system

Abstract

We provide the system. [Solution] A means for the user to input a question, Means for sending the aforementioned question to the server, The server has means for analyzing the question, The server provides means for generating an answer to the question, The server provides means for sending the response to the user, A system including means for displaying the aforementioned answer to the user.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional question - answering system, in order for a user to obtain an answer to a specific question, it is necessary to spend a lot of time referring to Q&A lists and manuals, resulting in a problem of reduced work efficiency. Especially in a base station construction project, many stakeholders are involved and the question contents are diverse, so this problem is even more prominent.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system having the following features: a means for a user to input a question, a means for sending the question to a server, a means for the server to analyze the question, a means for the server to generate an answer to the question, a means for the server to send the answer to the user, and a means for displaying the answer to the user. Furthermore, by combining a means for analyzing the question using a natural language processing engine and obtaining the answer from a database or dynamically generating it using an AI model, it is possible to provide a fast and accurate answer.

[0006] A "user" is a person who uses the system to input questions and receive answers.

[0007] A "device" is a device used by a user to input questions, and examples include personal computers, smartphones, and tablets.

[0008] A "server" is a centralized computing system that receives questions from users, analyzes them, generates answers, and sends them out.

[0009] A "question" is a request for information that a user inputs into a system and for which the system seeks an answer.

[0010] "Means of transmission" refers to the function of sending user questions and server answers as data packets over the communication network.

[0011] "Means of analysis" refers to the process of understanding a received question and extracting information to derive an appropriate answer.

[0012] "Means of generation" refers to the process of constructing and shaping an appropriate answer based on the analysis results.

[0013] A "natural language processing engine" is software that performs tasks such as syntactic analysis of a question and extraction of keywords to understand the intent of the question.

[0014] A "database" is an aggregation of information where pre-accumulated Q&A information and related materials are stored.

[0015] An "AI model" is a program that dynamically generates an optimal answer to a user's question using artificial intelligence technology.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It 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 Example 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 the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one 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.

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

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

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[0038] The user first enters the question using their device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[0039] The server receives an HTTP request and extracts the question text from the request body. This question text is passed to the server's natural language processing engine for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[0040] Next, the server begins the process of searching the database for appropriate answers based on the extracted keywords and intent. The database contains pre-stored Q&A information and related materials, and the server selects the best answer based on this information. If necessary, it can also dynamically generate answers using an AI model (e.g., GPT-3®).

[0041] The generated response is formatted in a way that is easy for the user to understand. This response includes specific steps, such as "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0042] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[0043] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives and analyzes this question, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to spend time consulting a manual.

[0044] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The user accesses the terminal interface and a question input form is displayed. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button.

[0048] Step 2:

[0049] The device retrieves the question text entered by the user and detects the click event of the submit button. The device then packets the data, including the question text, as an HTTP POST request.

[0050] Step 3:

[0051] The device sends an HTTP POST request to the server. The request includes the question text and user identification information, among other things.

[0052] Step 4:

[0053] The server receives the HTTP request and extracts the question text from the request body. The server then passes this question text to the natural language processing engine.

[0054] Step 5:

[0055] The server's natural language processing engine performs syntactic analysis of the question text and extracts key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[0056] Step 6:

[0057] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[0058] Step 7:

[0059] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the relevant procedures.

[0060] Step 8:

[0061] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[0062] Step 9:

[0063] The server formats the retrieved or generated response into a user-friendly format. For example, it might include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0064] Step 10:

[0065] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[0066] Step 11:

[0067] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[0068] Step 12:

[0069] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[0070] (Example 1)

[0071] 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."

[0072] Conventional question answering systems often lack accuracy and speed in responding to user questions, and are particularly inadequate for handling specialized or complex inquiries. Furthermore, they frequently fail to provide appropriate answers to questions not found in existing FAQ databases, leading to decreased operational efficiency.

[0073] 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.

[0074] In this invention, the server includes means for analyzing a question using a natural language processing engine, means for retrieving an answer from a database or dynamically generating an answer using a generative AI model, and means for formatting the generated answer. This makes it possible to provide a fast and accurate answer to a user's question.

[0075] A "user" is a person or entity that uses this system to input questions and receive answers.

[0076] A "device" is a device used by a user to input and submit questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0077] A "server" is a computer system that receives questions from users, analyzes them, and generates answers.

[0078] A "question" refers to the content of an inquiry that a user sends to the server via their device, and an appropriate answer should be provided to this inquiry.

[0079] A "natural language processing engine" is software that allows a server to analyze the text of a question and perform syntactic analysis and keyword extraction.

[0080] A "database" is a collection of information that a server accesses to search for answers, and it stores Q&A information and related materials.

[0081] A "generative AI model" is an artificial intelligence algorithm used by a server to dynamically generate answers when a suitable answer cannot be found in the database.

[0082] "Formatting" refers to the process of transforming a response generated or retrieved by a server into a format that is easy for the user to understand.

[0083] An "HTTP request" is a data transmission format based on a communication protocol used by a terminal to send query data to a server.

[0084] An "HTTP response" is a data response format based on a communication protocol used by a server to send response data to a terminal.

[0085] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[0086] The user first enters the question using a device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[0087] The server receives an HTTP request and extracts the question text from the request body. This question text is then passed to a natural language processing engine (e.g., SpaCy or NLTK) on the server for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[0088] Next, the server starts the process of searching for appropriate answers from a database (e.g., PostgreSQL, MongoDB) based on the extracted keywords and intent. The database already contains Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using a generative AI model (e.g., GPT-3).

[0089] The generated answers are formatted in a way that is easy for the user to understand. Specifically, detailed answers are provided, including step-by-step explanations. For example, they may include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0090] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[0091] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives this question, analyzes it, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to consult a manual.

[0092] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[0093] Example of a prompt:

[0094] "What are the procedures for installing a new base station?"

[0095] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0096] Step 1:

[0097] The user launches the application or web interface on their device and enters the question "What are the steps for installing a new base station?" into the input form. After entering the question, the user presses the submit button.

[0098] Input: Question: "What are the procedures for installing a new base station?"

[0099] Output: Question data sent as an HTTP request

[0100] Specific actions:

[0101] 1. Open the application or web interface.

[0102] 2. Type "What are the installation procedures for a new base station?"

[0103] 3. Click the Send button.

[0104] 4. The question data is sent to the server as an HTTP request.

[0105] Step 2:

[0106] The server receives the HTTP request and extracts the question text from the request body.

[0107] Input: HTTP Request

[0108] Output: Question text: "What are the installation procedures for a new base station?"

[0109] Specific actions:

[0110] 1. The server receives an HTTP request.

[0111] 2. Extract the question text from the request body.

[0112] Step 3:

[0113] The server passes the question text to a natural language processing engine (e.g., SpaCy or NLTK) for syntactic analysis and keyword extraction.

[0114] Input: Question text: "What are the procedures for installing a new base station?"

[0115] Output: Key keywords "base station" and "installation procedure"

[0116] Specific actions:

[0117] 1. Pass the question text to the natural language processing engine.

[0118] 2. Perform syntactic analysis.

[0119] 3. Extract the main keywords "base station" and "installation procedure".

[0120] Step 4:

[0121] The server searches the database based on the extracted keywords and retrieves relevant information. If a suitable answer does not exist in the database, it dynamically generates an answer using a generative AI model (e.g., GPT-3).

[0122] Input: Main keywords "base station" and "installation procedure"

[0123] Output: Response data "The procedure for installing the new base station is as follows..."

[0124] Specific actions:

[0125] 1. Search the database.

[0126] 2. Obtain relevant Q&A information.

[0127] 3. If a suitable answer is not found in the database, prompts are entered into the generation AI model to dynamically generate an answer.

[0128] Step 5:

[0129] The server formats the generated response into a format that is easy for the user to understand.

[0130] Input: Response data "The procedure for installing a new base station is as follows..."

[0131] Output: Formatted response data

[0132] Specific actions:

[0133] 1. Format the response data.

[0134] 2. Make the format easy for users to understand, for example, by adding step-by-step instructions.

[0135] Step 6:

[0136] The server sends the formatted response to the terminal as an HTTP response.

[0137] Input: Formatted response data

[0138] Output: HTTP response

[0139] Specific actions:

[0140] 1. Convert the formatted response into an HTTP response.

[0141] 2. Send it to the terminal as an HTTP response.

[0142] Step 7:

[0143] The terminal receives an HTTP response and displays the answer in the user interface.

[0144] Input: HTTP response

[0145] Output: The displayed response is "The procedure for installing the new base station is as follows..."

[0146] Specific actions:

[0147] 1. Receive the HTTP response.

[0148] 2. The user interface displays the following: "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0149] (Application Example 1)

[0150] 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."

[0151] Existing virtual stores have limited means for users to instantly obtain product information, and there are challenges in obtaining quick and accurate responses, especially when interacting with smart glasses. As a result, the user experience deteriorates, and the decision to purchase products takes longer.

[0152] 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.

[0153] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, means for interacting with the user using smart glasses, means for transmitting the question obtained using the smart glasses to the server, and means for displaying the answer on the display of the smart glasses. This makes it possible for a user to easily ask questions about products in a virtual store through smart glasses and to obtain quick and appropriate answers.

[0154] "Means for users to input questions" refers to providing an interface for users to input questions using a device.

[0155] "Means for sending the aforementioned question to the server" refers to a mechanism for sending a question entered by a user to a server via a network.

[0156] "Means by which the server analyzes the question" refers to a process in which the server analyzes the received question using natural language processing technology and extracts key keywords and the user's intent.

[0157] "Means by which the server generates an answer to the question" refers to a function that uses a database or AI model to generate an appropriate answer based on the analyzed question.

[0158] "Means by which the server transmits the response to the user" refers to a mechanism for transmitting the generated response to the user's terminal via the network.

[0159] "Means for displaying the aforementioned answer to the user" refers to an interface for displaying the answer on the user's device.

[0160] "A means of interacting with users using smart glasses" refers to a system that uses smart glasses to receive input from users and display responses.

[0161] "Means for transmitting questions obtained using the smart glasses to the server" refers to a mechanism for transmitting information acquired through the smart glasses to a server via a network.

[0162] "Means for displaying the answer on the display of the smart glasses" refers to a function that uses the visual display device of the smart glasses to display the acquired answer to the user.

[0163] This invention is a system that enables user interaction within a virtual store using smart glasses. A specific embodiment of this system is described below.

[0164] Program generation and processing explanation

[0165] Smart glasses application

[0166] The application installed on the smart glasses provides an interface for users to input questions using voice input or touch gestures. Once the user inputs a question, it is sent to a server via the smart glasses' network.

[0167] Server-based question analysis and answer generation.

[0168] The server utilizes a natural language processing engine (such as NLTK or Transformers) to analyze the received question. Once the question analysis is complete, the server uses a database and a generative AI model (e.g., GPT-3) to generate an appropriate answer. This answer is then formatted in a way that is easy for the user to understand.

[0169] Display the answer

[0170] The generated answers are then sent back to the smart glasses via the network and displayed on the smart glasses' screen. This entire process allows users to easily ask questions about products in a virtual store and receive quick answers.

[0171] Hardware and software to be used

[0172] Hardware: Smart glasses (e.g., Google® Glass® or Microsoft® HoloLens®)

[0173] Software: Natural language processing libraries (e.g., NLTK, Transformers), HTTP communication libraries (requests)

[0174] Specific example

[0175] As a concrete example, suppose a user walks through a virtual store and asks, "What can this product be used for?" through smart glasses. This question is sent to a server and analyzed by a natural language processing engine. Based on the analysis, the server generates an appropriate answer from its database, for example, "This product is used as camping equipment for outdoor activities," and sends it back to the smart glasses. The smart glasses display this answer on their screen, allowing the user to receive the response in real time.

[0176] Example of a prompt

[0177] The following are specific examples of prompt statements:

[0178] "What can this product be used for?"

[0179] "What is the warranty period for this product?"

[0180] "Please tell me about current sales."

[0181] In this way, smooth data communication and natural language processing between smart glasses and servers enable users to obtain information quickly and accurately.

[0182] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0183] Step 1:

[0184] The user enters a question using the voice input function or touch gestures of the smart glasses. The entered question is converted into text format by an application within the smart glasses. The input is voice data or gesture action, and the output is text data.

[0185] Step 2:

[0186] The smart glasses send the question, converted as text data, to a server over the network. This transmission is done using an HTTP request. The input is the converted text data, and the output is the HTTP request.

[0187] Step 3:

[0188] The server receives an HTTP request and extracts the question text from the request body. The input is the HTTP request, and the output is the extracted question text.

[0189] Step 4:

[0190] The server passes the extracted question text to a natural language processing engine (e.g., NLTK, Transformers) for analysis. The analysis process extracts key keywords and user intent. The input is the question text, and the output is the analysis result.

[0191] Step 5:

[0192] The server searches the database for appropriate answers based on the analyzed keywords and intent. Alternatively, it dynamically generates answers using a generative AI model (e.g., GPT-3) as needed. The input is the analysis result, and the output is the generated answer.

[0193] Step 6:

[0194] The generated responses are formatted into a user-friendly format and prepared as the final responses. The input is the generated response data, and the output is the formatted response data.

[0195] Step 7:

[0196] The server sends the formatted response data to the smart glasses as an HTTP response. The input is the formatted response data, and the output is the HTTP response.

[0197] Step 8:

[0198] The smart glasses retrieve response data from the received HTTP response and display it on the screen. The user confirms the response through this display. The input is the HTTP response, and the output is the response displayed on the screen.

[0199] Through these steps, users can engage in real-time question and answer exchanges via smart glasses.

[0200] 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.

[0201] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. The purpose of this system is to improve the user's work efficiency.

[0202] The user first accesses the terminal interface and displays a question input form. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button. This question submission action triggers the terminal to send data containing the question text to the server as an HTTP POST request.

[0203] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing engine for analysis. The natural language processing engine performs syntactic and contextual analysis of the question and extracts key keywords (e.g., "base station," "installation procedure").

[0204] Next, the server searches the Q&A database based on the extracted keywords and retrieves the most suitable answer. If a suitable answer does not exist in the database, an AI model (e.g., GPT-3) is used to dynamically generate an answer. The answer generated in this answer generation process is then formatted in a way that is easy for the user to understand.

[0205] One feature of this invention is the incorporation of an emotion engine. The server analyzes the user's emotional state using the question text and emotional signals from the user's input (e.g., voice tone and facial recognition data). Based on the results of this emotion analysis, the server adjusts the tone and content of the response.

[0206] For example, if a user enters "I'm having trouble figuring out the procedure for installing a new base station," the emotion engine will recognize the user's confusion and stress, and generate a response that takes those emotions into consideration. Specifically, it might generate a response like, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0207] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the system to provide customized responses for each user, contributing to an improved user experience.

[0208] Overall, this system not only speeds up question-answering but also enables more humane responses that respond to user emotions. This is expected to lead to higher satisfaction and improved work efficiency. Its effects are particularly pronounced in large-scale projects involving many stakeholders. The present invention aims to improve user work efficiency and satisfaction by providing such a system.

[0209] The following describes the processing flow.

[0210] Step 1:

[0211] The user accesses the terminal interface and displays a question input form. The user enters the question, "I'm having trouble figuring out the procedure for setting up the new base station," and clicks the submit button.

[0212] Step 2:

[0213] The terminal acquires the question text entered by the user, along with emotional data such as voice signals and facial recognition data as needed, and detects the click event of the submit button. The terminal packets the data, including the question text and emotional data, as an HTTP POST request.

[0214] Step 3:

[0215] The device sends an HTTP POST request to the server. The request includes the question text and user sentiment data.

[0216] Step 4:

[0217] The server receives an HTTP request and extracts the question text and sentiment data from the request body. The server then passes this question text to a natural language processing engine for analysis of the question content.

[0218] Step 5:

[0219] The server's natural language processing engine performs syntactic and contextual analysis of the question text, extracting key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[0220] Step 6:

[0221] The server's emotion engine analyzes the user's emotions based on audio signals and facial recognition data sent by the user. From this analysis, it identifies the user's emotional state, such as being confused or stressed.

[0222] Step 7:

[0223] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[0224] Step 8:

[0225] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the procedure.

[0226] Step 9:

[0227] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[0228] Step 10:

[0229] The server formats the generated or retrieved responses into a format that is easy for the user to understand. In this process, it adjusts the tone and content of the responses based on the results of the sentiment engine's analysis. For example, it might generate a response that includes specific steps such as, "The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0230] Step 11:

[0231] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[0232] Step 12:

[0233] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[0234] Step 13:

[0235] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[0236] Step 14:

[0237] The server records the user's emotional data analyzed by the emotion engine and uses it to improve future question responses. Based on this recorded data, the system can provide customized responses for each user.

[0238] (Example 2)

[0239] 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".

[0240] Traditional question-answering systems often fail to provide a satisfactory user experience because they generate answers without considering the user's emotional state. Furthermore, they lack the ability to dynamically generate appropriate answers when a suitable response does not exist in the database. Therefore, there are limitations to improving user work efficiency. The above problems need to be addressed.

[0241] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0242] In this invention, the server includes means for the user to input a question, means for the user to send the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to send the answer to the user, means for the server to display the answer to the user, means for the server to analyze the user's emotions, means for adjusting the tone and content of the answer based on the results of the emotion analysis, and means for recording the user's emotional state to help with future responses. This makes it possible to provide more humane answers that take the user's emotions into consideration, thereby improving user satisfaction and work efficiency.

[0243] A "user" is the entity that accesses the system, enters a question, and receives an answer.

[0244] A "server" is a computer system that analyzes questions submitted by users, generates answers, and sends them back.

[0245] "Means for entering questions" refers to the interface through which users input questions into a system. Specifically, this includes web forms and input fields in applications.

[0246] "Means of sending questions" refers to the communication protocol or function used to send questions entered by the user to a server. Generally, HTTP POST requests are used.

[0247] "Means for analyzing questions" refers to the technology used by a server to understand and analyze the questions it receives. Specifically, this includes natural language processing engines.

[0248] "Means of generating answers" refers to the process by which a server creates answers to questions. This includes Q&A databases and generative AI models.

[0249] "Means for sending responses" refers to the communication protocols and functions used by the server to send responses generated by the server to the user.

[0250] "Means of displaying responses" refers to an interface that allows users to view submitted responses. Specifically, this includes the display section of a web page or application.

[0251] "Means of analyzing emotions" refer to technologies that allow a server to identify and analyze a user's emotional state. Examples include voice tone analysis and facial expression recognition.

[0252] "Means of adjusting responses based on sentiment analysis results" refers to a function that refers to the results of sentiment analysis and generates responses with a tone and content that matches the user's emotions.

[0253] "Means for recording emotional states" refer to databases or storage devices that record user emotional data and use it to inform future responses.

[0254] This invention relates to a system in which a user inputs a question using a terminal, a server analyzes the question to generate an appropriate answer, and further recognizes the user's emotions and responds accordingly. Specific embodiments of this system will be described below.

[0255] The user first accesses the system interface from a device (e.g., a PC or smartphone). The interface displays a question input form, into which the user enters a question. For example, the user might enter the question, "What are the installation procedures for a new base station?" and click the submit button. The user's action of entering and submitting the question triggers the device to send data containing the question text to the server as an HTTP POST request.

[0256] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing (NLP) engine for analysis. The NLP engine (e.g., spaCy or NLTK) performs syntactic and contextual analysis of the question. It extracts key keywords (e.g., "base station," "installation procedure").

[0257] Next, the server searches the Q&A database based on the extracted keywords. If a suitable answer is found, it retrieves that answer. If a suitable answer does not exist in the database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI®'s GPT-3). In this case, the text "What are the installation procedures for a new base station?" is input to the AI ​​model as a prompt.

[0258] One feature of this invention is the incorporation of emotion analysis functionality. The server passes the received question text and the emotion signals from the user's input (e.g., voice tone and facial expression recognition data) to the emotion engine for analysis. In this embodiment, an emotion analysis API can be used as the emotion engine.

[0259] Based on the sentiment analysis results, the server adjusts the tone and content of its response. For example, if a user inputs "I'm having trouble understanding the procedure for installing a new base station," the sentiment engine recognizes the user's confusion and stress, and the server generates a response that takes those emotions into consideration. Specifically, it might generate a response such as, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0260] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the server to provide customized responses for each user, contributing to an improved user experience.

[0261] This system not only speeds up question-answering but also enables more personalized responses that respond to user emotions. This feature is expected to lead to higher satisfaction and improved work efficiency. Its effectiveness is particularly evident in large-scale projects involving numerous stakeholders.

[0262] The present invention aims to improve user work efficiency and satisfaction by providing the system described above.

[0263] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0264] Step 1:

[0265] The user accesses the system and enters a question into the question input form. For example, the user enters "What are the installation procedures for a new base station?" and clicks the submit button. The input data is the text entered by the user, and the output is an HTTP POST request containing that text.

[0266] Step 2:

[0267] The terminal retrieves the question text entered by the user and sends it to the server as an HTTP POST request. The input data is the question text entered by the user, and the output is an HTTP POST request containing that text. Specifically, the terminal generates a request containing data in JSON format as follows:

[0268] json

[0269] {

[0270] "Question": "What are the procedures for installing a new base station?"

[0271] }

[0272] Step 3:

[0273] The server parses the received HTTP request and extracts the question text from the request body. The input data is the HTTP request, and the output is the extracted question text. The server obtains text data like the following:

[0274] "What are the procedures for installing a new base station?"

[0275] Step 4:

[0276] The server passes the extracted question text to a natural language processing engine for analysis. The input data is the question text, and the output is the main keywords of the analysis results (e.g., "base station," "installation procedure"). The natural language processing engine (e.g., spaCy) obtains the following analysis results:

[0277] Keyword 1: Base station

[0278] Keyword 2: Installation procedure

[0279] Step 5:

[0280] The server searches the Q&A database based on the main keywords to find an answer. The input data is the main keywords, and the output is the appropriate answer. For example, the following answer corresponding to "Installation procedure of a new base station" is found in the database:

[0281] "The installation procedure of a new base station is as follows. 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation confirmation"

[0282] Step 6:

[0283] If no appropriate answer is found in the Q&A database, the server uses a generative AI model (e.g., GPT-3 of OpenAI) to dynamically generate an answer. The input data is the main keywords, and the output is the generated answer. The server inputs the following prompt text into the AI model to generate an answer:

[0284] "What is the installation procedure of a new base station?"

[0285] The generative AI model outputs the following answer:

[0286] "The installation procedure of a new base station is as follows. 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation confirmation"

[0287] Step 7:

[0288] The server uses the question text and the emotion signal at the time of the user's input to pass to the emotion engine for analysis. The input data is the question text and the emotion signal (voice tone and facial expression data), and the output is the emotion analysis result. The emotion engine analyzes the user's emotional state (e.g., confusion, stress).

[0289] Step 8:

[0290] The server adjusts the tone and content of the response based on the sentiment analysis results. The input data consists of the sentiment analysis results and the generated response, while the output is the adjusted response. For example, if the user is confused, the response will be reshaped to a gentler tone, as follows:

[0291] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0292] Step 9:

[0293] The server sends the formatted response to the terminal as an HTTP response. The input data is the formatted response, and the output is the HTTP response. Specifically, the server returns data in JSON format as follows:

[0294] json

[0295] {

[0296] "Answer": "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check"

[0297] }

[0298] Step 10:

[0299] The terminal displays the received response to the user. The input data is an HTTP response from the server, and the output is a text display that the user can view. Specifically, the terminal displays the following response in the display area of ​​a web page or application:

[0300] "Thank you for your question. The installation procedure for the new base station is as follows. Please follow the procedure with confidence: 1. Selection of land, 2. Arrangement of equipment, 3. Confirmation of power supply, 4. Installation work, 5. Operation check."

[0301] Through the above process, this system can respond to the user's question and provide a more considerate answer.

[0302] (Application Example 2)

[0303] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0304] In an autonomous vehicle, when a passenger asks a question about system trouble or operation method during operation, there is a problem that the person in charge is absent and it cannot be solved immediately, increasing the passenger's anxiety and confusion. Also, since no response considering the passenger's emotional state is made, it is also a problem that the user experience deteriorates.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0306] In this invention, the server includes means for the user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, emotional analysis means for recognizing the user's emotion, and means for adjusting the tone and content of the answer based on the emotion analyzed by the emotional analysis means. Thereby, when a passenger in an autonomous vehicle asks a question, it becomes possible to quickly provide appropriate feedback according to the emotional state.

[0307] A "user" refers to a person who uses this system.

[0308] "Means for entering questions" refers to an interface device that allows users to enter questions via text or voice.

[0309] A "server" is a computer system that has the computing resources to receive user questions, analyze them, and generate answers.

[0310] "Means for analyzing questions" refers to software or hardware used to analyze questions received from users using natural language processing techniques.

[0311] "Means for generating answers to questions" refers to devices or software that analyze the content of a question and dynamically generate the corresponding answer by obtaining it from a database or using a generation AI model.

[0312] "Means for sending responses to users" refers to an interface device for sending generated responses to a user's terminal via a network.

[0313] "Means of displaying the answer to the user" refers to a display device or audio output device for visually or audibly displaying the answer on the user's terminal.

[0314] "Emotion analysis means" refers to software or hardware used to analyze a user's emotions from input audio or image data.

[0315] "Means of adjusting the tone and content of responses" refers to software or hardware that appropriately modifies the content and expression of responses based on analyzed emotions.

[0316] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. This system is particularly intended for passenger support in autonomous vehicles, aiming to provide rapid and emotion-responsive feedback to passengers' questions.

[0317] Users input questions using interface devices such as touchscreen panels, smart glasses, or head-mounted displays within the autonomous vehicle. Users input questions via text or voice, and this input data is sent to the server. For example, if a user inputs the question, "How do I change my destination?", the question, along with the user's voice data and facial image data, will be sent to the server.

[0318] The server first uses a natural language processing engine (e.g., GPT-3) to analyze the question. Syntactic and contextual analysis of the question is performed, and key keywords are extracted. Next, based on the extracted keywords, an appropriate answer is generated using a Q&A database or a generative AI model. At this time, the question is entered as a prompt in a specific format, "The user is feeling {emotion}. {question}", so it is possible to generate an answer that reflects the user's emotion.

[0319] Emotion analysis methods include emotion recognition through voice analysis and emotion recognition through facial image analysis. The system analyzes the user's voice tone and facial expressions, and identifies the user's emotions based on the results. For example, if the user is confused, the server will recognize the emotion as "Confused."

[0320] Based on the analyzed emotions, the tone and content of the response are adjusted. For example, if the system detects that the user is confused, the generated response will be in the format of, "Please proceed with confidence. To change your destination, open the navigation menu, select 'Change Destination,' and enter the new address."

[0321] The generated responses are sent to the user's device and displayed on a touchscreen panel or smart glasses. They may also be played back via audio output. This allows for the rapid provision of appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[0322] For example, if a passenger asks in a confused tone, "How do I change my destination?" while the vehicle is in motion, the server will query the AI ​​model with the following prompt:

[0323] The user is feeling confused. How do I change the destination while the car is driving?

[0324] In response to this, the AI ​​model outputs a response that takes emotions into consideration, such as, "To change your destination, select the 'Change Destination' option from the navigation menu and enter the new address."

[0325] As described above, the present invention not only speeds up question-answering but also enables a more humane response that responds to the user's emotions. This is expected to lead to higher satisfaction and improved service.

[0326] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0327] Step 1:

[0328] The user enters a question.

[0329] Specific operation: The user inputs a question via text or voice using a touchscreen panel, smart glasses, or head-mounted display within the autonomous vehicle. For example, the user might text or voice ask, "How do I change my destination?" Input and output: The input is the user's text or voice question data, and the output is the preparation of that question data for transmission.

[0330] Step 2:

[0331] The terminal sends the question to the server.

[0332] Specific operation: The terminal sends the entered question data to the server in the form of an HTTP POST request. Input and output: The input is the user's question data, and the output is the HTTP request to the server.

[0333] Step 3:

[0334] The server analyzes the question.

[0335] Specific operation: The server extracts question data from the received HTTP request and passes it to the natural language processing engine. The natural language processing engine parses this question data syntactically and contextually, and extracts key keywords (e.g., "destination," "change"). Input and output: The input is the question data, and the output is the parsed keywords.

[0336] Step 4:

[0337] The server analyzes emotions.

[0338] Specific operation: The server passes the user's voice data and facial image data to the emotion analysis engine, which analyzes the user's emotional state. The results of the voice analysis and facial image analysis are integrated to make a final emotion determination. Input and output: The input is voice data and facial image data, and the output is the determination result of the user's emotional state.

[0339] Step 5:

[0340] The server generates the answer.

[0341] Specific operation: The server uses the analyzed keywords and the user's emotional state to create a prompt for the generative AI model. For example, it generates the prompt "The user is feeling confused. How do I change the destination while the car is driving?" and passes it to the generative AI model (e.g., GPT-3). The generative AI model returns an appropriate answer, which is then formatted. Input and output: The input is keywords and emotional state, and the output is the generated answer.

[0342] Step 6:

[0343] The server sends the answer to the user.

[0344] Specific operation: The server sends the formatted response to the user's terminal as an HTTP response. Input and output: The input is the generated response text, and the output is the HTTP response to the user.

[0345] Step 7:

[0346] The device displays the answer to the user.

[0347] Specific operation: The terminal visually displays the received response on a touchscreen panel or smart glasses. It also plays the response aloud using an audio output device as needed. Input and output: The input is the response data from the server, and the output is the response displayed to the user.

[0348] This makes it possible to quickly provide appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[0349] 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.

[0350] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0351] 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.

[0352] [Second Embodiment]

[0353] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0354] 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.

[0355] 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).

[0356] 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.

[0357] 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.

[0358] 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).

[0359] 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.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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".

[0365] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[0366] The user first enters the question using their device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[0367] The server receives an HTTP request and extracts the question text from the request body. This question text is passed to the server's natural language processing engine for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[0368] Next, the server begins the process of searching the database for appropriate answers based on the extracted keywords and intent. The database contains pre-stored Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using an AI model (e.g., GPT-3).

[0369] The generated response is formatted in a way that is easy for the user to understand. This response includes specific steps, such as "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0370] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[0371] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives and analyzes this question, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to spend time consulting a manual.

[0372] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[0373] The following describes the processing flow.

[0374] Step 1:

[0375] The user accesses the terminal interface and a question input form is displayed. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button.

[0376] Step 2:

[0377] The device retrieves the question text entered by the user and detects the click event of the submit button. The device then packets the data, including the question text, as an HTTP POST request.

[0378] Step 3:

[0379] The device sends an HTTP POST request to the server. The request includes the question text and user identification information, among other things.

[0380] Step 4:

[0381] The server receives the HTTP request and extracts the question text from the request body. The server then passes this question text to the natural language processing engine.

[0382] Step 5:

[0383] The server's natural language processing engine performs syntactic analysis of the question text and extracts key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[0384] Step 6:

[0385] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[0386] Step 7:

[0387] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the relevant procedures.

[0388] Step 8:

[0389] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[0390] Step 9:

[0391] The server formats the retrieved or generated response into a user-friendly format. For example, it might include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0392] Step 10:

[0393] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[0394] Step 11:

[0395] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[0396] Step 12:

[0397] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[0398] (Example 1)

[0399] 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."

[0400] Conventional question answering systems often lack accuracy and speed in responding to user questions, and are particularly inadequate for handling specialized or complex inquiries. Furthermore, they frequently fail to provide appropriate answers to questions not found in existing FAQ databases, leading to decreased operational efficiency.

[0401] 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.

[0402] In this invention, the server includes means for analyzing a question using a natural language processing engine, means for retrieving an answer from a database or dynamically generating an answer using a generative AI model, and means for formatting the generated answer. This makes it possible to provide a fast and accurate answer to a user's question.

[0403] A "user" is a person or entity that uses this system to input questions and receive answers.

[0404] A "device" is a device used by a user to input and submit questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0405] A "server" is a computer system that receives questions from users, analyzes them, and generates answers.

[0406] A "question" refers to the content of an inquiry that a user sends to the server via their device, and an appropriate answer should be provided to this inquiry.

[0407] A "natural language processing engine" is software that allows a server to analyze the text of a question and perform syntactic analysis and keyword extraction.

[0408] A "database" is a collection of information that a server accesses to search for answers, and it stores Q&A information and related materials.

[0409] A "generative AI model" is an artificial intelligence algorithm used by a server to dynamically generate answers when a suitable answer cannot be found in the database.

[0410] "Formatting" refers to the process of transforming a response generated or retrieved by a server into a format that is easy for the user to understand.

[0411] An "HTTP request" is a data transmission format based on a communication protocol used by a terminal to send query data to a server.

[0412] An "HTTP response" is a data response format based on a communication protocol used by a server to send response data to a terminal.

[0413] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[0414] The user first enters the question using a device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[0415] The server receives an HTTP request and extracts the question text from the request body. This question text is then passed to a natural language processing engine (e.g., SpaCy or NLTK) on the server for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[0416] Next, the server starts the process of searching for appropriate answers from a database (e.g., PostgreSQL, MongoDB) based on the extracted keywords and intent. The database already contains Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using a generative AI model (e.g., GPT-3).

[0417] The generated answers are formatted in a way that is easy for the user to understand. Specifically, detailed answers are provided, including step-by-step explanations. For example, they may include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0418] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[0419] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives this question, analyzes it, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to consult a manual.

[0420] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[0421] Example of a prompt:

[0422] "What are the procedures for installing a new base station?"

[0423] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0424] Step 1:

[0425] The user launches the application or web interface on their device and enters the question "What are the steps for installing a new base station?" into the input form. After entering the question, the user presses the submit button.

[0426] Input: Question: "What are the procedures for installing a new base station?"

[0427] Output: Question data sent as an HTTP request

[0428] Specific actions:

[0429] 1. Open the application or web interface.

[0430] 2. Type "What are the installation procedures for a new base station?"

[0431] 3. Click the Send button.

[0432] 4. The question data is sent to the server as an HTTP request.

[0433] Step 2:

[0434] The server receives the HTTP request and extracts the question text from the request body.

[0435] Input: HTTP Request

[0436] Output: Question text: "What are the installation procedures for a new base station?"

[0437] Specific actions:

[0438] 1. The server receives an HTTP request.

[0439] 2. Extract the question text from the request body.

[0440] Step 3:

[0441] The server passes the question text to a natural language processing engine (e.g., SpaCy or NLTK) for syntactic analysis and keyword extraction.

[0442] Input: Question text: "What are the procedures for installing a new base station?"

[0443] Output: Key keywords "base station" and "installation procedure"

[0444] Specific actions:

[0445] 1. Pass the question text to the natural language processing engine.

[0446] 2. Perform syntactic analysis.

[0447] 3. Extract the main keywords "base station" and "installation procedure".

[0448] Step 4:

[0449] The server searches the database based on the extracted keywords and retrieves relevant information. If a suitable answer does not exist in the database, it dynamically generates an answer using a generative AI model (e.g., GPT-3).

[0450] Input: Main keywords "base station" and "installation procedure"

[0451] Output: Response data "The procedure for installing the new base station is as follows..."

[0452] Specific actions:

[0453] 1. Search the database.

[0454] 2. Obtain relevant Q&A information.

[0455] 3. If a suitable answer is not found in the database, prompts are entered into the generation AI model to dynamically generate an answer.

[0456] Step 5:

[0457] The server formats the generated response into a format that is easy for the user to understand.

[0458] Input: Response data "The procedure for installing a new base station is as follows..."

[0459] Output: Formatted response data

[0460] Specific actions:

[0461] 1. Format the response data.

[0462] 2. Make the format easy for users to understand, for example, by adding step-by-step instructions.

[0463] Step 6:

[0464] The server sends the formatted response to the terminal as an HTTP response.

[0465] Input: Formatted response data

[0466] Output: HTTP response

[0467] Specific actions:

[0468] 1. Convert the formatted response into an HTTP response.

[0469] 2. Send it to the terminal as an HTTP response.

[0470] Step 7:

[0471] The terminal receives an HTTP response and displays the answer in the user interface.

[0472] Input: HTTP response

[0473] Output: The displayed response is "The procedure for installing the new base station is as follows..."

[0474] Specific actions:

[0475] 1. Receive the HTTP response.

[0476] 2. The user interface displays the following: "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0477] (Application Example 1)

[0478] 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."

[0479] Existing virtual stores have limited means for users to instantly obtain product information, and there are challenges in obtaining quick and accurate responses, especially when interacting with smart glasses. As a result, the user experience deteriorates, and the decision to purchase products takes longer.

[0480] 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.

[0481] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, means for interacting with the user using smart glasses, means for transmitting the question obtained using the smart glasses to the server, and means for displaying the answer on the display of the smart glasses. This makes it possible for a user to easily ask questions about products in a virtual store through smart glasses and to obtain quick and appropriate answers.

[0482] "Means for users to input questions" refers to providing an interface for users to input questions using a device.

[0483] "Means for sending the aforementioned question to the server" refers to a mechanism for sending a question entered by a user to a server via a network.

[0484] "Means by which the server analyzes the question" refers to a process in which the server analyzes the received question using natural language processing technology and extracts key keywords and the user's intent.

[0485] "Means by which the server generates an answer to the question" refers to a function that uses a database or AI model to generate an appropriate answer based on the analyzed question.

[0486] "Means by which the server transmits the response to the user" refers to a mechanism for transmitting the generated response to the user's terminal via the network.

[0487] "Means for displaying the aforementioned answer to the user" refers to an interface for displaying the answer on the user's device.

[0488] "A means of interacting with users using smart glasses" refers to a system that uses smart glasses to receive input from users and display responses.

[0489] "Means for transmitting questions obtained using the smart glasses to the server" refers to a mechanism for transmitting information acquired through the smart glasses to a server via a network.

[0490] "Means for displaying the answer on the display of the smart glasses" refers to a function that uses the visual display device of the smart glasses to display the acquired answer to the user.

[0491] This invention is a system that enables user interaction within a virtual store using smart glasses. A specific embodiment of this system is described below.

[0492] Program generation and processing explanation

[0493] Smart glasses application

[0494] The application installed on the smart glasses provides an interface for users to input questions using voice input or touch gestures. Once the user inputs a question, it is sent to a server via the smart glasses' network.

[0495] Server-based question analysis and answer generation.

[0496] The server utilizes a natural language processing engine (such as NLTK or Transformers) to analyze the received question. Once the question analysis is complete, the server uses a database and a generative AI model (e.g., GPT-3) to generate an appropriate answer. This answer is then formatted in a way that is easy for the user to understand.

[0497] Display the answer

[0498] The generated answers are then sent back to the smart glasses via the network and displayed on the smart glasses' screen. This entire process allows users to easily ask questions about products in a virtual store and receive quick answers.

[0499] Hardware and software to be used

[0500] Hardware: Smart glasses (e.g., Google Glass or Microsoft HoloLens)

[0501] Software: Natural language processing libraries (e.g., NLTK, Transformers), HTTP communication libraries (requests)

[0502] Specific example

[0503] As a concrete example, suppose a user walks through a virtual store and asks, "What can this product be used for?" through smart glasses. This question is sent to a server and analyzed by a natural language processing engine. Based on the analysis, the server generates an appropriate answer from its database, for example, "This product is used as camping equipment for outdoor activities," and sends it back to the smart glasses. The smart glasses display this answer on their screen, allowing the user to receive the response in real time.

[0504] Example of a prompt

[0505] The following are examples of prompt statements:

[0506] "What can this product be used for?"

[0507] "What is the warranty period for this product?"

[0508] "Please tell me about current sales."

[0509] In this way, smooth data communication and natural language processing between smart glasses and servers enable users to obtain information quickly and accurately.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The user enters a question using the voice input function or touch gestures of the smart glasses. The entered question is converted into text format by an application within the smart glasses. The input is voice data or gesture action, and the output is text data.

[0513] Step 2:

[0514] The smart glasses send the question, converted as text data, to a server over the network. This transmission is done using an HTTP request. The input is the converted text data, and the output is the HTTP request.

[0515] Step 3:

[0516] The server receives an HTTP request and extracts the question text from the request body. The input is the HTTP request, and the output is the extracted question text.

[0517] Step 4:

[0518] The server passes the extracted question text to a natural language processing engine (e.g., NLTK, Transformers) for analysis. The analysis process extracts key keywords and user intent. The input is the question text, and the output is the analysis result.

[0519] Step 5:

[0520] The server searches the database for appropriate answers based on the analyzed keywords and intent. Alternatively, it dynamically generates answers using a generative AI model (e.g., GPT-3) as needed. The input is the analysis result, and the output is the generated answer.

[0521] Step 6:

[0522] The generated responses are formatted into a user-friendly format and prepared as the final responses. The input is the generated response data, and the output is the formatted response data.

[0523] Step 7:

[0524] The server sends the formatted response data to the smart glasses as an HTTP response. The input is the formatted response data, and the output is the HTTP response.

[0525] Step 8:

[0526] The smart glasses retrieve response data from the received HTTP response and display it on the screen. The user confirms the response through this display. The input is the HTTP response, and the output is the response displayed on the screen.

[0527] Through these steps, users can engage in real-time question and answer exchanges via smart glasses.

[0528] 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.

[0529] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. The purpose of this system is to improve the user's work efficiency.

[0530] The user first accesses the terminal interface and displays a question input form. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button. This question submission action triggers the terminal to send data containing the question text to the server as an HTTP POST request.

[0531] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing engine for analysis. The natural language processing engine performs syntactic and contextual analysis of the question and extracts key keywords (e.g., "base station," "installation procedure").

[0532] Next, the server searches the Q&A database based on the extracted keywords and retrieves the most suitable answer. If a suitable answer does not exist in the database, an AI model (e.g., GPT-3) is used to dynamically generate an answer. The answer generated in this answer generation process is then formatted in a way that is easy for the user to understand.

[0533] One feature of this invention is the incorporation of an emotion engine. The server analyzes the user's emotional state using the question text and emotional signals from the user's input (e.g., voice tone and facial expression recognition data). Based on the results of this emotion analysis, the server adjusts the tone and content of the response.

[0534] For example, if a user enters "I'm having trouble figuring out the procedure for installing a new base station," the emotion engine will recognize the user's confusion and stress, and generate a response that takes those emotions into consideration. Specifically, it might generate a response like, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0535] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the system to provide customized responses for each user, contributing to an improved user experience.

[0536] Overall, this system not only speeds up question-answering but also enables more humane responses that respond to user emotions. This is expected to lead to higher satisfaction and improved work efficiency. Its effects are particularly pronounced in large-scale projects involving many stakeholders. The present invention aims to improve user work efficiency and satisfaction by providing such a system.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The user accesses the terminal interface and displays a question input form. The user enters the question, "I'm having trouble figuring out the procedure for setting up the new base station," and clicks the submit button.

[0540] Step 2:

[0541] The terminal acquires the question text entered by the user, along with emotional data such as voice signals and facial recognition data as needed, and detects the click event of the submit button. The terminal packets the data, including the question text and emotional data, as an HTTP POST request.

[0542] Step 3:

[0543] The device sends an HTTP POST request to the server. The request includes the question text and user sentiment data.

[0544] Step 4:

[0545] The server receives an HTTP request and extracts the question text and sentiment data from the request body. The server then passes this question text to a natural language processing engine for analysis of the question content.

[0546] Step 5:

[0547] The server's natural language processing engine performs syntactic and contextual analysis of the question text, extracting key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[0548] Step 6:

[0549] The server's emotion engine analyzes the user's emotions based on audio signals and facial recognition data sent by the user. From this analysis, it identifies the user's emotional state, such as being confused or stressed.

[0550] Step 7:

[0551] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[0552] Step 8:

[0553] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the procedure.

[0554] Step 9:

[0555] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[0556] Step 10:

[0557] The server formats the generated or retrieved responses into a format that is easy for the user to understand. In this process, it adjusts the tone and content of the responses based on the results of the sentiment engine's analysis. For example, it might generate a response that includes specific steps such as, "The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0558] Step 11:

[0559] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[0560] Step 12:

[0561] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[0562] Step 13:

[0563] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[0564] Step 14:

[0565] The server records the user's emotional data analyzed by the emotion engine and uses it to improve future question responses. Based on this recorded data, the system can provide customized responses for each user.

[0566] (Example 2)

[0567] 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".

[0568] Conventional question-answering systems often fail to provide a satisfactory user experience because they generate answers without considering the user's emotional state. Furthermore, they lack the ability to dynamically generate appropriate answers when a suitable answer does not exist in the database. Therefore, there are limitations to improving user work efficiency. The above problems need to be addressed.

[0569] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0570] In this invention, the server includes means for the user to input a question, means for the user to send the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to send the answer to the user, means for the server to display the answer to the user, means for the server to analyze the user's emotions, means for adjusting the tone and content of the answer based on the results of the emotion analysis, and means for recording the user's emotional state to help with future responses. This makes it possible to provide more humane answers that take the user's emotions into consideration, thereby improving user satisfaction and work efficiency.

[0571] A "user" is the entity that accesses the system, enters a question, and receives an answer.

[0572] A "server" is a computer system that analyzes questions submitted by users, generates answers, and sends them back.

[0573] "Means of entering questions" refers to the interface through which users enter questions into a system. Specifically, this includes web forms and input fields in applications.

[0574] "Means of sending questions" refers to the communication protocol or function used to send questions entered by the user to a server. Generally, HTTP POST requests are used.

[0575] "Means for analyzing questions" refers to the technology used by a server to understand and analyze the questions it receives. Specifically, this includes natural language processing engines.

[0576] "Means of generating answers" refers to the process by which a server creates answers to questions. This includes Q&A databases and generative AI models.

[0577] "Means for sending responses" refers to the communication protocols and functions used by the server to send responses generated by the server to the user.

[0578] "Means of displaying responses" refers to an interface that allows users to view submitted responses. Specifically, this includes the display section of a web page or application.

[0579] "Means of analyzing emotions" refer to technologies that allow a server to identify and analyze a user's emotional state. Examples include voice tone analysis and facial expression recognition.

[0580] "Means of adjusting responses based on sentiment analysis results" refers to a function that refers to the results of sentiment analysis and generates responses with a tone and content that matches the user's emotions.

[0581] "Means for recording emotional states" refer to databases or storage devices that record user emotional data and use it to inform future responses.

[0582] This invention relates to a system in which a user inputs a question using a terminal, a server analyzes the question to generate an appropriate answer, and further recognizes the user's emotions and responds accordingly. Specific embodiments of this system will be described below.

[0583] The user first accesses the system interface from a device (e.g., a PC or smartphone). The interface displays a question input form, into which the user enters a question. For example, the user might enter the question, "What are the installation procedures for a new base station?" and click the submit button. The user's action of entering and submitting the question triggers the device to send data containing the question text to the server as an HTTP POST request.

[0584] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing (NLP) engine for analysis. The NLP engine (e.g., spaCy or NLTK) performs syntactic and contextual analysis of the question. It extracts key keywords (e.g., "base station," "installation procedure").

[0585] Next, the server searches the Q&A database based on the extracted keywords. If a suitable answer is found, it retrieves that answer. If a suitable answer does not exist in the database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI's GPT-3). In this case, the text "What are the installation procedures for a new base station?" is input to the AI ​​model as a prompt.

[0586] One feature of this invention is the incorporation of emotion analysis functionality. The server passes the received question text and the emotion signals from the user's input (e.g., voice tone and facial expression recognition data) to the emotion engine for analysis. In this embodiment, an emotion analysis API can be used as the emotion engine.

[0587] Based on the sentiment analysis results, the server adjusts the tone and content of its response. For example, if a user inputs "I'm having trouble understanding the procedure for installing a new base station," the sentiment engine recognizes the user's confusion and stress, and the server generates a response that takes those emotions into consideration. Specifically, it might generate a response such as, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0588] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the server to provide customized responses for each user, contributing to an improved user experience.

[0589] This system not only speeds up question-answering but also enables more personalized responses that respond to user emotions. This feature is expected to lead to higher satisfaction and improved work efficiency. Its effectiveness is particularly evident in large-scale projects involving numerous stakeholders.

[0590] The present invention aims to improve user work efficiency and satisfaction by providing the system described above.

[0591] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0592] Step 1:

[0593] The user accesses the system and enters a question into the question input form. For example, the user enters "What are the installation procedures for a new base station?" and clicks the submit button. The input data is the text entered by the user, and the output is an HTTP POST request containing that text.

[0594] Step 2:

[0595] The terminal retrieves the question text entered by the user and sends it to the server as an HTTP POST request. The input data is the question text entered by the user, and the output is an HTTP POST request containing that text. Specifically, the terminal generates a request containing data in JSON format as follows:

[0596] json

[0597] {

[0598] "Question": "What are the procedures for installing a new base station?"

[0599] }

[0600] Step 3:

[0601] The server parses the received HTTP request and extracts the question text from the request body. The input data is the HTTP request, and the output is the extracted question text. The server obtains text data like the following:

[0602] "What are the procedures for installing a new base station?"

[0603] Step 4:

[0604] The server passes the extracted question text to a natural language processing engine for analysis. The input data is the question text, and the output is the main keywords of the analysis results (e.g., "base station," "installation procedure"). The natural language processing engine (e.g., spaCy) obtains the following analysis results:

[0605] Keyword 1: Base station

[0606] Keyword 2: Installation procedure

[0607] Step 5:

[0608] The server searches the Q&A database based on key keywords to find answers. The input data is the key keywords, and the output is the appropriate answer. For example, the following answer corresponding to "procedures for installing a new base station" is found in the database:

[0609] "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment layout, 3. Power supply confirmation, 4. Installation work, 5. Operational check."

[0610] Step 6:

[0611] If a suitable answer cannot be found in the Q&A database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI's GPT-3). The input data consists of key keywords, and the output is the generated answer. The server inputs the following prompt sentences into the AI ​​model to generate an answer:

[0612] "What are the procedures for installing a new base station?"

[0613] The generative AI model outputs the following response:

[0614] "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment layout, 3. Power supply confirmation, 4. Installation work, 5. Operational check."

[0615] Step 7:

[0616] The server uses the question text and the user's emotional signals to pass them to the emotion engine for analysis. The input data consists of the question text and emotional signals (voice tone and facial expression data), and the output is the result of the emotion analysis. The emotion engine analyzes the user's emotional state (e.g., confusion, stress).

[0617] Step 8:

[0618] The server adjusts the tone and content of the response based on the sentiment analysis results. The input data consists of the sentiment analysis results and the generated response, while the output is the adjusted response. For example, if the user is confused, the response will be reshaped to a gentler tone, as follows:

[0619] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0620] Step 9:

[0621] The server sends the formatted response to the terminal as an HTTP response. The input data is the formatted response, and the output is the HTTP response. Specifically, the server returns data in JSON format as follows:

[0622] json

[0623] {

[0624] "Answer": "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check"

[0625] }

[0626] Step 10:

[0627] The terminal displays the received response to the user. The input data is an HTTP response from the server, and the output is a text display that the user can view. Specifically, the terminal displays the following response in the display area of ​​a web page or application:

[0628] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0629] Through the above process, this system can respond to user questions and provide emotionally sensitive answers.

[0630] (Application Example 2)

[0631] 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."

[0632] In autonomous vehicles, a problem exists where passengers' questions about system problems or operating procedures during the ride cannot be immediately resolved because there is no staff member available, increasing their anxiety and confusion. Furthermore, the lack of responses that take into account the passengers' emotional state also leads to a diminished user experience.

[0633] 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.

[0634] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, emotion analysis means for recognizing the user's emotions, and means for adjusting the tone and content of the answer based on the emotions analyzed by the emotion analysis means. This makes it possible to quickly provide appropriate feedback according to the emotional state of a passenger when they ask a question while riding in an autonomous vehicle.

[0635] A "user" is a person who uses this system.

[0636] "Means for entering questions" refers to an interface device that allows users to enter questions via text or voice.

[0637] A "server" is a computer system that has the computing resources to receive user questions, analyze them, and generate answers.

[0638] "Means for analyzing questions" refers to software or hardware used to analyze questions received from users using natural language processing techniques.

[0639] "Means for generating answers to questions" refers to devices or software that analyze the content of a question and dynamically generate the corresponding answer by obtaining it from a database or using a generation AI model.

[0640] "Means for sending responses to users" refers to an interface device for sending generated responses to a user's terminal via a network.

[0641] "Means of displaying the answer to the user" refers to a display device or audio output device for visually or audibly displaying the answer on the user's terminal.

[0642] "Emotion analysis means" refers to software or hardware used to analyze a user's emotions from input audio or image data.

[0643] "Means of adjusting the tone and content of responses" refers to software or hardware that appropriately modifies the content and expression of responses based on analyzed emotions.

[0644] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. This system is particularly intended for passenger support in autonomous vehicles, aiming to provide rapid and emotion-responsive feedback to passengers' questions.

[0645] Users input questions using interface devices such as touchscreen panels, smart glasses, or head-mounted displays within the autonomous vehicle. Users input questions via text or voice, and this input data is sent to the server. For example, if a user inputs the question, "How do I change my destination?", the question, along with the user's voice data and facial image data, will be sent to the server.

[0646] The server first uses a natural language processing engine (e.g., GPT-3) to analyze the question. Syntactic and contextual analysis of the question is performed, and key keywords are extracted. Next, based on the extracted keywords, an appropriate answer is generated using a Q&A database or a generative AI model. At this time, the question is entered as a prompt in a specific format, "The user is feeling {emotion}. {question}", so it is possible to generate an answer that reflects the user's emotion.

[0647] Emotion analysis methods include emotion recognition through voice analysis and emotion recognition through facial image analysis. The system analyzes the user's voice tone and facial expressions, and identifies the user's emotions based on the results. For example, if the user is confused, the server will recognize the emotion as "Confused."

[0648] Based on the analyzed emotions, the tone and content of the response are adjusted. For example, if the system detects that the user is confused, the generated response will be in the format of, "Please proceed with confidence. To change your destination, open the navigation menu, select 'Change Destination,' and enter the new address."

[0649] The generated responses are sent to the user's device and displayed on a touchscreen panel or smart glasses. They may also be played back via audio output. This allows for the rapid provision of appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[0650] For example, if a passenger asks in a confused tone, "How do I change my destination?" while the vehicle is in motion, the server will query the AI ​​model with the following prompt:

[0651] The user is feeling confused. How do I change the destination while the car is driving?

[0652] In response to this, the AI ​​model outputs a response that takes emotions into consideration, such as, "To change your destination, select the 'Change Destination' option from the navigation menu and enter the new address."

[0653] As described above, the present invention not only speeds up question-answering but also enables a more humane response that responds to the user's emotions. This is expected to lead to higher satisfaction and improved service.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1:

[0656] The user enters a question.

[0657] Specific operation: The user inputs a question via text or voice using a touchscreen panel, smart glasses, or head-mounted display within the autonomous vehicle. For example, the user might text or voice ask, "How do I change my destination?" Input and output: The input is the user's text or voice question data, and the output is the preparation of that question data for transmission.

[0658] Step 2:

[0659] The terminal sends the question to the server.

[0660] Specific operation: The terminal sends the entered question data to the server in the form of an HTTP POST request. Input and output: The input is the user's question data, and the output is the HTTP request to the server.

[0661] Step 3:

[0662] The server analyzes the question.

[0663] Specific operation: The server extracts question data from the received HTTP request and passes it to the natural language processing engine. The natural language processing engine parses this question data syntactically and contextually, and extracts key keywords (e.g., "destination," "change"). Input and output: The input is the question data, and the output is the parsed keywords.

[0664] Step 4:

[0665] The server analyzes emotions.

[0666] Specific operation: The server passes the user's voice data and facial image data to the emotion analysis engine, which analyzes the user's emotional state. The results of the voice analysis and facial image analysis are integrated to make a final emotion determination. Input and output: The input is voice data and facial image data, and the output is the determination result of the user's emotional state.

[0667] Step 5:

[0668] The server generates the answer.

[0669] Specific operation: The server uses the analyzed keywords and the user's emotional state to create a prompt for the generative AI model. For example, it generates the prompt "The user is feeling confused. How do I change the destination while the car is driving?" and passes it to the generative AI model (e.g., GPT-3). The generative AI model returns an appropriate answer, which is then formatted. Input and output: The input is keywords and emotional state, and the output is the generated answer.

[0670] Step 6:

[0671] The server sends the answer to the user.

[0672] Specific operation: The server sends the formatted response to the user's terminal as an HTTP response. Input and output: The input is the generated response text, and the output is the HTTP response to the user.

[0673] Step 7:

[0674] The device displays the answer to the user.

[0675] Specific operation: The terminal visually displays the received response on a touchscreen panel or smart glasses. It also plays the response aloud using an audio output device as needed. Input and output: The input is the response data from the server, and the output is the response displayed to the user.

[0676] This makes it possible to quickly provide appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] [Third Embodiment]

[0681] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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".

[0693] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[0694] The user first enters the question using their device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[0695] The server receives an HTTP request and extracts the question text from the request body. This question text is passed to the server's natural language processing engine for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[0696] Next, the server begins the process of searching the database for appropriate answers based on the extracted keywords and intent. The database contains pre-stored Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using an AI model (e.g., GPT-3).

[0697] The generated response is formatted in a way that is easy for the user to understand. This response includes specific steps, such as "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0698] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[0699] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives and analyzes this question, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to spend time consulting a manual.

[0700] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[0701] The following describes the processing flow.

[0702] Step 1:

[0703] The user accesses the terminal interface and a question input form is displayed. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button.

[0704] Step 2:

[0705] The device retrieves the question text entered by the user and detects the click event of the submit button. The device then packets the data, including the question text, as an HTTP POST request.

[0706] Step 3:

[0707] The device sends an HTTP POST request to the server. The request includes the question text and user identification information, among other things.

[0708] Step 4:

[0709] The server receives the HTTP request and extracts the question text from the request body. The server then passes this question text to the natural language processing engine.

[0710] Step 5:

[0711] The server's natural language processing engine performs syntactic analysis of the question text and extracts key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[0712] Step 6:

[0713] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[0714] Step 7:

[0715] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the relevant procedures.

[0716] Step 8:

[0717] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[0718] Step 9:

[0719] The server formats the retrieved or generated response into a user-friendly format. For example, it might include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0720] Step 10:

[0721] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[0722] Step 11:

[0723] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[0724] Step 12:

[0725] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[0726] (Example 1)

[0727] 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."

[0728] Conventional question answering systems often lack accuracy and speed in responding to user questions, and are particularly inadequate for handling specialized or complex inquiries. Furthermore, they frequently fail to provide appropriate answers to questions not found in existing FAQ databases, leading to decreased operational efficiency.

[0729] 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.

[0730] In this invention, the server includes means for analyzing a question using a natural language processing engine, means for retrieving an answer from a database or dynamically generating an answer using a generative AI model, and means for formatting the generated answer. This makes it possible to provide a fast and accurate answer to a user's question.

[0731] A "user" is a person or entity that uses this system to input questions and receive answers.

[0732] A "device" is a device used by a user to input and submit questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0733] A "server" is a computer system that receives questions from users, analyzes them, and generates answers.

[0734] A "question" refers to the content of an inquiry that a user sends to the server via their device, and an appropriate answer should be provided to this inquiry.

[0735] A "natural language processing engine" is software that allows a server to analyze the text of a question and perform syntactic analysis and keyword extraction.

[0736] A "database" is a collection of information that a server accesses to search for answers, and it stores Q&A information and related materials.

[0737] A "generative AI model" is an artificial intelligence algorithm used by a server to dynamically generate answers when a suitable answer cannot be found in the database.

[0738] "Formatting" refers to the process of transforming a response generated or retrieved by a server into a format that is easy for the user to understand.

[0739] An "HTTP request" is a data transmission format based on a communication protocol used by a terminal to send query data to a server.

[0740] An "HTTP response" is a data response format based on a communication protocol used by a server to send response data to a terminal.

[0741] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[0742] The user first enters the question using a device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[0743] The server receives an HTTP request and extracts the question text from the request body. This question text is then passed to a natural language processing engine (e.g., SpaCy or NLTK) on the server for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[0744] Next, the server starts the process of searching for appropriate answers from a database (e.g., PostgreSQL, MongoDB) based on the extracted keywords and intent. The database already contains Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using a generative AI model (e.g., GPT-3).

[0745] The generated answers are formatted in a way that is easy for the user to understand. Specifically, detailed answers are provided, including step-by-step explanations. For example, they may include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[0746] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[0747] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives this question, analyzes it, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to consult a manual.

[0748] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[0749] Example of a prompt:

[0750] "What are the procedures for installing a new base station?"

[0751] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0752] Step 1:

[0753] The user launches the application or web interface on their device and enters the question "What are the steps for installing a new base station?" into the input form. After entering the question, the user presses the submit button.

[0754] Input: Question: "What are the procedures for installing a new base station?"

[0755] Output: Question data sent as an HTTP request

[0756] Specific actions:

[0757] 1. Open the application or web interface.

[0758] 2. Type "What are the installation procedures for a new base station?"

[0759] 3. Click the Send button.

[0760] 4. The question data is sent to the server as an HTTP request.

[0761] Step 2:

[0762] The server receives the HTTP request and extracts the question text from the request body.

[0763] Input: HTTP Request

[0764] Output: Question text: "What are the installation procedures for a new base station?"

[0765] Specific actions:

[0766] 1. The server receives an HTTP request.

[0767] 2. Extract the question text from the request body.

[0768] Step 3:

[0769] The server passes the question text to a natural language processing engine (e.g., SpaCy or NLTK) for syntactic analysis and keyword extraction.

[0770] Input: Question text: "What are the procedures for installing a new base station?"

[0771] Output: Key keywords "base station" and "installation procedure"

[0772] Specific actions:

[0773] 1. Pass the question text to the natural language processing engine.

[0774] 2. Perform syntactic analysis.

[0775] 3. Extract the main keywords "base station" and "installation procedure".

[0776] Step 4:

[0777] The server searches the database based on the extracted keywords and retrieves relevant information. If a suitable answer does not exist in the database, it dynamically generates an answer using a generative AI model (e.g., GPT-3).

[0778] Input: Main keywords "base station" and "installation procedure"

[0779] Output: Response data "The procedure for installing the new base station is as follows..."

[0780] Specific actions:

[0781] 1. Search the database.

[0782] 2. Obtain relevant Q&A information.

[0783] 3. If a suitable answer is not found in the database, prompts are entered into the generation AI model to dynamically generate an answer.

[0784] Step 5:

[0785] The server formats the generated response into a format that is easy for the user to understand.

[0786] Input: Response data "The procedure for installing a new base station is as follows..."

[0787] Output: Formatted response data

[0788] Specific actions:

[0789] 1. Format the response data.

[0790] 2. Make the format easy for users to understand, for example, by adding step-by-step instructions.

[0791] Step 6:

[0792] The server sends the formatted response to the terminal as an HTTP response.

[0793] Input: Formatted response data

[0794] Output: HTTP response

[0795] Specific actions:

[0796] 1. Convert the formatted response into an HTTP response.

[0797] 2. Send it to the terminal as an HTTP response.

[0798] Step 7:

[0799] The terminal receives an HTTP response and displays the answer in the user interface.

[0800] Input: HTTP response

[0801] Output: The displayed response is "The procedure for installing the new base station is as follows..."

[0802] Specific actions:

[0803] 1. Receive the HTTP response.

[0804] 2. The user interface displays the following: "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0805] (Application Example 1)

[0806] 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."

[0807] Existing virtual stores have limited means for users to instantly obtain product information, and there are challenges in obtaining quick and accurate responses, especially when interacting with smart glasses. As a result, the user experience deteriorates, and the decision to purchase products takes longer.

[0808] 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.

[0809] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, means for interacting with the user using smart glasses, means for transmitting the question obtained using the smart glasses to the server, and means for displaying the answer on the display of the smart glasses. This makes it possible for a user to easily ask questions about products in a virtual store through smart glasses and to obtain quick and appropriate answers.

[0810] "Means for users to input questions" refers to providing an interface for users to input questions using a device.

[0811] "Means for sending the aforementioned question to the server" refers to a mechanism for sending a question entered by a user to a server via a network.

[0812] "Means by which the server analyzes the question" refers to a process in which the server analyzes the received question using natural language processing technology and extracts key keywords and the user's intent.

[0813] "Means by which the server generates an answer to the question" refers to a function that uses a database or AI model to generate an appropriate answer based on the analyzed question.

[0814] "Means by which the server transmits the response to the user" refers to a mechanism for transmitting the generated response to the user's terminal via the network.

[0815] "Means for displaying the aforementioned answer to the user" refers to an interface for displaying the answer on the user's device.

[0816] "A means of interacting with users using smart glasses" refers to a system that uses smart glasses to receive input from users and display responses.

[0817] "Means for transmitting questions obtained using the smart glasses to the server" refers to a mechanism for transmitting information acquired through the smart glasses to a server via a network.

[0818] "Means for displaying the answer on the display of the smart glasses" refers to a function that uses the visual display device of the smart glasses to display the acquired answer to the user.

[0819] This invention is a system that enables user interaction within a virtual store using smart glasses. A specific embodiment of this system is described below.

[0820] Program generation and processing explanation

[0821] Smart glasses application

[0822] The application installed on the smart glasses provides an interface for users to input questions using voice input or touch gestures. Once the user inputs a question, it is sent to a server via the smart glasses' network.

[0823] Server-based question analysis and answer generation.

[0824] The server utilizes a natural language processing engine (such as NLTK or Transformers) to analyze the received question. Once the question analysis is complete, the server uses a database and a generative AI model (e.g., GPT-3) to generate an appropriate answer. This answer is then formatted in a way that is easy for the user to understand.

[0825] Display the answer

[0826] The generated answers are then sent back to the smart glasses via the network and displayed on the smart glasses' screen. This entire process allows users to easily ask questions about products in a virtual store and receive quick answers.

[0827] Hardware and software to be used

[0828] Hardware: Smart glasses (e.g., Google Glass or Microsoft HoloLens)

[0829] Software: Natural language processing libraries (e.g., NLTK, Transformers), HTTP communication libraries (requests)

[0830] Specific example

[0831] As a concrete example, suppose a user walks through a virtual store and asks, "What can this product be used for?" through smart glasses. This question is sent to a server and analyzed by a natural language processing engine. Based on the analysis, the server generates an appropriate answer from its database, for example, "This product is used as camping equipment for outdoor activities," and sends it back to the smart glasses. The smart glasses display this answer on their screen, allowing the user to receive the response in real time.

[0832] Example of a prompt

[0833] The following are examples of prompt statements:

[0834] "What can this product be used for?"

[0835] "What is the warranty period for this product?"

[0836] "Please tell me about current sales."

[0837] In this way, smooth data communication and natural language processing between smart glasses and servers enable users to obtain information quickly and accurately.

[0838] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0839] Step 1:

[0840] The user enters a question using the voice input function or touch gestures of the smart glasses. The entered question is converted into text format by an application within the smart glasses. The input is voice data or gesture action, and the output is text data.

[0841] Step 2:

[0842] The smart glasses send the question, converted as text data, to a server over the network. This transmission is done using an HTTP request. The input is the converted text data, and the output is the HTTP request.

[0843] Step 3:

[0844] The server receives an HTTP request and extracts the question text from the request body. The input is the HTTP request, and the output is the extracted question text.

[0845] Step 4:

[0846] The server passes the extracted question text to a natural language processing engine (e.g., NLTK, Transformers) for analysis. The analysis process extracts key keywords and user intent. The input is the question text, and the output is the analysis result.

[0847] Step 5:

[0848] The server searches the database for appropriate answers based on the analyzed keywords and intent. Alternatively, it dynamically generates answers using a generative AI model (e.g., GPT-3) as needed. The input is the analysis result, and the output is the generated answer.

[0849] Step 6:

[0850] The generated responses are formatted into a user-friendly format and prepared as the final responses. The input is the generated response data, and the output is the formatted response data.

[0851] Step 7:

[0852] The server sends the formatted response data to the smart glasses as an HTTP response. The input is the formatted response data, and the output is the HTTP response.

[0853] Step 8:

[0854] The smart glasses retrieve response data from the received HTTP response and display it on the screen. The user confirms the response through this display. The input is the HTTP response, and the output is the response displayed on the screen.

[0855] Through these steps, users can engage in real-time question and answer exchanges via smart glasses.

[0856] 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.

[0857] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. The purpose of this system is to improve the user's work efficiency.

[0858] The user first accesses the terminal interface and displays a question input form. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button. This question submission action triggers the terminal to send data containing the question text to the server as an HTTP POST request.

[0859] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing engine for analysis. The natural language processing engine performs syntactic and contextual analysis of the question and extracts key keywords (e.g., "base station," "installation procedure").

[0860] Next, the server searches the Q&A database based on the extracted keywords and retrieves the most suitable answer. If a suitable answer does not exist in the database, an AI model (e.g., GPT-3) is used to dynamically generate an answer. The answer generated in this answer generation process is then formatted in a way that is easy for the user to understand.

[0861] One feature of this invention is the incorporation of an emotion engine. The server analyzes the user's emotional state using the question text and emotional signals from the user's input (e.g., voice tone and facial expression recognition data). Based on the results of this emotion analysis, the server adjusts the tone and content of the response.

[0862] For example, if a user enters "I'm having trouble figuring out the procedure for installing a new base station," the emotion engine will recognize the user's confusion and stress, and generate a response that takes those emotions into consideration. Specifically, it might generate a response like, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0863] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the system to provide customized responses for each user, contributing to an improved user experience.

[0864] Overall, this system not only speeds up question-answering but also enables more humane responses that respond to user emotions. This is expected to lead to higher satisfaction and improved work efficiency. Its effects are particularly pronounced in large-scale projects involving many stakeholders. The present invention aims to improve user work efficiency and satisfaction by providing such a system.

[0865] The following describes the processing flow.

[0866] Step 1:

[0867] The user accesses the terminal interface and displays a question input form. The user enters the question, "I'm having trouble figuring out the procedure for setting up the new base station," and clicks the submit button.

[0868] Step 2:

[0869] The terminal acquires the question text entered by the user, along with emotional data such as voice signals and facial recognition data as needed, and detects the click event of the submit button. The terminal packets the data, including the question text and emotional data, as an HTTP POST request.

[0870] Step 3:

[0871] The device sends an HTTP POST request to the server. The request includes the question text and user sentiment data.

[0872] Step 4:

[0873] The server receives an HTTP request and extracts the question text and sentiment data from the request body. The server then passes this question text to a natural language processing engine for analysis of the question content.

[0874] Step 5:

[0875] The server's natural language processing engine performs syntactic and contextual analysis of the question text, extracting key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[0876] Step 6:

[0877] The server's emotion engine analyzes the user's emotions based on audio signals and facial recognition data sent by the user. From this analysis, it identifies the user's emotional state, such as being confused or stressed.

[0878] Step 7:

[0879] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[0880] Step 8:

[0881] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the procedure.

[0882] Step 9:

[0883] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[0884] Step 10:

[0885] The server formats the generated or retrieved responses into a format that is easy for the user to understand. In this process, it adjusts the tone and content of the responses based on the results of the sentiment engine's analysis. For example, it might generate a response that includes specific steps such as, "The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0886] Step 11:

[0887] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[0888] Step 12:

[0889] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[0890] Step 13:

[0891] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[0892] Step 14:

[0893] The server records the user's emotional data analyzed by the emotion engine and uses it to improve future question responses. Based on this recorded data, the system can provide customized responses for each user.

[0894] (Example 2)

[0895] 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."

[0896] Conventional question-answering systems often fail to provide a satisfactory user experience because they generate answers without considering the user's emotional state. Furthermore, they lack the ability to dynamically generate appropriate answers when a suitable answer does not exist in the database. Therefore, there are limitations to improving user work efficiency. The above problems need to be addressed.

[0897] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0898] In this invention, the server includes means for the user to input a question, means for the user to send the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to send the answer to the user, means for the server to display the answer to the user, means for the server to analyze the user's emotions, means for adjusting the tone and content of the answer based on the results of the emotion analysis, and means for recording the user's emotional state to help with future responses. This makes it possible to provide more humane answers that take the user's emotions into consideration, thereby improving user satisfaction and work efficiency.

[0899] A "user" is the entity that accesses the system, enters a question, and receives an answer.

[0900] A "server" is a computer system that analyzes questions submitted by users, generates answers, and sends them back.

[0901] "Means of entering questions" refers to the interface through which users enter questions into a system. Specifically, this includes web forms and input fields in applications.

[0902] "Means of sending questions" refers to the communication protocol or function used to send questions entered by the user to a server. Generally, HTTP POST requests are used.

[0903] "Means for analyzing questions" refers to the technology used by a server to understand and analyze the questions it receives. Specifically, this includes natural language processing engines.

[0904] "Means of generating answers" refers to the process by which a server creates answers to questions. This includes Q&A databases and generative AI models.

[0905] "Means for sending responses" refers to the communication protocols and functions used by the server to send responses generated by the server to the user.

[0906] "Means of displaying responses" refers to an interface that allows users to view submitted responses. Specifically, this includes the display section of a web page or application.

[0907] "Means of analyzing emotions" refer to technologies that allow a server to identify and analyze a user's emotional state. Examples include voice tone analysis and facial expression recognition.

[0908] "Means of adjusting responses based on sentiment analysis results" refers to a function that refers to the results of sentiment analysis and generates responses with a tone and content that matches the user's emotions.

[0909] "Means for recording emotional states" refer to databases or storage devices that record user emotional data and use it to inform future responses.

[0910] This invention relates to a system in which a user inputs a question using a terminal, a server analyzes the question to generate an appropriate answer, and further recognizes the user's emotions and responds accordingly. Specific embodiments of this system will be described below.

[0911] The user first accesses the system interface from a device (e.g., a PC or smartphone). The interface displays a question input form, into which the user enters a question. For example, the user might enter the question, "What are the installation procedures for a new base station?" and click the submit button. The user's action of entering and submitting the question triggers the device to send data containing the question text to the server as an HTTP POST request.

[0912] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing (NLP) engine for analysis. The NLP engine (e.g., spaCy or NLTK) performs syntactic and contextual analysis of the question. It extracts key keywords (e.g., "base station," "installation procedure").

[0913] Next, the server searches the Q&A database based on the extracted keywords. If a suitable answer is found, it retrieves that answer. If a suitable answer does not exist in the database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI's GPT-3). In this case, the text "What are the installation procedures for a new base station?" is input to the AI ​​model as a prompt.

[0914] One feature of this invention is the incorporation of emotion analysis functionality. The server passes the received question text and the emotion signals from the user's input (e.g., voice tone and facial expression recognition data) to the emotion engine for analysis. In this embodiment, an emotion analysis API can be used as the emotion engine.

[0915] Based on the sentiment analysis results, the server adjusts the tone and content of its response. For example, if a user inputs "I'm having trouble understanding the procedure for installing a new base station," the sentiment engine recognizes the user's confusion and stress, and the server generates a response that takes those emotions into consideration. Specifically, it might generate a response such as, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0916] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the server to provide customized responses for each user, contributing to an improved user experience.

[0917] This system not only speeds up question-answering but also enables more personalized responses that respond to user emotions. This feature is expected to lead to higher satisfaction and improved work efficiency. Its effectiveness is particularly evident in large-scale projects involving numerous stakeholders.

[0918] The present invention aims to improve user work efficiency and satisfaction by providing the system described above.

[0919] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0920] Step 1:

[0921] The user accesses the system and enters a question into the question input form. For example, the user enters "What are the installation procedures for a new base station?" and clicks the submit button. The input data is the text entered by the user, and the output is an HTTP POST request containing that text.

[0922] Step 2:

[0923] The terminal retrieves the question text entered by the user and sends it to the server as an HTTP POST request. The input data is the question text entered by the user, and the output is an HTTP POST request containing that text. Specifically, the terminal generates a request containing data in JSON format as follows:

[0924] json

[0925] {

[0926] "Question": "What are the procedures for installing a new base station?"

[0927] }

[0928] Step 3:

[0929] The server parses the received HTTP request and extracts the question text from the request body. The input data is the HTTP request, and the output is the extracted question text. The server obtains text data like the following:

[0930] "What are the procedures for installing a new base station?"

[0931] Step 4:

[0932] The server passes the extracted question text to a natural language processing engine for analysis. The input data is the question text, and the output is the main keywords of the analysis results (e.g., "base station," "installation procedure"). The natural language processing engine (e.g., spaCy) obtains the following analysis results:

[0933] Keyword 1: Base station

[0934] Keyword 2: Installation procedure

[0935] Step 5:

[0936] The server searches the Q&A database based on key keywords to find answers. The input data is the key keywords, and the output is the appropriate answer. For example, the following answer corresponding to "procedures for installing a new base station" is found in the database:

[0937] "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment layout, 3. Power supply confirmation, 4. Installation work, 5. Operational check."

[0938] Step 6:

[0939] If a suitable answer cannot be found in the Q&A database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI's GPT-3). The input data consists of key keywords, and the output is the generated answer. The server inputs the following prompt sentences into the AI ​​model to generate an answer:

[0940] "What are the procedures for installing a new base station?"

[0941] The generative AI model outputs the following response:

[0942] "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment layout, 3. Power supply confirmation, 4. Installation work, 5. Operational check."

[0943] Step 7:

[0944] The server uses the question text and the user's emotional signals to pass them to the emotion engine for analysis. The input data consists of the question text and emotional signals (voice tone and facial expression data), and the output is the result of the emotion analysis. The emotion engine analyzes the user's emotional state (e.g., confusion, stress).

[0945] Step 8:

[0946] The server adjusts the tone and content of the response based on the sentiment analysis results. The input data consists of the sentiment analysis results and the generated response, while the output is the adjusted response. For example, if the user is confused, the response will be reshaped to a gentler tone, as follows:

[0947] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0948] Step 9:

[0949] The server sends the formatted response to the terminal as an HTTP response. The input data is the formatted response, and the output is the HTTP response. Specifically, the server returns data in JSON format as follows:

[0950] json

[0951] {

[0952] "Answer": "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check"

[0953] }

[0954] Step 10:

[0955] The terminal displays the received response to the user. The input data is an HTTP response from the server, and the output is a text display that the user can view. Specifically, the terminal displays the following response in the display area of ​​a web page or application:

[0956] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[0957] Through the above process, this system can respond to user questions and provide emotionally sensitive answers.

[0958] (Application Example 2)

[0959] 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."

[0960] In autonomous vehicles, a problem exists where passengers' questions about system problems or operating procedures during the ride cannot be immediately resolved because there is no staff member available, increasing their anxiety and confusion. Furthermore, the lack of responses that take into account the passengers' emotional state also leads to a diminished user experience.

[0961] 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.

[0962] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, emotion analysis means for recognizing the user's emotions, and means for adjusting the tone and content of the answer based on the emotions analyzed by the emotion analysis means. This makes it possible to quickly provide appropriate feedback according to the emotional state of a passenger when they ask a question while riding in an autonomous vehicle.

[0963] A "user" is a person who uses this system.

[0964] "Means for entering questions" refers to an interface device that allows users to enter questions via text or voice.

[0965] A "server" is a computer system that has the computing resources to receive user questions, analyze them, and generate answers.

[0966] "Means for analyzing questions" refers to software or hardware used to analyze questions received from users using natural language processing techniques.

[0967] "Means for generating answers to questions" refers to devices or software that analyze the content of a question and dynamically generate the corresponding answer by obtaining it from a database or using a generation AI model.

[0968] "Means for sending responses to users" refers to an interface device for sending generated responses to a user's terminal via a network.

[0969] "Means of displaying the answer to the user" refers to a display device or audio output device for visually or audibly displaying the answer on the user's terminal.

[0970] "Emotion analysis means" refers to software or hardware used to analyze a user's emotions from input audio or image data.

[0971] "Means of adjusting the tone and content of responses" refers to software or hardware that appropriately modifies the content and expression of responses based on analyzed emotions.

[0972] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. This system is particularly intended for passenger support in autonomous vehicles, aiming to provide rapid and emotion-responsive feedback to passengers' questions.

[0973] Users input questions using interface devices such as touchscreen panels, smart glasses, or head-mounted displays within the autonomous vehicle. Users input questions via text or voice, and this input data is sent to the server. For example, if a user inputs the question, "How do I change my destination?", the question, along with the user's voice data and facial image data, will be sent to the server.

[0974] The server first uses a natural language processing engine (e.g., GPT-3) to analyze the question. Syntactic and contextual analysis of the question is performed, and key keywords are extracted. Next, based on the extracted keywords, an appropriate answer is generated using a Q&A database or a generative AI model. At this time, the question is entered as a prompt in a specific format, "The user is feeling {emotion}. {question}", so it is possible to generate an answer that reflects the user's emotion.

[0975] Emotion analysis methods include emotion recognition through voice analysis and emotion recognition through facial image analysis. The system analyzes the user's voice tone and facial expressions, and identifies the user's emotions based on the results. For example, if the user is confused, the server will recognize the emotion as "Confused."

[0976] Based on the analyzed emotions, the tone and content of the response are adjusted. For example, if the system detects that the user is confused, the generated response will be in the format of, "Please proceed with confidence. To change your destination, open the navigation menu, select 'Change Destination,' and enter the new address."

[0977] The generated responses are sent to the user's device and displayed on a touchscreen panel or smart glasses. They may also be played back via audio output. This allows for the rapid provision of appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[0978] For example, if a passenger asks in a confused tone, "How do I change my destination?" while the vehicle is in motion, the server will query the AI ​​model with the following prompt:

[0979] The user is feeling confused. How do I change the destination while the car is driving?

[0980] In response to this, the AI ​​model outputs a response that takes emotions into consideration, such as, "To change your destination, select the 'Change Destination' option from the navigation menu and enter the new address."

[0981] As described above, the present invention not only speeds up question-answering but also enables a more humane response that responds to the user's emotions. This is expected to lead to higher satisfaction and improved service.

[0982] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0983] Step 1:

[0984] The user enters a question.

[0985] Specific operation: The user inputs a question via text or voice using a touchscreen panel, smart glasses, or head-mounted display within the autonomous vehicle. For example, the user might text or voice ask, "How do I change my destination?" Input and output: The input is the user's text or voice question data, and the output is the preparation of that question data for transmission.

[0986] Step 2:

[0987] The terminal sends the question to the server.

[0988] Specific operation: The terminal sends the entered question data to the server in the form of an HTTP POST request. Input and output: The input is the user's question data, and the output is the HTTP request to the server.

[0989] Step 3:

[0990] The server analyzes the question.

[0991] Specific operation: The server extracts question data from the received HTTP request and passes it to the natural language processing engine. The natural language processing engine parses this question data syntactically and contextually, and extracts key keywords (e.g., "destination," "change"). Input and output: The input is the question data, and the output is the parsed keywords.

[0992] Step 4:

[0993] The server analyzes emotions.

[0994] Specific operation: The server passes the user's voice data and facial image data to the emotion analysis engine, which analyzes the user's emotional state. The results of the voice analysis and facial image analysis are integrated to make a final emotion determination. Input and output: The input is voice data and facial image data, and the output is the determination result of the user's emotional state.

[0995] Step 5:

[0996] The server generates the answer.

[0997] Specific operation: The server uses the analyzed keywords and the user's emotional state to create a prompt for the generative AI model. For example, it generates the prompt "The user is feeling confused. How do I change the destination while the car is driving?" and passes it to the generative AI model (e.g., GPT-3). The generative AI model returns an appropriate answer, which is then formatted. Input and output: The input is keywords and emotional state, and the output is the generated answer.

[0998] Step 6:

[0999] The server sends the answer to the user.

[1000] Specific operation: The server sends the formatted response to the user's terminal as an HTTP response. Input and output: The input is the generated response text, and the output is the HTTP response to the user.

[1001] Step 7:

[1002] The device displays the answer to the user.

[1003] Specific operation: The terminal visually displays the received response on a touchscreen panel or smart glasses. It also plays the response aloud using an audio output device as needed. Input and output: The input is the response data from the server, and the output is the response displayed to the user.

[1004] This makes it possible to quickly provide appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] [Fourth Embodiment]

[1009] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1010] 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.

[1011] 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).

[1012] 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.

[1013] 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.

[1014] 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).

[1015] 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.

[1016] 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.

[1017] 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.

[1018] 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.

[1019] 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.

[1020] 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.

[1021] 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".

[1022] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[1023] The user first enters the question using their device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[1024] The server receives an HTTP request and extracts the question text from the request body. This question text is passed to the server's natural language processing engine for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[1025] Next, the server begins the process of searching the database for appropriate answers based on the extracted keywords and intent. The database contains pre-stored Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using an AI model (e.g., GPT-3).

[1026] The generated response is formatted in a way that is easy for the user to understand. This response includes specific steps, such as "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[1027] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[1028] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives and analyzes this question, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to spend time consulting a manual.

[1029] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[1030] The following describes the processing flow.

[1031] Step 1:

[1032] The user accesses the terminal interface and a question input form is displayed. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button.

[1033] Step 2:

[1034] The device retrieves the question text entered by the user and detects the click event of the submit button. The device then packets the data, including the question text, as an HTTP POST request.

[1035] Step 3:

[1036] The device sends an HTTP POST request to the server. The request includes the question text and user identification information, among other things.

[1037] Step 4:

[1038] The server receives the HTTP request and extracts the question text from the request body. The server then passes this question text to the natural language processing engine.

[1039] Step 5:

[1040] The server's natural language processing engine performs syntactic analysis of the question text and extracts key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[1041] Step 6:

[1042] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[1043] Step 7:

[1044] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the relevant procedures.

[1045] Step 8:

[1046] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[1047] Step 9:

[1048] The server formats the retrieved or generated response into a user-friendly format. For example, it might include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[1049] Step 10:

[1050] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[1051] Step 11:

[1052] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[1053] Step 12:

[1054] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[1055] (Example 1)

[1056] 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".

[1057] Conventional question answering systems often lack accuracy and speed in responding to user questions, and are particularly inadequate for handling specialized or complex inquiries. Furthermore, they frequently fail to provide appropriate answers to questions not found in existing FAQ databases, leading to decreased operational efficiency.

[1058] 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.

[1059] In this invention, the server includes means for analyzing a question using a natural language processing engine, means for retrieving an answer from a database or dynamically generating an answer using a generative AI model, and means for formatting the generated answer. This makes it possible to provide a fast and accurate answer to a user's question.

[1060] A "user" is a person or entity that uses this system to input questions and receive answers.

[1061] A "device" is a device used by a user to input and submit questions, and includes personal computers, smartphones, tablets, and other similar devices.

[1062] A "server" is a computer system that receives questions from users, analyzes them, and generates answers.

[1063] A "question" refers to the content of an inquiry that a user sends to the server via their device, and an appropriate answer should be provided to this inquiry.

[1064] A "natural language processing engine" is software that allows a server to analyze the text of a question and perform syntactic analysis and keyword extraction.

[1065] A "database" is a collection of information that a server accesses to search for answers, and it stores Q&A information and related materials.

[1066] A "generative AI model" is an artificial intelligence algorithm used by a server to dynamically generate answers when a suitable answer cannot be found in the database.

[1067] "Formatting" refers to the process of transforming a response generated or retrieved by a server into a format that is easy for the user to understand.

[1068] An "HTTP request" is a data transmission format based on a communication protocol used by a terminal to send query data to a server.

[1069] An "HTTP response" is a data response format based on a communication protocol used by a server to send response data to a terminal.

[1070] This invention relates to a system in which a user inputs a question, a server analyzes the question, generates an appropriate answer, and provides it to the user. The purpose of this system is to improve the user's work efficiency.

[1071] The user first enters the question using a device. This device can be a PC, smartphone, or tablet, and provides a form for entering the question through a dedicated application or web interface. Once the user enters the question and presses the submit button, the device sends the question data to the server as an HTTP request.

[1072] The server receives an HTTP request and extracts the question text from the request body. This question text is then passed to a natural language processing engine (e.g., SpaCy or NLTK) on the server for analysis. The natural language processing engine performs syntactic analysis of the question and extracts key keywords and the user's intent. For example, in the question "What are the installation procedures for a new base station?", the keywords "base station" and "installation procedures" are extracted.

[1073] Next, the server starts the process of searching for appropriate answers from a database (e.g., PostgreSQL, MongoDB) based on the extracted keywords and intent. The database already contains Q&A information and related materials, and the server uses this information to select the best answer. If necessary, it can also dynamically generate answers using a generative AI model (e.g., GPT-3).

[1074] The generated answers are formatted in a way that is easy for the user to understand. Specifically, detailed answers are provided, including step-by-step explanations. For example, they may include specific steps such as, "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply verification, 4. Installation work, 5. Operation verification."

[1075] Finally, the server sends the formatted answer to the terminal as an HTTP response. The terminal receives this response and displays the answer in the user interface. This allows the user to easily obtain answers to their questions and proceed with their work quickly.

[1076] As a concrete example, consider its application to a base station construction project. When a user enters "What are the installation procedures for a new base station?", the server receives this question, analyzes it, retrieves the relevant installation procedures from the database, and sends them back to the user. In this way, the user can instantly obtain the necessary information without having to consult a manual.

[1077] This system significantly reduces the time required to respond to questions, improving user work efficiency. Its effectiveness is particularly pronounced in large-scale projects involving numerous stakeholders. The present invention aims to improve user work efficiency by providing such a system.

[1078] Example of a prompt:

[1079] "What are the procedures for installing a new base station?"

[1080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1081] Step 1:

[1082] The user launches the application or web interface on their device and enters the question "What are the steps for installing a new base station?" into the input form. After entering the question, the user presses the submit button.

[1083] Input: Question: "What are the procedures for installing a new base station?"

[1084] Output: Question data sent as an HTTP request

[1085] Specific actions:

[1086] 1. Open the application or web interface.

[1087] 2. Type "What are the installation procedures for a new base station?"

[1088] 3. Click the Send button.

[1089] 4. The question data is sent to the server as an HTTP request.

[1090] Step 2:

[1091] The server receives the HTTP request and extracts the question text from the request body.

[1092] Input: HTTP Request

[1093] Output: Question text: "What are the installation procedures for a new base station?"

[1094] Specific actions:

[1095] 1. The server receives an HTTP request.

[1096] 2. Extract the question text from the request body.

[1097] Step 3:

[1098] The server passes the question text to a natural language processing engine (e.g., SpaCy or NLTK) for syntactic analysis and keyword extraction.

[1099] Input: Question text: "What are the procedures for installing a new base station?"

[1100] Output: Key keywords "base station" and "installation procedure"

[1101] Specific actions:

[1102] 1. Pass the question text to the natural language processing engine.

[1103] 2. Perform syntactic analysis.

[1104] 3. Extract the main keywords "base station" and "installation procedure".

[1105] Step 4:

[1106] The server searches the database based on the extracted keywords and retrieves relevant information. If a suitable answer does not exist in the database, it dynamically generates an answer using a generative AI model (e.g., GPT-3).

[1107] Input: Main keywords "base station" and "installation procedure"

[1108] Output: Response data "The procedure for installing the new base station is as follows..."

[1109] Specific actions:

[1110] 1. Search the database.

[1111] 2. Obtain relevant Q&A information.

[1112] 3. If a suitable answer is not found in the database, prompts are entered into the generation AI model to dynamically generate an answer.

[1113] Step 5:

[1114] The server formats the generated response into a format that is easy for the user to understand.

[1115] Input: Response data "The procedure for installing a new base station is as follows..."

[1116] Output: Formatted response data

[1117] Specific actions:

[1118] 1. Format the response data.

[1119] 2. Make the format easy for users to understand, for example, by adding step-by-step instructions.

[1120] Step 6:

[1121] The server sends the formatted response to the terminal as an HTTP response.

[1122] Input: Formatted response data

[1123] Output: HTTP response

[1124] Specific actions:

[1125] 1. Convert the formatted response into an HTTP response.

[1126] 2. Send it to the terminal as an HTTP response.

[1127] Step 7:

[1128] The terminal receives an HTTP response and displays the answer in the user interface.

[1129] Input: HTTP response

[1130] Output: The displayed response is "The procedure for installing the new base station is as follows..."

[1131] Specific actions:

[1132] 1. Receive the HTTP response.

[1133] 2. The user interface displays the following: "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[1134] (Application Example 1)

[1135] 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".

[1136] Existing virtual stores have limited means for users to instantly obtain product information, and there are challenges in obtaining quick and accurate responses, especially when interacting with smart glasses. As a result, the user experience deteriorates, and the decision to purchase products takes longer.

[1137] 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.

[1138] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, means for interacting with the user using smart glasses, means for transmitting the question obtained using the smart glasses to the server, and means for displaying the answer on the display of the smart glasses. This makes it possible for a user to easily ask questions about products in a virtual store through smart glasses and to obtain quick and appropriate answers.

[1139] "Means for users to input questions" refers to providing an interface for users to input questions using a device.

[1140] "Means for sending the aforementioned question to the server" refers to a mechanism for sending a question entered by a user to a server via a network.

[1141] "Means by which the server analyzes the question" refers to a process in which the server analyzes the received question using natural language processing technology and extracts key keywords and the user's intent.

[1142] "Means by which the server generates an answer to the question" refers to a function that uses a database or AI model to generate an appropriate answer based on the analyzed question.

[1143] "Means by which the server transmits the response to the user" refers to a mechanism for transmitting the generated response to the user's terminal via the network.

[1144] "Means for displaying the aforementioned answer to the user" refers to an interface for displaying the answer on the user's device.

[1145] "A means of interacting with users using smart glasses" refers to a system that uses smart glasses to receive input from users and display responses.

[1146] "Means for transmitting questions obtained using the smart glasses to the server" refers to a mechanism for transmitting information acquired through the smart glasses to a server via a network.

[1147] "Means for displaying the answer on the display of the smart glasses" refers to a function that uses the visual display device of the smart glasses to display the acquired answer to the user.

[1148] This invention is a system that enables user interaction within a virtual store using smart glasses. A specific embodiment of this system is described below.

[1149] Program generation and processing explanation

[1150] Smart glasses application

[1151] The application installed on the smart glasses provides an interface for users to input questions using voice input or touch gestures. Once the user inputs a question, it is sent to a server via the smart glasses' network.

[1152] Server-based question analysis and answer generation.

[1153] The server utilizes a natural language processing engine (such as NLTK or Transformers) to analyze the received question. Once the question analysis is complete, the server uses a database and a generative AI model (e.g., GPT-3) to generate an appropriate answer. This answer is then formatted in a way that is easy for the user to understand.

[1154] Display the answer

[1155] The generated answers are then sent back to the smart glasses via the network and displayed on the smart glasses' screen. This entire process allows users to easily ask questions about products in a virtual store and receive quick answers.

[1156] Hardware and software to be used

[1157] Hardware: Smart glasses (e.g., Google Glass or Microsoft HoloLens)

[1158] Software: Natural language processing libraries (e.g., NLTK, Transformers), HTTP communication libraries (requests)

[1159] Specific example

[1160] As a concrete example, suppose a user walks through a virtual store and asks, "What can this product be used for?" through smart glasses. This question is sent to a server and analyzed by a natural language processing engine. Based on the analysis, the server generates an appropriate answer from its database, for example, "This product is used as camping equipment for outdoor activities," and sends it back to the smart glasses. The smart glasses display this answer on their screen, allowing the user to receive the response in real time.

[1161] Example of a prompt

[1162] The following are examples of prompt statements:

[1163] "What can this product be used for?"

[1164] "What is the warranty period for this product?"

[1165] "Please tell me about current sales."

[1166] In this way, smooth data communication and natural language processing between smart glasses and servers enable users to obtain information quickly and accurately.

[1167] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1168] Step 1:

[1169] The user enters a question using the voice input function or touch gestures of the smart glasses. The entered question is converted into text format by an application within the smart glasses. The input is voice data or gesture action, and the output is text data.

[1170] Step 2:

[1171] The smart glasses send the question, converted as text data, to a server over the network. This transmission is done using an HTTP request. The input is the converted text data, and the output is the HTTP request.

[1172] Step 3:

[1173] The server receives an HTTP request and extracts the question text from the request body. The input is the HTTP request, and the output is the extracted question text.

[1174] Step 4:

[1175] The server passes the extracted question text to a natural language processing engine (e.g., NLTK, Transformers) for analysis. The analysis process extracts key keywords and user intent. The input is the question text, and the output is the analysis result.

[1176] Step 5:

[1177] The server searches the database for appropriate answers based on the analyzed keywords and intent. Alternatively, it dynamically generates answers using a generative AI model (e.g., GPT-3) as needed. The input is the analysis result, and the output is the generated answer.

[1178] Step 6:

[1179] The generated responses are formatted into a user-friendly format and prepared as the final responses. The input is the generated response data, and the output is the formatted response data.

[1180] Step 7:

[1181] The server sends the formatted response data to the smart glasses as an HTTP response. The input is the formatted response data, and the output is the HTTP response.

[1182] Step 8:

[1183] The smart glasses retrieve response data from the received HTTP response and display it on the screen. The user confirms the response through this display. The input is the HTTP response, and the output is the response displayed on the screen.

[1184] Through these steps, users can engage in real-time question and answer exchanges via smart glasses.

[1185] 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.

[1186] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. The purpose of this system is to improve the user's work efficiency.

[1187] The user first accesses the terminal interface and displays a question input form. The user enters the question, "What are the installation procedures for a new base station?" and clicks the submit button. This question submission action triggers the terminal to send data containing the question text to the server as an HTTP POST request.

[1188] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing engine for analysis. The natural language processing engine performs syntactic and contextual analysis of the question and extracts key keywords (e.g., "base station," "installation procedure").

[1189] Next, the server searches the Q&A database based on the extracted keywords and retrieves the most suitable answer. If a suitable answer does not exist in the database, an AI model (e.g., GPT-3) is used to dynamically generate an answer. The answer generated in this answer generation process is then formatted in a way that is easy for the user to understand.

[1190] One feature of this invention is the incorporation of an emotion engine. The server analyzes the user's emotional state using the question text and emotional signals from the user's input (e.g., voice tone and facial expression recognition data). Based on the results of this emotion analysis, the server adjusts the tone and content of the response.

[1191] For example, if a user enters "I'm having trouble figuring out the procedure for installing a new base station," the emotion engine will recognize the user's confusion and stress, and generate a response that takes those emotions into consideration. Specifically, it might generate a response like, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[1192] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the system to provide customized responses for each user, contributing to an improved user experience.

[1193] Overall, this system not only speeds up question-answering but also enables more humane responses that respond to user emotions. This is expected to lead to higher satisfaction and improved work efficiency. Its effects are particularly pronounced in large-scale projects involving many stakeholders. The present invention aims to improve user work efficiency and satisfaction by providing such a system.

[1194] The following describes the processing flow.

[1195] Step 1:

[1196] The user accesses the terminal interface and displays a question input form. The user enters the question, "I'm having trouble figuring out the procedure for setting up the new base station," and clicks the submit button.

[1197] Step 2:

[1198] The terminal acquires the question text entered by the user, along with emotional data such as voice signals and facial recognition data as needed, and detects the click event of the submit button. The terminal packets the data, including the question text and emotional data, as an HTTP POST request.

[1199] Step 3:

[1200] The device sends an HTTP POST request to the server. The request includes the question text and user sentiment data.

[1201] Step 4:

[1202] The server receives an HTTP request and extracts the question text and sentiment data from the request body. The server then passes this question text to a natural language processing engine for analysis of the question content.

[1203] Step 5:

[1204] The server's natural language processing engine performs syntactic and contextual analysis of the question text, extracting key keywords (e.g., "base station," "installation procedure"). The natural language processing engine also analyzes contextual information to understand the intent of the question.

[1205] Step 6:

[1206] The server's emotion engine analyzes the user's emotions based on audio signals and facial recognition data sent by the user. From this analysis, it identifies the user's emotional state, such as being confused or stressed.

[1207] Step 7:

[1208] The server searches the Q&A database based on the extracted keywords and intent. The database contains pre-stored answer information.

[1209] Step 8:

[1210] When the server retrieves the appropriate answer from the database, it finds specific information such as relevant manuals and standard operating procedures (SOPs). For example, it might search for "procedures for installing a new base station" and extract the procedure.

[1211] Step 9:

[1212] If the server dynamically generates answers using an AI model, you input the question text and keywords into the AI ​​model (e.g., GPT-3) and receive the generated answers.

[1213] Step 10:

[1214] The server formats the generated or retrieved responses into a format that is easy for the user to understand. In this process, it adjusts the tone and content of the responses based on the results of the sentiment engine's analysis. For example, it might generate a response that includes specific steps such as, "The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[1215] Step 11:

[1216] The server then packets the formatted response back into an HTTP response and sends it to the terminal.

[1217] Step 12:

[1218] The terminal receives an HTTP response from the server and extracts the answer text from the response body. The terminal then displays this answer on the user interface for the user to confirm.

[1219] Step 13:

[1220] The user reviews the answers displayed on the device screen and obtains the necessary information. Based on this, the user can plan their next action.

[1221] Step 14:

[1222] The server records the user's emotional data analyzed by the emotion engine and uses it to improve future question responses. Based on this recorded data, the system can provide customized responses for each user.

[1223] (Example 2)

[1224] 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".

[1225] Conventional question-answering systems often fail to provide a satisfactory user experience because they generate answers without considering the user's emotional state. Furthermore, they lack the ability to dynamically generate appropriate answers when a suitable answer does not exist in the database. Therefore, there are limitations to improving user work efficiency. The above problems need to be addressed.

[1226] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1227] In this invention, the server includes means for the user to input a question, means for the user to send the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to send the answer to the user, means for the server to display the answer to the user, means for the server to analyze the user's emotions, means for adjusting the tone and content of the answer based on the results of the emotion analysis, and means for recording the user's emotional state to help with future responses. This makes it possible to provide more humane answers that take the user's emotions into consideration, thereby improving user satisfaction and work efficiency.

[1228] A "user" is the entity that accesses the system, enters a question, and receives an answer.

[1229] A "server" is a computer system that analyzes questions submitted by users, generates answers, and sends them back.

[1230] "Means of entering questions" refers to the interface through which users enter questions into a system. Specifically, this includes web forms and input fields in applications.

[1231] "Means of sending questions" refers to the communication protocol or function used to send questions entered by the user to a server. Generally, HTTP POST requests are used.

[1232] "Means for analyzing questions" refers to the technology used by a server to understand and analyze the questions it receives. Specifically, this includes natural language processing engines.

[1233] "Means of generating answers" refers to the process by which a server creates answers to questions. This includes Q&A databases and generative AI models.

[1234] "Means for sending responses" refers to the communication protocols and functions used by the server to send responses generated by the server to the user.

[1235] "Means of displaying responses" refers to an interface that allows users to view submitted responses. Specifically, this includes the display section of a web page or application.

[1236] "Means of analyzing emotions" refer to technologies that allow a server to identify and analyze a user's emotional state. Examples include voice tone analysis and facial expression recognition.

[1237] "Means of adjusting responses based on sentiment analysis results" refers to a function that refers to the results of sentiment analysis and generates responses with a tone and content that matches the user's emotions.

[1238] "Means for recording emotional states" refer to databases or storage devices that record user emotional data and use it to inform future responses.

[1239] This invention relates to a system in which a user inputs a question using a terminal, a server analyzes the question to generate an appropriate answer, and further recognizes the user's emotions and responds accordingly. Specific embodiments of this system will be described below.

[1240] The user first accesses the system interface from a device (e.g., a PC or smartphone). The interface displays a question input form, into which the user enters a question. For example, the user might enter the question, "What are the installation procedures for a new base station?" and click the submit button. The user's action of entering and submitting the question triggers the device to send data containing the question text to the server as an HTTP POST request.

[1241] The server receives an HTTP request and extracts the question text from the request body. The server then passes this question text to a natural language processing (NLP) engine for analysis. The NLP engine (e.g., spaCy or NLTK) performs syntactic and contextual analysis of the question. It extracts key keywords (e.g., "base station," "installation procedure").

[1242] Next, the server searches the Q&A database based on the extracted keywords. If a suitable answer is found, it retrieves that answer. If a suitable answer does not exist in the database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI's GPT-3). In this case, the text "What are the installation procedures for a new base station?" is input to the AI ​​model as a prompt.

[1243] One feature of this invention is the incorporation of emotion analysis functionality. The server passes the received question text and the emotion signals from the user's input (e.g., voice tone and facial expression recognition data) to the emotion engine for analysis. In this embodiment, an emotion analysis API can be used as the emotion engine.

[1244] Based on the sentiment analysis results, the server adjusts the tone and content of its response. For example, if a user inputs "I'm having trouble understanding the procedure for installing a new base station," the sentiment engine recognizes the user's confusion and stress, and the server generates a response that takes those emotions into consideration. Specifically, it might generate a response such as, "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[1245] Furthermore, the user's emotional data analyzed by the emotion engine is recorded to help with future question responses. This allows the server to provide customized responses for each user, contributing to an improved user experience.

[1246] This system not only speeds up question-answering but also enables more personalized responses that respond to user emotions. This feature is expected to lead to higher satisfaction and improved work efficiency. Its effectiveness is particularly evident in large-scale projects involving numerous stakeholders.

[1247] The present invention aims to improve user work efficiency and satisfaction by providing the system described above.

[1248] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1249] Step 1:

[1250] The user accesses the system and enters a question into the question input form. For example, the user enters "What are the installation procedures for a new base station?" and clicks the submit button. The input data is the text entered by the user, and the output is an HTTP POST request containing that text.

[1251] Step 2:

[1252] The terminal retrieves the question text entered by the user and sends it to the server as an HTTP POST request. The input data is the question text entered by the user, and the output is an HTTP POST request containing that text. Specifically, the terminal generates a request containing data in JSON format as follows:

[1253] json

[1254] {

[1255] "Question": "What are the procedures for installing a new base station?"

[1256] }

[1257] Step 3:

[1258] The server parses the received HTTP request and extracts the question text from the request body. The input data is the HTTP request, and the output is the extracted question text. The server obtains text data like the following:

[1259] "What are the procedures for installing a new base station?"

[1260] Step 4:

[1261] The server passes the extracted question text to a natural language processing engine for analysis. The input data is the question text, and the output is the main keywords of the analysis results (e.g., "base station," "installation procedure"). The natural language processing engine (e.g., spaCy) obtains the following analysis results:

[1262] Keyword 1: Base station

[1263] Keyword 2: Installation procedure

[1264] Step 5:

[1265] The server searches the Q&A database based on key keywords to find answers. The input data is the key keywords, and the output is the appropriate answer. For example, the following answer corresponding to "procedures for installing a new base station" is found in the database:

[1266] "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment layout, 3. Power supply confirmation, 4. Installation work, 5. Operational check."

[1267] Step 6:

[1268] If a suitable answer cannot be found in the Q&A database, the server dynamically generates an answer using a generative AI model (e.g., OpenAI's GPT-3). The input data consists of key keywords, and the output is the generated answer. The server inputs the following prompt sentences into the AI ​​model to generate an answer:

[1269] "What are the procedures for installing a new base station?"

[1270] The generative AI model outputs the following response:

[1271] "The procedure for installing a new base station is as follows: 1. Site selection, 2. Equipment layout, 3. Power supply confirmation, 4. Installation work, 5. Operational check."

[1272] Step 7:

[1273] The server uses the question text and the user's emotional signals to pass them to the emotion engine for analysis. The input data consists of the question text and emotional signals (voice tone and facial expression data), and the output is the result of the emotion analysis. The emotion engine analyzes the user's emotional state (e.g., confusion, stress).

[1274] Step 8:

[1275] The server adjusts the tone and content of the response based on the sentiment analysis results. The input data consists of the sentiment analysis results and the generated response, while the output is the adjusted response. For example, if the user is confused, the response will be reshaped to a gentler tone, as follows:

[1276] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[1277] Step 9:

[1278] The server sends the formatted response to the terminal as an HTTP response. The input data is the formatted response, and the output is the HTTP response. Specifically, the server returns data in JSON format as follows:

[1279] json

[1280] {

[1281] "Answer": "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check"

[1282] }

[1283] Step 10:

[1284] The terminal displays the received response to the user. The input data is an HTTP response from the server, and the output is a text display that the user can view. Specifically, the terminal displays the following response in the display area of ​​a web page or application:

[1285] "Thank you for your question. The procedure for installing a new base station is as follows. Please follow the steps with confidence: 1. Site selection, 2. Equipment placement, 3. Power supply confirmation, 4. Installation work, 5. Operation check."

[1286] Through the above process, this system can respond to user questions and provide emotionally sensitive answers.

[1287] (Application Example 2)

[1288] 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".

[1289] In autonomous vehicles, a problem exists where passengers' questions about system problems or operating procedures during the ride cannot be immediately resolved because there is no staff member available, increasing their anxiety and confusion. Furthermore, the lack of responses that take into account the passengers' emotional state also leads to a diminished user experience.

[1290] 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.

[1291] In this invention, the server includes means for a user to input a question, means for transmitting the question to the server, means for the server to analyze the question, means for the server to generate an answer to the question, means for the server to transmit the answer to the user, means for displaying the answer to the user, emotion analysis means for recognizing the user's emotions, and means for adjusting the tone and content of the answer based on the emotions analyzed by the emotion analysis means. This makes it possible to quickly provide appropriate feedback according to the emotional state of a passenger when they ask a question while riding in an autonomous vehicle.

[1292] A "user" is a person who uses this system.

[1293] "Means for entering questions" refers to an interface device that allows users to enter questions via text or voice.

[1294] A "server" is a computer system that has the computing resources to receive user questions, analyze them, and generate answers.

[1295] "Means for analyzing questions" refers to software or hardware used to analyze questions received from users using natural language processing techniques.

[1296] "Means for generating answers to questions" refers to devices or software that analyze the content of a question and dynamically generate the corresponding answer by obtaining it from a database or using a generation AI model.

[1297] "Means for sending responses to users" refers to an interface device for sending generated responses to a user's terminal via a network.

[1298] "Means of displaying the answer to the user" refers to a display device or audio output device for visually or audibly displaying the answer on the user's terminal.

[1299] "Emotion analysis means" refers to software or hardware used to analyze a user's emotions from input audio or image data.

[1300] "Means of adjusting the tone and content of responses" refers to software or hardware that appropriately modifies the content and expression of responses based on analyzed emotions.

[1301] This invention relates to a system in which a user inputs a question, a server analyzes the question to generate an appropriate answer, and also recognizes the user's emotions and responds accordingly. This system is particularly intended for passenger support in autonomous vehicles, aiming to provide rapid and emotion-responsive feedback to passengers' questions.

[1302] Users input questions using interface devices such as touchscreen panels, smart glasses, or head-mounted displays within the autonomous vehicle. Users input questions via text or voice, and this input data is sent to the server. For example, if a user inputs the question, "How do I change my destination?", the question, along with the user's voice data and facial image data, will be sent to the server.

[1303] The server first uses a natural language processing engine (e.g., GPT-3) to analyze the question. Syntactic and contextual analysis of the question is performed, and key keywords are extracted. Next, based on the extracted keywords, an appropriate answer is generated using a Q&A database or a generative AI model. At this time, the question is entered as a prompt in a specific format, "The user is feeling {emotion}. {question}", so it is possible to generate an answer that reflects the user's emotion.

[1304] Emotion analysis methods include emotion recognition through voice analysis and emotion recognition through facial image analysis. The system analyzes the user's voice tone and facial expressions, and identifies the user's emotions based on the results. For example, if the user is confused, the server will recognize the emotion as "Confused."

[1305] Based on the analyzed emotions, the tone and content of the response are adjusted. For example, if the system detects that the user is confused, the generated response will be in the format of, "Please proceed with confidence. To change your destination, open the navigation menu, select 'Change Destination,' and enter the new address."

[1306] The generated responses are sent to the user's device and displayed on a touchscreen panel or smart glasses. They may also be played back via audio output. This allows for the rapid provision of appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[1307] For example, if a passenger asks in a confused tone, "How do I change my destination?" while the vehicle is in motion, the server will query the AI ​​model with the following prompt:

[1308] The user is feeling confused. How do I change the destination while the car is driving?

[1309] In response to this, the AI ​​model outputs a response that takes emotions into consideration, such as, "To change your destination, select the 'Change Destination' option from the navigation menu and enter the new address."

[1310] As described above, the present invention not only speeds up question-answering but also enables a more humane response that responds to the user's emotions. This is expected to lead to higher satisfaction and improved service.

[1311] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1312] Step 1:

[1313] The user enters a question.

[1314] Specific operation: The user inputs a question via text or voice using a touchscreen panel, smart glasses, or head-mounted display within the autonomous vehicle. For example, the user might text or voice ask, "How do I change my destination?" Input and output: The input is the user's text or voice question data, and the output is the preparation of that question data for transmission.

[1315] Step 2:

[1316] The terminal sends the question to the server.

[1317] Specific operation: The terminal sends the entered question data to the server in the form of an HTTP POST request. Input and output: The input is the user's question data, and the output is the HTTP request to the server.

[1318] Step 3:

[1319] The server analyzes the question.

[1320] Specific operation: The server extracts question data from the received HTTP request and passes it to the natural language processing engine. The natural language processing engine parses this question data syntactically and contextually, and extracts key keywords (e.g., "destination," "change"). Input and output: The input is the question data, and the output is the parsed keywords.

[1321] Step 4:

[1322] The server analyzes emotions.

[1323] Specific operation: The server passes the user's voice data and facial image data to the emotion analysis engine, which analyzes the user's emotional state. The results of the voice analysis and facial image analysis are integrated to make a final emotion determination. Input and output: The input is voice data and facial image data, and the output is the determination result of the user's emotional state.

[1324] Step 5:

[1325] The server generates the answer.

[1326] Specific operation: The server uses the analyzed keywords and the user's emotional state to create a prompt for the generative AI model. For example, it generates the prompt "The user is feeling confused. How do I change the destination while the car is driving?" and passes it to the generative AI model (e.g., GPT-3). The generative AI model returns an appropriate answer, which is then formatted. Input and output: The input is keywords and emotional state, and the output is the generated answer.

[1327] Step 6:

[1328] The server sends the answer to the user.

[1329] Specific operation: The server sends the formatted response to the user's terminal as an HTTP response. Input and output: The input is the generated response text, and the output is the HTTP response to the user.

[1330] Step 7:

[1331] The device displays the answer to the user.

[1332] Specific operation: The terminal visually displays the received response on a touchscreen panel or smart glasses. It also plays the response aloud using an audio output device as needed. Input and output: The input is the response data from the server, and the output is the response displayed to the user.

[1333] This makes it possible to quickly provide appropriate feedback tailored to the emotional state of passengers when they ask questions while riding in an autonomous vehicle.

[1334] 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.

[1335] 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.

[1336] 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 robot 414.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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."

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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 to be incorporated by reference.

[1355] The following is further disclosed regarding the embodiments described above.

[1356] (Claim 1)

[1357] A means for the user to input a question,

[1358] Means for sending the aforementioned question to the server,

[1359] The server has means for analyzing the question,

[1360] The server provides means for generating an answer to the question,

[1361] The server provides means for sending the response to the user,

[1362] A system including means for displaying the aforementioned answer to the user.

[1363] (Claim 2)

[1364] The system according to claim 1, which analyzes the aforementioned question using a natural language processing engine.

[1365] (Claim 3)

[1366] The system according to claim 1, which obtains the aforementioned answer from a database or dynamically generates it using an AI model.

[1367] "Example 1"

[1368] (Claim 1)

[1369] A means for the user to input a question,

[1370] Means for sending the aforementioned question to the server,

[1371] The server uses a natural language processing engine to analyze the question,

[1372] The server has means to retrieve an answer from a database or dynamically generate an answer using a generative AI model based on the analysis results of the question.

[1373] The server provides means for formatting the generated response,

[1374] The server provides means for sending the formatted response to the user,

[1375] A system including means for displaying the aforementioned answer to the user.

[1376] (Claim 2)

[1377] The system according to claim 1, which analyzes the aforementioned question using a natural language processing engine.

[1378] (Claim 3)

[1379] The system according to claim 1, wherein the aforementioned answer is obtained from a database or dynamically generated using a generative AI model.

[1380] "Application Example 1"

[1381] (Claim 1)

[1382] A means for the user to input a question,

[1383] Means for sending the aforementioned question to the server,

[1384] The server has means for analyzing the question,

[1385] The server provides means for generating an answer to the question,

[1386] The server provides means for sending the response to the user,

[1387] A means for displaying the aforementioned answer to the user,

[1388] A means of interacting with the user using smart glasses,

[1389] A means for transmitting a question obtained using the smart glasses to the server,

[1390] A system including means for displaying the answer on the display of the smart glasses.

[1391] (Claim 2)

[1392] The system according to claim 1, which analyzes the aforementioned question using a natural language processing engine.

[1393] (Claim 3)

[1394] The system according to claim 1, wherein the aforementioned answer is obtained from a database or dynamically generated using a generative AI model.

[1395] "Example 2 of combining an emotion engine"

[1396] (Claim 1)

[1397] A means for the user to input a question,

[1398] Means for sending the aforementioned question to the server,

[1399] The server has means for analyzing the question,

[1400] The server provides means for generating an answer to the question,

[1401] The server provides means for sending the response to the user,

[1402] A means for displaying the aforementioned answer to the user,

[1403] The server has means for analyzing the user's emotions,

[1404] A means for adjusting the tone and content of the response based on the results of the aforementioned sentiment analysis,

[1405] A system including means for recording the emotional state of the aforementioned user and using that information to inform future responses.

[1406] (Claim 2)

[1407] The system according to claim 1, which analyzes the aforementioned question using a natural language processing engine.

[1408] (Claim 3)

[1409] The system according to claim 1, wherein the aforementioned answer is obtained from a database or dynamically generated using a generative AI model.

[1410] "Application example 2 when combining with an emotional engine"

[1411] (Claim 1)

[1412] A means for the user to input a question,

[1413] Means for sending the aforementioned question to the server,

[1414] The server has means for analyzing the question,

[1415] The server provides means for generating an answer to the question,

[1416] The server provides means for sending the response to the user,

[1417] A means for displaying the aforementioned answer to the user,

[1418] A means of analyzing user emotions,

[1419] A system including means for adjusting the tone and content of the response based on the emotions analyzed by the emotion analysis means.

[1420] (Claim 2)

[1421] The system according to claim 1, which analyzes the aforementioned question using a natural language processing engine.

[1422] (Claim 3)

[1423] The system according to claim 1, wherein the aforementioned answer is obtained from a database or dynamically generated using a generative AI model. [Explanation of Symbols]

[1424] 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 for the user to input a question, Means for sending the aforementioned question to the server, The server has means for analyzing the question, The server provides means for generating an answer to the question, The server provides means for sending the response to the user, A system including means for displaying the aforementioned answer to the user.

2. The system according to claim 1, which analyzes the aforementioned question using a natural language processing engine.

3. The system according to claim 1, wherein the aforementioned answer is obtained from a database or dynamically generated using an AI model.

Images