system

Abstract

We provide the system. [Solution] A means for receiving an inquiry from a terminal and recording that inquiry, A means of generating answers to inquiries, A means for recording the generated response and sending a response to the terminal, A means for exporting the logs of the aforementioned inquiries and responses, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional inquiry system, there is a problem that the consistency of answers is lost when the person in charge changes. Also, since it is difficult to provide 24-hour support, there is a problem that the convenience for users is reduced. Furthermore, the answers may not be specific or may include inaccurate answers, which may reduce user satisfaction.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving and recording inquiries from a terminal, means for generating answers to inquiries, means for recording the generated answers and returning them to the terminal, and means for exporting inquiry and answer logs. The means for generating answers includes means for checking whether the inquiry already exists in the database and, if not, obtaining new information. The means for obtaining new information may also include means for obtaining information from multiple sources. This makes it possible to provide consistent answers 24 hours a day and deliver specific and accurate information to the user.

[0006] An "inquiry" is a question or request for information that a user enters and sends to a system from their device.

[0007] A "terminal" is a computing device used by a user to access a system, and includes personal computers, smartphones, tablets, and other similar devices.

[0008] "Means of recording" refers to mechanisms or functions that save inquiries and responses as logs.

[0009] "Means of generation" refers to the function of generating appropriate responses to received inquiries.

[0010] "Means of responding" refers to the mechanism or function that sends the generated response back to the user's device.

[0011] A "log" is historical data in which a system records each inquiry and its corresponding response.

[0012] "Exporting" refers to a function that outputs logs in the format of an external file or other similar format.

[0013] A "database" is a system or storage medium that systematically stores data such as inquiries and answers, making it searchable and accessible.

[0014] "The means for acquiring information" refers to the function or process of collecting necessary data from information sources outside the system.

[0015] "Information source" refers to a data - providing system such as a website, database, API, etc. that is used to generate new answers.

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. <000×075> [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 multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple 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 language used in the following description will be explained.

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

[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, etc.

[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] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and sends a response back to the terminal, and includes means for exporting inquiry and answer logs.

[0038] System Configuration

[0039] The server consists of modules with the following main functions:

[0040] 1. Query receiving module: The server receives queries sent from the terminal.

[0041] 2. Recording module: The server records queries as logs.

[0042] 3. Response generation module: The server generates an appropriate response to the query.

[0043] 4. Answer Recording Module: Records the generated answers as a log.

[0044] 5. Response module: The server sends the generated response back to the terminal.

[0045] 6. Log Export Module: The server exports logs of queries and responses.

[0046] System processing flow

[0047] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[0048] 2. The device sends this question to the server.

[0049] 3. The server's query receiving module receives the question sent from the terminal.

[0050] 4. The server's logging module logs the questions it receives.

[0051] 5. The server's answer generation module generates an answer to the question. First, it checks if the question already exists in the database, and if it does, it uses that answer. If it does not exist, the server's information retrieval function collects new information and generates an answer.

[0052] 6. The server's response logging module logs the generated responses.

[0053] 7. The server's response module sends the generated response back to the terminal.

[0054] 8. The terminal receives the response sent from the server and displays it to the user.

[0055] 9. If necessary, the server's log export module will export the logs, and the administrator will perform the analysis.

[0056] Specific example

[0057] User example

[0058] A user uses a device to type and send the question "What is the capital of France?". The device sends this question to the server, which receives and logs it. The server checks its database and, finding no data for this question, gathers and logs the new information from the internet: "The capital of France is Paris." It then saves this answer to the log and sends it back to the device. The device displays the received answer to the user. The server can also export the log of this interaction later for administrator review.

[0059] Server Example

[0060] The server receives the question "What is the capital of France?" using the query receiving module. The logging module logs this question, and the answer generation module checks the database. Since the question is not found in the database, the server retrieves new information from the internet and generates the answer "The capital of France is Paris." This answer is logged, and the response module sends a reply to the terminal. Finally, the log export module exports the logs as needed.

[0061] This invention allows users to obtain consistent answers 24 hours a day, and enables servers to efficiently process queries and manage logs.

[0062] The following describes the processing flow.

[0063] Step 1:

[0064] The user uses a device to type and submit a question. For example, the user might ask, "What is the capital of France?"

[0065] Step 2:

[0066] The terminal sends the entered question to the server. During this process, the terminal establishes communication with the server and transfers the query data.

[0067] Step 3:

[0068] The server receives queries sent from the terminal via a query receiving module. The server stores the received queries in temporary memory.

[0069] Step 4:

[0070] The server's logging module records received queries in a log. The log includes the query content and a timestamp.

[0071] Step 5:

[0072] The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query.

[0073] Step 6:

[0074] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server then uses an external information source to obtain the information.

[0075] Step 7:

[0076] The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[0077] Step 8:

[0078] The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[0079] Step 9:

[0080] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[0081] Step 10:

[0082] The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[0083] Step 11:

[0084] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[0085] This processing step allows users to receive consistent answers 24 / 7, and enables the server to efficiently handle queries and manage logs.

[0086] (Example 1)

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

[0088] In conventional systems, providing prompt and appropriate responses to user inquiries required significant human resources, and the means of efficiently managing inquiry content and responses were limited. This contributed to decreased user satisfaction and operational efficiency. Furthermore, the procedures for retrospectively analyzing and evaluating inquiry content and responses were complex and difficult to manage.

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

[0090] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for generating answers to inquiries, means for recording the generated answers and sending them back to the terminal, means for exporting logs of inquiries and answers, means for receiving inquiries and recording them in a log, means for collecting new information related to inquiries from external sources and generating answers, and means for recording the generated answers as logs and sending them back to the terminal. This makes it possible to provide quick and appropriate answers to user inquiries and to efficiently manage and analyze the logs.

[0091] A "terminal" refers to a device used by a user to communicate with a server, and includes, for example, smartphones, personal computers, and tablets.

[0092] A "server" refers to a computer system that processes user inquiries and generates and responds to them.

[0093] An "inquiry" refers to a question or request that a user sends using their device.

[0094] "Answer" refers to the response or information that a server generates in response to a query.

[0095] "Means of recording" refers to functions for saving the content of inquiries and responses in a database or similar system.

[0096] A "log" refers to a collection of historical information about inquiries and responses, including metadata such as timestamps and IP addresses.

[0097] "Exporting" refers to the function of converting log data into an external file format (such as CSV or Excel) and saving it.

[0098] "Information source" refers to data provision systems such as databases or external APIs that are referenced to generate answers.

[0099] A "database" refers to a data management system used to efficiently store and retrieve inquiries and answers.

[0100] "External information sources" refer to knowledge bases and API services on the internet that the server references.

[0101] "Means of collecting information" refers to functions for obtaining necessary data from external information sources.

[0102] This invention is a system in which a user makes an inquiry via a terminal, and a server automatically generates and responds to that inquiry with an appropriate answer. The main components of this system and the details of each process are described below.

[0103] System Configuration

[0104] This system uses the following hardware and software:

[0105] Terminal: A device used by users to enter and submit inquiries. This includes smartphones, personal computers, tablets, etc.

[0106] Server: A computer system for processing queries, generating, recording, and responding to answers.

[0107] Nginx: Web server software that accepts server requests.

[0108] MySQL (registered trademark): A database system that stores logs of queries and responses.

[0109] External APIs: Sources of information for obtaining new data. An example is the Wolfram Alpha API.

[0110] System operation

[0111] 1. The user enters their inquiry.

[0112] The user uses a terminal to enter their inquiry. For example, they might type "What is the capital of France?" and press the send button.

[0113] 2. The device sends the query to the server.

[0114] The terminal securely sends the user's input to the server using the HTTPS protocol.

[0115] 3. The server receives the query.

[0116] The server's query receiving module receives the query sent from the terminal. Nginx accepts this request and passes it to the application server.

[0117] 4. The server records the query.

[0118] The recording module records the queries received by the server in a MySQL database. The recorded data includes the query text, date and time, and source IP address.

[0119] 5. The server generates the answer.

[0120] The answer generation module checks if the query already exists in the database. If it does, it uses that answer; otherwise, it retrieves new information from an external API and generates the answer. For example, it uses the Wolfram Alpha API to generate the answer "The capital of France is Paris."

[0121] 6. The server records the response.

[0122] The recording module logs the generated response to a MySQL database. The recorded data includes the response text, date and time, and the associated query ID.

[0123] 7. The server sends a response back to the terminal.

[0124] The response module sends the generated answer back to the terminal. The response is in JSON format, making it easy for the terminal to parse.

[0125] 8. The device displays the answer.

[0126] The device analyzes the received response and displays it to the user in a visually easy-to-understand format. For example, it might display "The capital of France is Paris." on the screen.

[0127] 9. The server exports the logs.

[0128] If necessary, the log export module exports inquiry and response logs in CSV or Excel format. Administrators can use these logs to analyze the system and analyze user inquiry trends.

[0129] Specific example

[0130] Example of a prompt

[0131] The user types "What is the capital of France?" on their device and sends it. The device sends this question to the server. The server receives this question and logs it. The server then uses its database and an external API to generate the answer "The capital of France is Paris." It logs this answer and sends it back to the device. The device displays the received answer to the user. The server exports the logs for the administrator to analyze.

[0132] The implementation of this system allows users to receive quick and accurate answers, and enables servers to efficiently process inquiries and manage logs.

[0133] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0134] Step 1:

[0135] The user enters the question using their device and presses the submit button.

[0136] Input: The user types "What is the capital of France?" into a text box in a browser or app.

[0137] Output: The terminal converts the user's query into a JSON data packet and creates an HTTPS request.

[0138] Specific action: The user enters a question and clicks the "Submit" button.

[0139] Step 2:

[0140] The terminal sends a question to the server.

[0141] Input: The HTTPS request generated on the device after the user presses the submit button.

[0142] Output: The request received by the server's query receiving module.

[0143] Specific operation: The terminal sends a data packet in JSON format to the server over the network.

[0144] Step 3:

[0145] The server receives the question.

[0146] Input: HTTPS request sent from the terminal.

[0147] Output: Data for recording received questions in the built-in logging system.

[0148] Specific operation: The Nginx server accepts the request and passes it to the application server. The request is parsed within the server, and the question text is extracted.

[0149] Step 4:

[0150] The server's logging module logs the question.

[0151] Input: Text of the received question, date and time, and source IP address.

[0152] Output: Log entries stored in the "Questions" table of the MySQL database.

[0153] Specific action: Execute an SQL insert operation on the database and save the query content.

[0154] Step 5:

[0155] The server's answer generation module generates the answer to the question.

[0156] Input: The question text recorded in the log.

[0157] Output: The corresponding answer text.

[0158] Specific operation: Search the "Existing Questions" table in the database to check if the same query already exists. If it does not exist, use an external API (e.g., Wolfram Alpha API) to gather new information and generate an answer.

[0159] Step 6:

[0160] The server's response logging module logs the generated responses.

[0161] Input: Generated answer text, answer date and time, and related question ID.

[0162] Output: Log entries stored in the "Answers" table of the MySQL database.

[0163] Specific operation: Execute an SQL insert operation on the database and save the response.

[0164] Step 7:

[0165] The server's response module sends the generated answer back to the terminal.

[0166] Input: Generated response data.

[0167] Output: HTTP response containing the answer.

[0168] Specific operation: The server creates an HTTP response and sends it to the terminal, including the response data in JSON format.

[0169] Step 8:

[0170] The terminal receives the response sent from the server and displays it to the user.

[0171] Input: Response data in JSON format sent from the server.

[0172] Output: The response text displayed to the user.

[0173] Specific operation: The device parses the JSON data it receives and displays it to the user in a visually easy-to-understand format (e.g., "The capital of France is Paris.").

[0174] Step 9:

[0175] The server exports the logs.

[0176] Input: Question and answer data recorded in a MySQL database.

[0177] Output: Export file in CSV or Excel format.

[0178] Specific actions: Execute database queries and retrieve log data. Convert the retrieved data to the appropriate file format and save it to the file server.

[0179] (Application Example 1)

[0180] 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."

[0181] While factory staff are required to obtain information quickly and accurately, the current system often results in delayed responses to inquiries. Furthermore, inadequate log management of inquiries makes subsequent analysis difficult, hindering efficiency improvements.

[0182] 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.

[0183] In this invention, the server includes means for receiving and recording an inquiry from a terminal, means for generating a response to the inquiry, means for recording the generated response and sending it back to the terminal, means for exporting the inquiry and response logs, and a response generation module that generates the inquiry content using natural language processing and responds in voice or text. This enables factory staff to obtain information quickly and accurately, and centralized log management contributes to subsequent analysis and efficiency improvements.

[0184] "A means of receiving inquiries from a terminal and recording those inquiries" refers to a function in which a robot receives inquiries from factory staff and saves the content of those inquiries as logs in a database.

[0185] "Means for generating responses to inquiries" refers to a process for generating appropriate responses to received inquiries, and natural language processing techniques can be used for this purpose.

[0186] "Means for recording the generated response and sending a response to the terminal" refers to a function that saves the generated response in a database and then sends that response back to the factory staff in voice or text.

[0187] "Means for exporting the logs of the aforementioned inquiries and answers" refers to a function that exports the recorded inquiry and answer data so that administrators can analyze the data.

[0188] "Means equipped with a response generation module that generate inquiry content using natural language processing and respond in voice or text" refers to a module that uses natural language processing technology to generate a response to an inquiry received and has the function of responding to the factory staff with the result in voice or text.

[0189] This invention relates to a factory robot inquiry response system for enabling factory staff to quickly obtain information. The configuration and operating procedures for specifically implementing this invention are shown below.

[0190] System Configuration

[0191] This system consists of the following main hardware and software components.

[0192] Hardware: Factory robots, voice recognition microphones, touch panel displays

[0193] Software: Flask (Python web framework), JSON (for log storage)

[0194] This section explains the roles of each piece of hardware and software.

[0195] 1. Factory robots: These are central devices for receiving and processing inquiries. Equipped with voice recognition microphones and touch panel displays, they can quickly receive inquiries from staff.

[0196] 2. Voice recognition microphone and touch panel display: These are means for staff to input inquiries. Voice inquiries are received via the voice recognition microphone, and text inquiries are received via the touch panel display.

[0197] 3. Flask application: This software is used for receiving, recording, generating, responding to, and exporting logs of inquiries. This application runs on factory robots.

[0198] 4. JSON format logs: This is a data format for saving records of inquiries and responses.

[0199] System Processing Overview

[0200] 1. Factory staff input inquiries to the robot via a voice recognition microphone or touch panel display.

[0201] 2. The inquiry details are sent to the server via the Flask application and recorded.

[0202] 3. The Flask application uses natural language processing to generate appropriate answers. During this process, it checks if existing information exists in the database; if not, it retrieves new information.

[0203] 4. The generated response is recorded again and sent back to the factory staff via voice or text.

[0204] 5. If necessary, the administrator will retrieve all logs from the export endpoint and use them for later analysis.

[0205] Specific example

[0206] A factory staff member asks the robot by voice, "When is the next production line maintenance?" This voice is sent to the robot via a voice recognition microphone, and the Flask application begins processing. If there is no information in the database about "the next production line maintenance," the robot retrieves an answer from an external source such as the internet, such as "The next production line maintenance is next Monday." The generated answer is recorded again and returned to the factory staff by voice.

[0207] Example of a prompt

[0208] "I'd like to know the next maintenance schedule for the production line. When is the next maintenance scheduled?"

[0209] Thus, the present invention allows factory staff to obtain information quickly and accurately, and the system can efficiently process inquiries and manage logs.

[0210] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0211] Step 1:

[0212] Users input inquiries to factory robots using a voice recognition microphone or touch panel display. The input inquiries are sent to the terminal as text data. For example, a question such as "When is the next maintenance for the production line?"

[0213] Step 2:

[0214] The terminal sends the entered query to the server. The server receives the query content through the Flask application. Here, the query data is converted to JSON format.

[0215] Step 3:

[0216] The server's logging module records the query in the database. This step generates a log containing the query content and a timestamp. For example, "Query: 'When is the next production line maintenance?', Timestamp: '2023-10-05 10:00:00'".

[0217] Step 4:

[0218] The server's answer generation module checks the database to see if an existing answer exists. If no matching answer is found in the database, it retrieves new information from an external source (e.g., the internet or an internal factory system). It then uses natural language processing to generate an appropriate answer. For example, based on the newly collected information, it might generate the answer, "The next production line maintenance is next Monday."

[0219] Step 5:

[0220] The server's response logging module records the generated response in the database. This step generates a log containing the response and the corresponding query ID. For example, "Response: 'The next production line maintenance is next Monday.', Query ID: '123'".

[0221] Step 6:

[0222] The server's response module sends a generated answer back to the terminal. The terminal receives this answer and displays it to the user as audio or text. For example, the answer, "The next production line maintenance is next Monday," might be played back using speech synthesis technology.

[0223] Step 7:

[0224] If necessary, the administrator can export all logs from the server using the log export endpoint. This step compiles the recorded inquiry and response data, making it available for download in JSON or CSV format. For example, files such as "All Inquiry Logs" and "All Response Logs" will be generated.

[0225] 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.

[0226] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and returns them to the terminal. It combines means for exporting inquiry and answer logs with an emotion engine that recognizes user emotions to improve the quality and consistency of responses according to the individual needs of the user.

[0227] System Configuration

[0228] The server consists of modules with the following main functions:

[0229] 1. Query receiving module: The server receives queries sent from the terminal.

[0230] 2. Recording module: The server records queries as logs.

[0231] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[0232] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[0233] 5. Answer Recording Module: Records the generated answers as a log.

[0234] 6. Response module: The server sends the generated response back to the terminal.

[0235] 7. Log Export Module: The server exports logs of queries and responses.

[0236] System processing flow

[0237] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[0238] 2. The device sends this question to the server.

[0239] 3. The server's query receiving module receives the query sent from the terminal. The server stores the received query in temporary memory.

[0240] 4. The server's logging module logs the received queries. The log includes the query content and a timestamp.

[0241] 5. The server's sentiment engine module analyzes the user's sentiment from their text input. For example, it analyzes the text "What is the capital of France?" and determines that the sentiment is neutral.

[0242] 6. The server's emotion engine module logs the analyzed emotion results.

[0243] 7. The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query content.

[0244] 8. If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server uses external information sources to obtain information.

[0245] 9. The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[0246] 10. The server's response generation module adjusts the tone of the generated responses based on the sentiment analysis results. For example, if the user's sentiment is dissatisfied, it will use more polite and friendly language.

[0247] 11. The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[0248] 12. The server's response module sends the generated response back to the terminal. The server re-establishes communication with the terminal and transfers the response data.

[0249] 13. The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[0250] 14. If necessary, the server's log export module will export the logs. The logs will be saved to a file in JSON format or similar.

[0251] Specific example

[0252] User example

[0253] A user uses a terminal to type and send a question expressing dissatisfaction, such as "Why is my order late?". The terminal sends this question to the server, which receives and logs the question, and analyzes the sentiment using the sentiment engine module. The server determines the user's sentiment is dissatisfaction and logs this result. The response generation module checks the database, adjusts the tone when generating an appropriate response, and produces a polite response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days." This response is then saved to the log and sent back to the terminal. The terminal displays the received response to the user. The server can also export the log of this interaction later for administrator review.

[0254] Server Example

[0255] The server receives the question "Why is my order late?" in the query receiving module. The logging module logs this question, and the sentiment engine module analyzes the user's sentiment from the text and logs it. The response generation module checks the database, and if new information is needed, the information retrieval module gathers the information and generates a response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days," adjusting the tone based on the sentiment analysis results. The response logging module logs the generated response, and the response module sends the response back to the terminal. Finally, the log export module exports the logs as needed.

[0256] This invention allows users to receive consistent, emotionally sensitive responses 24 hours a day, and enables servers to efficiently process inquiries and manage logs.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] The user uses a device to type and submit a question. For example, the user might type the question "Why is my order late?"

[0260] Step 2:

[0261] The terminal sends the entered question to the server. The terminal establishes communication to transfer this question to the server.

[0262] Step 3:

[0263] The server's query receiving module receives the question sent from the terminal. The server stores the received question in temporary memory.

[0264] Step 4:

[0265] The server's logging module records the received questions in a log. The log includes the question content and a timestamp.

[0266] Step 5:

[0267] The server's sentiment engine module analyzes the text of the received question to identify the user's sentiment. For example, it can detect dissatisfaction from the text "Why is my order late?".

[0268] Step 6:

[0269] The server's emotion engine module logs the results of the emotion analysis. The type of emotion and its details are also recorded.

[0270] Step 7:

[0271] The server's answer generation module checks the database to see if there is an existing answer to the query. The server searches the database for an answer corresponding to "Why is my order late?".

[0272] Step 8:

[0273] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server communicates with an external information source (e.g., a customer support system) to retrieve the information.

[0274] Step 9:

[0275] The server's response generation module generates an appropriate response based on the newly acquired information. For example, it might generate a response such as, "We apologize for the delay. Your order is expected to arrive within the next 2 days."

[0276] Step 10:

[0277] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. If feelings of dissatisfaction are detected, the response is adjusted to be more polite and friendly.

[0278] Step 11:

[0279] The server's response logging module logs the generated responses, including the response content and a timestamp.

[0280] Step 12:

[0281] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[0282] Step 13:

[0283] The terminal receives the response from the server and displays it to the user. The user can view the response.

[0284] Step 14:

[0285] The server's log export module exports the log as needed. The log is saved in a file in JSON format or the like.

[0286] Through this processing step, the user can obtain a consistent and considerate response at any time of the day. The server can efficiently process inquiries and manage logs.

[0287] [[ID=!16]] (Example 2)

[0288] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0289] When the user makes an inquiry to the system, in the conventional system, the user's emotions are not considered, so a response in an appropriate tone is not given, and there is a problem of a decline in the user experience. Also, there is a lack of means to accurately save and manage the inquiry content and the response content, making subsequent analysis and auditing difficult. Furthermore, a function for quickly and accurately obtaining information from multiple information sources is required.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0291] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for analyzing the content of the inquiry and determining its sentiment, means for generating a response to the inquiry and adjusting the tone of the response based on the sentiment determination result, means for recording the generated response and sending it back to the terminal, and means for exporting the inquiry and response logs. This enables responses in an appropriate tone that takes the user's sentiment into consideration, thereby improving the user experience. Furthermore, accurate storage and management of inquiry and response content facilitates subsequent analysis and auditing. In addition, it becomes possible to quickly obtain information from multiple sources and generate accurate responses.

[0292] A "terminal" is an electronic device used by users to input inquiries and send them to a server.

[0293] An "inquiry" refers to a question or request for information that a user sends to a server through their device.

[0294] "Recording" means saving received inquiries and generated responses to log files or databases.

[0295] "Means" refers to modules or sets of functions used to perform specific functions or processes.

[0296] A "server" is a central computer that receives inquiries from terminals, processes them, generates the necessary responses, and sends them back to the terminals.

[0297] "Means for recording inquiries" refers to devices or programs that have the function of saving received inquiries as logs.

[0298] "Answer" refers to the response from the server to an inquiry.

[0299] "Means of generating responses" refers to the processes or programs used to create appropriate replies based on the content of inquiries.

[0300] The "means for determining emotions" refers to algorithms or engines for analyzing the content of inquiries to infer and determine the emotional state of the user.

[0301] "Adjusting the tone of the response" means appropriately changing the expression and tone of the response based on the emotion determination result.

[0302] The "means for replying to the terminal" refers to communication modules or programs for transmitting the generated response to the user's terminal.

[0303] The "means for exporting logs" refers to devices or programs having the function of outputting the logged inquiry and response logs as external files.

[0304] The "means for obtaining new information" refers to processes or systems for collecting necessary information from external information sources when there is no existing response in the database.

[0305] "Multiple information sources" refers to different information providers such as websites on the Internet, APIs, databases, etc. that the server refers to when collecting information.

[0306] This invention is a system that receives an inquiry from a terminal, records the inquiry, further generates and records a response, and finally makes a reply. Here, how to specifically implement the system will be described.

[0307] Hardware and Software to be Used

[0308] Hardware: Server, User's Terminal

[0309] Software: Emotion Engine (e.g., Natural Language Processing Library), Database (e.g., SQL Database), Log Management System (e.g., ELK Stack), API Client for External Information Acquisition

[0310] Program processing

[0311] This system consists of the following main functional modules:

[0312] 1. Query receiving module: The server receives queries sent from the terminal.

[0313] 2. Recording module: The server records queries as logs.

[0314] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[0315] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[0316] 5. Answer Recording Module: Records the generated answers as a log.

[0317] 6. Response module: The server sends the generated response back to the terminal.

[0318] 7. Log Export Module: The server exports logs of queries and responses.

[0319] Specific data processing and data operations used

[0320] After receiving a query from a terminal, the server stores its contents in temporary memory. The received content is then logged by the recording module. Next, the emotion engine module analyzes the query content and determines the user's emotion. The emotion analysis results are recorded in the log.

[0321] Next, the response generation module checks if an existing response exists in the database. If the relevant response does not exist in the database, it gathers new information from an external source. An information retrieval API client is used in this process. Based on the new information, a response is generated, and its tone is adjusted.

[0322] The generated responses are logged by the response logging module and sent back to the terminal via the response module. If necessary, the administrator can export the log files using the log export module.

[0323] Specific example

[0324] Example 1: General Questions

[0325] The user uses a device to type and send the question, "What is the capital of France?". When the device sends this question to the server, the server receives the question, logs it, and analyzes the sentiment using the sentiment engine module. If the sentiment is determined to be neutral, the result is logged. The answer generation module checks the database and generates the answer, "The capital of France is Paris." The generated answer is saved to the log and sent back to the device. The device displays the received answer to the user.

[0326] Example of a prompt

[0327] A user submitted the question, "What is the highest mountain in the world?" The emotion engine determined the emotion was neutral. Please generate an appropriate answer.

[0328] In this way, the present invention improves the user experience by providing responses that take user emotions into consideration. Furthermore, by recording the inquiry content and the generated response as logs, subsequent analysis and auditing can be easily performed.

[0329] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0330] Step 1:

[0331] The user enters an inquiry on their device and presses the send button. For example, they might enter and send the inquiry "What is the capital of France?". At this time, the input data is sent from the device to the server in text format.

[0332] Step 2:

[0333] The terminal sends user input data to the server. The terminal transfers the input data to the server using an HTTP request. The input data is a text-based query.

[0334] Step 3:

[0335] The server's query receiving module receives queries sent from the terminal. The received data is temporarily stored in temporary memory. The input is the query content, and the output is the act of storing it in temporary memory.

[0336] Step 4:

[0337] The server's logging module records the query details. It creates a log entry containing the received query data and saves it to a log file along with its timestamp. The input is the query details and timestamp, and the output is the saved log entry.

[0338] Step 5:

[0339] The server's emotion engine module analyzes the query content and determines the user's emotion. For example, it analyzes the query "What is the capital of France?" and determines the emotion to be neutral. The input is the query content, and the output is the emotion analysis result.

[0340] Step 6:

[0341] The server logs the sentiment assessment results. The analyzed sentiment results are saved as log entries, and a timestamp is also recorded. The input is the sentiment analysis result and timestamp, and the output is the saved log entry.

[0342] Step 7:

[0343] The server's answer generation module checks the database for existing answers. It performs a database search based on the query "What is the capital of France?". The input is the query, and the output is the search result (no matching answer found).

[0344] Step 8:

[0345] The server collects new information from external sources. It uses an information retrieval module to call an external API (e.g., an encyclopedia API) to obtain "the capital of France." The input is the query, and the output is the retrieved new information.

[0346] Step 9:

[0347] The server's answer generation module generates an answer based on the retrieved information. It generates the answer "The capital of France is Paris." The input is new information, and the output is the generated answer.

[0348] Step 10:

[0349] The server adjusts the tone of the response based on the sentiment analysis results. If the emotion is neutral, no special tone adjustment is made, and the response is used as is. The input is the sentiment analysis results and the generated response, and the output is the final response.

[0350] Step 11:

[0351] The server's response logging module logs the generated responses. The generated responses and their timestamps are saved to a log file. The input is the final response and its timestamp, and the output is the saved log entry.

[0352] Step 12:

[0353] The server's response module sends the generated answer back to the terminal. The generated answer is sent back to the terminal as an HTTP response. The input is the final answer, and the output is the HTTP response containing the answer.

[0354] Step 13:

[0355] The device receives a response from the server and displays it to the user. The device's screen displays the response, "The capital of France is Paris." The input is the HTTP response from the server, and the output is the display result that the user can see.

[0356] Step 14:

[0357] The server exports logs as needed. Based on administrator instructions, inquiry and response logs are exported in JSON format and saved as a file. The input is the log data, and the output is the exported log file.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0360] Traditional customer service systems often suffer from a poor user experience because they only provide simple question-and-answer responses without considering the user's emotions. Furthermore, the inability to provide responses with an appropriate tone that takes emotions into account could negatively impact user satisfaction. Additionally, existing systems have incomplete log export capabilities, preventing administrators from properly managing inquiry history.

[0361] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a terminal and recording the inquiry, means for generating an answer to the inquiry, means for recording the generated answer and sending it back to the terminal, means for exporting the inquiry and answer logs, means including an emotion engine for analyzing the user's emotions associated with the inquiry, and means for adjusting the tone of the answer based on the user's emotions. This enables the provision of consistent, high-quality answers while taking the user's emotions into consideration, thereby improving the user experience. Furthermore, tone adjustment based on the emotion analysis results can increase user satisfaction, and enhanced log export functionality allows administrators to manage inquiry history more appropriately.

[0362] A "terminal" is an electronic device operated by a user, used for inputting inquiries and receiving responses from a server.

[0363] An "inquiry" refers to a question or request entered by a user using their device, and is information sent to the server.

[0364] "To record" means to save received or generated information in a database or log file.

[0365] A "response" is the information provided to the user by a server, which generates a response based on a query.

[0366] "Generating" refers to the process of creating new information or responses.

[0367] A "log" refers to data that records the history of system activity and data.

[0368] "Exporting" is the operation of saving or transferring recorded data as an external file.

[0369] An "emotion engine" is an algorithm or software module used to analyze a user's emotions.

[0370] "Tone" refers to the overall feel and style of the expression and phrasing used in a response.

[0371] "To adjust" means to change or modify existing content based on specific criteria.

[0372] Adjusting the "quality" means appropriately changing the wording and style of the responses based on the user's emotions.

[0373] This invention is a system that recognizes the user's emotions when they use a terminal to make product inquiries or receive customer support within a virtual store, and provides a response with the most appropriate tone based on those emotions. This system consists of the following main modules:

[0374] Main component modules

[0375] 1. Query receiving module: The server receives queries sent from the terminal.

[0376] 2. Recording module: The server records queries as logs.

[0377] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[0378] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[0379] 5. Answer Recording Module: Records the generated answers as a log.

[0380] 6. Response module: The server sends the generated response back to the terminal.

[0381] 7. Log Export Module: The server exports logs of queries and responses.

[0382] Hardware and software configuration

[0383] The server requires a high-performance processor, sufficient memory, and large-capacity storage. The sentiment engine module uses a sentiment analysis engine based on machine learning models. Specifically, it incorporates a sentiment analysis model that utilizes natural language processing (NLP) techniques. For example, it includes a sentiment analysis tool built using the Python programming language. The database stores existing FAQs and past inquiry logs, and new information is obtained by web scraping tools and data acquisition from APIs.

[0384] Program Processing Description

[0385] The server receives inquiries sent from a terminal using the inquiry receiving module, and then records their contents using the logging module. Next, the sentiment engine module analyzes the user's sentiment from the text and stores the results. Subsequently, the response generation module refers to the database to generate an appropriate response, adjusting the tone based on the analysis results. For example, if the user's sentiment is dissatisfaction, a more polite tone will be used to generate the response. The generated response is logged by the response recording module and finally sent back to the terminal via the response module. The logs of the entire process can be exported via the log export module as needed.

[0386] Specific example

[0387] The user uses their device to type and send a question expressing dissatisfaction, such as "Why is my order late?". When the device sends this question to the server, the server receives and logs the question and analyzes the sentiment using its sentiment engine module. The server determines that the user's sentiment is dissatisfaction and generates a polite response: "We apologize for the delay. Your order is expected to arrive within the next 2 days." The server then logs this response and sends it back to the device. The device displays the received response to the user.

[0388] Example of a prompt

[0389] "A user made an emotional inquiry: 'I am not happy with my purchase, can I return it?' Please generate an appropriate and emotionally sensitive response."

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The user enters and submits a query using a terminal. When the user enters the text "Why is my order late?" into the terminal's input field and presses the submit button, the terminal sends the query to the server. The input is the user's text, and the output is the query data sent to the server.

[0393] Step 2:

[0394] The server's query receiving module receives queries sent from the terminal. The server receives the query data and stores it in temporary memory. The input is the query data sent from the terminal, and the output is the query data in temporary memory.

[0395] Step 3:

[0396] The server's logging module logs the queries it receives. The server saves the query content and timestamp to a log file. The input is the query data in temporary memory, and the output is the query content and timestamp recorded in the log file.

[0397] Step 4:

[0398] The server's emotion engine module analyzes the user's emotions from their text input. The server inputs the query into a machine learning model to perform emotion analysis. The input is the query, and the output is the emotion analysis result (e.g., "dissatisfied").

[0399] Step 5:

[0400] The server's emotion engine module logs the emotion analysis results. The server saves the emotion analysis results to a log file. The input is the emotion analysis results, and the output is the emotion analysis results recorded in the log file.

[0401] Step 6:

[0402] The server's answer generation module checks if a matching answer already exists in the database. The server searches the database for the relevant answer. The input is the query, and the output is either the matching answer or no match found in the database.

[0403] Step 7:

[0404] If the server cannot find an answer in the database, it runs an information retrieval module to obtain new information. The server uses external sources to collect new information. The input is the search result with no matches, and the output is the information obtained from the new sources.

[0405] Step 8:

[0406] The server's response generation module generates an appropriate response based on the newly acquired information. The server creates the response "We apologize for the delay. Your order is expected to arrive within the next 2 days." based on the acquired information. The input is the new information, and the output is the generated response.

[0407] Step 9:

[0408] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. Because the sentiment is dissatisfied, the server adds polite language to the generated response. The input is the generated response and the sentiment analysis results, and the output is the response with the adjusted tone.

[0409] Step 10:

[0410] The server's response logging module logs the generated responses. The server saves the response content and timestamp to a log file. The input is the tone-adjusted response, and the output is the response content and timestamp recorded in the log file.

[0411] Step 11:

[0412] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data. The input is the tone-adjusted answer, and the output is the answer sent to the terminal.

[0413] Step 12:

[0414] The terminal receives the response from the server and displays it to the user. The terminal displays the received response to the user. The input is the response data sent from the server, and the output is the response displayed to the user.

[0415] Step 13:

[0416] If necessary, the server's log export module exports the logs. The server exports the log files in JSON format or another suitable format for administrator review. The input is the log file, and the output is the exported log data.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Second Embodiment]

[0421] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and sends a response back to the terminal, and includes means for exporting inquiry and answer logs.

[0434] System Configuration

[0435] The server consists of modules with the following main functions:

[0436] 1. Query receiving module: The server receives queries sent from the terminal.

[0437] 2. Recording module: The server records queries as logs.

[0438] 3. Response generation module: The server generates an appropriate response to the query.

[0439] 4. Answer Recording Module: Records the generated answers as a log.

[0440] 5. Response module: The server sends the generated response back to the terminal.

[0441] 6. Log Export Module: The server exports logs of queries and responses.

[0442] System processing flow

[0443] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[0444] 2. The device sends this question to the server.

[0445] 3. The server's query receiving module receives the question sent from the terminal.

[0446] 4. The server's logging module logs the questions it receives.

[0447] 5. The server's answer generation module generates an answer to the question. First, it checks if the question already exists in the database, and if it does, it uses that answer. If it does not exist, the server's information retrieval function collects new information and generates an answer.

[0448] 6. The server's response logging module logs the generated responses.

[0449] 7. The server's response module sends the generated response back to the terminal.

[0450] 8. The terminal receives the response sent from the server and displays it to the user.

[0451] 9. If necessary, the server's log export module will export the logs, and the administrator will perform the analysis.

[0452] Specific example

[0453] User example

[0454] A user uses a device to type and send the question "What is the capital of France?". The device sends this question to the server, which receives and logs it. The server checks its database and, finding no data for this question, gathers and logs the new information from the internet: "The capital of France is Paris." It then saves this answer to the log and sends it back to the device. The device displays the received answer to the user. The server can also export the log of this interaction later for administrator review.

[0455] Server Example

[0456] The server receives the question "What is the capital of France?" using the query receiving module. The logging module logs this question, and the answer generation module checks the database. Since the question is not found in the database, the server retrieves new information from the internet and generates the answer "The capital of France is Paris." This answer is logged, and the response module sends a reply to the terminal. Finally, the log export module exports the logs as needed.

[0457] This invention allows users to obtain consistent answers 24 hours a day, and enables servers to efficiently process queries and manage logs.

[0458] The following describes the processing flow.

[0459] Step 1:

[0460] The user uses a device to type and submit a question. For example, the user might ask, "What is the capital of France?"

[0461] Step 2:

[0462] The terminal sends the entered question to the server. During this process, the terminal establishes communication with the server and transfers the query data.

[0463] Step 3:

[0464] The server receives queries sent from the terminal via a query receiving module. The server then stores the received queries in temporary memory.

[0465] Step 4:

[0466] The server's logging module records received queries in a log. The log includes the query content and a timestamp.

[0467] Step 5:

[0468] The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query.

[0469] Step 6:

[0470] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server then uses an external information source to obtain the information.

[0471] Step 7:

[0472] The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[0473] Step 8:

[0474] The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[0475] Step 9:

[0476] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[0477] Step 10:

[0478] The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[0479] Step 11:

[0480] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[0481] This processing step allows users to receive consistent answers 24 / 7, and enables the server to efficiently handle queries and manage logs.

[0482] (Example 1)

[0483] 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."

[0484] In conventional systems, providing prompt and appropriate responses to user inquiries required significant human resources, and the means of efficiently managing inquiry content and responses were limited. This contributed to decreased user satisfaction and operational efficiency. Furthermore, the procedures for retrospectively analyzing and evaluating inquiry content and responses were complex and difficult to manage.

[0485] 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.

[0486] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for generating answers to inquiries, means for recording the generated answers and sending them back to the terminal, means for exporting logs of inquiries and answers, means for receiving inquiries and recording them in a log, means for collecting new information related to inquiries from external sources and generating answers, and means for recording the generated answers as logs and sending them back to the terminal. This makes it possible to provide quick and appropriate answers to user inquiries and to efficiently manage and analyze the logs.

[0487] A "terminal" refers to a device used by a user to communicate with a server, and includes, for example, smartphones, personal computers, and tablets.

[0488] A "server" refers to a computer system that processes user inquiries and generates and responds to them.

[0489] An "inquiry" refers to a question or request that a user sends using their device.

[0490] "Answer" refers to the response or information that a server generates in response to a query.

[0491] "Means of recording" refers to functions for saving the content of inquiries and responses in a database or similar system.

[0492] A "log" refers to a collection of historical information about inquiries and responses, including metadata such as timestamps and IP addresses.

[0493] "Exporting" refers to the function of converting log data into an external file format (such as CSV or Excel) and saving it.

[0494] "Information source" refers to data provision systems such as databases or external APIs that are referenced to generate answers.

[0495] A "database" refers to a data management system used to efficiently store and retrieve inquiries and answers.

[0496] "External information sources" refer to knowledge bases and API services on the internet that the server references.

[0497] "Means of collecting information" refers to functions for obtaining necessary data from external information sources.

[0498] This invention is a system in which a user makes an inquiry via a terminal, and a server automatically generates and responds to that inquiry with an appropriate answer. The main components of this system and the details of each process are described below.

[0499] System Configuration

[0500] This system uses the following hardware and software:

[0501] Terminal: A device used by users to enter and submit inquiries. This includes smartphones, personal computers, tablets, etc.

[0502] Server: A computer system for processing queries, generating, recording, and responding to answers.

[0503] Nginx: Web server software that accepts server requests.

[0504] MySQL: A database system that stores logs of queries and responses.

[0505] External APIs: Sources of information for obtaining new data. An example is the Wolfram Alpha API.

[0506] System operation

[0507] 1. The user enters their inquiry.

[0508] The user uses a terminal to enter their inquiry. For example, they might type "What is the capital of France?" and press the send button.

[0509] 2. The device sends the query to the server.

[0510] The terminal securely sends the user's input to the server using the HTTPS protocol.

[0511] 3. The server receives the query.

[0512] The server's query receiving module receives the query sent from the terminal. Nginx accepts this request and passes it to the application server.

[0513] 4. The server records the query.

[0514] The recording module records the queries received by the server in a MySQL database. The recorded data includes the query text, date and time, and source IP address.

[0515] 5. The server generates the answer.

[0516] The answer generation module checks if the query already exists in the database. If it does, it uses that answer; otherwise, it retrieves new information from an external API and generates the answer. For example, it uses the Wolfram Alpha API to generate the answer "The capital of France is Paris."

[0517] 6. The server records the response.

[0518] The recording module logs the generated response to a MySQL database. The recorded data includes the response text, date and time, and the associated query ID.

[0519] 7. The server sends a response back to the terminal.

[0520] The response module sends the generated answer back to the terminal. The response is in JSON format, making it easy for the terminal to parse.

[0521] 8. The device displays the answer.

[0522] The device analyzes the received response and displays it to the user in a visually easy-to-understand format. For example, it might display "The capital of France is Paris." on the screen.

[0523] 9. The server exports the logs.

[0524] If necessary, the log export module exports inquiry and response logs in CSV or Excel format. Administrators can use these logs to analyze the system and analyze user inquiry trends.

[0525] Specific example

[0526] Example of a prompt

[0527] The user types "What is the capital of France?" on their device and sends it. The device sends this question to the server. The server receives this question and logs it. The server then uses its database and an external API to generate the answer "The capital of France is Paris." It logs this answer and sends it back to the device. The device displays the received answer to the user. The server exports the logs for the administrator to analyze.

[0528] The implementation of this system allows users to receive quick and accurate answers, and enables servers to efficiently process inquiries and manage logs.

[0529] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0530] Step 1:

[0531] The user enters the question using their device and presses the submit button.

[0532] Input: The user types "What is the capital of France?" into a text box in a browser or app.

[0533] Output: The terminal converts the user's query into a JSON data packet and creates an HTTPS request.

[0534] Specific action: The user enters a question and clicks the "Submit" button.

[0535] Step 2:

[0536] The terminal sends a question to the server.

[0537] Input: The HTTPS request generated on the device after the user presses the submit button.

[0538] Output: The request received by the server's query receiving module.

[0539] Specific operation: The terminal sends a data packet in JSON format to the server over the network.

[0540] Step 3:

[0541] The server receives the question.

[0542] Input: HTTPS request sent from the terminal.

[0543] Output: Data for recording received questions in the built-in logging system.

[0544] Specific operation: The Nginx server accepts the request and passes it to the application server. The request is parsed within the server, and the question text is extracted.

[0545] Step 4:

[0546] The server's logging module logs the question.

[0547] Input: Text of the received question, date and time, and source IP address.

[0548] Output: Log entries stored in the "Questions" table of the MySQL database.

[0549] Specific action: Execute an SQL insert operation on the database and save the query content.

[0550] Step 5:

[0551] The server's answer generation module generates the answer to the question.

[0552] Input: The question text recorded in the log.

[0553] Output: The corresponding answer text.

[0554] Specific operation: Search the "Existing Questions" table in the database to check if the same query already exists. If it does not exist, use an external API (e.g., Wolfram Alpha API) to gather new information and generate an answer.

[0555] Step 6:

[0556] The server's response logging module logs the generated responses.

[0557] Input: Generated answer text, answer date and time, and related question ID.

[0558] Output: Log entries stored in the "Answers" table of the MySQL database.

[0559] Specific operation: Execute an SQL insert operation on the database and save the response.

[0560] Step 7:

[0561] The server's response module sends the generated answer back to the terminal.

[0562] Input: Generated response data.

[0563] Output: HTTP response containing the answer.

[0564] Specific operation: The server creates an HTTP response and sends it to the terminal, including the response data in JSON format.

[0565] Step 8:

[0566] The terminal receives the response sent from the server and displays it to the user.

[0567] Input: Response data in JSON format sent from the server.

[0568] Output: The response text displayed to the user.

[0569] Specific operation: The device parses the JSON data it receives and displays it to the user in a visually easy-to-understand format (e.g., "The capital of France is Paris.").

[0570] Step 9:

[0571] The server exports the logs.

[0572] Input: Question and answer data recorded in a MySQL database.

[0573] Output: Export file in CSV or Excel format.

[0574] Specific actions: Execute database queries and retrieve log data. Convert the retrieved data to the appropriate file format and save it to the file server.

[0575] (Application Example 1)

[0576] 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."

[0577] While factory staff are required to obtain information quickly and accurately, the current system often results in delayed responses to inquiries. Furthermore, inadequate log management of inquiries makes subsequent analysis difficult, hindering efficiency improvements.

[0578] 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.

[0579] In this invention, the server includes means for receiving and recording an inquiry from a terminal, means for generating a response to the inquiry, means for recording the generated response and sending it back to the terminal, means for exporting the inquiry and response logs, and a response generation module that generates the inquiry content using natural language processing and responds in voice or text. This enables factory staff to obtain information quickly and accurately, and centralized log management contributes to subsequent analysis and efficiency improvements.

[0580] "A means of receiving inquiries from a terminal and recording those inquiries" refers to a function in which a robot receives inquiries from factory staff and saves the content of those inquiries as logs in a database.

[0581] "Means for generating responses to inquiries" refers to a process for generating appropriate responses to received inquiries, and natural language processing techniques can be used for this purpose.

[0582] "Means for recording the generated response and sending a response to the terminal" refers to a function that saves the generated response in a database and then sends that response back to the factory staff in voice or text.

[0583] "Means for exporting the logs of the aforementioned inquiries and answers" refers to a function that exports the recorded inquiry and answer data so that administrators can analyze the data.

[0584] "A means of generating a response module that generates inquiry content using natural language processing and responds in voice or text" refers to a module that uses natural language processing technology to generate a response to an inquiry received and has the function of responding to the factory staff with the result in voice or text.

[0585] This invention relates to a factory robot inquiry response system for enabling factory staff to quickly obtain information. The configuration and operating procedures for specifically implementing this invention are shown below.

[0586] System Configuration

[0587] This system consists of the following main hardware and software components.

[0588] Hardware: Factory robots, voice recognition microphones, touch panel displays

[0589] Software: Flask (Python web framework), JSON (for log storage)

[0590] This section explains the roles of each piece of hardware and software.

[0591] 1. Factory robots: These are central devices for receiving and processing inquiries. Equipped with voice recognition microphones and touch panel displays, they can quickly receive inquiries from staff.

[0592] 2. Voice recognition microphone and touch panel display: These are means for staff to input inquiries. Voice inquiries are received via the voice recognition microphone, and text inquiries are received via the touch panel display.

[0593] 3. Flask application: This software is used for receiving, recording, generating, responding to, and exporting logs of inquiries. This application runs on factory robots.

[0594] 4. JSON format logs: This is a data format for saving records of inquiries and responses.

[0595] System Processing Overview

[0596] 1. Factory staff input inquiries to the robot via a voice recognition microphone or touch panel display.

[0597] 2. The inquiry details are sent to the server via the Flask application and recorded.

[0598] 3. The Flask application uses natural language processing to generate appropriate answers. During this process, it checks if existing information exists in the database; if not, it retrieves new information.

[0599] 4. The generated response is recorded again and sent back to the factory staff via voice or text.

[0600] 5. If necessary, the administrator will retrieve all logs from the export endpoint and use them for later analysis.

[0601] Specific example

[0602] A factory staff member asks the robot by voice, "When is the next production line maintenance?" This voice is sent to the robot via a voice recognition microphone, and the Flask application begins processing. If there is no information in the database about "the next production line maintenance," the robot retrieves an answer from an external source such as the internet, such as "The next production line maintenance is next Monday." The generated answer is recorded again and returned to the factory staff by voice.

[0603] Example of a prompt

[0604] "I'd like to know the next maintenance schedule for the production line. When is the next maintenance scheduled?"

[0605] Thus, the present invention allows factory staff to obtain information quickly and accurately, and the system can efficiently process inquiries and manage logs.

[0606] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0607] Step 1:

[0608] Users input inquiries to factory robots using a voice recognition microphone or touch panel display. The input inquiries are sent to the terminal as text data. For example, a question such as "When is the next maintenance for the production line?"

[0609] Step 2:

[0610] The terminal sends the entered query to the server. The server receives the query content through the Flask application. Here, the query data is converted to JSON format.

[0611] Step 3:

[0612] The server's logging module records the query in the database. This step generates a log containing the query content and a timestamp. For example, "Query: 'When is the next production line maintenance?', Timestamp: '2023-10-05 10:00:00'".

[0613] Step 4:

[0614] The server's answer generation module checks the database to see if an existing answer exists. If no matching answer is found in the database, it retrieves new information from an external source (e.g., the internet or an internal factory system). It then uses natural language processing to generate an appropriate answer. For example, based on the newly collected information, it might generate the answer, "The next production line maintenance is next Monday."

[0615] Step 5:

[0616] The server's response logging module records the generated response in the database. This step generates a log containing the response and the corresponding query ID. For example, "Response: 'The next production line maintenance is next Monday.', Query ID: '123'".

[0617] Step 6:

[0618] The server's response module sends a generated answer back to the terminal. The terminal receives this answer and displays it to the user as audio or text. For example, the answer, "The next production line maintenance is next Monday," might be played back using speech synthesis technology.

[0619] Step 7:

[0620] If necessary, the administrator can export all logs from the server using the log export endpoint. This step compiles the recorded inquiry and response data, making it available for download in JSON or CSV format. For example, files such as "All Inquiry Logs" and "All Response Logs" will be generated.

[0621] 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.

[0622] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and returns them to the terminal. It combines means for exporting inquiry and answer logs with an emotion engine that recognizes user emotions to improve the quality and consistency of responses according to the individual needs of the user.

[0623] System Configuration

[0624] The server consists of modules with the following main functions:

[0625] 1. Query receiving module: The server receives queries sent from the terminal.

[0626] 2. Recording module: The server records queries as logs.

[0627] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[0628] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[0629] 5. Answer Recording Module: Records the generated answers as a log.

[0630] 6. Response module: The server sends the generated response back to the terminal.

[0631] 7. Log Export Module: The server exports logs of queries and responses.

[0632] System processing flow

[0633] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[0634] 2. The device sends this question to the server.

[0635] 3. The server's query receiving module receives the query sent from the terminal. The server stores the received query in temporary memory.

[0636] 4. The server's logging module logs the received queries. The log includes the query content and a timestamp.

[0637] 5. The server's sentiment engine module analyzes the user's sentiment from their text input. For example, it analyzes the text "What is the capital of France?" and determines that the sentiment is neutral.

[0638] 6. The server's emotion engine module logs the analyzed emotion results.

[0639] 7. The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query content.

[0640] 8. If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server uses external information sources to obtain information.

[0641] 9. The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[0642] 10. The server's response generation module adjusts the tone of the generated responses based on the sentiment analysis results. For example, if the user's sentiment is dissatisfied, it will use more polite and friendly language.

[0643] 11. The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[0644] 12. The server's response module sends the generated response back to the terminal. The server re-establishes communication with the terminal and transfers the response data.

[0645] 13. The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[0646] 14. If necessary, the server's log export module will export the logs. The logs will be saved to a file in JSON format or similar.

[0647] Specific example

[0648] User example

[0649] A user uses a terminal to type and send a question expressing dissatisfaction, such as "Why is my order late?". The terminal sends this question to the server, which receives and logs the question, and analyzes the sentiment using the sentiment engine module. The server determines the user's sentiment is dissatisfaction and logs this result. The response generation module checks the database, adjusts the tone when generating an appropriate response, and produces a polite response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days." This response is then saved to the log and sent back to the terminal. The terminal displays the received response to the user. The server can also export the log of this interaction later for administrator review.

[0650] Server Example

[0651] The server receives the question "Why is my order late?" in the query receiving module. The logging module logs this question, and the sentiment engine module analyzes the user's sentiment from the text and logs it. The response generation module checks the database, and if new information is needed, the information retrieval module gathers the information and generates a response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days," adjusting the tone based on the sentiment analysis results. The response logging module logs the generated response, and the response module sends the response back to the terminal. Finally, the log export module exports the logs as needed.

[0652] This invention allows users to receive consistent, emotionally sensitive responses 24 hours a day, and enables servers to efficiently process inquiries and manage logs.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] The user uses a device to type and submit a question. For example, the user might type the question "Why is my order late?"

[0656] Step 2:

[0657] The terminal sends the entered question to the server. The terminal establishes communication to transfer this question to the server.

[0658] Step 3:

[0659] The server's query receiving module receives the question sent from the terminal. The server stores the received question in temporary memory.

[0660] Step 4:

[0661] The server's logging module records the received questions in a log. The log includes the question content and a timestamp.

[0662] Step 5:

[0663] The server's sentiment engine module analyzes the text of the received question to identify the user's sentiment. For example, it can detect dissatisfaction from the text "Why is my order late?".

[0664] Step 6:

[0665] The server's emotion engine module logs the results of the emotion analysis. The type of emotion and its details are also recorded.

[0666] Step 7:

[0667] The server's answer generation module checks the database to see if there is an existing answer to the query. The server searches the database for an answer corresponding to "Why is my order late?".

[0668] Step 8:

[0669] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server communicates with an external information source (e.g., a customer support system) to retrieve the information.

[0670] Step 9:

[0671] The server's response generation module generates an appropriate response based on the newly acquired information. For example, it might generate a response such as, "We apologize for the delay. Your order is expected to arrive within the next 2 days."

[0672] Step 10:

[0673] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. If feelings of dissatisfaction are detected, the response is adjusted to be more polite and friendly.

[0674] Step 11:

[0675] The server's response logging module logs the generated responses, including the response content and a timestamp.

[0676] Step 12:

[0677] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[0678] Step 13:

[0679] The device receives the response from the server and displays it to the user. The user can then verify the response.

[0680] Step 14:

[0681] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[0682] This processing step ensures that users receive consistent, emotionally sensitive responses 24 / 7. The server can efficiently process queries and manage logs.

[0683] (Example 2)

[0684] 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".

[0685] In traditional systems, when users made inquiries, the lack of consideration for user emotions resulted in inappropriate responses and a poor user experience. Furthermore, there was a lack of means to accurately store and manage inquiry and response content, making subsequent analysis and auditing difficult. Additionally, there is a need for functionality to quickly and accurately retrieve information from multiple sources.

[0686] 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.

[0687] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for analyzing the content of the inquiry and determining its sentiment, means for generating a response to the inquiry and adjusting the tone of the response based on the sentiment determination result, means for recording the generated response and sending it back to the terminal, and means for exporting the inquiry and response logs. This enables responses in an appropriate tone that takes the user's sentiment into consideration, thereby improving the user experience. Furthermore, accurate storage and management of inquiry and response content facilitates subsequent analysis and auditing. In addition, it becomes possible to quickly obtain information from multiple sources and generate accurate responses.

[0688] A "terminal" is an electronic device used by users to input inquiries and send them to a server.

[0689] An "inquiry" refers to a question or request for information that a user sends to a server through their device.

[0690] "Recording" means saving received inquiries and generated responses to log files or databases.

[0691] "Means" refers to modules or sets of functions used to perform specific functions or processes.

[0692] A "server" is a central computer that receives inquiries from terminals, processes them, generates the necessary responses, and sends them back to the terminals.

[0693] "Means for recording inquiries" refers to devices or programs that have the function of saving received inquiries as logs.

[0694] "Answer" refers to the response from the server to an inquiry.

[0695] "Means of generating responses" refers to the processes or programs used to create appropriate replies based on the content of inquiries.

[0696] "Means for determining emotions" refers to algorithms or engines that analyze the content of inquiries to infer and determine the emotional state of the user.

[0697] "Adjusting the tone of the response" means appropriately changing the wording and tone of the response based on the emotion assessment results.

[0698] "Means of responding to the terminal" refers to communication modules or programs used to send the generated response to the user's terminal.

[0699] "Means for exporting logs" refers to devices or programs that have the function of outputting recorded inquiry and response logs as external files.

[0700] "Means of acquiring new information" refers to the processes and systems for collecting necessary information from external sources when there is no existing answer in the database.

[0701] "Multiple information sources" refers to different sources of information that a server references when collecting information, such as websites, APIs, and databases on the internet.

[0702] This invention is a system that receives inquiries from a terminal, records those inquiries, generates and records answers, and finally provides a response. This section explains how to implement this system in detail.

[0703] Hardware and software to be used

[0704] Hardware: Server, user terminal

[0705] Software: Sentiment engine (e.g., natural language processing library), database (e.g., SQL database), log management system (e.g., ELK Stack), API client for retrieving external information.

[0706] Program processing

[0707] This system consists of the following main functional modules:

[0708] 1. Query receiving module: The server receives queries sent from the terminal.

[0709] 2. Recording module: The server records queries as logs.

[0710] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[0711] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[0712] 5. Answer Recording Module: Records the generated answers as a log.

[0713] 6. Response module: The server sends the generated response back to the terminal.

[0714] 7. Log Export Module: The server exports logs of queries and responses.

[0715] Specific data processing and data operations used

[0716] After receiving a query from a terminal, the server stores its contents in temporary memory. The received content is then logged by the recording module. Next, the emotion engine module analyzes the query content and determines the user's emotion. The emotion analysis results are recorded in the log.

[0717] Next, the response generation module checks if an existing response exists in the database. If the relevant response does not exist in the database, it gathers new information from an external source. An information retrieval API client is used in this process. Based on the new information, a response is generated, and its tone is adjusted.

[0718] The generated responses are logged by the response logging module and sent back to the terminal via the response module. If necessary, the administrator can export the log files using the log export module.

[0719] Specific example

[0720] Example 1: General Questions

[0721] The user uses a device to type and send the question, "What is the capital of France?". When the device sends this question to the server, the server receives the question, logs it, and analyzes the sentiment using the sentiment engine module. If the sentiment is determined to be neutral, the result is logged. The answer generation module checks the database and generates the answer, "The capital of France is Paris." The generated answer is saved to the log and sent back to the device. The device displays the received answer to the user.

[0722] Example of a prompt

[0723] A user submitted the question, "What is the highest mountain in the world?" The emotion engine determined the emotion was neutral. Please generate an appropriate answer.

[0724] In this way, the present invention improves the user experience by providing responses that take user emotions into consideration. Furthermore, by recording the inquiry content and the generated response as logs, subsequent analysis and auditing can be easily performed.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] The user enters an inquiry on their device and presses the send button. For example, they might enter and send the inquiry "What is the capital of France?". At this time, the input data is sent from the device to the server in text format.

[0728] Step 2:

[0729] The terminal sends user input data to the server. The terminal transfers the input data to the server using an HTTP request. The input data is a text-based query.

[0730] Step 3:

[0731] The server's query receiving module receives queries sent from the terminal. The received data is temporarily stored in temporary memory. The input is the query content, and the output is the act of storing it in temporary memory.

[0732] Step 4:

[0733] The server's logging module records the query details. It creates a log entry containing the received query data and saves it to a log file along with its timestamp. The input is the query details and timestamp, and the output is the saved log entry.

[0734] Step 5:

[0735] The server's emotion engine module analyzes the query content and determines the user's emotion. For example, it analyzes the query "What is the capital of France?" and determines the emotion to be neutral. The input is the query content, and the output is the emotion analysis result.

[0736] Step 6:

[0737] The server logs the sentiment assessment results. The analyzed sentiment results are saved as log entries, and a timestamp is also recorded. The input is the sentiment analysis result and timestamp, and the output is the saved log entry.

[0738] Step 7:

[0739] The server's answer generation module checks the database for existing answers. It performs a database search based on the query "What is the capital of France?". The input is the query, and the output is the search result (no matching answer found).

[0740] Step 8:

[0741] The server collects new information from external sources. It uses an information retrieval module to call an external API (e.g., an encyclopedia API) to obtain "the capital of France." The input is the query, and the output is the retrieved new information.

[0742] Step 9:

[0743] The server's answer generation module generates an answer based on the retrieved information. It generates the answer "The capital of France is Paris." The input is new information, and the output is the generated answer.

[0744] Step 10:

[0745] The server adjusts the tone of the response based on the sentiment analysis results. If the emotion is neutral, no special tone adjustment is made, and the response is used as is. The input is the sentiment analysis results and the generated response, and the output is the final response.

[0746] Step 11:

[0747] The server's response logging module logs the generated responses. The generated responses and their timestamps are saved to a log file. The input is the final response and its timestamp, and the output is the saved log entry.

[0748] Step 12:

[0749] The server's response module sends the generated answer back to the terminal. The generated answer is sent back to the terminal as an HTTP response. The input is the final answer, and the output is the HTTP response containing the answer.

[0750] Step 13:

[0751] The device receives a response from the server and displays it to the user. The device's screen displays the response, "The capital of France is Paris." The input is the HTTP response from the server, and the output is the display result that the user can see.

[0752] Step 14:

[0753] The server exports logs as needed. Based on administrator instructions, inquiry and response logs are exported in JSON format and saved as a file. The input is the log data, and the output is the exported log file.

[0754] (Application Example 2)

[0755] 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."

[0756] Traditional customer service systems often suffer from a poor user experience because they only provide simple question-and-answer responses without considering the user's emotions. Furthermore, the inability to provide responses with an appropriate tone that takes emotions into account could negatively impact user satisfaction. Additionally, existing systems have incomplete log export capabilities, preventing administrators from properly managing inquiry history.

[0757] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a terminal and recording the inquiry, means for generating an answer to the inquiry, means for recording the generated answer and sending it back to the terminal, means for exporting the inquiry and answer logs, means including an emotion engine for analyzing the user's emotions associated with the inquiry, and means for adjusting the tone of the answer based on the user's emotions. This enables the provision of consistent, high-quality answers while taking the user's emotions into consideration, thereby improving the user experience. Furthermore, tone adjustment based on the emotion analysis results can increase user satisfaction, and enhanced log export functionality allows administrators to manage inquiry history more appropriately.

[0758] A "terminal" is an electronic device operated by a user, used for inputting inquiries and receiving responses from a server.

[0759] An "inquiry" refers to a question or request entered by a user using their device, and is information sent to the server.

[0760] "To record" means to save received or generated information in a database or log file.

[0761] A "response" is the information provided to the user by a server, which generates a response based on a query.

[0762] "Generating" refers to the process of creating new information or responses.

[0763] A "log" refers to data that records the history of system activity and data.

[0764] "Exporting" is the operation of saving or transferring recorded data as an external file.

[0765] An "emotion engine" is an algorithm or software module used to analyze a user's emotions.

[0766] "Tone" refers to the overall feel and style of the expression and phrasing used in a response.

[0767] "To adjust" means to change or modify existing content based on specific criteria.

[0768] Adjusting the "quality" means appropriately changing the wording and style of the responses based on the user's emotions.

[0769] This invention is a system that recognizes the user's emotions when they use a terminal to make product inquiries or receive customer support within a virtual store, and provides a response with the most appropriate tone based on those emotions. This system consists of the following main modules:

[0770] Main component modules

[0771] 1. Query receiving module: The server receives queries sent from the terminal.

[0772] 2. Recording module: The server records queries as logs.

[0773] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[0774] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[0775] 5. Answer Recording Module: Records the generated answers as a log.

[0776] 6. Response module: The server sends the generated response back to the terminal.

[0777] 7. Log Export Module: The server exports logs of queries and responses.

[0778] Hardware and software configuration

[0779] The server requires a high-performance processor, sufficient memory, and large-capacity storage. The sentiment engine module uses a sentiment analysis engine based on machine learning models. Specifically, it incorporates a sentiment analysis model that utilizes natural language processing (NLP) techniques. For example, it includes a sentiment analysis tool built using the Python programming language. The database stores existing FAQs and past inquiry logs, and new information is obtained by web scraping tools and data acquisition from APIs.

[0780] Program Processing Description

[0781] The server receives inquiries sent from a terminal using the inquiry receiving module, and then records their contents using the logging module. Next, the sentiment engine module analyzes the user's sentiment from the text and stores the results. Subsequently, the response generation module refers to the database to generate an appropriate response, adjusting the tone based on the analysis results. For example, if the user's sentiment is dissatisfaction, a more polite tone will be used to generate the response. The generated response is logged by the response recording module and finally sent back to the terminal via the response module. The logs of the entire process can be exported via the log export module as needed.

[0782] Specific example

[0783] The user uses their device to type and send a question expressing dissatisfaction, such as "Why is my order late?". When the device sends this question to the server, the server receives and logs the question and analyzes the sentiment using its sentiment engine module. The server determines that the user's sentiment is dissatisfaction and generates a polite response: "We apologize for the delay. Your order is expected to arrive within the next 2 days." The server then logs this response and sends it back to the device. The device displays the received response to the user.

[0784] Example of a prompt

[0785] "A user made an emotional inquiry: 'I am not happy with my purchase, can I return it?' Please generate an appropriate and emotionally sensitive response."

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The user enters and submits a query using a terminal. When the user enters the text "Why is my order late?" into the terminal's input field and presses the submit button, the terminal sends the query to the server. The input is the user's text, and the output is the query data sent to the server.

[0789] Step 2:

[0790] The server's query receiving module receives queries sent from the terminal. The server receives the query data and stores it in temporary memory. The input is the query data sent from the terminal, and the output is the query data in temporary memory.

[0791] Step 3:

[0792] The server's logging module logs the queries it receives. The server saves the query content and timestamp to a log file. The input is the query data in temporary memory, and the output is the query content and timestamp recorded in the log file.

[0793] Step 4:

[0794] The server's emotion engine module analyzes the user's emotions from their text input. The server inputs the query into a machine learning model to perform emotion analysis. The input is the query, and the output is the emotion analysis result (e.g., "dissatisfied").

[0795] Step 5:

[0796] The server's emotion engine module logs the emotion analysis results. The server saves the emotion analysis results to a log file. The input is the emotion analysis results, and the output is the emotion analysis results recorded in the log file.

[0797] Step 6:

[0798] The server's answer generation module checks if a matching answer already exists in the database. The server searches the database for the relevant answer. The input is the query, and the output is either the matching answer or no match found in the database.

[0799] Step 7:

[0800] If the server cannot find an answer in the database, it runs an information retrieval module to obtain new information. The server uses external sources to collect new information. The input is the search result with no matches, and the output is the information obtained from the new sources.

[0801] Step 8:

[0802] The server's response generation module generates an appropriate response based on the newly acquired information. The server creates the response "We apologize for the delay. Your order is expected to arrive within the next 2 days." based on the acquired information. The input is the new information, and the output is the generated response.

[0803] Step 9:

[0804] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. Because the sentiment is dissatisfied, the server adds polite language to the generated response. The input is the generated response and the sentiment analysis results, and the output is the response with the adjusted tone.

[0805] Step 10:

[0806] The server's response logging module logs the generated responses. The server saves the response content and timestamp to a log file. The input is the tone-adjusted response, and the output is the response content and timestamp recorded in the log file.

[0807] Step 11:

[0808] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data. The input is the tone-adjusted answer, and the output is the answer sent to the terminal.

[0809] Step 12:

[0810] The terminal receives the response from the server and displays it to the user. The terminal displays the received response to the user. The input is the response data sent from the server, and the output is the response displayed to the user.

[0811] Step 13:

[0812] If necessary, the server's log export module exports the logs. The server exports the log files in JSON format or another suitable format for administrator review. The input is the log file, and the output is the exported log data.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] [Third Embodiment]

[0817] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0818] 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.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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".

[0829] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and sends a response back to the terminal, and includes means for exporting inquiry and answer logs.

[0830] System Configuration

[0831] The server consists of modules with the following main functions:

[0832] 1. Query receiving module: The server receives queries sent from the terminal.

[0833] 2. Recording module: The server records queries as logs.

[0834] 3. Response generation module: The server generates an appropriate response to the query.

[0835] 4. Answer Recording Module: Records the generated answers as a log.

[0836] 5. Response module: The server sends the generated response back to the terminal.

[0837] 6. Log Export Module: The server exports logs of queries and responses.

[0838] System processing flow

[0839] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[0840] 2. The device sends this question to the server.

[0841] 3. The server's query receiving module receives the question sent from the terminal.

[0842] 4. The server's logging module logs the questions it receives.

[0843] 5. The server's answer generation module generates an answer to the question. First, it checks if the question already exists in the database, and if it does, it uses that answer. If it does not exist, the server's information retrieval function collects new information and generates an answer.

[0844] 6. The server's response logging module logs the generated responses.

[0845] 7. The server's response module sends the generated response back to the terminal.

[0846] 8. The terminal receives the response sent from the server and displays it to the user.

[0847] 9. If necessary, the server's log export module will export the logs, and the administrator will perform the analysis.

[0848] Specific example

[0849] User example

[0850] A user uses a device to type and send the question "What is the capital of France?". The device sends this question to the server, which receives and logs it. The server checks its database and, finding no data for this question, gathers and logs the new information from the internet: "The capital of France is Paris." It then saves this answer to the log and sends it back to the device. The device displays the received answer to the user. The server can also export the log of this interaction later for administrator review.

[0851] Server Example

[0852] The server receives the question "What is the capital of France?" using the query receiving module. The logging module logs this question, and the answer generation module checks the database. Since the question is not found in the database, the server retrieves new information from the internet and generates the answer "The capital of France is Paris." This answer is logged, and the response module sends a reply to the terminal. Finally, the log export module exports the logs as needed.

[0853] This invention allows users to obtain consistent answers 24 hours a day, and enables servers to efficiently process queries and manage logs.

[0854] The following describes the processing flow.

[0855] Step 1:

[0856] The user uses a device to type and submit a question. For example, the user might ask, "What is the capital of France?"

[0857] Step 2:

[0858] The terminal sends the entered question to the server. During this process, the terminal establishes communication with the server and transfers the query data.

[0859] Step 3:

[0860] The server receives queries sent from the terminal via a query receiving module. The server then stores the received queries in temporary memory.

[0861] Step 4:

[0862] The server's logging module records received queries in a log. The log includes the query content and a timestamp.

[0863] Step 5:

[0864] The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query.

[0865] Step 6:

[0866] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server then uses an external information source to obtain the information.

[0867] Step 7:

[0868] The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[0869] Step 8:

[0870] The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[0871] Step 9:

[0872] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[0873] Step 10:

[0874] The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[0875] Step 11:

[0876] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[0877] This processing step allows users to receive consistent answers 24 / 7, and enables the server to efficiently handle queries and manage logs.

[0878] (Example 1)

[0879] 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."

[0880] In conventional systems, providing prompt and appropriate responses to user inquiries required significant human resources, and the means of efficiently managing inquiry content and responses were limited. This contributed to decreased user satisfaction and operational efficiency. Furthermore, the procedures for retrospectively analyzing and evaluating inquiry content and responses were complex and difficult to manage.

[0881] 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.

[0882] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for generating answers to inquiries, means for recording the generated answers and sending them back to the terminal, means for exporting logs of inquiries and answers, means for receiving inquiries and recording them in a log, means for collecting new information related to inquiries from external sources and generating answers, and means for recording the generated answers as logs and sending them back to the terminal. This makes it possible to provide quick and appropriate answers to user inquiries and to efficiently manage and analyze the logs.

[0883] A "terminal" refers to a device used by a user to communicate with a server, and includes, for example, smartphones, personal computers, and tablets.

[0884] A "server" refers to a computer system that processes user inquiries and generates and responds to them.

[0885] An "inquiry" refers to a question or request that a user sends using their device.

[0886] "Answer" refers to the response or information that a server generates in response to a query.

[0887] "Means of recording" refers to functions for saving the content of inquiries and responses in a database or similar system.

[0888] A "log" refers to a collection of historical information about inquiries and responses, including metadata such as timestamps and IP addresses.

[0889] "Exporting" refers to the function of converting log data into an external file format (such as CSV or Excel) and saving it.

[0890] "Information source" refers to data provision systems such as databases or external APIs that are referenced to generate answers.

[0891] A "database" refers to a data management system used to efficiently store and retrieve inquiries and answers.

[0892] "External information sources" refer to knowledge bases and API services on the internet that the server references.

[0893] "Means of collecting information" refers to functions for obtaining necessary data from external information sources.

[0894] This invention is a system in which a user makes an inquiry via a terminal, and a server automatically generates and responds to that inquiry with an appropriate answer. The main components of this system and the details of each process are described below.

[0895] System Configuration

[0896] This system uses the following hardware and software:

[0897] Terminal: A device used by users to enter and submit inquiries. This includes smartphones, personal computers, tablets, etc.

[0898] Server: A computer system for processing queries, generating, recording, and responding to answers.

[0899] Nginx: Web server software that accepts server requests.

[0900] MySQL: A database system that stores logs of queries and responses.

[0901] External APIs: Sources of information for obtaining new data. An example is the Wolfram Alpha API.

[0902] System operation

[0903] 1. The user enters their inquiry.

[0904] The user uses a terminal to enter their inquiry. For example, they might type "What is the capital of France?" and press the send button.

[0905] 2. The device sends the query to the server.

[0906] The terminal securely sends the user's input to the server using the HTTPS protocol.

[0907] 3. The server receives the query.

[0908] The server's query receiving module receives the query sent from the terminal. Nginx accepts this request and passes it to the application server.

[0909] 4. The server records the query.

[0910] The recording module records the queries received by the server in a MySQL database. The recorded data includes the query text, date and time, and source IP address.

[0911] 5. The server generates the answer.

[0912] The answer generation module checks if the query already exists in the database. If it does, it uses that answer; otherwise, it retrieves new information from an external API and generates the answer. For example, it uses the Wolfram Alpha API to generate the answer "The capital of France is Paris."

[0913] 6. The server records the response.

[0914] The recording module logs the generated response to a MySQL database. The recorded data includes the response text, date and time, and the associated query ID.

[0915] 7. The server sends a response back to the terminal.

[0916] The response module sends the generated answer back to the terminal. The response is in JSON format, making it easy for the terminal to parse.

[0917] 8. The device displays the answer.

[0918] The device analyzes the received response and displays it to the user in a visually easy-to-understand format. For example, it might display "The capital of France is Paris." on the screen.

[0919] 9. The server exports the logs.

[0920] If necessary, the log export module exports inquiry and response logs in CSV or Excel format. Administrators can use these logs to analyze the system and analyze user inquiry trends.

[0921] Specific example

[0922] Example of a prompt

[0923] The user types "What is the capital of France?" on their device and sends it. The device sends this question to the server. The server receives this question and logs it. The server then uses its database and an external API to generate the answer "The capital of France is Paris." It logs this answer and sends it back to the device. The device displays the received answer to the user. The server exports the logs for the administrator to analyze.

[0924] The implementation of this system allows users to receive quick and accurate answers, and enables servers to efficiently process inquiries and manage logs.

[0925] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0926] Step 1:

[0927] The user enters the question using their device and presses the submit button.

[0928] Input: The user types "What is the capital of France?" into a text box in a browser or app.

[0929] Output: The terminal converts the user's query into a JSON data packet and creates an HTTPS request.

[0930] Specific action: The user enters a question and clicks the "Submit" button.

[0931] Step 2:

[0932] The terminal sends a question to the server.

[0933] Input: The HTTPS request generated on the device after the user presses the submit button.

[0934] Output: The request received by the server's query receiving module.

[0935] Specific operation: The terminal sends a data packet in JSON format to the server over the network.

[0936] Step 3:

[0937] The server receives the question.

[0938] Input: HTTPS request sent from the terminal.

[0939] Output: Data for recording received questions in the built-in logging system.

[0940] Specific operation: The Nginx server accepts the request and passes it to the application server. The request is parsed within the server, and the question text is extracted.

[0941] Step 4:

[0942] The server's logging module logs the question.

[0943] Input: Text of the received question, date and time, and source IP address.

[0944] Output: Log entries stored in the "Questions" table of the MySQL database.

[0945] Specific action: Execute an SQL insert operation on the database and save the query content.

[0946] Step 5:

[0947] The server's answer generation module generates the answer to the question.

[0948] Input: The question text recorded in the log.

[0949] Output: The corresponding answer text.

[0950] Specific operation: Search the "Existing Questions" table in the database to check if the same query already exists. If it does not exist, use an external API (e.g., Wolfram Alpha API) to gather new information and generate an answer.

[0951] Step 6:

[0952] The server's response logging module logs the generated responses.

[0953] Input: Generated answer text, answer date and time, and related question ID.

[0954] Output: Log entries stored in the "Answers" table of the MySQL database.

[0955] Specific operation: Execute an SQL insert operation on the database and save the response.

[0956] Step 7:

[0957] The server's response module sends the generated answer back to the terminal.

[0958] Input: Generated response data.

[0959] Output: HTTP response containing the answer.

[0960] Specific operation: The server creates an HTTP response and sends it to the terminal, including the response data in JSON format.

[0961] Step 8:

[0962] The terminal receives the response sent from the server and displays it to the user.

[0963] Input: Response data in JSON format sent from the server.

[0964] Output: The response text displayed to the user.

[0965] Specific operation: The device parses the JSON data it receives and displays it to the user in a visually easy-to-understand format (e.g., "The capital of France is Paris.").

[0966] Step 9:

[0967] The server exports the logs.

[0968] Input: Question and answer data recorded in a MySQL database.

[0969] Output: Export file in CSV or Excel format.

[0970] Specific actions: Execute database queries and retrieve log data. Convert the retrieved data to the appropriate file format and save it to the file server.

[0971] (Application Example 1)

[0972] 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."

[0973] While factory staff are required to obtain information quickly and accurately, the current system often results in delayed responses to inquiries. Furthermore, inadequate log management of inquiries makes subsequent analysis difficult, hindering efficiency improvements.

[0974] 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.

[0975] In this invention, the server includes means for receiving and recording an inquiry from a terminal, means for generating a response to the inquiry, means for recording the generated response and sending it back to the terminal, means for exporting the inquiry and response logs, and a response generation module that generates the inquiry content using natural language processing and responds in voice or text. This enables factory staff to obtain information quickly and accurately, and centralized log management contributes to subsequent analysis and efficiency improvements.

[0976] "A means of receiving inquiries from a terminal and recording those inquiries" refers to a function in which a robot receives inquiries from factory staff and saves the content of those inquiries as logs in a database.

[0977] "Means for generating responses to inquiries" refers to a process for generating appropriate responses to received inquiries, and natural language processing techniques can be used for this purpose.

[0978] "Means for recording the generated response and sending a response to the terminal" refers to a function that saves the generated response in a database and then sends that response back to the factory staff in voice or text.

[0979] "Means for exporting the logs of the aforementioned inquiries and answers" refers to a function that exports the recorded inquiry and answer data so that administrators can analyze the data.

[0980] "A means of generating a response module that generates inquiry content using natural language processing and responds in voice or text" refers to a module that uses natural language processing technology to generate a response to an inquiry received and has the function of responding to the factory staff with the result in voice or text.

[0981] This invention relates to a factory robot inquiry response system for enabling factory staff to quickly obtain information. The configuration and operating procedures for specifically implementing this invention are shown below.

[0982] System Configuration

[0983] This system consists of the following main hardware and software components.

[0984] Hardware: Factory robots, voice recognition microphones, touch panel displays

[0985] Software: Flask (Python web framework), JSON (for log storage)

[0986] This section explains the roles of each piece of hardware and software.

[0987] 1. Factory robots: These are central devices for receiving and processing inquiries. Equipped with voice recognition microphones and touch panel displays, they can quickly receive inquiries from staff.

[0988] 2. Voice recognition microphone and touch panel display: These are means for staff to input inquiries. Voice inquiries are received via the voice recognition microphone, and text inquiries are received via the touch panel display.

[0989] 3. Flask application: This software is used for receiving, recording, generating, responding to, and exporting logs of inquiries. This application runs on factory robots.

[0990] 4. JSON format logs: This is a data format for saving records of inquiries and responses.

[0991] System Processing Overview

[0992] 1. Factory staff input inquiries to the robot via a voice recognition microphone or touch panel display.

[0993] 2. The inquiry details are sent to the server via the Flask application and recorded.

[0994] 3. The Flask application uses natural language processing to generate appropriate answers. During this process, it checks if existing information exists in the database; if not, it retrieves new information.

[0995] 4. The generated response is recorded again and sent back to the factory staff via voice or text.

[0996] 5. If necessary, the administrator will retrieve all logs from the export endpoint and use them for later analysis.

[0997] Specific example

[0998] A factory staff member asks the robot by voice, "When is the next production line maintenance?" This voice is sent to the robot via a voice recognition microphone, and the Flask application begins processing. If there is no information in the database about "the next production line maintenance," the robot retrieves an answer from an external source such as the internet, such as "The next production line maintenance is next Monday." The generated answer is recorded again and returned to the factory staff by voice.

[0999] Example of a prompt

[1000] "I'd like to know the next maintenance schedule for the production line. When is the next maintenance scheduled?"

[1001] Thus, the present invention allows factory staff to obtain information quickly and accurately, and the system can efficiently process inquiries and manage logs.

[1002] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1003] Step 1:

[1004] The user inputs a question to the factory robot using a voice recognition microphone or touch panel display. The input question is sent to the terminal as text data. For example, a question such as "When is the next maintenance for the production line?"

[1005] Step 2:

[1006] The terminal sends the entered query to the server. The server receives the query content through the Flask application. Here, the query data is converted to JSON format.

[1007] Step 3:

[1008] The server's logging module records the query in the database. This step generates a log containing the query content and a timestamp. For example, "Query: 'When is the next production line maintenance?', Timestamp: '2023-10-05 10:00:00'".

[1009] Step 4:

[1010] The server's answer generation module checks the database to see if an existing answer exists. If no matching answer is found in the database, it retrieves new information from an external source (e.g., the internet or an internal factory system). It then uses natural language processing to generate an appropriate answer. For example, based on the newly collected information, it might generate the answer, "The next production line maintenance is next Monday."

[1011] Step 5:

[1012] The server's response logging module records the generated response in the database. This step generates a log containing the response and the corresponding query ID. For example, "Response: 'The next production line maintenance is next Monday.', Query ID: '123'".

[1013] Step 6:

[1014] The server's response module sends a generated answer back to the terminal. The terminal receives this answer and displays it to the user as audio or text. For example, the answer, "The next production line maintenance is next Monday," might be played back using speech synthesis technology.

[1015] Step 7:

[1016] If necessary, the administrator can export all logs from the server using the log export endpoint. This step compiles the recorded inquiry and response data, making it available for download in JSON or CSV format. For example, files such as "All Inquiry Logs" and "All Response Logs" will be generated.

[1017] 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.

[1018] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and returns them to the terminal. It combines means for exporting inquiry and answer logs with an emotion engine that recognizes user emotions to improve the quality and consistency of responses according to the individual needs of the user.

[1019] System Configuration

[1020] The server consists of modules with the following main functions:

[1021] 1. Query receiving module: The server receives queries sent from the terminal.

[1022] 2. Recording module: The server records queries as logs.

[1023] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[1024] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[1025] 5. Answer Recording Module: Records the generated answers as a log.

[1026] 6. Response module: The server sends the generated response back to the terminal.

[1027] 7. Log Export Module: The server exports logs of queries and responses.

[1028] System processing flow

[1029] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[1030] 2. The device sends this question to the server.

[1031] 3. The server's query receiving module receives the query sent from the terminal. The server stores the received query in temporary memory.

[1032] 4. The server's logging module logs the received queries. The log includes the query content and a timestamp.

[1033] 5. The server's sentiment engine module analyzes the user's sentiment from their text input. For example, it analyzes the text "What is the capital of France?" and determines that the sentiment is neutral.

[1034] 6. The server's emotion engine module logs the analyzed emotion results.

[1035] 7. The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query content.

[1036] 8. If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server uses external information sources to obtain information.

[1037] 9. The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[1038] 10. The server's response generation module adjusts the tone of the generated responses based on the sentiment analysis results. For example, if the user's sentiment is dissatisfied, it will use more polite and friendly language.

[1039] 11. The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[1040] 12. The server's response module sends the generated response back to the terminal. The server re-establishes communication with the terminal and transfers the response data.

[1041] 13. The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[1042] 14. If necessary, the server's log export module will export the logs. The logs will be saved to a file in JSON format or similar.

[1043] Specific example

[1044] User example

[1045] A user uses a terminal to type and send a question expressing dissatisfaction, such as "Why is my order late?". The terminal sends this question to the server, which receives and logs the question, and analyzes the sentiment using the sentiment engine module. The server determines the user's sentiment is dissatisfaction and logs this result. The response generation module checks the database, adjusts the tone when generating an appropriate response, and produces a polite response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days." This response is then saved to the log and sent back to the terminal. The terminal displays the received response to the user. The server can also export the log of this interaction later for administrator review.

[1046] Server Example

[1047] The server receives the question "Why is my order late?" in the query receiving module. The logging module logs this question, and the sentiment engine module analyzes the user's sentiment from the text and logs it. The response generation module checks the database, and if new information is needed, the information retrieval module gathers the information and generates a response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days," adjusting the tone based on the sentiment analysis results. The response logging module logs the generated response, and the response module sends the response back to the terminal. Finally, the log export module exports the logs as needed.

[1048] This invention allows users to receive consistent, emotionally sensitive responses 24 hours a day, and enables servers to efficiently process inquiries and manage logs.

[1049] The following describes the processing flow.

[1050] Step 1:

[1051] The user uses a device to type and submit a question. For example, the user might type the question "Why is my order late?"

[1052] Step 2:

[1053] The terminal sends the entered question to the server. The terminal establishes communication to transfer this question to the server.

[1054] Step 3:

[1055] The server's query receiving module receives the question sent from the terminal. The server stores the received question in temporary memory.

[1056] Step 4:

[1057] The server's logging module records the received questions in a log. The log includes the question content and a timestamp.

[1058] Step 5:

[1059] The server's sentiment engine module analyzes the text of the received question to identify the user's sentiment. For example, it can detect dissatisfaction from the text "Why is my order late?".

[1060] Step 6:

[1061] The server's emotion engine module logs the results of the emotion analysis. The type of emotion and its details are also recorded.

[1062] Step 7:

[1063] The server's answer generation module checks the database to see if there is an existing answer to the query. The server searches the database for an answer corresponding to "Why is my order late?".

[1064] Step 8:

[1065] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server communicates with an external information source (e.g., a customer support system) to retrieve the information.

[1066] Step 9:

[1067] The server's response generation module generates an appropriate response based on the newly acquired information. For example, it might generate a response such as, "We apologize for the delay. Your order is expected to arrive within the next 2 days."

[1068] Step 10:

[1069] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. If dissatisfaction is detected, the response is adjusted to be more polite and friendly.

[1070] Step 11:

[1071] The server's response logging module logs the generated responses, including the response content and a timestamp.

[1072] Step 12:

[1073] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[1074] Step 13:

[1075] The device receives the response from the server and displays it to the user. The user can then verify the response.

[1076] Step 14:

[1077] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[1078] This processing step ensures that users receive consistent, emotionally sensitive responses 24 / 7. The server can efficiently process queries and manage logs.

[1079] (Example 2)

[1080] 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."

[1081] In traditional systems, when users made inquiries, the lack of consideration for user emotions resulted in inappropriate responses and a poor user experience. Furthermore, there was a lack of means to accurately store and manage inquiry and response content, making subsequent analysis and auditing difficult. Additionally, there is a need for functionality to quickly and accurately retrieve information from multiple sources.

[1082] 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.

[1083] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for analyzing the content of the inquiry and determining its sentiment, means for generating a response to the inquiry and adjusting the tone of the response based on the sentiment determination result, means for recording the generated response and sending it back to the terminal, and means for exporting the inquiry and response logs. This enables responses in an appropriate tone that takes the user's sentiment into consideration, thereby improving the user experience. Furthermore, accurate storage and management of inquiry and response content facilitates subsequent analysis and auditing. In addition, it becomes possible to quickly obtain information from multiple sources and generate accurate responses.

[1084] A "terminal" is an electronic device used by users to input inquiries and send them to a server.

[1085] An "inquiry" refers to a question or request for information that a user sends to a server through their device.

[1086] "Recording" means saving received inquiries and generated responses to log files or databases.

[1087] "Means" refers to modules or sets of functions used to perform specific functions or processes.

[1088] A "server" is a central computer that receives inquiries from terminals, processes them, generates the necessary responses, and sends them back to the terminals.

[1089] "Means for recording inquiries" refers to devices or programs that have the function of saving received inquiries as logs.

[1090] "Answer" refers to the response from the server to an inquiry.

[1091] "Means of generating responses" refers to the processes or programs used to create appropriate replies based on the content of inquiries.

[1092] "Means for determining emotions" refers to algorithms or engines that analyze the content of inquiries to infer and determine the emotional state of the user.

[1093] "Adjusting the tone of the response" means appropriately changing the wording and tone of the response based on the emotion assessment results.

[1094] "Means of responding to the terminal" refers to communication modules or programs used to send the generated response to the user's terminal.

[1095] "Means for exporting logs" refers to devices or programs that have the function of outputting recorded inquiry and response logs as external files.

[1096] "Means of acquiring new information" refers to the processes and systems for collecting necessary information from external sources when there is no existing answer in the database.

[1097] "Multiple information sources" refers to different sources of information that a server references when collecting information, such as websites, APIs, and databases on the internet.

[1098] This invention is a system that receives inquiries from a terminal, records those inquiries, generates and records answers, and finally provides a response. This section explains how to implement this system in detail.

[1099] Hardware and software to be used

[1100] Hardware: Server, user terminal

[1101] Software: Emotion engine (e.g., natural language processing library), database (e.g., SQL database), log management system (e.g., ELK Stack), API client for retrieving external information.

[1102] Program processing

[1103] This system consists of the following main functional modules:

[1104] 1. Query receiving module: The server receives queries sent from the terminal.

[1105] 2. Recording module: The server records queries as logs.

[1106] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[1107] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[1108] 5. Answer Recording Module: Records the generated answers as a log.

[1109] 6. Response module: The server sends the generated response back to the terminal.

[1110] 7. Log Export Module: The server exports logs of queries and responses.

[1111] Specific data processing and data operations used

[1112] After receiving a query from a terminal, the server stores its contents in temporary memory. The received content is then logged by the recording module. Next, the emotion engine module analyzes the query content and determines the user's emotion. The emotion analysis results are recorded in the log.

[1113] Next, the response generation module checks if an existing response exists in the database. If the relevant response does not exist in the database, it gathers new information from an external source. An information retrieval API client is used in this process. Based on the new information, a response is generated, and its tone is adjusted.

[1114] The generated responses are logged by the response logging module and sent back to the terminal via the response module. If necessary, the administrator can export the log files using the log export module.

[1115] Specific example

[1116] Example 1: General Questions

[1117] The user uses a device to type and send the question, "What is the capital of France?". When the device sends this question to the server, the server receives the question, logs it, and analyzes the sentiment using the sentiment engine module. If the sentiment is determined to be neutral, the result is logged. The answer generation module checks the database and generates the answer, "The capital of France is Paris." The generated answer is saved to the log and sent back to the device. The device displays the received answer to the user.

[1118] Example of a prompt

[1119] A user submitted the question, "What is the highest mountain in the world?" The emotion engine determined the emotion was neutral. Please generate an appropriate answer.

[1120] In this way, the present invention improves the user experience by providing responses that take user emotions into consideration. Furthermore, by recording the inquiry content and the generated response as logs, subsequent analysis and auditing can be easily performed.

[1121] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1122] Step 1:

[1123] The user enters an inquiry on their device and presses the send button. For example, they might enter and send the inquiry "What is the capital of France?". At this time, the input data is sent from the device to the server in text format.

[1124] Step 2:

[1125] The terminal sends user input data to the server. The terminal transfers the input data to the server using an HTTP request. The input data is a text-based query.

[1126] Step 3:

[1127] The server's query receiving module receives queries sent from the terminal. The received data is temporarily stored in temporary memory. The input is the query content, and the output is the act of storing it in temporary memory.

[1128] Step 4:

[1129] The server's logging module records the query details. It creates a log entry containing the received query data and saves it to a log file along with its timestamp. The input is the query details and timestamp, and the output is the saved log entry.

[1130] Step 5:

[1131] The server's emotion engine module analyzes the query content and determines the user's emotion. For example, it analyzes the query "What is the capital of France?" and determines the emotion to be neutral. The input is the query content, and the output is the emotion analysis result.

[1132] Step 6:

[1133] The server logs the sentiment assessment results. The analyzed sentiment results are saved as log entries, and a timestamp is also recorded. The input is the sentiment analysis result and timestamp, and the output is the saved log entry.

[1134] Step 7:

[1135] The server's answer generation module checks the database for existing answers. It performs a database search based on the query "What is the capital of France?". The input is the query, and the output is the search result (no matching answer found).

[1136] Step 8:

[1137] The server collects new information from external sources. It uses an information retrieval module to call an external API (e.g., an encyclopedia API) to obtain "the capital of France." The input is the query, and the output is the retrieved new information.

[1138] Step 9:

[1139] The server's answer generation module generates an answer based on the retrieved information. It generates the answer "The capital of France is Paris." The input is new information, and the output is the generated answer.

[1140] Step 10:

[1141] The server adjusts the tone of the response based on the sentiment analysis results. If the emotion is neutral, no special tone adjustment is made, and the response is used as is. The input is the sentiment analysis results and the generated response, and the output is the final response.

[1142] Step 11:

[1143] The server's response logging module logs the generated responses. The generated responses and their timestamps are saved to a log file. The input is the final response and its timestamp, and the output is the saved log entry.

[1144] Step 12:

[1145] The server's response module sends the generated answer back to the terminal. The generated answer is sent back to the terminal as an HTTP response. The input is the final answer, and the output is the HTTP response containing the answer.

[1146] Step 13:

[1147] The device receives a response from the server and displays it to the user. The device's screen displays the response, "The capital of France is Paris." The input is the HTTP response from the server, and the output is the display result that the user can see.

[1148] Step 14:

[1149] The server exports logs as needed. Based on administrator instructions, inquiry and response logs are exported in JSON format and saved as a file. The input is the log data, and the output is the exported log file.

[1150] (Application Example 2)

[1151] 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."

[1152] Traditional customer service systems often suffer from a poor user experience because they only provide simple question-and-answer responses without considering the user's emotions. Furthermore, the inability to provide responses with an appropriate tone that takes emotions into account could negatively impact user satisfaction. Additionally, existing systems have incomplete log export capabilities, preventing administrators from properly managing inquiry history.

[1153] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a terminal and recording the inquiry, means for generating an answer to the inquiry, means for recording the generated answer and sending it back to the terminal, means for exporting the inquiry and answer logs, means including an emotion engine for analyzing the user's emotions associated with the inquiry, and means for adjusting the tone of the answer based on the user's emotions. This enables the provision of consistent, high-quality answers while taking the user's emotions into consideration, thereby improving the user experience. Furthermore, tone adjustment based on the emotion analysis results can increase user satisfaction, and enhanced log export functionality allows administrators to manage inquiry history more appropriately.

[1154] A "terminal" is an electronic device operated by a user, used for inputting inquiries and receiving responses from a server.

[1155] An "inquiry" refers to a question or request entered by a user using their device, and is information sent to the server.

[1156] "To record" means to save received or generated information in a database or log file.

[1157] A "response" is the information provided to the user by a server, which generates a response based on a query.

[1158] "Generating" refers to the process of creating new information or responses.

[1159] A "log" refers to data that records the history of system activity and data.

[1160] "Exporting" is the operation of saving or transferring recorded data as an external file.

[1161] An "emotion engine" is an algorithm or software module used to analyze a user's emotions.

[1162] "Tone" refers to the overall feel and style of the expression and phrasing used in a response.

[1163] "To adjust" means to change or modify existing content based on specific criteria.

[1164] Adjusting the "quality" means appropriately changing the wording and style of the responses based on the user's emotions.

[1165] This invention is a system that recognizes the user's emotions when they use a terminal to make product inquiries or receive customer support within a virtual store, and provides a response with the most appropriate tone based on those emotions. This system consists of the following main modules:

[1166] Main component modules

[1167] 1. Query receiving module: The server receives queries sent from the terminal.

[1168] 2. Recording module: The server records queries as logs.

[1169] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[1170] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[1171] 5. Answer Recording Module: Records the generated answers as a log.

[1172] 6. Response module: The server sends the generated response back to the terminal.

[1173] 7. Log Export Module: The server exports logs of queries and responses.

[1174] Hardware and software configuration

[1175] The server requires a high-performance processor, sufficient memory, and large-capacity storage. The sentiment engine module uses a sentiment analysis engine based on machine learning models. Specifically, it incorporates a sentiment analysis model that utilizes natural language processing (NLP) techniques. For example, it includes a sentiment analysis tool built using the Python programming language. The database stores existing FAQs and past inquiry logs, and new information is obtained by web scraping tools and data acquisition from APIs.

[1176] Program Processing Description

[1177] The server receives inquiries sent from a terminal using the inquiry receiving module, and then records their contents using the logging module. Next, the sentiment engine module analyzes the user's sentiment from the text and stores the results. Subsequently, the response generation module refers to the database to generate an appropriate response, adjusting the tone based on the analysis results. For example, if the user's sentiment is dissatisfaction, a more polite tone will be used to generate the response. The generated response is logged by the response recording module and finally sent back to the terminal via the response module. The logs of the entire process can be exported via the log export module as needed.

[1178] Specific example

[1179] The user uses their device to type and send a question expressing dissatisfaction, such as "Why is my order late?". When the device sends this question to the server, the server receives and logs the question and analyzes the sentiment using its sentiment engine module. The server determines that the user's sentiment is dissatisfaction and generates a polite response: "We apologize for the delay. Your order is expected to arrive within the next 2 days." The server then logs this response and sends it back to the device. The device displays the received response to the user.

[1180] Example of a prompt

[1181] "A user made an emotional inquiry: 'I am not happy with my purchase, can I return it?' Please generate an appropriate and emotionally sensitive response."

[1182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1183] Step 1:

[1184] The user enters and submits a query using a terminal. When the user enters the text "Why is my order late?" into the terminal's input field and presses the submit button, the terminal sends the query to the server. The input is the user's text, and the output is the query data sent to the server.

[1185] Step 2:

[1186] The server's query receiving module receives queries sent from the terminal. The server receives the query data and stores it in temporary memory. The input is the query data sent from the terminal, and the output is the query data in temporary memory.

[1187] Step 3:

[1188] The server's logging module logs the queries it receives. The server saves the query content and timestamp to a log file. The input is the query data in temporary memory, and the output is the query content and timestamp recorded in the log file.

[1189] Step 4:

[1190] The server's emotion engine module analyzes the user's emotions from their text input. The server inputs the query into a machine learning model to perform emotion analysis. The input is the query, and the output is the emotion analysis result (e.g., "dissatisfied").

[1191] Step 5:

[1192] The server's emotion engine module logs the emotion analysis results. The server saves the emotion analysis results to a log file. The input is the emotion analysis results, and the output is the emotion analysis results recorded in the log file.

[1193] Step 6:

[1194] The server's answer generation module checks if a matching answer already exists in the database. The server searches the database for the relevant answer. The input is the query, and the output is either the matching answer or no match found in the database.

[1195] Step 7:

[1196] If the server cannot find an answer in the database, it runs an information retrieval module to obtain new information. The server uses external sources to collect new information. The input is the search result with no matches, and the output is the information obtained from the new sources.

[1197] Step 8:

[1198] The server's response generation module generates an appropriate response based on the newly acquired information. The server creates the response "We apologize for the delay. Your order is expected to arrive within the next 2 days." based on the acquired information. The input is the new information, and the output is the generated response.

[1199] Step 9:

[1200] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. Because the sentiment is dissatisfied, the server adds polite language to the generated response. The input is the generated response and the sentiment analysis results, and the output is the response with the adjusted tone.

[1201] Step 10:

[1202] The server's response logging module logs the generated responses. The server saves the response content and timestamp to a log file. The input is the tone-adjusted response, and the output is the response content and timestamp recorded in the log file.

[1203] Step 11:

[1204] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data. The input is the tone-adjusted answer, and the output is the answer sent to the terminal.

[1205] Step 12:

[1206] The terminal receives the response from the server and displays it to the user. The terminal displays the received response to the user. The input is the response data sent from the server, and the output is the response displayed to the user.

[1207] Step 13:

[1208] If necessary, the server's log export module exports the logs. The server exports the log files in JSON format or another suitable format for administrator review. The input is the log file, and the output is the exported log data.

[1209] 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.

[1210] 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.

[1211] 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.

[1212] [Fourth Embodiment]

[1213] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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).

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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".

[1226] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and sends a response back to the terminal, and includes means for exporting inquiry and answer logs.

[1227] System Configuration

[1228] The server consists of modules with the following main functions:

[1229] 1. Query receiving module: The server receives queries sent from the terminal.

[1230] 2. Recording module: The server records queries as logs.

[1231] 3. Response generation module: The server generates an appropriate response to the query.

[1232] 4. Answer Recording Module: Records the generated answers as a log.

[1233] 5. Response module: The server sends the generated response back to the terminal.

[1234] 6. Log Export Module: The server exports logs of queries and responses.

[1235] System processing flow

[1236] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[1237] 2. The device sends this question to the server.

[1238] 3. The server's query receiving module receives the question sent from the terminal.

[1239] 4. The server's logging module logs the questions it receives.

[1240] 5. The server's answer generation module generates an answer to the question. First, it checks if the question already exists in the database, and if it does, it uses that answer. If it does not exist, the server's information retrieval function collects new information and generates an answer.

[1241] 6. The server's response logging module logs the generated responses.

[1242] 7. The server's response module sends the generated response back to the terminal.

[1243] 8. The terminal receives the response sent from the server and displays it to the user.

[1244] 9. If necessary, the server's log export module will export the logs, and the administrator will perform the analysis.

[1245] Specific example

[1246] User example

[1247] A user uses a device to type and send the question "What is the capital of France?". The device sends this question to the server, which receives and logs it. The server checks its database and, finding no data for this question, gathers and logs the new information from the internet: "The capital of France is Paris." It then saves this answer to the log and sends it back to the device. The device displays the received answer to the user. The server can also export the log of this interaction later for administrator review.

[1248] Server Example

[1249] The server receives the question "What is the capital of France?" using the query receiving module. The logging module logs this question, and the answer generation module checks the database. Since the question is not found in the database, the server retrieves new information from the internet and generates the answer "The capital of France is Paris." This answer is logged, and the response module sends a reply to the terminal. Finally, the log export module exports the logs as needed.

[1250] This invention allows users to obtain consistent answers 24 hours a day, and enables servers to efficiently process queries and manage logs.

[1251] The following describes the processing flow.

[1252] Step 1:

[1253] The user uses a device to type and submit a question. For example, the user might ask, "What is the capital of France?"

[1254] Step 2:

[1255] The terminal sends the entered question to the server. During this process, the terminal establishes communication with the server and transfers the query data.

[1256] Step 3:

[1257] The server receives queries sent from the terminal via a query receiving module. The server then stores the received queries in temporary memory.

[1258] Step 4:

[1259] The server's logging module records received queries in a log. The log includes the query content and a timestamp.

[1260] Step 5:

[1261] The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query.

[1262] Step 6:

[1263] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server then uses an external information source to obtain the information.

[1264] Step 7:

[1265] The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[1266] Step 8:

[1267] The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[1268] Step 9:

[1269] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[1270] Step 10:

[1271] The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[1272] Step 11:

[1273] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[1274] This processing step allows users to receive consistent answers 24 / 7, and enables the server to efficiently handle queries and manage logs.

[1275] (Example 1)

[1276] 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".

[1277] In conventional systems, providing prompt and appropriate responses to user inquiries required significant human resources, and the means of efficiently managing inquiry content and responses were limited. This contributed to decreased user satisfaction and operational efficiency. Furthermore, the procedures for retrospectively analyzing and evaluating inquiry content and responses were complex and difficult to manage.

[1278] 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.

[1279] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for generating answers to inquiries, means for recording the generated answers and sending them back to the terminal, means for exporting logs of inquiries and answers, means for receiving inquiries and recording them in a log, means for collecting new information related to inquiries from external sources and generating answers, and means for recording the generated answers as logs and sending them back to the terminal. This makes it possible to provide quick and appropriate answers to user inquiries and to efficiently manage and analyze the logs.

[1280] A "terminal" refers to a device used by a user to communicate with a server, and includes, for example, smartphones, personal computers, and tablets.

[1281] A "server" refers to a computer system that processes user inquiries and generates and responds to them.

[1282] An "inquiry" refers to a question or request that a user sends using their device.

[1283] "Answer" refers to the response or information that a server generates in response to a query.

[1284] "Means of recording" refers to functions for saving the content of inquiries and responses in a database or similar system.

[1285] A "log" refers to a collection of historical information about inquiries and responses, including metadata such as timestamps and IP addresses.

[1286] "Exporting" refers to the function of converting log data into an external file format (such as CSV or Excel) and saving it.

[1287] "Information source" refers to data provision systems such as databases or external APIs that are referenced to generate answers.

[1288] A "database" refers to a data management system used to efficiently store and retrieve inquiries and answers.

[1289] "External information sources" refer to knowledge bases and API services on the internet that the server references.

[1290] "Means of collecting information" refers to functions for obtaining necessary data from external information sources.

[1291] This invention is a system in which a user makes an inquiry via a terminal, and a server automatically generates and responds to that inquiry with an appropriate answer. The main components of this system and the details of each process are described below.

[1292] System Configuration

[1293] This system uses the following hardware and software:

[1294] Terminal: A device used by users to enter and submit inquiries. This includes smartphones, personal computers, tablets, etc.

[1295] Server: A computer system for processing queries, generating, recording, and responding to answers.

[1296] Nginx: Web server software that accepts server requests.

[1297] MySQL: A database system that stores logs of queries and responses.

[1298] External APIs: Sources of information for obtaining new data. An example is the Wolfram Alpha API.

[1299] System operation

[1300] 1. The user enters their inquiry.

[1301] The user uses a terminal to enter their inquiry. For example, they might type "What is the capital of France?" and press the send button.

[1302] 2. The device sends the query to the server.

[1303] The terminal securely sends the user's input to the server using the HTTPS protocol.

[1304] 3. The server receives the query.

[1305] The server's query receiving module receives the query sent from the terminal. Nginx accepts this request and passes it to the application server.

[1306] 4. The server records the query.

[1307] The recording module records the queries received by the server in a MySQL database. The recorded data includes the query text, date and time, and source IP address.

[1308] 5. The server generates the answer.

[1309] The answer generation module checks if the query already exists in the database. If it does, it uses that answer; otherwise, it retrieves new information from an external API and generates the answer. For example, it uses the Wolfram Alpha API to generate the answer "The capital of France is Paris."

[1310] 6. The server records the response.

[1311] The recording module logs the generated response to a MySQL database. The recorded data includes the response text, date and time, and the associated query ID.

[1312] 7. The server sends a response back to the terminal.

[1313] The response module sends the generated answer back to the terminal. The response is in JSON format, making it easy for the terminal to parse.

[1314] 8. The device displays the answer.

[1315] The device analyzes the received response and displays it to the user in a visually easy-to-understand format. For example, it might display "The capital of France is Paris." on the screen.

[1316] 9. The server exports the logs.

[1317] If necessary, the log export module exports inquiry and response logs in CSV or Excel format. Administrators can use these logs to analyze the system and analyze user inquiry trends.

[1318] Specific example

[1319] Example of a prompt

[1320] The user types "What is the capital of France?" on their device and sends it. The device sends this question to the server. The server receives this question and logs it. The server then uses its database and an external API to generate the answer "The capital of France is Paris." It logs this answer and sends it back to the device. The device displays the received answer to the user. The server exports the logs for the administrator to analyze.

[1321] The implementation of this system allows users to receive quick and accurate answers, and enables servers to efficiently process inquiries and manage logs.

[1322] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1323] Step 1:

[1324] The user enters the question using their device and presses the submit button.

[1325] Input: The user types "What is the capital of France?" into a text box in a browser or app.

[1326] Output: The terminal converts the user's query into a JSON data packet and creates an HTTPS request.

[1327] Specific action: The user enters a question and clicks the "Submit" button.

[1328] Step 2:

[1329] The terminal sends a question to the server.

[1330] Input: The HTTPS request generated on the device after the user presses the submit button.

[1331] Output: The request received by the server's query receiving module.

[1332] Specific operation: The terminal sends a data packet in JSON format to the server over the network.

[1333] Step 3:

[1334] The server receives the question.

[1335] Input: HTTPS request sent from the terminal.

[1336] Output: Data for recording received questions in the built-in logging system.

[1337] Specific operation: The Nginx server accepts the request and passes it to the application server. The request is parsed within the server, and the question text is extracted.

[1338] Step 4:

[1339] The server's logging module logs the question.

[1340] Input: Text of the received question, date and time, and source IP address.

[1341] Output: Log entries stored in the "Questions" table of the MySQL database.

[1342] Specific action: Execute an SQL insert operation on the database and save the query content.

[1343] Step 5:

[1344] The server's answer generation module generates the answer to the question.

[1345] Input: The question text recorded in the log.

[1346] Output: The corresponding answer text.

[1347] Specific operation: Search the "Existing Questions" table in the database to check if the same query already exists. If it does not exist, use an external API (e.g., Wolfram Alpha API) to gather new information and generate an answer.

[1348] Step 6:

[1349] The server's response logging module logs the generated responses.

[1350] Input: Generated answer text, answer date and time, and related question ID.

[1351] Output: Log entries stored in the "Answers" table of the MySQL database.

[1352] Specific operation: Execute an SQL insert operation on the database and save the response.

[1353] Step 7:

[1354] The server's response module sends the generated answer back to the terminal.

[1355] Input: Generated response data.

[1356] Output: HTTP response containing the answer.

[1357] Specific operation: The server creates an HTTP response and sends it to the terminal, including the response data in JSON format.

[1358] Step 8:

[1359] The terminal receives the response sent from the server and displays it to the user.

[1360] Input: Response data in JSON format sent from the server.

[1361] Output: The response text displayed to the user.

[1362] Specific operation: The device parses the JSON data it receives and displays it to the user in a visually easy-to-understand format (e.g., "The capital of France is Paris.").

[1363] Step 9:

[1364] The server exports the logs.

[1365] Input: Question and answer data recorded in a MySQL database.

[1366] Output: Export file in CSV or Excel format.

[1367] Specific actions: Execute database queries and retrieve log data. Convert the retrieved data to the appropriate file format and save it to the file server.

[1368] (Application Example 1)

[1369] 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".

[1370] While factory staff are required to obtain information quickly and accurately, the current system often results in delayed responses to inquiries. Furthermore, inadequate log management of inquiries makes subsequent analysis difficult, hindering efficiency improvements.

[1371] 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.

[1372] In this invention, the server includes means for receiving and recording an inquiry from a terminal, means for generating a response to the inquiry, means for recording the generated response and sending it back to the terminal, means for exporting the inquiry and response logs, and a response generation module that generates the inquiry content using natural language processing and responds in voice or text. This enables factory staff to obtain information quickly and accurately, and centralized log management contributes to subsequent analysis and efficiency improvements.

[1373] "A means of receiving inquiries from a terminal and recording those inquiries" refers to a function in which a robot receives inquiries from factory staff and saves the content of those inquiries as logs in a database.

[1374] "Means for generating responses to inquiries" refers to a process for generating appropriate responses to received inquiries, and natural language processing techniques can be used for this purpose.

[1375] "Means for recording the generated response and sending a response to the terminal" refers to a function that saves the generated response in a database and then sends that response back to the factory staff in voice or text.

[1376] "Means for exporting the logs of the aforementioned inquiries and answers" refers to a function that exports the recorded inquiry and answer data so that administrators can analyze the data.

[1377] "A means of generating a response module that generates inquiry content using natural language processing and responds in voice or text" refers to a module that uses natural language processing technology to generate a response to an inquiry received and has the function of responding to the factory staff with the result in voice or text.

[1378] This invention relates to a factory robot inquiry response system for enabling factory staff to quickly obtain information. The configuration and operating procedures for specifically implementing this invention are shown below.

[1379] System Configuration

[1380] This system consists of the following main hardware and software components.

[1381] Hardware: Factory robots, voice recognition microphones, touch panel displays

[1382] Software: Flask (Python web framework), JSON (for log storage)

[1383] This section explains the roles of each piece of hardware and software.

[1384] 1. Factory robots: These are central devices for receiving and processing inquiries. Equipped with voice recognition microphones and touch panel displays, they can quickly receive inquiries from staff.

[1385] 2. Voice recognition microphone and touch panel display: These are means for staff to input inquiries. Voice inquiries are received via the voice recognition microphone, and text inquiries are received via the touch panel display.

[1386] 3. Flask application: This software is used for receiving, recording, generating, responding to, and exporting logs of inquiries. This application runs on factory robots.

[1387] 4. JSON format logs: This is a data format for saving records of inquiries and responses.

[1388] System Processing Overview

[1389] 1. Factory staff input inquiries to the robot via a voice recognition microphone or touch panel display.

[1390] 2. The inquiry details are sent to the server via the Flask application and recorded.

[1391] 3. The Flask application uses natural language processing to generate appropriate answers. During this process, it checks if existing information exists in the database; if not, it retrieves new information.

[1392] 4. The generated response is recorded again and sent back to the factory staff via voice or text.

[1393] 5. If necessary, the administrator will retrieve all logs from the export endpoint and use them for later analysis.

[1394] Specific example

[1395] A factory staff member asks the robot by voice, "When is the next production line maintenance?" This voice is sent to the robot via a voice recognition microphone, and the Flask application begins processing. If there is no information in the database about "the next production line maintenance," the robot retrieves an answer from an external source such as the internet, such as "The next production line maintenance is next Monday." The generated answer is recorded again and returned to the factory staff by voice.

[1396] Example of a prompt

[1397] "I'd like to know the next maintenance schedule for the production line. When is the next maintenance scheduled?"

[1398] Thus, the present invention allows factory staff to obtain information quickly and accurately, and the system can efficiently process inquiries and manage logs.

[1399] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1400] Step 1:

[1401] The user inputs a question to the factory robot using a voice recognition microphone or touch panel display. The input question is sent to the terminal as text data. For example, a question such as "When is the next maintenance for the production line?"

[1402] Step 2:

[1403] The terminal sends the entered query to the server. The server receives the query content through the Flask application. Here, the query data is converted to JSON format.

[1404] Step 3:

[1405] The server's logging module records the query in the database. This step generates a log containing the query content and a timestamp. For example, "Query: 'When is the next production line maintenance?', Timestamp: '2023-10-05 10:00:00'".

[1406] Step 4:

[1407] The server's answer generation module checks the database to see if an existing answer exists. If no matching answer is found in the database, it retrieves new information from an external source (e.g., the internet or an internal factory system). It then uses natural language processing to generate an appropriate answer. For example, based on the newly collected information, it might generate the answer, "The next production line maintenance is next Monday."

[1408] Step 5:

[1409] The server's response logging module records the generated response in the database. This step generates a log containing the response and the corresponding query ID. For example, "Response: 'The next production line maintenance is next Monday.', Query ID: '123'".

[1410] Step 6:

[1411] The server's response module sends a generated answer back to the terminal. The terminal receives this answer and displays it to the user as audio or text. For example, the answer, "The next production line maintenance is next Monday," might be played back using speech synthesis technology.

[1412] Step 7:

[1413] If necessary, the administrator can export all logs from the server using the log export endpoint. This step compiles the recorded inquiry and response data, making it available for download in JSON or CSV format. For example, files such as "All Inquiry Logs" and "All Response Logs" will be generated.

[1414] 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.

[1415] The present invention is a system that receives inquiries from a terminal, records those inquiries, generates answers, records the generated answers, and returns them to the terminal. It combines means for exporting inquiry and answer logs with an emotion engine that recognizes user emotions to improve the quality and consistency of responses according to the individual needs of the user.

[1416] System Configuration

[1417] The server consists of modules with the following main functions:

[1418] 1. Query receiving module: The server receives queries sent from the terminal.

[1419] 2. Recording module: The server records queries as logs.

[1420] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[1421] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[1422] 5. Answer Recording Module: Records the generated answers as a log.

[1423] 6. Response module: The server sends the generated response back to the terminal.

[1424] 7. Log Export Module: The server exports logs of queries and responses.

[1425] System processing flow

[1426] 1. The user uses their device to type and send a question, for example, "What is the capital of France?".

[1427] 2. The device sends this question to the server.

[1428] 3. The server's query receiving module receives the query sent from the terminal. The server stores the received query in temporary memory.

[1429] 4. The server's logging module logs the received queries. The log includes the query content and a timestamp.

[1430] 5. The server's sentiment engine module analyzes the user's sentiment from their text input. For example, it analyzes the text "What is the capital of France?" and determines that the sentiment is neutral.

[1431] 6. The server's emotion engine module logs the analyzed emotion results.

[1432] 7. The server's response generation module checks if a matching response already exists in the database. The server searches the database for the query content.

[1433] 8. If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server uses external information sources to obtain information.

[1434] 9. The server's answer generation module generates an appropriate answer based on the newly acquired information. For example, the answer "The capital of France is Paris." is generated.

[1435] 10. The server's response generation module adjusts the tone of the generated responses based on the sentiment analysis results. For example, if the user's sentiment is dissatisfied, it will use more polite and friendly language.

[1436] 11. The server's response logging module logs the generated responses. The log includes the response content and a timestamp.

[1437] 12. The server's response module sends the generated response back to the terminal. The server re-establishes communication with the terminal and transfers the response data.

[1438] 13. The terminal receives the response from the server and displays it to the user. The user can then verify the response.

[1439] 14. If necessary, the server's log export module will export the logs. The logs will be saved to a file in JSON format or similar.

[1440] Specific example

[1441] User example

[1442] A user uses a terminal to type and send a question expressing dissatisfaction, such as "Why is my order late?". The terminal sends this question to the server, which receives and logs the question, and analyzes the sentiment using the sentiment engine module. The server determines the user's sentiment is dissatisfaction and logs this result. The response generation module checks the database, adjusts the tone when generating an appropriate response, and produces a polite response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days." This response is then saved to the log and sent back to the terminal. The terminal displays the received response to the user. The server can also export the log of this interaction later for administrator review.

[1443] Server Example

[1444] The server receives the question "Why is my order late?" in the query receiving module. The logging module logs this question, and the sentiment engine module analyzes the user's sentiment from the text and logs it. The response generation module checks the database, and if new information is needed, the information retrieval module gathers the information and generates a response such as "We apologize for the delay. Your order is expected to arrive within the next 2 days," adjusting the tone based on the sentiment analysis results. The response logging module logs the generated response, and the response module sends the response back to the terminal. Finally, the log export module exports the logs as needed.

[1445] This invention allows users to receive consistent, emotionally sensitive responses 24 hours a day, and enables servers to efficiently process inquiries and manage logs.

[1446] The following describes the processing flow.

[1447] Step 1:

[1448] The user uses a device to type and submit a question. For example, the user might type the question "Why is my order late?"

[1449] Step 2:

[1450] The terminal sends the entered question to the server. The terminal establishes communication to transfer this question to the server.

[1451] Step 3:

[1452] The server's query receiving module receives the question sent from the terminal. The server stores the received question in temporary memory.

[1453] Step 4:

[1454] The server's logging module records the received questions in a log. The log includes the question content and a timestamp.

[1455] Step 5:

[1456] The server's sentiment engine module analyzes the text of the received question to identify the user's sentiment. For example, it can detect dissatisfaction from the text "Why is my order late?".

[1457] Step 6:

[1458] The server's emotion engine module logs the results of the emotion analysis. The type of emotion and its details are also recorded.

[1459] Step 7:

[1460] The server's answer generation module checks the database to see if there is an existing answer to the query. The server searches the database for an answer corresponding to "Why is my order late?".

[1461] Step 8:

[1462] If the server cannot find an answer in the database, it runs an information retrieval module to collect new information. The server communicates with an external information source (e.g., a customer support system) to retrieve the information.

[1463] Step 9:

[1464] The server's response generation module generates an appropriate response based on the newly acquired information. For example, it might generate a response such as, "We apologize for the delay. Your order is expected to arrive within the next 2 days."

[1465] Step 10:

[1466] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. If dissatisfaction is detected, the response is adjusted to be more polite and friendly.

[1467] Step 11:

[1468] The server's response logging module logs the generated responses, including the response content and a timestamp.

[1469] Step 12:

[1470] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data.

[1471] Step 13:

[1472] The device receives the response from the server and displays it to the user. The user can then verify the response.

[1473] Step 14:

[1474] The server's log export module exports logs as needed. The logs are saved to a file in JSON format or similar.

[1475] This processing step ensures that users receive consistent, emotionally sensitive responses 24 / 7. The server can efficiently process queries and manage logs.

[1476] (Example 2)

[1477] 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".

[1478] In traditional systems, when users made inquiries, the lack of consideration for user emotions resulted in inappropriate responses and a poor user experience. Furthermore, there was a lack of means to accurately store and manage inquiry and response content, making subsequent analysis and auditing difficult. Additionally, there is a need for functionality to quickly and accurately retrieve information from multiple sources.

[1479] 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.

[1480] In this invention, the server includes means for receiving and recording inquiries from a terminal, means for analyzing the content of the inquiry and determining its sentiment, means for generating a response to the inquiry and adjusting the tone of the response based on the sentiment determination result, means for recording the generated response and sending it back to the terminal, and means for exporting the inquiry and response logs. This enables responses in an appropriate tone that takes the user's sentiment into consideration, thereby improving the user experience. Furthermore, accurate storage and management of inquiry and response content facilitates subsequent analysis and auditing. In addition, it becomes possible to quickly obtain information from multiple sources and generate accurate responses.

[1481] A "terminal" is an electronic device used by users to input inquiries and send them to a server.

[1482] An "inquiry" refers to a question or request for information that a user sends to a server through their device.

[1483] "Recording" means saving received inquiries and generated responses to log files or databases.

[1484] "Means" refers to modules or sets of functions used to perform specific functions or processes.

[1485] A "server" is a central computer that receives inquiries from terminals, processes them, generates the necessary responses, and sends them back to the terminals.

[1486] "Means for recording inquiries" refers to devices or programs that have the function of saving received inquiries as logs.

[1487] "Answer" refers to the response from the server to an inquiry.

[1488] "Means of generating responses" refers to the processes or programs used to create appropriate replies based on the content of inquiries.

[1489] "Means for determining emotions" refers to algorithms or engines that analyze the content of inquiries to infer and determine the emotional state of the user.

[1490] "Adjusting the tone of the response" means appropriately changing the wording and tone of the response based on the emotion assessment results.

[1491] "Means of responding to the terminal" refers to communication modules or programs used to send the generated response to the user's terminal.

[1492] "Means for exporting logs" refers to devices or programs that have the function of outputting recorded inquiry and response logs as external files.

[1493] "Means of acquiring new information" refers to the processes and systems for collecting necessary information from external sources when there is no existing answer in the database.

[1494] "Multiple information sources" refers to different sources of information that a server references when collecting information, such as websites, APIs, and databases on the internet.

[1495] This invention is a system that receives inquiries from a terminal, records those inquiries, generates and records answers, and finally provides a response. This section explains how to implement this system in detail.

[1496] Hardware and software to be used

[1497] Hardware: Server, user terminal

[1498] Software: Emotion engine (e.g., natural language processing library), database (e.g., SQL database), log management system (e.g., ELK Stack), API client for retrieving external information.

[1499] Program processing

[1500] This system consists of the following main functional modules:

[1501] 1. Query receiving module: The server receives queries sent from the terminal.

[1502] 2. Recording module: The server records queries as logs.

[1503] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[1504] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[1505] 5. Answer Recording Module: Records the generated answers as a log.

[1506] 6. Response module: The server sends the generated response back to the terminal.

[1507] 7. Log Export Module: The server exports logs of queries and responses.

[1508] Specific data processing and data operations used

[1509] After receiving a query from a terminal, the server stores its contents in temporary memory. The received content is then logged by the recording module. Next, the emotion engine module analyzes the query content and determines the user's emotion. The emotion analysis results are recorded in the log.

[1510] Next, the response generation module checks if an existing response exists in the database. If the relevant response does not exist in the database, it gathers new information from an external source. An information retrieval API client is used in this process. Based on the new information, a response is generated, and its tone is adjusted.

[1511] The generated responses are logged by the response logging module and sent back to the terminal via the response module. If necessary, the administrator can export the log files using the log export module.

[1512] Specific example

[1513] Example 1: General Questions

[1514] The user uses a device to type and send the question, "What is the capital of France?". When the device sends this question to the server, the server receives the question, logs it, and analyzes the sentiment using the sentiment engine module. If the sentiment is determined to be neutral, the result is logged. The answer generation module checks the database and generates the answer, "The capital of France is Paris." The generated answer is saved to the log and sent back to the device. The device displays the received answer to the user.

[1515] Example of a prompt

[1516] A user submitted the question, "What is the highest mountain in the world?" The emotion engine determined the emotion was neutral. Please generate an appropriate answer.

[1517] In this way, the present invention improves the user experience by providing responses that take user emotions into consideration. Furthermore, by recording the inquiry content and the generated response as logs, subsequent analysis and auditing can be easily performed.

[1518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1519] Step 1:

[1520] The user enters an inquiry on their device and presses the send button. For example, they might enter and send the inquiry "What is the capital of France?". At this time, the input data is sent from the device to the server in text format.

[1521] Step 2:

[1522] The terminal sends user input data to the server. The terminal transfers the input data to the server using an HTTP request. The input data is a text-based query.

[1523] Step 3:

[1524] The server's query receiving module receives queries sent from the terminal. The received data is temporarily stored in temporary memory. The input is the query content, and the output is the act of storing it in temporary memory.

[1525] Step 4:

[1526] The server's logging module records the query details. It creates a log entry containing the received query data and saves it to a log file along with its timestamp. The input is the query details and timestamp, and the output is the saved log entry.

[1527] Step 5:

[1528] The server's emotion engine module analyzes the query content and determines the user's emotion. For example, it analyzes the query "What is the capital of France?" and determines the emotion to be neutral. The input is the query content, and the output is the emotion analysis result.

[1529] Step 6:

[1530] The server logs the sentiment assessment results. The analyzed sentiment results are saved as log entries, and a timestamp is also recorded. The input is the sentiment analysis result and timestamp, and the output is the saved log entry.

[1531] Step 7:

[1532] The server's answer generation module checks the database for existing answers. It performs a database search based on the query "What is the capital of France?". The input is the query, and the output is the search result (no matching answer found).

[1533] Step 8:

[1534] The server collects new information from external sources. It uses an information retrieval module to call an external API (e.g., an encyclopedia API) to obtain "the capital of France." The input is the query, and the output is the retrieved new information.

[1535] Step 9:

[1536] The server's answer generation module generates an answer based on the retrieved information. It generates the answer "The capital of France is Paris." The input is new information, and the output is the generated answer.

[1537] Step 10:

[1538] The server adjusts the tone of the response based on the sentiment analysis results. If the emotion is neutral, no special tone adjustment is made, and the response is used as is. The input is the sentiment analysis results and the generated response, and the output is the final response.

[1539] Step 11:

[1540] The server's response logging module logs the generated responses. The generated responses and their timestamps are saved to a log file. The input is the final response and its timestamp, and the output is the saved log entry.

[1541] Step 12:

[1542] The server's response module sends the generated answer back to the terminal. The generated answer is sent back to the terminal as an HTTP response. The input is the final answer, and the output is the HTTP response containing the answer.

[1543] Step 13:

[1544] The device receives a response from the server and displays it to the user. The device's screen displays the response, "The capital of France is Paris." The input is the HTTP response from the server, and the output is the display result that the user can see.

[1545] Step 14:

[1546] The server exports logs as needed. Based on administrator instructions, inquiry and response logs are exported in JSON format and saved as a file. The input is the log data, and the output is the exported log file.

[1547] (Application Example 2)

[1548] 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".

[1549] Traditional customer service systems often suffer from a poor user experience because they only provide simple question-and-answer responses without considering the user's emotions. Furthermore, the inability to provide responses with an appropriate tone that takes emotions into account could negatively impact user satisfaction. Additionally, existing systems have incomplete log export capabilities, preventing administrators from properly managing inquiry history.

[1550] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a terminal and recording the inquiry, means for generating an answer to the inquiry, means for recording the generated answer and sending it back to the terminal, means for exporting the inquiry and answer logs, means including an emotion engine for analyzing the user's emotions associated with the inquiry, and means for adjusting the tone of the answer based on the user's emotions. This enables the provision of consistent, high-quality answers while taking the user's emotions into consideration, thereby improving the user experience. Furthermore, tone adjustment based on the emotion analysis results can increase user satisfaction, and enhanced log export functionality allows administrators to manage inquiry history more appropriately.

[1551] A "terminal" is an electronic device operated by a user, used for inputting inquiries and receiving responses from a server.

[1552] An "inquiry" refers to a question or request entered by a user using their device, and is information sent to the server.

[1553] "To record" means to save received or generated information in a database or log file.

[1554] A "response" is the information provided to the user by a server, which generates a response based on a query.

[1555] "Generating" refers to the process of creating new information or responses.

[1556] A "log" refers to data that records the history of system activity and data.

[1557] "Exporting" is the operation of saving or transferring recorded data as an external file.

[1558] An "emotion engine" is an algorithm or software module used to analyze a user's emotions.

[1559] "Tone" refers to the overall feel and style of the expression and phrasing used in a response.

[1560] "To adjust" means to change or modify existing content based on specific criteria.

[1561] Adjusting the "quality" means appropriately changing the wording and style of the responses based on the user's emotions.

[1562] This invention is a system that recognizes the user's emotions when they use a terminal to make product inquiries or receive customer support within a virtual store, and provides a response with the most appropriate tone based on those emotions. This system consists of the following main modules:

[1563] Main component modules

[1564] 1. Query receiving module: The server receives queries sent from the terminal.

[1565] 2. Recording module: The server records queries as logs.

[1566] 3. Emotion Engine Module: The server analyzes the emotions from the user's text input and stores the results.

[1567] 4. Response Generation Module: The server generates an appropriate response to the query. In doing so, the tone of the response is adjusted according to the user's emotional state.

[1568] 5. Answer Recording Module: Records the generated answers as a log.

[1569] 6. Response module: The server sends the generated response back to the terminal.

[1570] 7. Log Export Module: The server exports logs of queries and responses.

[1571] Hardware and software configuration

[1572] The server requires a high-performance processor, sufficient memory, and large-capacity storage. The sentiment engine module uses a sentiment analysis engine based on machine learning models. Specifically, it incorporates a sentiment analysis model that utilizes natural language processing (NLP) techniques. For example, it includes a sentiment analysis tool built using the Python programming language. The database stores existing FAQs and past inquiry logs, and new information is obtained by web scraping tools and data acquisition from APIs.

[1573] Program Processing Description

[1574] The server receives inquiries sent from a terminal using the inquiry receiving module, and then records their contents using the logging module. Next, the sentiment engine module analyzes the user's sentiment from the text and stores the results. Subsequently, the response generation module refers to the database to generate an appropriate response, adjusting the tone based on the analysis results. For example, if the user's sentiment is dissatisfaction, a more polite tone will be used to generate the response. The generated response is logged by the response recording module and finally sent back to the terminal via the response module. The logs of the entire process can be exported via the log export module as needed.

[1575] Specific example

[1576] The user uses their device to type and send a question expressing dissatisfaction, such as "Why is my order late?". When the device sends this question to the server, the server receives and logs the question and analyzes the sentiment using its sentiment engine module. The server determines that the user's sentiment is dissatisfaction and generates a polite response: "We apologize for the delay. Your order is expected to arrive within the next 2 days." The server then logs this response and sends it back to the device. The device displays the received response to the user.

[1577] Example of a prompt

[1578] "A user made an emotional inquiry: 'I am not happy with my purchase, can I return it?' Please generate an appropriate and emotionally sensitive response."

[1579] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1580] Step 1:

[1581] The user enters and submits a query using a terminal. When the user enters the text "Why is my order late?" into the terminal's input field and presses the submit button, the terminal sends the query to the server. The input is the user's text, and the output is the query data sent to the server.

[1582] Step 2:

[1583] The server's query receiving module receives queries sent from the terminal. The server receives the query data and stores it in temporary memory. The input is the query data sent from the terminal, and the output is the query data in temporary memory.

[1584] Step 3:

[1585] The server's logging module logs the queries it receives. The server saves the query content and timestamp to a log file. The input is the query data in temporary memory, and the output is the query content and timestamp recorded in the log file.

[1586] Step 4:

[1587] The server's emotion engine module analyzes the user's emotions from their text input. The server inputs the query into a machine learning model to perform emotion analysis. The input is the query, and the output is the emotion analysis result (e.g., "dissatisfied").

[1588] Step 5:

[1589] The server's emotion engine module logs the emotion analysis results. The server saves the emotion analysis results to a log file. The input is the emotion analysis results, and the output is the emotion analysis results recorded in the log file.

[1590] Step 6:

[1591] The server's answer generation module checks if a matching answer already exists in the database. The server searches the database for the relevant answer. The input is the query, and the output is either the matching answer or no match found in the database.

[1592] Step 7:

[1593] If the server cannot find an answer in the database, it runs an information retrieval module to obtain new information. The server uses external sources to collect new information. The input is the search result with no matches, and the output is the information obtained from the new sources.

[1594] Step 8:

[1595] The server's response generation module generates an appropriate response based on the newly acquired information. The server creates the response "We apologize for the delay. Your order is expected to arrive within the next 2 days." based on the acquired information. The input is the new information, and the output is the generated response.

[1596] Step 9:

[1597] The server's response generation module adjusts the tone of the generated response based on the sentiment analysis results. Because the sentiment is dissatisfied, the server adds polite language to the generated response. The input is the generated response and the sentiment analysis results, and the output is the response with the adjusted tone.

[1598] Step 10:

[1599] The server's response logging module logs the generated responses. The server saves the response content and timestamp to a log file. The input is the tone-adjusted response, and the output is the response content and timestamp recorded in the log file.

[1600] Step 11:

[1601] The server's response module sends the generated answer back to the terminal. The server re-establishes communication with the terminal and transfers the answer data. The input is the tone-adjusted answer, and the output is the answer sent to the terminal.

[1602] Step 12:

[1603] The terminal receives the response from the server and displays it to the user. The terminal displays the received response to the user. The input is the response data sent from the server, and the output is the response displayed to the user.

[1604] Step 13:

[1605] If necessary, the server's log export module exports the logs. The server exports the log files in JSON format or another suitable format for administrator review. The input is the log file, and the output is the exported log data.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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."

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] 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.

[1627] The following is further disclosed regarding the embodiments described above.

[1628] (Claim 1)

[1629] A means of receiving inquiries from a single terminal and recording those inquiries,

[1630] A means of generating answers to inquiries,

[1631] A means for recording the generated response and sending a response to the terminal,

[1632] A means for exporting the logs of the aforementioned inquiries and responses,

[1633] A system that includes this.

[1634] (Claim 2)

[1635] The means for generating a response to the aforementioned query checks whether the query already exists in the database,

[1636] The system according to claim 1, comprising means for obtaining new information if it does not exist.

[1637] (Claim 3)

[1638] The means for acquiring the new information includes means for acquiring information from multiple sources.

[1639] The system according to claim 1.

[1640] "Example 1"

[1641] (Claim 1)

[1642] A means of receiving inquiries from a terminal and recording those inquiries,

[1643] A means of generating answers to inquiries,

[1644] A means for recording the generated response and sending a response to the terminal,

[1645] A means for exporting the logs of the aforementioned inquiries and responses,

[1646] A means of receiving and logging inquiries,

[1647] A means of collecting new information regarding inquiries from external sources and generating responses,

[1648] A means of recording the generated response as a log and sending a response to the terminal,

[1649] A system that includes this.

[1650] (Claim 2)

[1651] The system according to claim 1, wherein the means for generating a response to the query includes means for checking whether the query already exists in the database and, if not, obtaining new information.

[1652] (Claim 3)

[1653] The system according to claim 1, wherein the means for acquiring the new information includes means for acquiring information from multiple sources.

[1654] "Application Example 1"

[1655] (Claim 1)

[1656] A means of receiving inquiries from a single terminal and recording those inquiries,

[1657] A means of generating answers to inquiries,

[1658] A means for recording the generated response and sending a response to the terminal,

[1659] A means for exporting the logs of the aforementioned inquiries and responses,

[1660] A response generation module is provided, which generates the query content using natural language processing and provides a response in voice or text.

[1661] A system that includes this.

[1662] (Claim 2)

[1663] The means for generating a response to the aforementioned query checks whether the query already exists in the database,

[1664] The system according to claim 1, comprising means for obtaining new information if it does not exist.

[1665] (Claim 3)

[1666] The response generation module includes means for receiving inquiries from factory staff and responding in voice or text.

[1667] The system according to claim 1.

[1668] "Example 2 of combining an emotion engine"

[1669] (Claim 1)

[1670] A means of receiving inquiries from a single terminal and recording those inquiries,

[1671] A means of generating answers to inquiries,

[1672] A means for recording the generated response and sending a response to the terminal,

[1673] A means for exporting the logs of the aforementioned inquiries and responses,

[1674] This includes methods for analyzing the content of inquiries and determining emotions.

[1675] A means of adjusting the tone of the response based on the emotion assessment results,

[1676] A system that includes this.

[1677] (Claim 2)

[1678] The means for generating a response to the aforementioned query checks whether the query already exists in the database,

[1679] The system according to claim 1, comprising means for obtaining new information if it does not exist.

[1680] (Claim 3)

[1681] The means for acquiring the new information includes means for acquiring information from multiple sources.

[1682] The system according to claim 1.

[1683] "Application example 2 when combining with an emotional engine"

[1684] (Claim 1)

[1685] A means of receiving inquiries from a single terminal and recording those inquiries,

[1686] A means of generating answers to inquiries,

[1687] A means for recording the generated response and sending a response to the terminal,

[1688] A means for exporting the logs of the aforementioned inquiries and responses,

[1689] A means including an emotion engine that analyzes the user's emotions associated with an inquiry,

[1690] A means of adjusting the tone of responses based on the user's emotions,

[1691] A system that includes this.

[1692] (Claim 2)

[1693] The means for generating a response to the aforementioned query checks whether the query already exists in the database,

[1694] The system according to claim 1, comprising means for obtaining new information if it does not exist.

[1695] (Claim 3)

[1696] The means for acquiring the new information includes means for acquiring information from multiple sources.

[1697] The system according to claim 1. [Explanation of symbols]

[1698] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving inquiries from a single terminal and recording those inquiries, A means of generating answers to inquiries, A means for recording the generated response and sending a response to the terminal, A means for exporting the logs of the aforementioned inquiries and responses, A system that includes this.

2. The means for generating a response to the aforementioned query checks whether the query already exists in the database, The system according to claim 1, comprising means for obtaining new information if it does not exist.

3. The means for acquiring the new information includes means for acquiring information from multiple sources. The system according to claim 1.

Images