the user's emotions, improving the user experience.

[1585] (Application Example 2)

[1586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1587] Modern consumers ask a variety of questions in physical stores and expect quick and appropriate answers, but traditional systems struggle to provide sufficient information immediately and respond flexibly to customer emotions. To solve these problems, technology is needed that analyzes user questions and provides optimal answers while considering emotions. In particular, multilingual support and information provision that takes emotions into account are required.

[1588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1589] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question using natural language processing and converting it into multiple segmented questions, means for querying a database based on the segmented questions and obtaining corresponding information, means for adjusting the answer in a way that takes the user's emotions into account using an emotion engine, and means for displaying the final answer on a mobile information terminal used in a physical store. This enables quick and appropriate responses to customer questions in physical stores and the provision of highly satisfying services tailored to the customer's emotions.

[1590] A "user" refers to a person who uses a system or service.

[1591] A "terminal" refers to an electronic device that a user can operate.

[1592] A "question" refers to a question or request that a user enters into the system.

[1593] "Natural language processing" is a technology that analyzes natural language spoken by humans and processes it using computers.

[1594] "Analysis" refers to the process of understanding a given question based on its meaning and structure.

[1595] A "divided question" refers to the original question that has been transformed into multiple specific questions.

[1596] A "database" is a system in which information is systematically stored.

[1597] "Inquiry" refers to the act of accessing a database to retrieve information.

[1598] "Information" refers to answers and data obtained from a database.

[1599] "Integration" refers to the act of bringing together multiple pieces of information in a consistent manner.

[1600] The "final answer" refers to the answer generated based on integrated information.

[1601] An "emotion engine" is a program that analyzes a user's emotions and adjusts the information provided based on those emotions.

[1602] A "multilingual database" is a database that can provide information in multiple languages.

[1603] A "physical store" refers to a store that has a physical presence.

[1604] "Personal information terminals" refer to portable electronic devices such as mobile phones, smartphones, and tablets.

[1605] This invention is a system that receives questions from users in physical stores and provides quick and appropriate answers using natural language processing and an emotion engine. The specific implementation of this system is described below.

[1606] First, this system will be implemented using a portable information terminal such as smart glasses. The terminal is equipped with a microphone that can receive voice input from the user. Once voice input is received, the data is sent to a server.

[1607] The server first uses a speech recognition engine to convert the audio data into text. This transcribed data represents the question in the system, which is then analyzed by natural language processing (NLP). This analysis breaks down the question into multiple specific questions.

[1608] Next, the server uses an emotion engine to determine the user's emotions. This emotion determination extracts emotional information from the user's text and recognizes the emotions behind the question (e.g., joy, anger, sadness, etc.).

[1609] The segmented questions and sentiment information are stored on the server, and queries are then sent to the database based on this information. The database is multilingual and can access a wide range of databases, particularly in English. Therefore, detailed and highly accurate information can be obtained.

[1610] The system integrates acquired information with emotional data to generate a final response that takes emotions into consideration. Because the response is adjusted to reflect the user's emotions, the user experience is improved.

[1611] The final response is sent to the device and displayed on the screen. This allows in-store staff to provide customers with quick and emotionally sensitive answers.

[1612] Hardware and software to use

[1613] Hardware: Portable information devices such as smart glasses equipped with a microphone.

[1614] Software: Speech recognition engine (e.g., speech_recognition library), natural language processing (e.g., transformers library), emotion engine, database access library (e.g., requests library).

[1615] Specific example

[1616] For example, if a customer speaks into the microphone built into the smart glasses and says, "Please tell me how to use this product," the system analyzes and breaks down the question, recognizes the customer's emotions, and provides the most appropriate answer.

[1617] Example of a prompt

[1618] If you are asked about the intended use of the product, please generate your answer using the following method:

[1619] 1. Analyze the question and divide it into individual sentences.

[1620] 2. Determine the emotions contained in the question.

[1621] 3. Query the database based on the question and sentiment to obtain the best answer.

[1622] 4. Integrate the divided questions and answers to generate sentiment-sensitive responses.

[1623] As a specific example, if a question is entered such as "How do I use this product?", we will provide links to detailed user instructions and related videos for that product.

[1624] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1625] Step 1:

[1626] The device receives the user's voice input. The user speaks into the microphone attached to the device, and voice data is collected. The input is the user's question, and the output is voice data.

[1627] Step 2:

[1628] The terminal sends audio data to the server. The audio data is converted to a digital format and transferred to the server. The input is audio data, and the output is the digital audio data sent to the server.

[1629] Step 3:

[1630] The server uses a speech recognition engine to convert the audio data into text. The converted text becomes the question. The input is digital audio data, and the output is converted text data.

[1631] Step 4:

[1632] The server uses a natural language processing engine to analyze the question. Through this analysis, the question is broken down into sentences. The input is text data, and the output is the multiple, divided questions.

[1633] Step 5:

[1634] The server uses an emotion engine to determine the user's emotions from segmented questions. Emotional information is extracted, and emotions such as joy, anger, and sadness are identified. The input is segmented questions, and the output is emotional information.

[1635] Step 6:

[1636] The server queries a database based on segmented questions and sentiment information to retrieve corresponding information. It also accesses multilingual databases to collect detailed and appropriate information. The input is segmented questions and sentiment information, and the output is the retrieved information.

[1637] Step 7:

[1638] The server integrates the acquired information with the segmented questions and sentiment information to generate the final answer. By incorporating sentiment information, the answer is refined to resonate with the user. The input is the acquired information and sentiment information, and the output is the final answer.

[1639] Step 8:

[1640] The server sends the final answer to the terminal. The terminal displays this final answer on its screen. The input is the final answer, and the output is the answer information sent to the terminal.

[1641] Step 9:

[1642] The device displays the response information to the user. The final response is displayed on the device's screen and can be viewed by the user. The input is the submitted response information, and the output is the response displayed on the screen.

[1643] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1644] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1645] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1646] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1647] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1648] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1649] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1650] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1651] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1652] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1653] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1654] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1655] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1656] 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.

[1657] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1658] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1659] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1660] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1661] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1662] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1663] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1664] The following is further disclosed regarding the embodiments described above.

[1665] (Claim 1)

[1666] A means of receiving questions entered by the user,

[1667] A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions,

[1668] A means for querying a database based on the aforementioned divided questions and obtaining corresponding information,

[1669] A means for integrating the divided questions and corresponding information to generate a final answer,

[1670] A means of providing the user with the aforementioned final answer,

[1671] A system that includes this.

[1672] (Claim 2)

[1673] The system according to claim 1, further comprising means for accessing relevant English databases and obtaining more detailed information based on the aforementioned questions.

[1674] (Claim 3)

[1675] The system according to claim 1, further comprising means for appropriately segmenting a question analyzed using the natural language processing described above and progressively subdividing the question.

[1676] "Example 1"

[1677] (Claim 1)

[1678] A means of receiving questions entered by the user,

[1679] A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions,

[1680] A means for querying a data storage device based on the aforementioned divided questions and obtaining corresponding information,

[1681] A means for integrating the divided questions and corresponding information to generate a final answer,

[1682] A means of providing the user with the aforementioned final answer,

[1683] A means of performing tokenization and dependency analysis based on natural language processing to divide the question into sentence units,

[1684] A means of querying an external information provider in response to a generated question and analyzing the acquired information,

[1685] A means of generating consistent answers using a generative model based on acquired information,

[1686] A system that includes this.

[1687] (Claim 2)

[1688] The system according to claim 1, further comprising means for accessing data storage devices in other relevant languages ​​and obtaining more detailed information based on the aforementioned question.

[1689] (Claim 3)

[1690] A means for appropriately segmenting the questions analyzed using the aforementioned natural language processing and progressively subdividing the questions,

[1691] The system according to claim 1, further comprising means for regenerating the optimal answer using the generation model.

[1692] "Application Example 1"

[1693] (Claim 1)

[1694] A means of receiving questions entered by the user,

[1695] A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions,

[1696] A means for querying a database based on the aforementioned divided questions and obtaining corresponding information,

[1697] A means for integrating the divided questions and corresponding information to generate a final answer,

[1698] A means of providing the user with the aforementioned final answer,

[1699] A means for users to input instructions via voice or text, which are then analyzed and broken down into specific questions.

[1700] A means of generating and providing the optimal answer in real time based on the acquired information,

[1701] A system that includes this.

[1702] (Claim 2)

[1703] The system according to claim 1, further comprising means for accessing a number of relevant databases and obtaining more detailed information based on the aforementioned question.

[1704] (Claim 3)

[1705] The system according to claim 1, further comprising means for providing necessary information in real time based on means for appropriately segmenting a question analyzed using the natural language processing described above and progressively subdividing the question.

[1706] "Example 2 of combining an emotion engine"

[1707] (Claim 1)

[1708] A means of receiving questions entered by the user,

[1709] A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions,

[1710] A means for querying a database based on the aforementioned divided questions and obtaining corresponding information,

[1711] A means for integrating emotional information in addition to the information corresponding to the divided questions to generate a final answer,

[1712] A means of providing the user with the aforementioned final answer,

[1713] A system that includes this.

[1714] (Claim 2)

[1715] The system according to claim 1, further comprising means for accessing relevant multilingual databases and obtaining more detailed information based on the aforementioned question.

[1716] (Claim 3)

[1717] The system according to claim 1, further comprising means for appropriately segmenting a question analyzed using the natural language processing described above and progressively subdividing the question.

[1718] (Claim 4)

[1719] The system according to claim 1, further comprising means for extracting and analyzing emotional information from user inquiries.

[1720] "Application example 2 when combining with an emotional engine"

[1721] (Claim 1)

[1722] A means of receiving questions entered by the user,

[1723] A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions,

[1724] A means for querying a database based on the aforementioned divided questions and obtaining corresponding information,

[1725] A means for integrating the divided questions and corresponding information to generate a final answer,

[1726] A means of adjusting the aforementioned response in a way that takes the user's emotions into consideration using an emotion engine,

[1727] A means of providing the user with the aforementioned final answer,

[1728] A system that includes this.

[1729] (Claim 2)

[1730] The system according to claim 1, further comprising means for accessing relevant multilingual databases and obtaining more detailed information based on the aforementioned question.

[1731] (Claim 3)

[1732] The system according to claim 1, further comprising means for appropriately segmenting the questions analyzed using the natural language processing described above and for progressively subdividing the questions.

[1733] (Claim 4)

[1734] The system according to claim 1, further comprising means for displaying the aforementioned final answer on a mobile information terminal used in a physical store. [Explanation of Symbols]

[1735] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving questions entered by the user, A means for analyzing the aforementioned question using natural language processing and converting it into multiple divided questions, A means for querying a database based on the aforementioned divided questions and obtaining corresponding information, A means for integrating the divided questions and corresponding information to generate a final answer, A means of providing the user with the aforementioned final answer, A system that includes this.

2. The system according to claim 1, further comprising means for accessing relevant English databases and obtaining more detailed information based on the aforementioned questions.

3. The system according to claim 1, further comprising means for appropriately segmenting the questions analyzed using the natural language processing described above and for progressively subdividing the questions.

Images