system

Abstract

We provide the system. [Solution] A means for receiving inquiries from users, A means of analyzing received inquiries, A means for generating an answer based on the analysis results, A means of sending the generated response to the user, A means for recording questions and their corresponding answers in a database, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 as a 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 recent years, online inquiries and support have increased, and there is a demand for quick and accurate responses. However, existing systems have limitations in the quality and speed of generating responses to inquiries, and often cannot sufficiently ensure user satisfaction. In addition, the accumulation and analysis of inquiry content are insufficient, and it is difficult to build and improve a knowledge base. Therefore, there is a need for a system that automatically analyzes inquiry content and generates and provides high-precision responses.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing the following means: a system including means for receiving inquiries from users, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user, and means for recording questions and their corresponding answers in a database. Furthermore, by including means for analyzing inquiries and generating answers using a natural language processing model, it is possible to provide answers with higher accuracy. In addition, by including means for recording and managing logs of dialogues including inquiries and answers, the construction and improvement of the knowledge base is facilitated, and continuous learning and performance improvement of the system are realized.

[0006] A "user" is an end-user or user who accesses the system and makes inquiries.

[0007] An "inquiry" refers to a question or request for information sent by a user.

[0008] "Means of receiving" refers to functions or devices for obtaining inquiries sent by users.

[0009] "Means of analysis" refer to algorithms and programs used to evaluate the content of received inquiries and understand their meaning.

[0010] "Means for generating answers" refers to functions or systems that create appropriate answers based on analysis results.

[0011] "Means of transmission" refers to communication means or devices used to send the generated response back to the user.

[0012] "Means of recording in a database" refers to functions or systems for storing and managing questions and their corresponding answers.

[0013] A "natural language processing model" refers to a machine learning model or algorithm used to understand and process human language.

[0014] "Means for recording and managing dialogue logs" refers to functions or devices that save the history of interactions (dialogues) between a user and a system, and allow them to be referenced later.

[0015] A "system" refers to a mechanism or device consisting of a series of computer programs and hardware that operate by combining the means described above. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

[0020] In the following embodiments, a RAM (Random Access Memory) with a reference numeral 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 signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. This system primarily consists of a server, a user terminal, and the user. Specific embodiments of this system are described in detail below.

[0038] System configuration and operation

[0039] User actions

[0040] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[0041] Processing at the user terminal

[0042] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0043] Processing on the server

[0044] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[0045] 1. Received:

[0046] The server accepts POST requests to a specific endpoint (for example, / query).

[0047] 2. Analysis:

[0048] The received inquiry is analyzed using a natural language processing (NLP) model. This model often includes machine learning models or deep learning models.

[0049] 3. Answer generation:

[0050] Based on the analysis results, generate the most appropriate answer.

[0051] 4. Submit your response:

[0052] The generated response is formatted in JSON format and sent back to the user's terminal.

[0053] Use of natural language processing models

[0054] The server analyzes queries using a natural language processing model. This model uses, for example, a natural language processing toolkit provided by Company X. This allows the server to understand the user's input question and context, and to form a meaningful response.

[0055] Specific example

[0056] Suppose a user sends the following inquiry from their device:

[0057] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0058] Question: What are Python used for?

[0059] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[0060] Answer: "It is widely used in data analysis, web development, AI, machine learning, etc."

[0061] This response is sent back to the user's terminal in JSON format. In this way, the user can obtain information quickly and accurately.

[0062] Records and management

[0063] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0064] The above describes the embodiments of the present invention. This system enables a rapid and accurate response to user inquiries, thereby contributing to improved customer service.

[0065] The following describes the processing flow.

[0066] Step 1:

[0067] Server startup

[0068] The server executes a Python script to launch the Flask application.

[0069] The server listens for requests at the specified endpoint (for example, / query).

[0070] Step 2:

[0071] User inquiry submission

[0072] The user enters their inquiry details from their device.

[0073] For example, you could enter the question, "What are Python used for?"

[0074] The user's terminal converts this query into JSON format and sends a POST request to the server's endpoint.

[0075] Step 3:

[0076] Inquiry received

[0077] The server receives the POST request.

[0078] The request data is read and converted from JSON format to a Python dictionary object.

[0079] Step 4:

[0080] Inquiry analysis

[0081] The server extracts the context and question from the JSON data.

[0082] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[0083] Step 5:

[0084] Answer generation

[0085] The server inputs the extracted context and question into a natural language processing (NLP) model.

[0086] The NLP model uses this information to generate the optimal response.

[0087] Example: Servers receive the answer, "They are widely used for data analysis, web development, AI, machine learning, etc."

[0088] Step 6:

[0089] Submit your response

[0090] The server formats the generated response into JSON format.

[0091] This JSON response is sent to the user's device.

[0092] Step 7:

[0093] Display the answer

[0094] The user's terminal displays the received JSON-formatted response in the display area.

[0095] The user sees the response on the screen that says, "It is widely used in data analysis, web development, AI, machine learning, etc."

[0096] Step 8:

[0097] Records and management

[0098] The server stores the questions and their answers in a database.

[0099] This will allow the data to be used as reference for responding to future inquiries.

[0100] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers.

[0101] (Example 1)

[0102] 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."

[0103] In today's information and communication society, there is a demand for quick and accurate responses to user inquiries. Traditional systems have faced challenges in improving user satisfaction due to slow processing times and low accuracy in responses. Furthermore, these systems often suffer from inadequate management of response logs, making it difficult to improve future inquiry handling.

[0104] 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.

[0105] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for sending the formatted data to the server, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for formatting the generated answers in JSON format, means for returning the formatted answers to the user terminal, and means for recording the questions and their corresponding answers in a database. This enables rapid and accurate processing of inquiries and generation of answers. Furthermore, by recording and managing logs of the interactions, the accuracy of responses to future inquiries can be improved.

[0106] A "user" refers to a person or organization that makes inquiries to the system.

[0107] An "inquiry" refers to a question or request from a user seeking information from the system or a solution to a problem.

[0108] "Means of receiving" refers to the function of retrieving inquiries sent by users.

[0109] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a format for concisely representing data in text format.

[0110] "Formatting" refers to a function that arranges data into a specific structure or format.

[0111] A "server" refers to a computing device or system that analyzes received queries and generates and transmits responses.

[0112] "Means of analysis" refers to the function of breaking down and evaluating information in order to understand received inquiries and process them appropriately.

[0113] "Means for generating answers" refers to a function that creates appropriate answers to user inquiries based on analysis results.

[0114] "Method of sending back" refers to the function of sending the generated response to the user's terminal.

[0115] A "database" refers to a digital warehouse where information is systematically managed and stored.

[0116] "Means of recording" refers to the function of saving the generated answers and their corresponding queries to a database.

[0117] "Means for recording and managing logs" refers to a function that saves the system's operation history and user interaction history so that it can be referenced and analyzed in the future.

[0118] System Overview

[0119] This invention relates to a system that automatically analyzes user inquiries, generates appropriate responses, and sends them back. This system consists of three elements: a server, a terminal (such as a personal computer or smartphone), and the user. Detailed embodiments are described below.

[0120] User actions

[0121] Users send inquiries to the system using their own devices (such as PCs or smartphones). For example, a user might enter an inquiry such as, "What are Python used for?" The user enters this question into a text box and clicks the submit button.

[0122] Processing at the user terminal

[0123] The user terminal receives the entered query and formats it in JSON format. This data includes the query context and the specific question. The formatted data is sent to the server using the HTTP POST method.

[0124] Processing on the server

[0125] The server accepts POST requests at a specific endpoint. The received data is analyzed using a natural language processing (NLP) model. This model can utilize, for example, a natural language processing toolkit provided by a major company.

[0126] Once the analysis is complete, the server uses a generative AI model to generate the most appropriate answer. This generative AI model takes prompt sentences as input and generates high-quality text. Examples of prompt sentences are as follows:

[0127] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0128] Question: What are Python used for?

[0129] The generated response is formatted in JSON format and sent back to the user's terminal. For example, the output of the generating AI model might produce a response such as "Python is mainly used for data analysis, web development, AI, and machine learning."

[0130] Data recording and management

[0131] The server records the generated answers and corresponding queries in a database. This accumulates a history of user interactions, which is expected to improve the system's learning ability and accuracy in future queries. A standard database management system is used for log management.

[0132] Specific example

[0133] For example, consider a scenario where a user submits a query asking, "What are Python used for?" The user's device converts this query into JSON format and sends it to the server. The server receives it and analyzes it using a natural language processing model. As a result, an appropriate answer is generated by an AI model, and the answer, "It is widely used in data analysis, web development, AI, and machine learning," is sent back to the user's device. This answer is recorded in a database and used as reference data for future queries.

[0134] The above describes the "modes for carrying out the invention" of this invention. This system makes it possible to respond quickly and accurately to user inquiries, and is expected to improve user satisfaction.

[0135] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0136] Step 1: Submit a user inquiry

[0137] The user sends a query to the system from their terminal. As input, the user enters a question in text format, such as "What are Python used for?", and clicks the send button. The output is the query transmitted to the user's terminal in text format.

[0138] Step 2: Data formatting on the user terminal

[0139] The user terminal receives the input query and formats it in JSON format. It receives the user's text-based query as input, including the query context. The terminal then converts it into data similar to the following:

[0140] json

[0141] {

[0142] "context": "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning."

[0143] "Question": "What are Python used for?"

[0144] }

[0145] The output is a query in JSON format that is sent to the server.

[0146] Step 3: Receiving the request on the server

[0147] The server accepts POST requests at a specific endpoint. It receives JSON data sent from the user's terminal as input. The output is data containing the query details necessary for analysis.

[0148] Step 4: Server query analysis

[0149] The server analyzes the received JSON data using a natural language processing (NLP) model. This model extracts the intent of the query and important keywords. The server receives JSON data to be analyzed as input. For example, the server might use a natural language processing toolkit from company X for the analysis. The output is a data structure containing the analysis results.

[0150] Step 5: Server-side response generation

[0151] The server uses a generative AI model to generate the most appropriate answer based on the analysis results. It receives the analysis results as input and feeds them to the generative AI model as prompts. An example of a prompt is as follows:

[0152] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0153] Question: What are Python used for?

[0154] The output is the generated answer text. For example, the generated answer might be "Python is mainly used for data analysis, web development, AI, and machine learning."

[0155] Step 6: Sending the response to the user's terminal

[0156] The server converts the generated response into JSON format and sends it back to the user's terminal. It receives the generated response text as input and formats it into JSON format. The output is the JSON formatted response data sent to the user's terminal.

[0157] Step 7: Recording and managing data in the database

[0158] The server records the generated answers and their corresponding queries in a database. It receives user questions and their corresponding answers as input. The output is the recorded data entries, which are used as reference data for handling future queries.

[0159] The above outlines the specific processing steps of this system's program.

[0160] (Application Example 1)

[0161] 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."

[0162] Traditional food delivery services have struggled to respond quickly and accurately to user inquiries. In particular, there was a lack of efficient systems to provide appropriate answers to specific questions regarding delivery times, menu information, and payment methods. This resulted in decreased user convenience and satisfaction.

[0163] 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.

[0164] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries, and means for generating answers based on the analysis results. This makes it possible to quickly and accurately analyze inquiries regarding food delivery services and provide appropriate answers.

[0165] A "user" is an individual or legal entity that uses the service.

[0166] An "inquiry" is a question or request from a user seeking information about a service.

[0167] "Means of receiving" refers to the function for receiving inquiries from users.

[0168] "Means of analysis" refers to functions for understanding received inquiries and extracting or processing necessary information.

[0169] "Means for generating responses" refers to a function that creates appropriate information to provide to the user based on the analysis results.

[0170] "Means of transmission" refers to the function for communicating the generated response to the user.

[0171] "Means of recording" refers to a function for saving questions and their corresponding answers in a database.

[0172] A "natural language processing model" is an algorithm or program that analyzes human language and converts it into a format that machines can understand.

[0173] A "food delivery service" is a service that delivers meals to a specific location.

[0174] A "dialogue log" is data that records a series of interactions between a user and a system.

[0175] This invention relates to a system for responding quickly and accurately to user inquiries, particularly in food delivery services. Specific embodiments thereof are described below.

[0176] System configuration and operation

[0177] This system primarily consists of user terminals, servers, and databases.

[0178] User actions

[0179] Users submit inquiries from their own devices, such as smartphones. These inquiries are typically entered as text-based questions. For example, specific questions such as "When will my ordered pizza arrive?" are submitted.

[0180] Processing at the user terminal

[0181] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0182] Processing on the server

[0183] The server plays a primary role in parsing incoming queries and generating appropriate responses. The server's processing involves the following steps:

[0184] 1. Received:

[0185] The server accepts POST requests to a specific endpoint (for example, / query).

[0186] 2. Analysis:

[0187] The received query is analyzed using a natural language processing (NLP) model. This model could be a generative AI model such as GPT-3® or BERT.

[0188] 3. Answer generation:

[0189] Based on the analysis results, generate the most appropriate answer.

[0190] 4. Submit your response:

[0191] The generated response is formatted in JSON format and sent back to the user's terminal.

[0192] Use of natural language processing models

[0193] The server parses queries using a natural language processing model. This model utilizes, for example, the Transformers library from Hugging Face. This allows the server to understand the user's input question and context and formulate a meaningful response.

[0194] Records and management

[0195] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0196] Specific example

[0197] Consider a scenario where a user sends the following inquiry from their device:

[0198] Inquiry: "What time will my ordered pizza arrive?"

[0199] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[0200] Answer: "We are currently checking the delivery status. Pizzas are usually delivered within 30 minutes."

[0201] By sending this response back to the user's terminal, the user can obtain quick and accurate information.

[0202] Example of a prompt

[0203] Examples of prompt statements are as follows:

[0204] "Please tell me the delivery status of the pizza I ordered."

[0205] In this way, the embodiment of this invention makes it possible to respond quickly and accurately to inquiries from users.

[0206] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0207] Step 1:

[0208] Users input and submit inquiries using their own devices, such as smartphones. This input includes text-based questions, such as "What is the estimated arrival time for my ordered pizza?". When a user presses an inquiry button on their device, the inquiry content is treated as input data.

[0209] Step 2:

[0210] The user terminal converts the entered query content into JSON format. At this stage, the input data is in text format, and the output data is in JSON format. The terminal formats the input text into a specific format and prepares to send it to the server.

[0211] Step 3:

[0212] The user terminal sends the converted JSON query to the server as a POST request. The input data is formatted JSON, and the request is sent to the appropriate endpoint (e.g., / query) on the server.

[0213] Step 4:

[0214] The server receives POST requests at a specific endpoint. The input data is a query in JSON format, which is then prepared for the necessary parsing processes within the server.

[0215] Step 5:

[0216] The server parses incoming queries using natural language processing models (e.g., GPT-3, BERT). The input data is the query content in JSON format, and the output data is the parsing result. The parsing process uses libraries such as Hugging Face's Transformers library.

[0217] Step 6:

[0218] The server generates an appropriate response based on the analysis results. Based on the analysis results, the AI ​​model selects and generates the most appropriate response. The input data is the analysis results, and the output data is the generated response.

[0219] Step 7:

[0220] The server formats the generated response into JSON format and prepares it for return to the user's terminal. The input data is the generated response, which is then formatted as a JSON response.

[0221] Step 8:

[0222] The server sends a formatted JSON response to the user's terminal as a POST response. The input data is in JSON format and is sent in a format that is easy for the user's terminal to receive.

[0223] Step 9:

[0224] The user terminal parses the JSON response received from the server and converts it into an appropriate format for display to the user. The input data is a JSON response, and the output data is a text response that the user can understand.

[0225] Step 10:

[0226] The user checks the answer displayed on the device. This allows the user to quickly obtain the appropriate answer to the question. The input data is the converted answer, and the output data is usable information based on the user's understanding.

[0227] As described above, the present invention is a system that provides quick and accurate answers to user inquiries in food delivery services.

[0228] 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.

[0229] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses, further incorporating an emotion engine that recognizes user emotions. This system primarily consists of a server, a user terminal, and the user. Specific embodiments are described in detail below.

[0230] System configuration and operation

[0231] User actions

[0232] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[0233] Processing at the user terminal

[0234] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0235] Processing on the server

[0236] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[0237] 1. Received:

[0238] The server accepts POST requests to a specific endpoint (for example, / query).

[0239] 2. Analysis:

[0240] The received inquiry is analyzed using a natural language processing (NLP) model. This model often utilizes, for example, industry-standard natural language processing toolkits.

[0241] 3. Emotion analysis:

[0242] An emotion engine is used to analyze the user's emotions contained in their inquiry. For example, based on the wording and context in which the user enters their question, the emotion engine determines whether the user is happy, angry, anxious, etc.

[0243] 4. Answer generation:

[0244] Based on the analysis results, the most appropriate response is generated. By also taking sentiment analysis results into consideration, responses adapted to the user's emotions are generated.

[0245] 5. Submit your response:

[0246] The generated response is formatted in JSON format and sent back to the user's terminal.

[0247] Use of natural language processing models

[0248] The server analyzes queries using a natural language processing model. This model, for example, uses an industry-standard natural language processing toolkit. This allows the server to understand the user's input question and context and formulate a meaningful response.

[0249] Using an Emotion Engine

[0250] The server uses an emotion engine to analyze the user's emotions from their inquiries. The emotion engine analyzes the text data entered by the user and employs algorithms to identify specific emotional states. This allows the server to provide responses tailored to the user's emotions.

[0251] Specific example

[0252] Suppose a user sends the following inquiry from their device:

[0253] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0254] Question: What are Python's uses? (Sentimental state: Interested)

[0255] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response similar to the following:

[0256] Answer: "Python is widely used in data analysis, web development, AI / machine learning, and more. It's also extremely useful in game development and education."

[0257] This response is sent back to the user's terminal in JSON format. In this way, the user can receive quick and accurate information along with a response that suits their feelings.

[0258] Records and management

[0259] Furthermore, this system records the generated answers and corresponding questions in a database. In addition, user sentiment data is also recorded. This can be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0260] The above describes the embodiments of the present invention. This system makes it possible to respond quickly and accurately to user inquiries and to provide appropriate answers that take into account the user's feelings.

[0261] The following describes the processing flow.

[0262] Step 1:

[0263] Server startup

[0264] The server executes a computer program to launch the Flask application.

[0265] The system enters a request-waiting state at a specific endpoint (e.g., / query).

[0266] Step 2:

[0267] User inquiry submission

[0268] The user enters their inquiry details using a terminal.

[0269] For example, you could enter the question, "What are Python used for?"

[0270] The user's terminal formats the inquiry content in JSON format and sends a POST request to the server's endpoint.

[0271] Step 3:

[0272] Receiving an Inquiry

[0273] The server receives a POST request.

[0274] Read the request data and convert it from JSON format to a Python dictionary object.

[0275] Step 4:

[0276] Analyzing the Inquiry

[0277] The server extracts the context and question of the inquiry from the JSON data.

[0278] Example: Extract the context "Python is a programming language widely used for various purposes. In particular, it is widely used in data analysis, web development, AI and machine learning, etc." and the question "What purposes is Python used for?"

[0279] Step 5:

[0280] Sentiment Analysis<000(0888>

[0281] The server uses a sentiment engine to analyze the sentiment state based on the user's input text.

[0282] Example: The user's question is analyzed as showing interest.

[0283] Step 6: y

[0284] Generating an Answer

[0285] The server inputs the extracted context, question, and the result of sentiment analysis into a natural language processing (NLP) model. y

[0286] The NLP model generates the most appropriate answer.

[0287] Example: The server receives the response, "Python is widely used for data analysis, web development, AI, machine learning, etc."

[0288] Step 7:

[0289] Submit your response

[0290] The server formats the generated response into JSON format.

[0291] This JSON response is sent to the user's device.

[0292] Step 8:

[0293] Display the answer

[0294] The user's terminal displays the received response in JSON format on the screen.

[0295] The user confirms the answer, "Python is widely used for data analysis, web development, AI, and machine learning."

[0296] Step 9:

[0297] Log

[0298] The server stores the questions, their answers, and the user's emotional state in a database.

[0299] This data will be used as reference information to respond to future inquiries.

[0300] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers, as well as receive responses that are appropriate to their emotions.

[0301] (Example 2)

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

[0303] In a conventional inquiry response system, it is difficult to quickly generate an appropriate response to an inquiry from a user, and there is a problem that it is particularly impossible to provide a response considering the user's feelings. Furthermore, there was also a lack of a method for effectively managing the logs of inquiries and responses. As a result, the improvement of user satisfaction and the improvement of system accuracy have been hindered.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0305] In this invention, the server includes means for receiving an inquiry from a user, means for formatting the received inquiry in JSON format, means for analyzing the formatted inquiry, means for generating a response based on the analysis result, means for transmitting the generated response to the user in JSON format, and means for recording questions and corresponding answers in a database. Thereby, it becomes possible to generate a quick and appropriate response to the user's inquiry and to provide a response considering the user's feelings. Also, the dialogue log can be effectively recorded and managed, and an improvement in system accuracy can be expected.

[0306] The "means for receiving an inquiry from a user" is a device or program for transmitting and receiving an inquiry input by the user in text format to the server via a network.

[0307] The "means for formatting the received inquiry in JSON format" is a device or program having a function of converting a text-format inquiry received from a user into JSON, which is a structured data format.

[0308] "Means for parsing formatted queries" refers to a device or program that uses natural language processing techniques and algorithms to analyze structured JSON query data and understand its meaning and intent.

[0309] "Means for generating answers based on analysis results" refers to a device or program that has the function of automatically generating appropriate answers based on the content of the analyzed inquiry.

[0310] "Means for sending the generated response to the user in JSON format" refers to a device or program that formats the generated response back into JSON format and sends it to the user's terminal via a network.

[0311] "Means for recording questions and corresponding answers in a database" refers to a device or program that has the function of storing user inquiries and their corresponding answers in a database in order to centrally manage them.

[0312] A "natural language processing model" refers to algorithms and technologies used to analyze text data and understand and generate human language.

[0313] "Emotional analysis" is a technology that analyzes and identifies the user's emotional state (joy, anger, anxiety, etc.) contained within text.

[0314] "Means for recording and managing dialogue logs" refers to a device or program for recording all interactions between a user and a system and managing them in a format that can be referenced later.

[0315] Modes for carrying out the invention

[0316] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. In particular, by combining it with an emotion engine that recognizes user emotions, it can provide responses that are adapted to the user's emotions. This system mainly consists of a server, a user terminal, and the user.

[0317] System Configuration

[0318] 1. User terminal:

[0319] User terminals include personal computers and smartphones. Users send inquiries to the system through their terminals. Inquiries entered by users are usually in text format, and are submitted by entering the question in an input field on the screen and clicking the submit button.

[0320] 2. Server:

[0321] The server performs the main processing of receiving, parsing, and generating responses to queries sent from user terminals. The server includes the following main components:

[0322] Receiving unit: Receives POST requests at a specific endpoint.

[0323] Formatting section: Formats the received inquiry into JSON format.

[0324] Analysis Unit: Analyzes queries using natural language processing (NLP) models. For example, it uses industry-standard natural language processing toolkits (e.g., SpaCy or NLTK).

[0325] Sentiment Analysis Unit: Uses an emotion engine to analyze the user's emotions included in the inquiry. For example, it uses a standard sentiment analysis algorithm.

[0326] Response generation unit: Based on the analysis results and sentiment analysis results, it generates appropriate responses using a generation AI model (e.g., GPT-3).

[0327] Transmission unit: Formats the generated response into JSON format and sends it to the user's terminal.

[0328] Records Management Department: Records inquiries, responses, and emotional data in a database.

[0329] Specific example

[0330] Suppose a user sends the following inquiry from their device:

[0331] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0332] Question: What are Python's uses? (Sentimental state: Interested)

[0333] The server receives this query and processes it using the following steps:

[0334] 1. The receiving unit receives POST requests to a specific endpoint.

[0335] 2. The formatting section formats the received text into JSON format.

[0336] 3. The analysis unit analyzes the query using an NLP model.

[0337] 4. The emotion analysis unit analyzes the user's emotions.

[0338] 5. The response generation unit inputs prompt text into the generation AI model to generate a response.

[0339] 6. The sending unit sends the generated response in JSON format to the user's terminal.

[0340] 7. The Records Management Department will record inquiries and responses in the database.

[0341] Example of a prompt

[0342] The following is an example of a prompt:

[0343] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[0344] In this way, the system can provide prompt and appropriate answers to user inquiries, and also respond in a way that is sensitive to the user's feelings. This makes it possible to improve both user satisfaction and the accuracy of the system.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Program processing flow

[0347] Step 1:

[0348] The user sends a query from their terminal to the system. Specifically, the user uses their computer to type "What are Python used for?" into the chat box and clicks the send button. The input is a text-based query. The output is that the query text is stored on the terminal.

[0349] Step 2:

[0350] The terminal formats user input into JSON format. Specifically, the query content (text) and the current timestamp are converted into JSON data. The input for this step is the query text entered by the user, and the output is the formatted JSON data.

[0351] Step 3:

[0352] The terminal sends formatted JSON data to the server. Specifically, the terminal sends an HTTP POST request to a specific endpoint on the server (e.g., / query). The input for this step is query data in JSON format, and the output is the request data received on the server side.

[0353] Step 4:

[0354] The server receives a POST request at a specific endpoint. Specifically, the server extracts JSON data from the request body and prepares it for parsing. The input for this step is JSON data sent from the terminal, and the output is data in a parsable format.

[0355] Step 5:

[0356] The server sends the received JSON data to a natural language processing (NLP) model for analysis. Specifically, the server uses industry-standard NLP toolkits (e.g., SpaCy or NLTK) to understand the structure and intent of the text. The input for this step is formalized query data, and the output is structured data as a result of the analysis.

[0357] Step 6:

[0358] The server uses an emotion engine to analyze the user's emotions contained in the query. Specifically, the emotion engine analyzes the user's query text and determines a specific emotional state. The input for this step is the query text, and the output is the emotion analysis result.

[0359] Step 7:

[0360] The server inputs prompt sentences into the generative AI model based on the results of NLP analysis and sentiment analysis, and generates a response. Specifically, the server sends the following prompt sentences to the generative AI model (e.g., GPT-3):

[0361] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[0362] The input for this step is a prompt message containing the analysis results and sentiment analysis results, and the output is the generated response text.

[0363] Step 8:

[0364] The server formats the generated response into JSON format and sends it to the user's terminal. Specifically, the server converts the generated text response into a JSON object and returns it as an HTTP response. The input for this step is the generated response text, and the output is formatted JSON data.

[0365] Step 9:

[0366] The server records queries, generated responses, and sentiment data in a database. Specifically, the server performs INSERT operations on the database to persist query-response pairs. The inputs to this step are query data, response data, and their sentiment analysis results, and the output is the records stored in the database.

[0367] (Application Example 2)

[0368] 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".

[0369] While conventional systems could automatically generate appropriate answers to user inquiries, they lacked the ability to consider user emotions. Furthermore, no system existed that could generate advertising messages tailored to the user's emotions based on their inquiries. Therefore, there was a need for a mechanism that could provide effective advertising that resonated with users' emotions and improve the user experience.

[0370] 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 inquiries from users, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user, means for recording questions and corresponding answers in a database, means for analyzing the user's emotions from the inquiries, means for generating appropriate advertising messages based on the results of the emotion analysis, and means for sending the generated advertising messages to the user. This makes it possible to provide appropriate answers and advertising messages that take the user's emotions into consideration.

[0371] "Means of receiving user inquiries" refers to a function that incorporates user-entered questions and comments into the system.

[0372] "Means for analyzing received inquiries" refers to a function that uses natural language processing (NLP) models to understand and analyze the content of text data received from users.

[0373] "Means for generating answers based on analysis results" refers to a function that automatically creates appropriate answers according to the analyzed inquiry content.

[0374] "Means for sending generated responses to users" refers to a function for sending automatically generated responses back to the user's device in real time.

[0375] "Means for recording questions and corresponding answers in a database" refers to a function that stores user inquiries and the system's responses in a database for future reference and analysis.

[0376] "Methods for analyzing user emotions from inquiries" refers to a function that analyzes the content of a user's inquiry and identifies the emotions contained within it (for example, joy, anxiety, anger, etc.).

[0377] "Means for generating appropriate advertising messages based on sentiment analysis results" refers to a function that automatically creates advertising messages adapted to the user's emotions, taking into account the results of sentiment analysis.

[0378] "Means for sending generated advertising messages to users" refers to the function for sending generated advertising messages to the user's device.

[0379] A "natural language processing model" refers to machine learning algorithms and tools used to analyze text data and understand its meaning and context.

[0380] This invention is a system that analyzes user inquiries and automatically generates appropriate responses and advertising messages according to the user's emotions. A specific embodiment of this system is described in detail below.

[0381] System Configuration

[0382] User actions

[0383] Users submit inquiries from devices such as smartphones. Inquiries are typically entered by the user in text format. For example, they can submit specific questions such as, "Is this new product really useful? I'm a little worried."

[0384] Processing at the user terminal

[0385] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0386] Processing on the server

[0387] Received

[0388] The server accepts POST requests to a specific endpoint (e.g., / query). Received queries are recorded in the database.

[0389] analysis

[0390] The server analyzes incoming queries using a natural language processing (NLP) model. Specifically, it uses a model from the Transformer library to understand the context of the query.

[0391] Emotion analysis

[0392] The server uses an emotion engine to analyze the user's emotions contained in the inquiry. For example, it uses Hugging Face's emotion analysis pipeline to determine whether the user is interested, anxious, angry, etc.

[0393] Response and advertising message generation

[0394] Based on the analysis results, the server generates responses. It also considers the sentiment analysis results to generate advertising messages tailored to the user's emotions. For example, if the user is feeling anxious, it will generate a message that provides reassurance.

[0395] send

[0396] The generated responses and advertising messages are formatted in JSON format and sent back to the user's device.

[0397] Hardware and software to be used

[0398] This system primarily uses the following hardware and software:

[0399] Hardware: Smartphones, servers

[0400] Software: Python, Transformers (Hugging Face), TextBlob

[0401] Data format: JSON

[0402] Specific example

[0403] For example, suppose a user sends the following inquiry from their device:

[0404] Example of a user inquiry: "Is this new product really useful? I'm a little worried."

[0405] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response and advertising message like the following:

[0406] Example of a generated response: "We understand your concerns. This product has received very positive reviews. We believe you will be reassured once you review the detailed information and customer feedback."

[0407] Example of a prompt:

[0408] User: Will this new product really be useful? I'm a little worried.

[0409] System: We understand your concerns. This product has received very high ratings. We believe you will be reassured if you review the detailed information and customer reviews.

[0410] The above describes the embodiments of the present invention. This system enables prompt and accurate responses to user inquiries and provides appropriate answers and advertising messages that take into account the user's emotions.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] Users input and submit inquiries in text format from devices such as smartphones. The user's input is then formatted in JSON format as both the context of the inquiry and the specific question. For example, a user might input the question, "Is this new product really useful? I'm a little worried." Input: User's text inquiry. Output: Inquiry formatted in JSON format.

[0414] Step 2:

[0415] The terminal sends a formatted query as a POST request to the server. The server accepts POST requests at a specific endpoint (e.g., / query). Input: A query in JSON format. Output: The request that reached the server's specific endpoint.

[0416] Step 3:

[0417] The server receives the incoming query and records it in the database. Next, it analyzes the query content using a natural language processing (NLP) model. For this analysis, a model from the Transformers library, for example, is used to understand the context of the query. Input: Query data in JSON format. Output: Text analysis data with context understood.

[0418] Step 4:

[0419] The server uses an emotion engine to identify the user's emotions from the inquiry content. It utilizes Hugging Face's emotion analysis pipeline to analyze whether the user is experiencing emotions such as interest, anxiety, joy, or anger. Input: Analyzed text data. Output: User's emotional state information.

[0420] Step 5:

[0421] The server automatically generates appropriate responses based on the analysis results. It also generates advertising messages tailored to the user's emotions based on the sentiment analysis results. For example, if the user is feeling anxious, it generates a message to provide reassurance. Input: Contextual analysis data and emotional state information. Output: User-appropriate responses and advertising messages.

[0422] Step 6:

[0423] The generated responses and advertising messages are formatted in JSON format and sent back to the device. The server sends the generated messages to the user's device. Input: Responses and advertising messages. Output: Return messages in JSON format.

[0424] Step 7:

[0425] The device displays the response and advertising message received from the server. The user can review this and then make further inquiries or utilize the provided information. Input: JSON-formatted message from the server. Output: Response and advertising message displayed on the device.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] [Second Embodiment]

[0430] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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".

[0442] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. This system primarily consists of a server, a user terminal, and the user. Specific embodiments of this system are described in detail below.

[0443] System configuration and operation

[0444] User actions

[0445] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[0446] Processing at the user terminal

[0447] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0448] Processing on the server

[0449] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[0450] 1. Received:

[0451] The server accepts POST requests to a specific endpoint (for example, / query).

[0452] 2. Analysis:

[0453] The received inquiry is analyzed using a natural language processing (NLP) model. This model often includes machine learning models or deep learning models.

[0454] 3. Answer generation:

[0455] Based on the analysis results, generate the most appropriate answer.

[0456] 4. Submit your response:

[0457] The generated response is formatted in JSON format and sent back to the user's terminal.

[0458] Use of natural language processing models

[0459] The server analyzes queries using a natural language processing model. This model uses, for example, a natural language processing toolkit provided by Company X. This allows the server to understand the user's input question and context, and to form a meaningful response.

[0460] Specific example

[0461] Suppose a user sends the following inquiry from their device:

[0462] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0463] Question: What are Python used for?

[0464] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[0465] Answer: "It is widely used in data analysis, web development, AI, machine learning, etc."

[0466] This response is sent back to the user's terminal in JSON format. In this way, the user can obtain information quickly and accurately.

[0467] Records and management

[0468] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0469] The above describes the embodiments of the present invention. This system enables a rapid and accurate response to user inquiries, thereby contributing to improved customer service.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] Server startup

[0473] The server executes a Python script to launch the Flask application.

[0474] The server listens for requests at the specified endpoint (for example, / query).

[0475] Step 2:

[0476] User inquiry submission

[0477] The user enters their inquiry details from their device.

[0478] For example, you could enter the question, "What are Python used for?"

[0479] The user's terminal converts this query into JSON format and sends a POST request to the server's endpoint.

[0480] Step 3:

[0481] Inquiry received

[0482] The server receives the POST request.

[0483] The request data is read and converted from JSON format to a Python dictionary object.

[0484] Step 4:

[0485] Inquiry analysis

[0486] The server extracts the context and question from the JSON data.

[0487] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[0488] Step 5:

[0489] Answer generation

[0490] The server inputs the extracted context and question into a natural language processing (NLP) model.

[0491] The NLP model uses this information to generate the optimal response.

[0492] Example: Servers receive the answer, "They are widely used for data analysis, web development, AI, machine learning, etc."

[0493] Step 6:

[0494] Submit your response

[0495] The server formats the generated response into JSON format.

[0496] This JSON response is sent to the user's device.

[0497] Step 7:

[0498] Display the answer

[0499] The user's terminal displays the received JSON-formatted response in the display area.

[0500] The user sees the response on the screen that says, "It is widely used in data analysis, web development, AI, machine learning, etc."

[0501] Step 8:

[0502] Records and management

[0503] The server stores the questions and their answers in a database.

[0504] This will allow the data to be used as reference for responding to future inquiries.

[0505] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers.

[0506] (Example 1)

[0507] 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."

[0508] In today's information and communication society, there is a demand for quick and accurate responses to user inquiries. Traditional systems have faced challenges in improving user satisfaction due to slow processing times and low accuracy in responses. Furthermore, these systems often suffer from inadequate management of response logs, making it difficult to improve future inquiry handling.

[0509] 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.

[0510] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for sending the formatted data to the server, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for formatting the generated answers in JSON format, means for returning the formatted answers to the user terminal, and means for recording the questions and their corresponding answers in a database. This enables rapid and accurate processing of inquiries and generation of answers. Furthermore, by recording and managing logs of the interactions, the accuracy of responses to future inquiries can be improved.

[0511] A "user" refers to a person or organization that makes inquiries to the system.

[0512] An "inquiry" refers to a question or request from a user seeking information from the system or a solution to a problem.

[0513] "Means of receiving" refers to the function of retrieving inquiries sent by users.

[0514] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a format for concisely representing data in text format.

[0515] "Formatting" refers to a function that arranges data into a specific structure or format.

[0516] A "server" refers to a computing device or system that analyzes received queries and generates and transmits responses.

[0517] "Means of analysis" refers to the function of breaking down and evaluating information in order to understand received inquiries and process them appropriately.

[0518] "Means for generating answers" refers to a function that creates appropriate answers to user inquiries based on analysis results.

[0519] "Method of sending back" refers to the function of sending the generated response to the user's terminal.

[0520] A "database" refers to a digital warehouse where information is systematically managed and stored.

[0521] "Means of recording" refers to the function of saving the generated answers and their corresponding queries to a database.

[0522] "Means for recording and managing logs" refers to a function that saves the system's operation history and user interaction history so that it can be referenced and analyzed in the future.

[0523] System Overview

[0524] This invention relates to a system that automatically analyzes user inquiries, generates appropriate responses, and sends them back. This system consists of three elements: a server, a terminal (such as a personal computer or smartphone), and the user. Detailed embodiments are described below.

[0525] User actions

[0526] Users send inquiries to the system using their own devices (such as PCs or smartphones). For example, a user might enter an inquiry such as, "What are Python used for?" The user enters this question into a text box and clicks the submit button.

[0527] Processing at the user terminal

[0528] The user terminal receives the entered query and formats it in JSON format. This data includes the query context and the specific question. The formatted data is sent to the server using the HTTP POST method.

[0529] Processing on the server

[0530] The server accepts POST requests at a specific endpoint. The received data is analyzed using a natural language processing (NLP) model. This model can utilize, for example, a natural language processing toolkit provided by a major company.

[0531] Once the analysis is complete, the server uses a generative AI model to generate the most appropriate answer. This generative AI model takes prompt sentences as input and generates high-quality text. Examples of prompt sentences are as follows:

[0532] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0533] Question: What are Python used for?

[0534] The generated response is formatted in JSON format and sent back to the user's terminal. For example, the output of the generating AI model might produce a response such as "Python is mainly used for data analysis, web development, AI, and machine learning."

[0535] Data recording and management

[0536] The server records the generated answers and corresponding queries in a database. This accumulates a history of interactions with users, which is expected to allow the system to learn from future queries and improve the accuracy of its answers. A general database management system is used to manage the logs.

[0537] Specific example

[0538] For example, consider a scenario where a user submits a query asking, "What are Python used for?" The user's device converts this query into JSON format and sends it to the server. The server receives it and analyzes it using a natural language processing model. As a result, an appropriate answer is generated by an AI model, and the answer, "It is widely used in data analysis, web development, AI, and machine learning," is sent back to the user's device. This answer is recorded in a database and used as reference data for future queries.

[0539] The above describes the "modes for carrying out the invention" of this invention. This system makes it possible to respond quickly and accurately to user inquiries, and is expected to improve user satisfaction.

[0540] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0541] Step 1: Submit a user inquiry

[0542] The user sends a query to the system from their terminal. As input, the user enters a question in text format, such as "What are Python used for?", and clicks the send button. The output is the query transmitted to the user's terminal in text format.

[0543] Step 2: Data formatting on the user terminal

[0544] The user terminal receives the input query and formats it in JSON format. It receives the user's text-based query as input, including the query context. The terminal then converts it into data similar to the following:

[0545] json

[0546] {

[0547] "context": "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning."

[0548] "Question": "What are Python used for?"

[0549] }

[0550] The output is a query in JSON format that is sent to the server.

[0551] Step 3: Receiving the request on the server

[0552] The server accepts POST requests at a specific endpoint. It receives JSON data sent from the user's terminal as input. The output is data containing the query details necessary for analysis.

[0553] Step 4: Server query analysis

[0554] The server analyzes the received JSON data using a natural language processing (NLP) model. This model extracts the intent of the query and important keywords. The server receives JSON data to be analyzed as input. For example, the server might use a natural language processing toolkit from company X for the analysis. The output is a data structure containing the analysis results.

[0555] Step 5: Server-side response generation

[0556] The server uses a generative AI model to generate the most appropriate answer based on the analysis results. It receives the analysis results as input and feeds them to the generative AI model as prompts. An example of a prompt is as follows:

[0557] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0558] Question: What are Python used for?

[0559] The output is the generated answer text. For example, the generated answer might be "Python is mainly used for data analysis, web development, AI, and machine learning."

[0560] Step 6: Sending the response to the user's terminal

[0561] The server converts the generated response into JSON format and sends it back to the user's terminal. It receives the generated response text as input and formats it into JSON format. The output is the JSON formatted response data sent to the user's terminal.

[0562] Step 7: Recording and managing data in the database

[0563] The server records the generated answers and their corresponding queries in a database. It receives user questions and their corresponding answers as input. The output is the recorded data entries, which are used as reference data for handling future queries.

[0564] The above outlines the specific processing steps of this system's program.

[0565] (Application Example 1)

[0566] 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."

[0567] Traditional food delivery services have struggled to respond quickly and accurately to user inquiries. In particular, there was a lack of efficient systems to provide appropriate answers to specific questions regarding delivery times, menu information, and payment methods. This resulted in decreased user convenience and satisfaction.

[0568] 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.

[0569] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries, and means for generating answers based on the analysis results. This makes it possible to quickly and accurately analyze inquiries regarding food delivery services and provide appropriate answers.

[0570] A "user" is an individual or legal entity that uses the service.

[0571] An "inquiry" is a question or request from a user seeking information about a service.

[0572] "Means of receiving" refers to the function for receiving inquiries from users.

[0573] "Means of analysis" refers to functions for understanding received inquiries and extracting or processing necessary information.

[0574] "Means for generating responses" refers to a function that creates appropriate information to provide to the user based on the analysis results.

[0575] "Means of transmission" refers to the function for communicating the generated response to the user.

[0576] "Means of recording" refers to a function for saving questions and their corresponding answers in a database.

[0577] A "natural language processing model" is an algorithm or program that analyzes human language and converts it into a format that machines can understand.

[0578] A "food delivery service" is a service that delivers meals to a specific location.

[0579] A "dialogue log" is data that records a series of interactions between a user and a system.

[0580] This invention relates to a system for responding quickly and accurately to user inquiries, particularly in food delivery services. Specific embodiments thereof are described below.

[0581] System configuration and operation

[0582] This system primarily consists of user terminals, servers, and databases.

[0583] User actions

[0584] Users submit inquiries from their own devices, such as smartphones. These inquiries are typically entered as text-based questions. For example, specific questions such as "What time will my ordered pizza arrive?" are submitted.

[0585] Processing at the user terminal

[0586] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0587] Processing on the server

[0588] The server plays a primary role in parsing incoming queries and generating appropriate responses. The server's processing involves the following steps:

[0589] 1. Received:

[0590] The server accepts POST requests to a specific endpoint (for example, / query).

[0591] 2. Analysis:

[0592] The received query is analyzed using a natural language processing (NLP) model. This model could be a generative AI model such as GPT-3 or BERT.

[0593] 3. Answer generation:

[0594] Based on the analysis results, generate the most appropriate answer.

[0595] 4. Submit your response:

[0596] The generated response is formatted in JSON format and sent back to the user's terminal.

[0597] Use of natural language processing models

[0598] The server parses queries using a natural language processing model. This model utilizes, for example, the Transformers library from Hugging Face. This allows the server to understand the user's input question and context and formulate a meaningful response.

[0599] Records and management

[0600] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0601] Specific example

[0602] Consider a scenario where a user sends the following inquiry from their device:

[0603] Inquiry: "What time will my ordered pizza arrive?"

[0604] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[0605] Answer: "We are currently checking the delivery status. Pizzas are usually delivered within 30 minutes."

[0606] By sending this response back to the user's terminal, the user can obtain quick and accurate information.

[0607] Example of a prompt

[0608] Examples of prompt statements are as follows:

[0609] "Please tell me the delivery status of the pizza I ordered."

[0610] In this way, the embodiment of this invention makes it possible to respond quickly and accurately to inquiries from users.

[0611] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0612] Step 1:

[0613] Users input and submit inquiries using their own devices, such as smartphones. This input includes text-based questions, such as "What is the estimated arrival time for my ordered pizza?". When a user presses an inquiry button on their device, the inquiry content is treated as input data.

[0614] Step 2:

[0615] The user terminal converts the entered query content into JSON format. At this stage, the input data is in text format, and the output data is in JSON format. The terminal formats the input text into a specific format and prepares to send it to the server.

[0616] Step 3:

[0617] The user terminal sends the converted JSON query to the server as a POST request. The input data is formatted JSON, and the request is sent to the appropriate endpoint (e.g., / query) on the server.

[0618] Step 4:

[0619] The server receives POST requests at a specific endpoint. The input data is a query in JSON format, which is then prepared for the necessary parsing processes within the server.

[0620] Step 5:

[0621] The server parses incoming queries using natural language processing models (e.g., GPT-3, BERT). The input data is the query content in JSON format, and the output data is the parsing result. The parsing process uses libraries such as Hugging Face's Transformers library.

[0622] Step 6:

[0623] The server generates an appropriate response based on the analysis results. Based on the analysis results, the AI ​​model selects and generates the most appropriate response. The input data is the analysis results, and the output data is the generated response.

[0624] Step 7:

[0625] The server formats the generated response into JSON format and prepares it for return to the user's terminal. The input data is the generated response, which is then formatted as a JSON response.

[0626] Step 8:

[0627] The server sends a formatted JSON response to the user's terminal as a POST response. The input data is in JSON format and is sent in a format that is easy for the user's terminal to receive.

[0628] Step 9:

[0629] The user terminal parses the JSON response received from the server and converts it into an appropriate format for display to the user. The input data is a JSON response, and the output data is a text response that the user can understand.

[0630] Step 10:

[0631] The user checks the answer displayed on the device. This allows the user to quickly obtain the appropriate answer to the question. The input data is the converted answer, and the output data is usable information based on the user's understanding.

[0632] As described above, the present invention is a system that provides quick and accurate answers to user inquiries in food delivery services.

[0633] 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.

[0634] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses, further incorporating an emotion engine that recognizes user emotions. This system primarily consists of a server, a user terminal, and the user. Specific embodiments are described in detail below.

[0635] System configuration and operation

[0636] User actions

[0637] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[0638] Processing at the user terminal

[0639] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0640] Processing on the server

[0641] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[0642] 1. Received:

[0643] The server accepts POST requests to a specific endpoint (for example, / query).

[0644] 2. Analysis:

[0645] The received inquiry is analyzed using a natural language processing (NLP) model. This model often utilizes, for example, industry-standard natural language processing toolkits.

[0646] 3. Emotion analysis:

[0647] An emotion engine is used to analyze the user's emotions contained in their inquiry. For example, based on the wording and context in which the user enters their question, the emotion engine determines whether the user is happy, angry, anxious, etc.

[0648] 4. Answer generation:

[0649] Based on the analysis results, the most appropriate response is generated. By also taking sentiment analysis results into consideration, responses adapted to the user's emotions are generated.

[0650] 5. Submit your response:

[0651] The generated response is formatted in JSON format and sent back to the user's terminal.

[0652] Use of natural language processing models

[0653] The server analyzes queries using a natural language processing model. This model, for example, uses an industry-standard natural language processing toolkit. This allows the server to understand the user's input question and context and formulate a meaningful response.

[0654] Using an Emotion Engine

[0655] The server uses an emotion engine to analyze the user's emotions from their inquiries. The emotion engine analyzes the text data entered by the user and employs algorithms to identify specific emotional states. This allows the server to provide responses tailored to the user's emotions.

[0656] Specific example

[0657] Suppose a user sends the following inquiry from their device:

[0658] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0659] Question: What are Python's uses? (Sentimental state: Interested)

[0660] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response similar to the following:

[0661] Answer: "Python is widely used in data analysis, web development, AI / machine learning, and more. It's also extremely useful in game development and education."

[0662] This response is sent back to the user's terminal in JSON format. In this way, the user can receive quick and accurate information along with an answer that suits their feelings.

[0663] Records and management

[0664] Furthermore, this system records the generated answers and corresponding questions in a database. In addition, user sentiment data is also recorded. This can be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0665] The above describes the embodiments of the present invention. This system makes it possible to respond quickly and accurately to user inquiries and to provide appropriate answers that take into account the user's feelings.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] Server startup

[0669] The server executes a computer program to launch the Flask application.

[0670] The system enters a request-waiting state at a specific endpoint (e.g., / query).

[0671] Step 2:

[0672] User inquiry submission

[0673] The user enters their inquiry details using a terminal.

[0674] For example, you could enter the question, "What are Python used for?"

[0675] The user's terminal formats the inquiry content in JSON format and sends a POST request to the server's endpoint.

[0676] Step 3:

[0677] Inquiry received

[0678] The server receives the POST request.

[0679] The request data is read and converted from JSON format to a Python dictionary object.

[0680] Step 4:

[0681] Inquiry analysis

[0682] The server extracts the query context and question from the JSON data.

[0683] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[0684] Step 5:

[0685] Emotion analysis

[0686] The server uses an emotion engine to analyze the user's emotional state based on the text they input.

[0687] Example: The user's question is analyzed as indicating interest.

[0688] Step 6:

[0689] Answer generation

[0690] The server inputs the extracted context and questions, along with the sentiment analysis results, into a natural language processing (NLP) model.

[0691] NLP models generate the most appropriate answers.

[0692] Example: The server receives the response, "Python is widely used for data analysis, web development, AI, machine learning, etc."

[0693] Step 7:

[0694] Submit your response

[0695] The server formats the generated response into JSON format.

[0696] This JSON response is sent to the user's device.

[0697] Step 8:

[0698] Display the answer

[0699] The user's terminal displays the received response in JSON format on the screen.

[0700] The user confirms the answer, "Python is widely used for data analysis, web development, AI, and machine learning."

[0701] Step 9:

[0702] Log

[0703] The server stores the questions, their answers, and the user's emotional state in a database.

[0704] This data will be used as reference information to respond to future inquiries.

[0705] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers, as well as receive responses that are appropriate to their emotions.

[0706] (Example 2)

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

[0708] Conventional inquiry response systems struggled to quickly generate appropriate answers to user inquiries, particularly in providing responses that considered user emotions. Furthermore, there was a lack of effective methods for managing inquiry and response logs. As a result, improvements in user satisfaction and system accuracy were hindered.

[0709] 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.

[0710] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for analyzing the formatted inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user in JSON format, and means for recording questions and their corresponding answers in a database. This makes it possible to generate quick and appropriate answers to user inquiries and to provide responses that take into account the user's feelings. Furthermore, it is possible to effectively record and manage conversation logs, and improvements in system accuracy can be expected.

[0711] "Means for receiving user inquiries" refers to a device or program for sending inquiries entered by users in text format to a server via a network and receiving them.

[0712] "Means for formatting received queries into JSON format" refers to a device or program that has the function of converting text-based queries received from a user into JSON, a structured data format.

[0713] "Means for parsing formatted queries" refers to a device or program that uses natural language processing techniques and algorithms to analyze structured JSON query data and understand its meaning and intent.

[0714] "Means for generating answers based on analysis results" refers to a device or program that has the function of automatically generating appropriate answers based on the content of the analyzed inquiry.

[0715] "Means for sending the generated response to the user in JSON format" refers to a device or program that formats the generated response back into JSON format and sends it to the user's terminal via a network.

[0716] "Means for recording questions and corresponding answers in a database" refers to a device or program that has the function of storing user inquiries and their corresponding answers in a database in order to centrally manage them.

[0717] A "natural language processing model" refers to algorithms and technologies used to analyze text data and understand and generate human language.

[0718] "Emotional analysis" is a technology that analyzes and identifies the user's emotional state (joy, anger, anxiety, etc.) contained within text.

[0719] "Means for recording and managing dialogue logs" refers to a device or program for recording all interactions between a user and a system and managing them in a format that can be referenced later.

[0720] Modes for carrying out the invention

[0721] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. In particular, by combining it with an emotion engine that recognizes user emotions, it can provide responses that are adapted to the user's emotions. This system mainly consists of a server, a user terminal, and the user.

[0722] System Configuration

[0723] 1. User terminal:

[0724] User terminals include personal computers and smartphones. Users send inquiries to the system through their terminals. Inquiries entered by users are usually in text format, and are submitted by entering the question in an input field on the screen and clicking the submit button.

[0725] 2. Server:

[0726] The server performs the main processing of receiving, parsing, and generating responses to queries sent from user terminals. The server includes the following main components:

[0727] Receiving unit: Receives POST requests at a specific endpoint.

[0728] Formatting section: Formats the received inquiry into JSON format.

[0729] Analysis Unit: Analyzes queries using natural language processing (NLP) models. For example, it uses industry-standard natural language processing toolkits (e.g., SpaCy or NLTK).

[0730] Sentiment Analysis Unit: Uses an emotion engine to analyze the user's emotions included in the inquiry. For example, it uses a standard sentiment analysis algorithm.

[0731] Response generation unit: Based on the analysis results and sentiment analysis results, it generates appropriate responses using a generation AI model (e.g., GPT-3).

[0732] Transmission unit: Formats the generated response into JSON format and sends it to the user's terminal.

[0733] Records Management Department: Records inquiries, responses, and emotional data in a database.

[0734] Specific example

[0735] Suppose a user sends the following inquiry from their device:

[0736] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0737] Question: What are Python's uses? (Sentimental state: Interested)

[0738] The server receives this query and processes it using the following steps:

[0739] 1. The receiving unit receives POST requests to a specific endpoint.

[0740] 2. The formatting section formats the received text into JSON format.

[0741] 3. The analysis unit analyzes the query using an NLP model.

[0742] 4. The emotion analysis unit analyzes the user's emotions.

[0743] 5. The response generation unit inputs prompt text into the generation AI model to generate a response.

[0744] 6. The sending unit sends the generated response in JSON format to the user's terminal.

[0745] 7. The Records Management Department will record inquiries and responses in the database.

[0746] Example of a prompt

[0747] The following is an example of a prompt:

[0748] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[0749] In this way, the system can provide prompt and appropriate answers to user inquiries, and also respond in a way that is sensitive to the user's feelings. This makes it possible to improve both user satisfaction and the accuracy of the system.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Program processing flow

[0752] Step 1:

[0753] The user sends a query from their terminal to the system. Specifically, the user uses their computer to type "What are Python used for?" into the chat box and clicks the send button. The input is a text-based query. The output is that the query text is stored on the terminal.

[0754] Step 2:

[0755] The terminal formats user input into JSON format. Specifically, the query content (text) and the current timestamp are converted into JSON data. The input for this step is the query text entered by the user, and the output is the formatted JSON data.

[0756] Step 3:

[0757] The terminal sends formatted JSON data to the server. Specifically, the terminal sends an HTTP POST request to a specific endpoint on the server (e.g., / query). The input for this step is query data in JSON format, and the output is the request data received on the server side.

[0758] Step 4:

[0759] The server receives a POST request at a specific endpoint. Specifically, the server extracts JSON data from the request body and prepares it for parsing. The input for this step is JSON data sent from the terminal, and the output is data in a parsable format.

[0760] Step 5:

[0761] The server sends the received JSON data to a natural language processing (NLP) model for analysis. Specifically, the server uses industry-standard NLP toolkits (e.g., SpaCy or NLTK) to understand the structure and intent of the text. The input for this step is formalized query data, and the output is structured data as a result of the analysis.

[0762] Step 6:

[0763] The server uses an emotion engine to analyze the user's emotions contained in the query. Specifically, the emotion engine analyzes the user's query text and determines a specific emotional state. The input for this step is the query text, and the output is the emotion analysis result.

[0764] Step 7:

[0765] The server inputs prompt sentences into the generative AI model based on the results of NLP analysis and sentiment analysis, and generates a response. Specifically, the server sends the following prompt sentences to the generative AI model (e.g., GPT-3):

[0766] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[0767] The input for this step is a prompt message containing the analysis results and sentiment analysis results, and the output is the generated response text.

[0768] Step 8:

[0769] The server formats the generated response into JSON format and sends it to the user's terminal. Specifically, the server converts the generated text response into a JSON object and returns it as an HTTP response. The input for this step is the generated response text, and the output is formatted JSON data.

[0770] Step 9:

[0771] The server records queries, generated responses, and sentiment data in a database. Specifically, the server performs INSERT operations on the database to persist query-response pairs. The inputs to this step are query data, response data, and their sentiment analysis results, and the output is the records stored in the database.

[0772] (Application Example 2)

[0773] 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."

[0774] While conventional systems could automatically generate appropriate answers to user inquiries, they lacked the ability to consider user emotions. Furthermore, no system existed that could generate advertising messages tailored to the user's emotions based on their inquiries. Therefore, there was a need for a mechanism that could provide effective advertising that resonated with users' emotions and improve the user experience.

[0775] 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 inquiries from users, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user, means for recording questions and corresponding answers in a database, means for analyzing the user's emotions from the inquiries, means for generating appropriate advertising messages based on the results of the emotion analysis, and means for sending the generated advertising messages to the user. This makes it possible to provide appropriate answers and advertising messages that take the user's emotions into consideration.

[0776] "Means of receiving user inquiries" refers to a function that incorporates user-entered questions and comments into the system.

[0777] "Means for analyzing received inquiries" refers to a function that uses natural language processing (NLP) models to understand and analyze the content of text data received from users.

[0778] "Means for generating answers based on analysis results" refers to a function that automatically creates appropriate answers according to the analyzed inquiry content.

[0779] "Means for sending generated responses to users" refers to a function for sending automatically generated responses back to the user's device in real time.

[0780] "Means for recording questions and corresponding answers in a database" refers to a function that stores user inquiries and the system's responses in a database for future reference and analysis.

[0781] "Methods for analyzing user emotions from inquiries" refers to a function that analyzes the content of a user's inquiry and identifies the emotions contained within it (for example, joy, anxiety, anger, etc.).

[0782] "Means for generating appropriate advertising messages based on sentiment analysis results" refers to a function that automatically creates advertising messages adapted to the user's emotions, taking into account the results of sentiment analysis.

[0783] "Means for sending generated advertising messages to users" refers to the function for sending generated advertising messages to the user's device.

[0784] A "natural language processing model" refers to machine learning algorithms and tools used to analyze text data and understand its meaning and context.

[0785] This invention is a system that analyzes user inquiries and automatically generates appropriate responses and advertising messages according to the user's emotions. Specific embodiments of this system are described in detail below.

[0786] System Configuration

[0787] User actions

[0788] Users submit inquiries from devices such as smartphones. Inquiries are typically entered by the user in text format. For example, they can submit specific questions such as, "Is this new product really useful? I'm a little worried."

[0789] Processing at the user terminal

[0790] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0791] Processing on the server

[0792] Received

[0793] The server accepts POST requests to a specific endpoint (e.g., / query). Received queries are recorded in the database.

[0794] analysis

[0795] The server analyzes incoming queries using a natural language processing (NLP) model. Specifically, it uses a model from the Transformer library to understand the context of the query.

[0796] Emotion analysis

[0797] The server uses an emotion engine to analyze the user's emotions contained in the inquiry. For example, it uses Hugging Face's emotion analysis pipeline to determine whether the user is interested, anxious, angry, etc.

[0798] Response and advertising message generation

[0799] Based on the analysis results, the server generates responses. It also considers the sentiment analysis results to generate advertising messages tailored to the user's emotions. For example, if the user is feeling anxious, it will generate a message that provides reassurance.

[0800] send

[0801] The generated responses and advertising messages are formatted in JSON format and sent back to the user's device.

[0802] Hardware and software to be used

[0803] This system primarily uses the following hardware and software:

[0804] Hardware: Smartphones, servers

[0805] Software: Python, Transformers (Hugging Face), TextBlob

[0806] Data format: JSON

[0807] Specific example

[0808] For example, suppose a user sends the following inquiry from their device:

[0809] Example of a user inquiry: "Is this new product really useful? I'm a little worried."

[0810] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response and advertising message like the following:

[0811] Example of a generated response: "We understand your concerns. This product has received very positive reviews. We believe you will be reassured once you review the detailed information and customer feedback."

[0812] Example of a prompt:

[0813] User: Will this new product really be useful? I'm a little worried.

[0814] System: We understand your concerns. This product has received very high ratings. We believe you will be reassured if you review the detailed information and customer reviews.

[0815] The above describes the embodiments of the present invention. This system enables prompt and accurate responses to user inquiries and provides appropriate answers and advertising messages that take into account the user's emotions.

[0816] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0817] Step 1:

[0818] Users input and submit inquiries in text format from devices such as smartphones. The user's input is then formatted in JSON format as both the context of the inquiry and the specific question. For example, a user might input the question, "Is this new product really useful? I'm a little worried." Input: User's text inquiry. Output: Inquiry formatted in JSON format.

[0819] Step 2:

[0820] The terminal sends a formatted query as a POST request to the server. The server accepts POST requests at a specific endpoint (e.g., / query). Input: A query in JSON format. Output: The request that reached the server's specific endpoint.

[0821] Step 3:

[0822] The server receives the incoming query and records it in the database. Next, it analyzes the query content using a natural language processing (NLP) model. For this analysis, a model from the Transformers library, for example, is used to understand the context of the query. Input: Query data in JSON format. Output: Text analysis data with context understood.

[0823] Step 4:

[0824] The server uses an emotion engine to identify the user's emotions from the inquiry content. It utilizes Hugging Face's emotion analysis pipeline to analyze whether the user is experiencing emotions such as interest, anxiety, joy, or anger. Input: Analyzed text data. Output: User's emotional state information.

[0825] Step 5:

[0826] The server automatically generates appropriate responses based on the analysis results. It also generates advertising messages tailored to the user's emotions based on the sentiment analysis results. For example, if the user is feeling anxious, it generates a message to provide reassurance. Input: Contextual analysis data and emotional state information. Output: User-appropriate responses and advertising messages.

[0827] Step 6:

[0828] The generated responses and advertising messages are formatted in JSON format and sent back to the device. The server sends the generated messages to the user's device. Input: Responses and advertising messages. Output: Return messages in JSON format.

[0829] Step 7:

[0830] The device displays the response and advertising message received from the server. The user can review this and then make further inquiries or utilize the provided information. Input: JSON-formatted message from the server. Output: Response and advertising message displayed on the device.

[0831] 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.

[0832] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0833] 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.

[0834] [Third Embodiment]

[0835] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0836] 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.

[0837] 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).

[0838] 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.

[0839] 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.

[0840] 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).

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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".

[0847] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. This system primarily consists of a server, a user terminal, and the user. Specific embodiments of this system are described in detail below.

[0848] System configuration and operation

[0849] User actions

[0850] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[0851] Processing at the user terminal

[0852] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0853] Processing on the server

[0854] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[0855] 1. Received:

[0856] The server accepts POST requests to a specific endpoint (for example, / query).

[0857] 2. Analysis:

[0858] The received inquiry is analyzed using a natural language processing (NLP) model. This model often includes machine learning models or deep learning models.

[0859] 3. Answer generation:

[0860] Based on the analysis results, generate the most appropriate answer.

[0861] 4. Submit your response:

[0862] The generated response is formatted in JSON format and sent back to the user's terminal.

[0863] Use of natural language processing models

[0864] The server analyzes queries using a natural language processing model. This model uses, for example, a natural language processing toolkit provided by Company X. This allows the server to understand the user's input question and context, and to form a meaningful response.

[0865] Specific example

[0866] Suppose a user sends the following inquiry from their device:

[0867] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0868] Question: What are Python used for?

[0869] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[0870] Answer: "It is widely used in data analysis, web development, AI, machine learning, etc."

[0871] This response is sent back to the user's terminal in JSON format. In this way, the user can obtain information quickly and accurately.

[0872] Records and management

[0873] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[0874] The above describes the embodiments of the present invention. This system enables a rapid and accurate response to user inquiries, thereby contributing to improved customer service.

[0875] The following describes the processing flow.

[0876] Step 1:

[0877] Server startup

[0878] The server executes a Python script to launch the Flask application.

[0879] The server listens for requests at the specified endpoint (for example, / query).

[0880] Step 2:

[0881] User inquiry submission

[0882] The user enters their inquiry details from their device.

[0883] For example, you could enter the question, "What are Python used for?"

[0884] The user's terminal converts this query into JSON format and sends a POST request to the server's endpoint.

[0885] Step 3:

[0886] Inquiry received

[0887] The server receives the POST request.

[0888] The request data is read and converted from JSON format to a Python dictionary object.

[0889] Step 4:

[0890] Inquiry analysis

[0891] The server extracts the context and question from the JSON data.

[0892] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[0893] Step 5:

[0894] Answer generation

[0895] The server inputs the extracted context and question into a natural language processing (NLP) model.

[0896] The NLP model uses this information to generate the optimal response.

[0897] Example: Servers receive the answer, "They are widely used for data analysis, web development, AI, machine learning, etc."

[0898] Step 6:

[0899] Submit your response

[0900] The server formats the generated response into JSON format.

[0901] This JSON response is sent to the user's device.

[0902] Step 7:

[0903] Display the answer

[0904] The user's terminal displays the received JSON-formatted response in the display area.

[0905] The user sees the response on the screen that says, "It is widely used in data analysis, web development, AI, machine learning, etc."

[0906] Step 8:

[0907] Records and management

[0908] The server stores the questions and their answers in a database.

[0909] This will allow the data to be used as reference for responding to future inquiries.

[0910] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers.

[0911] (Example 1)

[0912] 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."

[0913] In today's information and communication society, there is a demand for quick and accurate responses to user inquiries. Traditional systems have faced challenges in improving user satisfaction due to slow processing times and low accuracy in responses. Furthermore, these systems often suffer from inadequate management of response logs, making it difficult to improve future inquiry handling.

[0914] 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.

[0915] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for sending the formatted data to the server, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for formatting the generated answers in JSON format, means for returning the formatted answers to the user terminal, and means for recording the questions and their corresponding answers in a database. This enables rapid and accurate processing of inquiries and generation of answers. Furthermore, by recording and managing logs of the interactions, the accuracy of responses to future inquiries can be improved.

[0916] A "user" refers to a person or organization that makes inquiries to the system.

[0917] An "inquiry" refers to a question or request from a user seeking information from the system or a solution to a problem.

[0918] "Means of receiving" refers to the function of retrieving inquiries sent by users.

[0919] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a format for concisely representing data in text format.

[0920] "Formatting" refers to a function that arranges data into a specific structure or format.

[0921] A "server" refers to a computing device or system that analyzes received queries and generates and transmits responses.

[0922] "Means of analysis" refers to the function of breaking down and evaluating information in order to understand received inquiries and process them appropriately.

[0923] "Means for generating answers" refers to a function that creates appropriate answers to user inquiries based on analysis results.

[0924] "Method of sending back" refers to the function of sending the generated response to the user's terminal.

[0925] A "database" refers to a digital warehouse where information is systematically managed and stored.

[0926] "Means of recording" refers to the function of saving the generated answers and their corresponding queries to a database.

[0927] "Means for recording and managing logs" refers to a function that saves the system's operation history and user interaction history so that it can be referenced and analyzed in the future.

[0928] System Overview

[0929] This invention relates to a system that automatically analyzes user inquiries, generates appropriate responses, and sends them back. This system consists of three elements: a server, a terminal (such as a personal computer or smartphone), and the user. Detailed embodiments are described below.

[0930] User actions

[0931] Users send inquiries to the system using their own devices (such as PCs or smartphones). For example, a user might enter an inquiry such as, "What are Python used for?" The user enters this question into a text box and clicks the submit button.

[0932] Processing at the user terminal

[0933] The user terminal receives the entered query and formats it in JSON format. This data includes the query context and the specific question. The formatted data is sent to the server using the HTTP POST method.

[0934] Processing on the server

[0935] The server accepts POST requests at a specific endpoint. The received data is analyzed using a natural language processing (NLP) model. This model can utilize, for example, a natural language processing toolkit provided by a major company.

[0936] Once the analysis is complete, the server uses a generative AI model to generate the most appropriate answer. This generative AI model takes prompt sentences as input and generates high-quality text. Examples of prompt sentences are as follows:

[0937] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0938] Question: What are Python used for?

[0939] The generated response is formatted in JSON format and sent back to the user's terminal. For example, the output of the generating AI model might produce a response such as "Python is mainly used for data analysis, web development, AI, and machine learning."

[0940] Data recording and management

[0941] The server records the generated answers and corresponding queries in a database. This accumulates a history of interactions with users, which is expected to allow the system to learn from future queries and improve the accuracy of its answers. A general database management system is used to manage the logs.

[0942] Specific example

[0943] For example, consider a scenario where a user submits a query asking, "What are Python used for?" The user's device converts this query into JSON format and sends it to the server. The server receives it and analyzes it using a natural language processing model. As a result, an appropriate answer is generated by an AI model, and the answer, "It is widely used in data analysis, web development, AI, and machine learning," is sent back to the user's device. This answer is recorded in a database and used as reference data for future queries.

[0944] The above describes the "modes for carrying out the invention" of this invention. This system makes it possible to respond quickly and accurately to user inquiries, and is expected to improve user satisfaction.

[0945] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0946] Step 1: Submit a user inquiry

[0947] The user sends a query to the system from their terminal. As input, the user enters a question in text format, such as "What are Python used for?", and clicks the send button. The output is the query transmitted to the user's terminal in text format.

[0948] Step 2: Data formatting on the user terminal

[0949] The user terminal receives the input query and formats it in JSON format. It receives the user's text-based query as input, including the query context. The terminal then converts it into data similar to the following:

[0950] json

[0951] {

[0952] "context": "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning."

[0953] "Question": "What are Python used for?"

[0954] }

[0955] The output is a query in JSON format that is sent to the server.

[0956] Step 3: Receiving the request on the server

[0957] The server accepts POST requests at a specific endpoint. It receives JSON data sent from the user's terminal as input. The output is data containing the query details necessary for analysis.

[0958] Step 4: Server query analysis

[0959] The server analyzes the received JSON data using a natural language processing (NLP) model. This model extracts the intent of the query and important keywords. The server receives JSON data to be analyzed as input. For example, the server might use a natural language processing toolkit from company X for the analysis. The output is a data structure containing the analysis results.

[0960] Step 5: Server-side response generation

[0961] The server uses a generative AI model to generate the most appropriate answer based on the analysis results. It receives the analysis results as input and feeds them to the generative AI model as prompts. An example of a prompt is as follows:

[0962] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[0963] Question: What are Python used for?

[0964] The output is the generated answer text. For example, the generated answer might be "Python is mainly used for data analysis, web development, AI, and machine learning."

[0965] Step 6: Sending the response to the user's terminal

[0966] The server converts the generated response into JSON format and sends it back to the user's terminal. It receives the generated response text as input and formats it into JSON format. The output is the JSON formatted response data sent to the user's terminal.

[0967] Step 7: Recording and managing data in the database

[0968] The server records the generated answers and their corresponding queries in a database. It receives user questions and their corresponding answers as input. The output is the recorded data entries, which are used as reference data for handling future queries.

[0969] The above outlines the specific processing steps of this system's program.

[0970] (Application Example 1)

[0971] 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."

[0972] Traditional food delivery services have struggled to respond quickly and accurately to user inquiries. In particular, there was a lack of efficient systems to provide appropriate answers to specific questions regarding delivery times, menu information, and payment methods. This resulted in decreased user convenience and satisfaction.

[0973] 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.

[0974] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries, and means for generating answers based on the analysis results. This makes it possible to quickly and accurately analyze inquiries regarding food delivery services and provide appropriate answers.

[0975] A "user" is an individual or legal entity that uses the service.

[0976] An "inquiry" is a question or request from a user seeking information about a service.

[0977] "Means of receiving" refers to the function for receiving inquiries from users.

[0978] "Means of analysis" refers to functions for understanding received inquiries and extracting or processing necessary information.

[0979] "Means for generating responses" refers to a function that creates appropriate information to provide to the user based on the analysis results.

[0980] "Means of transmission" refers to the function for communicating the generated response to the user.

[0981] "Means of recording" refers to a function for saving questions and their corresponding answers in a database.

[0982] A "natural language processing model" is an algorithm or program that analyzes human language and converts it into a format that machines can understand.

[0983] A "food delivery service" is a service that delivers meals to a specific location.

[0984] A "dialogue log" is data that records a series of interactions between a user and a system.

[0985] This invention relates to a system for responding quickly and accurately to user inquiries, particularly in food delivery services. Specific embodiments thereof are described below.

[0986] System configuration and operation

[0987] This system primarily consists of user terminals, servers, and databases.

[0988] User actions

[0989] Users submit inquiries from their own devices, such as smartphones. These inquiries are typically entered as text-based questions. For example, specific questions such as "What time will my ordered pizza arrive?" are submitted.

[0990] Processing at the user terminal

[0991] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[0992] Processing on the server

[0993] The server plays a primary role in parsing incoming queries and generating appropriate responses. The server's processing involves the following steps:

[0994] 1. Received:

[0995] The server accepts POST requests to a specific endpoint (for example, / query).

[0996] 2. Analysis:

[0997] The received query is analyzed using a natural language processing (NLP) model. This model could be a generative AI model such as GPT-3 or BERT.

[0998] 3. Answer generation:

[0999] Based on the analysis results, generate the most appropriate answer.

[1000] 4. Submit your response:

[1001] The generated response is formatted in JSON format and sent back to the user's terminal.

[1002] Use of natural language processing models

[1003] The server parses queries using a natural language processing model. This model utilizes, for example, the Transformers library from Hugging Face. This allows the server to understand the user's input question and context and formulate a meaningful response.

[1004] Records and management

[1005] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[1006] Specific example

[1007] Consider a scenario where a user sends the following inquiry from their device:

[1008] Inquiry: "What time will my ordered pizza arrive?"

[1009] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[1010] Answer: "We are currently checking the delivery status. Pizzas are usually delivered within 30 minutes."

[1011] By sending this response back to the user's terminal, the user can obtain quick and accurate information.

[1012] Example of a prompt

[1013] Examples of prompt statements are as follows:

[1014] "Please tell me the delivery status of the pizza I ordered."

[1015] In this way, the embodiment of this invention makes it possible to respond quickly and accurately to inquiries from users.

[1016] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1017] Step 1:

[1018] Users input and submit inquiries using their own devices, such as smartphones. This input includes text-based questions, such as "What is the estimated arrival time for my ordered pizza?". When a user presses an inquiry button on their device, the inquiry content is treated as input data.

[1019] Step 2:

[1020] The user terminal converts the entered query content into JSON format. At this stage, the input data is in text format, and the output data is in JSON format. The terminal formats the input text into a specific format and prepares to send it to the server.

[1021] Step 3:

[1022] The user terminal sends the converted JSON query to the server as a POST request. The input data is formatted JSON, and the request is sent to the appropriate endpoint (e.g., / query) on the server.

[1023] Step 4:

[1024] The server receives POST requests at a specific endpoint. The input data is a query in JSON format, which is then prepared for the necessary parsing processes within the server.

[1025] Step 5:

[1026] The server parses incoming queries using natural language processing models (e.g., GPT-3, BERT). The input data is the query content in JSON format, and the output data is the parsing result. The parsing process uses libraries such as Hugging Face's Transformers library.

[1027] Step 6:

[1028] The server generates an appropriate response based on the analysis results. Based on the analysis results, the AI ​​model selects and generates the most appropriate response. The input data is the analysis results, and the output data is the generated response.

[1029] Step 7:

[1030] The server formats the generated response into JSON format and prepares it for return to the user's terminal. The input data is the generated response, which is then formatted as a JSON response.

[1031] Step 8:

[1032] The server sends a formatted JSON response to the user's terminal as a POST response. The input data is in JSON format and is sent in a format that is easy for the user's terminal to receive.

[1033] Step 9:

[1034] The user terminal parses the JSON response received from the server and converts it into an appropriate format for display to the user. The input data is a JSON response, and the output data is a text response that the user can understand.

[1035] Step 10:

[1036] The user checks the answer displayed on the device. This allows the user to quickly obtain the appropriate answer to the question. The input data is the converted answer, and the output data is usable information based on the user's understanding.

[1037] As described above, the present invention is a system that provides quick and accurate answers to user inquiries in food delivery services.

[1038] 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.

[1039] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses, further incorporating an emotion engine that recognizes user emotions. This system primarily consists of a server, a user terminal, and the user. Specific embodiments are described in detail below.

[1040] System configuration and operation

[1041] User actions

[1042] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[1043] Processing at the user terminal

[1044] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[1045] Processing on the server

[1046] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[1047] 1. Received:

[1048] The server accepts POST requests to a specific endpoint (for example, / query).

[1049] 2. Analysis:

[1050] The received inquiry is analyzed using a natural language processing (NLP) model. This model often utilizes, for example, industry-standard natural language processing toolkits.

[1051] 3. Emotion analysis:

[1052] An emotion engine is used to analyze the user's emotions contained in their inquiry. For example, based on the wording and context in which the user enters their question, the emotion engine determines whether the user is happy, angry, anxious, etc.

[1053] 4. Answer generation:

[1054] Based on the analysis results, the most appropriate response is generated. By also taking sentiment analysis results into consideration, responses adapted to the user's emotions are generated.

[1055] 5. Submit your response:

[1056] The generated response is formatted in JSON format and sent back to the user's terminal.

[1057] Use of natural language processing models

[1058] The server analyzes queries using a natural language processing model. This model, for example, uses an industry-standard natural language processing toolkit. This allows the server to understand the user's input question and context and formulate a meaningful response.

[1059] Using an Emotion Engine

[1060] The server uses an emotion engine to analyze the user's emotions from their inquiries. The emotion engine analyzes the text data entered by the user and employs algorithms to identify specific emotional states. This allows the server to provide responses tailored to the user's emotions.

[1061] Specific example

[1062] Suppose a user sends the following inquiry from their device:

[1063] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1064] Question: What are Python's uses? (Sentimental state: Interested)

[1065] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response similar to the following:

[1066] Answer: "Python is widely used in data analysis, web development, AI / machine learning, and more. It's also extremely useful in game development and education."

[1067] This response is sent back to the user's terminal in JSON format. In this way, the user can receive quick and accurate information along with an answer that suits their feelings.

[1068] Records and management

[1069] Furthermore, this system records the generated answers and corresponding questions in a database. In addition, user sentiment data is also recorded. This can be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[1070] The above describes the embodiments of the present invention. This system makes it possible to respond quickly and accurately to user inquiries and to provide appropriate answers that take into account the user's feelings.

[1071] The following describes the processing flow.

[1072] Step 1:

[1073] Server startup

[1074] The server executes a computer program to launch the Flask application.

[1075] The system enters a request-waiting state at a specific endpoint (e.g., / query).

[1076] Step 2:

[1077] User inquiry submission

[1078] The user enters their inquiry details using a terminal.

[1079] For example, you could enter the question, "What are Python used for?"

[1080] The user's terminal formats the inquiry content in JSON format and sends a POST request to the server's endpoint.

[1081] Step 3:

[1082] Inquiry received

[1083] The server receives the POST request.

[1084] The request data is read and converted from JSON format to a Python dictionary object.

[1085] Step 4:

[1086] Inquiry analysis

[1087] The server extracts the query context and question from the JSON data.

[1088] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[1089] Step 5:

[1090] Emotion analysis

[1091] The server uses an emotion engine to analyze the user's emotional state based on the text they input.

[1092] Example: The user's question is analyzed as indicating interest.

[1093] Step 6:

[1094] Answer generation

[1095] The server inputs the extracted context and questions, along with the sentiment analysis results, into a natural language processing (NLP) model.

[1096] NLP models generate the most appropriate answers.

[1097] Example: The server receives the response, "Python is widely used for data analysis, web development, AI, machine learning, etc."

[1098] Step 7:

[1099] Submit your response

[1100] The server formats the generated response into JSON format.

[1101] This JSON response is sent to the user's device.

[1102] Step 8:

[1103] Display the answer

[1104] The user's terminal displays the received response in JSON format on the screen.

[1105] The user confirms the answer, "Python is widely used for data analysis, web development, AI, and machine learning."

[1106] Step 9:

[1107] Log

[1108] The server stores the questions, their answers, and the user's emotional state in a database.

[1109] This data will be used as reference information to respond to future inquiries.

[1110] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers, as well as receive responses that are appropriate to their emotions.

[1111] (Example 2)

[1112] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1113] Conventional inquiry response systems struggled to quickly generate appropriate answers to user inquiries, particularly in providing responses that considered user emotions. Furthermore, there was a lack of effective methods for managing inquiry and response logs. As a result, improvements in user satisfaction and system accuracy were hindered.

[1114] 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.

[1115] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for analyzing the formatted inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user in JSON format, and means for recording questions and their corresponding answers in a database. This makes it possible to generate quick and appropriate answers to user inquiries and to provide responses that take into account the user's feelings. Furthermore, it is possible to effectively record and manage conversation logs, and improvements in system accuracy can be expected.

[1116] "Means for receiving user inquiries" refers to a device or program for sending inquiries entered by users in text format to a server via a network and receiving them.

[1117] "Means for formatting received queries into JSON format" refers to a device or program that has the function of converting text-based queries received from a user into JSON, a structured data format.

[1118] "Means for parsing formatted queries" refers to a device or program that uses natural language processing techniques and algorithms to analyze structured JSON query data and understand its meaning and intent.

[1119] "Means for generating answers based on analysis results" refers to a device or program that has the function of automatically generating appropriate answers based on the content of the analyzed inquiry.

[1120] "Means for sending the generated response to the user in JSON format" refers to a device or program that formats the generated response back into JSON format and sends it to the user's terminal via a network.

[1121] "Means for recording questions and corresponding answers in a database" refers to a device or program that has the function of storing user inquiries and their corresponding answers in a database in order to centrally manage them.

[1122] A "natural language processing model" refers to algorithms and technologies used to analyze text data and understand and generate human language.

[1123] "Emotional analysis" is a technology that analyzes and identifies the user's emotional state (joy, anger, anxiety, etc.) contained within text.

[1124] "Means for recording and managing dialogue logs" refers to a device or program for recording all interactions between a user and a system and managing them in a format that can be referenced later.

[1125] Modes for carrying out the invention

[1126] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. In particular, by combining it with an emotion engine that recognizes user emotions, it can provide responses that are adapted to the user's emotions. This system mainly consists of a server, a user terminal, and the user.

[1127] System Configuration

[1128] 1. User terminal:

[1129] User terminals include personal computers and smartphones. Users send inquiries to the system through their terminals. Inquiries entered by users are usually in text format, and are submitted by entering the question in an input field on the screen and clicking the submit button.

[1130] 2. Server:

[1131] The server performs the main processing of receiving, parsing, and generating responses to queries sent from user terminals. The server includes the following main components:

[1132] Receiving unit: Receives POST requests at a specific endpoint.

[1133] Formatting section: Formats the received inquiry into JSON format.

[1134] Analysis Unit: Analyzes queries using natural language processing (NLP) models. For example, it uses industry-standard natural language processing toolkits (e.g., SpaCy or NLTK).

[1135] Sentiment Analysis Unit: Uses an emotion engine to analyze the user's emotions included in the inquiry. For example, it uses a standard sentiment analysis algorithm.

[1136] Response generation unit: Based on the analysis results and sentiment analysis results, it generates appropriate responses using a generation AI model (e.g., GPT-3).

[1137] Transmission unit: Formats the generated response into JSON format and sends it to the user's terminal.

[1138] Records Management Department: Records inquiries, responses, and emotional data in a database.

[1139] Specific example

[1140] Suppose a user sends the following inquiry from their device:

[1141] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1142] Question: What are Python's uses? (Sentimental state: Interested)

[1143] The server receives this query and processes it using the following steps:

[1144] 1. The receiving unit receives POST requests to a specific endpoint.

[1145] 2. The formatting section formats the received text into JSON format.

[1146] 3. The analysis unit analyzes the query using an NLP model.

[1147] 4. The emotion analysis unit analyzes the user's emotions.

[1148] 5. The response generation unit inputs prompt text into the generation AI model to generate a response.

[1149] 6. The sending unit sends the generated response in JSON format to the user's terminal.

[1150] 7. The Records Management Department will record inquiries and responses in the database.

[1151] Example of a prompt

[1152] The following is an example of a prompt:

[1153] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[1154] In this way, the system can provide prompt and appropriate answers to user inquiries, and also respond in a way that is sensitive to the user's feelings. This makes it possible to improve both user satisfaction and the accuracy of the system.

[1155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1156] Program processing flow

[1157] Step 1:

[1158] The user sends a query from their terminal to the system. Specifically, the user uses their computer to type "What are Python used for?" into the chat box and clicks the send button. The input is a text-based query. The output is that the query text is stored on the terminal.

[1159] Step 2:

[1160] The terminal formats user input into JSON format. Specifically, the query content (text) and the current timestamp are converted into JSON data. The input for this step is the query text entered by the user, and the output is the formatted JSON data.

[1161] Step 3:

[1162] The terminal sends formatted JSON data to the server. Specifically, the terminal sends an HTTP POST request to a specific endpoint on the server (e.g., / query). The input for this step is query data in JSON format, and the output is the request data received on the server side.

[1163] Step 4:

[1164] The server receives a POST request at a specific endpoint. Specifically, the server extracts JSON data from the request body and prepares it for parsing. The input for this step is JSON data sent from the terminal, and the output is data in a parsable format.

[1165] Step 5:

[1166] The server sends the received JSON data to a natural language processing (NLP) model for analysis. Specifically, the server uses industry-standard NLP toolkits (e.g., SpaCy or NLTK) to understand the structure and intent of the text. The input for this step is formalized query data, and the output is structured data as a result of the analysis.

[1167] Step 6:

[1168] The server uses an emotion engine to analyze the user's emotions contained in the query. Specifically, the emotion engine analyzes the user's query text and determines a specific emotional state. The input for this step is the query text, and the output is the emotion analysis result.

[1169] Step 7:

[1170] The server inputs prompt sentences into the generative AI model based on the results of NLP analysis and sentiment analysis, and generates a response. Specifically, the server sends the following prompt sentences to the generative AI model (e.g., GPT-3):

[1171] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[1172] The input for this step is a prompt message containing the analysis results and sentiment analysis results, and the output is the generated response text.

[1173] Step 8:

[1174] The server formats the generated response into JSON format and sends it to the user's terminal. Specifically, the server converts the generated text response into a JSON object and returns it as an HTTP response. The input for this step is the generated response text, and the output is formatted JSON data.

[1175] Step 9:

[1176] The server records queries, generated responses, and sentiment data in a database. Specifically, the server performs INSERT operations on the database to persist query-response pairs. The inputs to this step are query data, response data, and their sentiment analysis results, and the output is the records stored in the database.

[1177] (Application Example 2)

[1178] 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."

[1179] While conventional systems could automatically generate appropriate answers to user inquiries, they lacked the ability to consider user emotions. Furthermore, no system existed that could generate advertising messages tailored to the user's emotions based on their inquiries. Therefore, there was a need for a mechanism that could provide effective advertising that resonated with users' emotions and improve the user experience.

[1180] 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 inquiries from users, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user, means for recording questions and corresponding answers in a database, means for analyzing the user's emotions from the inquiries, means for generating appropriate advertising messages based on the results of the emotion analysis, and means for sending the generated advertising messages to the user. This makes it possible to provide appropriate answers and advertising messages that take the user's emotions into consideration.

[1181] "Means of receiving user inquiries" refers to a function that incorporates user-entered questions and comments into the system.

[1182] "Means for analyzing received inquiries" refers to a function that uses natural language processing (NLP) models to understand and analyze the content of text data received from users.

[1183] "Means for generating answers based on analysis results" refers to a function that automatically creates appropriate answers according to the analyzed inquiry content.

[1184] "Means for sending generated responses to users" refers to a function for sending automatically generated responses back to the user's device in real time.

[1185] "Means for recording questions and corresponding answers in a database" refers to a function that stores user inquiries and the system's responses in a database for future reference and analysis.

[1186] "Methods for analyzing user emotions from inquiries" refers to a function that analyzes the content of a user's inquiry and identifies the emotions contained within it (for example, joy, anxiety, anger, etc.).

[1187] "Means for generating appropriate advertising messages based on sentiment analysis results" refers to a function that automatically creates advertising messages adapted to the user's emotions, taking into account the results of sentiment analysis.

[1188] "Means for sending generated advertising messages to users" refers to the function for sending generated advertising messages to the user's device.

[1189] A "natural language processing model" refers to machine learning algorithms and tools used to analyze text data and understand its meaning and context.

[1190] This invention is a system that analyzes user inquiries and automatically generates appropriate responses and advertising messages according to the user's emotions. Specific embodiments of this system are described in detail below.

[1191] System Configuration

[1192] User actions

[1193] Users submit inquiries from devices such as smartphones. Inquiries are typically entered by the user in text format. For example, they can submit specific questions such as, "Is this new product really useful? I'm a little worried."

[1194] Processing at the user terminal

[1195] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[1196] Processing on the server

[1197] Received

[1198] The server accepts POST requests to a specific endpoint (e.g., / query). Received queries are recorded in the database.

[1199] analysis

[1200] The server analyzes incoming queries using a natural language processing (NLP) model. Specifically, it uses a model from the Transformer library to understand the context of the query.

[1201] Emotion analysis

[1202] The server uses an emotion engine to analyze the user's emotions contained in the inquiry. For example, it uses Hugging Face's emotion analysis pipeline to determine whether the user is interested, anxious, angry, etc.

[1203] Response and advertising message generation

[1204] Based on the analysis results, the server generates responses. It also considers the sentiment analysis results to generate advertising messages tailored to the user's emotions. For example, if the user is feeling anxious, it will generate a message that provides reassurance.

[1205] send

[1206] The generated responses and advertising messages are formatted in JSON format and sent back to the user's device.

[1207] Hardware and software to be used

[1208] This system primarily uses the following hardware and software:

[1209] Hardware: Smartphones, servers

[1210] Software: Python, Transformers (Hugging Face), TextBlob

[1211] Data format: JSON

[1212] Specific example

[1213] For example, suppose a user sends the following inquiry from their device:

[1214] Example of a user inquiry: "Is this new product really useful? I'm a little worried."

[1215] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response and advertising message like the following:

[1216] Example of a generated response: "We understand your concerns. This product has received very positive reviews. We believe you will be reassured once you review the detailed information and customer feedback."

[1217] Example of a prompt:

[1218] User: Will this new product really be useful? I'm a little worried.

[1219] System: We understand your concerns. This product has received very high ratings. We believe you will be reassured if you review the detailed information and customer reviews.

[1220] The above describes the embodiments of the present invention. This system enables prompt and accurate responses to user inquiries and provides appropriate answers and advertising messages that take into account the user's emotions.

[1221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1222] Step 1:

[1223] Users input and submit inquiries in text format from devices such as smartphones. The user's input is then formatted in JSON format as both the context of the inquiry and the specific question. For example, a user might input the question, "Is this new product really useful? I'm a little worried." Input: User's text inquiry. Output: Inquiry formatted in JSON format.

[1224] Step 2:

[1225] The terminal sends a formatted query as a POST request to the server. The server accepts POST requests at a specific endpoint (e.g., / query). Input: A query in JSON format. Output: The request that reached the server's specific endpoint.

[1226] Step 3:

[1227] The server receives the incoming query and records it in the database. Next, it analyzes the query content using a natural language processing (NLP) model. For this analysis, a model from the Transformers library, for example, is used to understand the context of the query. Input: Query data in JSON format. Output: Text analysis data with context understood.

[1228] Step 4:

[1229] The server uses an emotion engine to identify the user's emotions from the inquiry content. It utilizes Hugging Face's emotion analysis pipeline to analyze whether the user is experiencing emotions such as interest, anxiety, joy, or anger. Input: Analyzed text data. Output: User's emotional state information.

[1230] Step 5:

[1231] The server automatically generates appropriate responses based on the analysis results. It also generates advertising messages tailored to the user's emotions based on the sentiment analysis results. For example, if the user is feeling anxious, it generates a message to provide reassurance. Input: Contextual analysis data and emotional state information. Output: User-appropriate responses and advertising messages.

[1232] Step 6:

[1233] The generated responses and advertising messages are formatted in JSON format and sent back to the device. The server sends the generated messages to the user's device. Input: Responses and advertising messages. Output: Return messages in JSON format.

[1234] Step 7:

[1235] The device displays the response and advertising message received from the server. The user can review this and then make further inquiries or utilize the provided information. Input: JSON-formatted message from the server. Output: Response and advertising message displayed on the device.

[1236] 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.

[1237] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[1238] 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.

[1239] [Fourth Embodiment]

[1240] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1241] 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.

[1242] 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).

[1243] 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.

[1244] 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.

[1245] 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).

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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".

[1253] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. This system primarily consists of a server, a user terminal, and the user. Specific embodiments of this system are described in detail below.

[1254] System configuration and operation

[1255] User actions

[1256] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[1257] Processing at the user terminal

[1258] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[1259] Processing on the server

[1260] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[1261] 1. Received:

[1262] The server accepts POST requests to a specific endpoint (for example, / query).

[1263] 2. Analysis:

[1264] The received inquiry is analyzed using a natural language processing (NLP) model. This model often includes machine learning models or deep learning models.

[1265] 3. Answer generation:

[1266] Based on the analysis results, generate the most appropriate answer.

[1267] 4. Submit your response:

[1268] The generated response is formatted in JSON format and sent back to the user's terminal.

[1269] Use of natural language processing models

[1270] The server analyzes queries using a natural language processing model. This model uses, for example, a natural language processing toolkit provided by Company X. This allows the server to understand the user's input question and context, and to form a meaningful response.

[1271] Specific example

[1272] Suppose a user sends the following inquiry from their device:

[1273] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1274] Question: What are Python used for?

[1275] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[1276] Answer: "It is widely used in data analysis, web development, AI, machine learning, etc."

[1277] This response is sent back to the user's terminal in JSON format. In this way, the user can obtain information quickly and accurately.

[1278] Records and management

[1279] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[1280] The above describes the embodiments of the present invention. This system enables a rapid and accurate response to user inquiries, thereby contributing to improved customer service.

[1281] The following describes the processing flow.

[1282] Step 1:

[1283] Server startup

[1284] The server executes a Python script to launch the Flask application.

[1285] The server listens for requests at the specified endpoint (for example, / query).

[1286] Step 2:

[1287] User inquiry submission

[1288] The user enters their inquiry details from their device.

[1289] For example, you could enter the question, "What are Python used for?"

[1290] The user's terminal converts this query into JSON format and sends a POST request to the server's endpoint.

[1291] Step 3:

[1292] Inquiry received

[1293] The server receives the POST request.

[1294] The request data is read and converted from JSON format to a Python dictionary object.

[1295] Step 4:

[1296] Inquiry analysis

[1297] The server extracts the context and question from the JSON data.

[1298] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[1299] Step 5:

[1300] Answer generation

[1301] The server inputs the extracted context and question into a natural language processing (NLP) model.

[1302] The NLP model uses this information to generate the optimal response.

[1303] Example: Servers receive the answer, "They are widely used for data analysis, web development, AI, machine learning, etc."

[1304] Step 6:

[1305] Submit your response

[1306] The server formats the generated response into JSON format.

[1307] This JSON response is sent to the user's device.

[1308] Step 7:

[1309] Display the answer

[1310] The user's terminal displays the received JSON-formatted response in the display area.

[1311] The user sees the response on the screen that says, "It is widely used in data analysis, web development, AI, machine learning, etc."

[1312] Step 8:

[1313] Records and management

[1314] The server stores the questions and their answers in a database.

[1315] This will allow the data to be used as reference for responding to future inquiries.

[1316] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers.

[1317] (Example 1)

[1318] 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".

[1319] In today's information and communication society, there is a demand for quick and accurate responses to user inquiries. Traditional systems have faced challenges in improving user satisfaction due to slow processing times and low accuracy in responses. Furthermore, these systems often suffer from inadequate management of response logs, making it difficult to improve future inquiry handling.

[1320] 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.

[1321] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for sending the formatted data to the server, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for formatting the generated answers in JSON format, means for returning the formatted answers to the user terminal, and means for recording the questions and their corresponding answers in a database. This enables rapid and accurate processing of inquiries and generation of answers. Furthermore, by recording and managing logs of the interactions, the accuracy of responses to future inquiries can be improved.

[1322] A "user" refers to a person or organization that makes inquiries to the system.

[1323] An "inquiry" refers to a question or request from a user seeking information from the system or a solution to a problem.

[1324] "Means of receiving" refers to the function of retrieving inquiries sent by users.

[1325] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a format for concisely representing data in text format.

[1326] "Formatting" refers to a function that arranges data into a specific structure or format.

[1327] A "server" refers to a computing device or system that analyzes received queries and generates and transmits responses.

[1328] "Means of analysis" refers to the function of breaking down and evaluating information in order to understand received inquiries and process them appropriately.

[1329] "Means for generating answers" refers to a function that creates appropriate answers to user inquiries based on analysis results.

[1330] "Method of sending back" refers to the function of sending the generated response to the user's terminal.

[1331] A "database" refers to a digital warehouse where information is systematically managed and stored.

[1332] "Means of recording" refers to the function of saving the generated answers and their corresponding queries to a database.

[1333] "Means for recording and managing logs" refers to a function that saves the system's operation history and user interaction history so that it can be referenced and analyzed in the future.

[1334] System Overview

[1335] This invention relates to a system that automatically analyzes user inquiries, generates appropriate responses, and sends them back. This system consists of three elements: a server, a terminal (such as a personal computer or smartphone), and the user. Detailed embodiments are described below.

[1336] User actions

[1337] Users send inquiries to the system using their own devices (such as PCs or smartphones). For example, a user might enter an inquiry such as, "What are Python used for?" The user enters this question into a text box and clicks the submit button.

[1338] Processing at the user terminal

[1339] The user terminal receives the entered query and formats it in JSON format. This data includes the query context and the specific question. The formatted data is sent to the server using the HTTP POST method.

[1340] Processing on the server

[1341] The server accepts POST requests at a specific endpoint. The received data is analyzed using a natural language processing (NLP) model. This model can utilize, for example, a natural language processing toolkit provided by a major company.

[1342] Once the analysis is complete, the server uses a generative AI model to generate the most appropriate answer. This generative AI model takes prompt sentences as input and generates high-quality text. Examples of prompt sentences are as follows:

[1343] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1344] Question: What are Python used for?

[1345] The generated response is formatted in JSON format and sent back to the user's terminal. For example, the output of the generating AI model might produce a response such as "Python is mainly used for data analysis, web development, AI, and machine learning."

[1346] Data recording and management

[1347] The server records the generated answers and corresponding queries in a database. This accumulates a history of interactions with users, which is expected to allow the system to learn from future queries and improve the accuracy of its answers. A general database management system is used to manage the logs.

[1348] Specific example

[1349] For example, consider a scenario where a user submits a query asking, "What are Python used for?" The user's device converts this query into JSON format and sends it to the server. The server receives it and analyzes it using a natural language processing model. As a result, an appropriate answer is generated by an AI model, and the answer, "It is widely used in data analysis, web development, AI, and machine learning," is sent back to the user's device. This answer is recorded in a database and used as reference data for future queries.

[1350] The above describes the "modes for carrying out the invention" of this invention. This system makes it possible to respond quickly and accurately to user inquiries, and is expected to improve user satisfaction.

[1351] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1352] Step 1: Submit a user inquiry

[1353] The user sends a query to the system from their terminal. As input, the user enters a question in text format, such as "What are Python used for?", and clicks the send button. The output is the query transmitted to the user's terminal in text format.

[1354] Step 2: Data formatting on the user terminal

[1355] The user terminal receives the input query and formats it in JSON format. It receives the user's text-based query as input, including the query context. The terminal then converts it into data similar to the following:

[1356] json

[1357] {

[1358] "context": "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning."

[1359] "Question": "What are Python used for?"

[1360] }

[1361] The output is a query in JSON format that is sent to the server.

[1362] Step 3: Receiving the request on the server

[1363] The server accepts POST requests at a specific endpoint. It receives JSON data sent from the user's terminal as input. The output is data containing the query details necessary for analysis.

[1364] Step 4: Server query analysis

[1365] The server analyzes the received JSON data using a natural language processing (NLP) model. This model extracts the intent of the query and important keywords. The server receives JSON data to be analyzed as input. For example, the server might use a natural language processing toolkit from company X for the analysis. The output is a data structure containing the analysis results.

[1366] Step 5: Server-side response generation

[1367] The server uses a generative AI model to generate the most appropriate answer based on the analysis results. It receives the analysis results as input and feeds them to the generative AI model as prompts. An example of a prompt is as follows:

[1368] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1369] Question: What are Python used for?

[1370] The output is the generated answer text. For example, the generated answer might be "Python is mainly used for data analysis, web development, AI, and machine learning."

[1371] Step 6: Sending the response to the user's terminal

[1372] The server converts the generated response into JSON format and sends it back to the user's terminal. It receives the generated response text as input and formats it into JSON format. The output is the JSON formatted response data sent to the user's terminal.

[1373] Step 7: Recording and managing data in the database

[1374] The server records the generated answers and their corresponding queries in a database. It receives user questions and their corresponding answers as input. The output is the recorded data entries, which are used as reference data for handling future queries.

[1375] The above outlines the specific processing steps of this system's program.

[1376] (Application Example 1)

[1377] 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".

[1378] Traditional food delivery services have struggled to respond quickly and accurately to user inquiries. In particular, there was a lack of efficient systems to provide appropriate answers to specific questions regarding delivery times, menu information, and payment methods. This resulted in decreased user convenience and satisfaction.

[1379] 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.

[1380] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries, and means for generating answers based on the analysis results. This makes it possible to quickly and accurately analyze inquiries regarding food delivery services and provide appropriate answers.

[1381] A "user" is an individual or legal entity that uses the service.

[1382] An "inquiry" is a question or request from a user seeking information about a service.

[1383] "Means of receiving" refers to the function for receiving inquiries from users.

[1384] "Means of analysis" refers to functions for understanding received inquiries and extracting or processing necessary information.

[1385] "Means for generating responses" refers to a function that creates appropriate information to provide to the user based on the analysis results.

[1386] "Means of transmission" refers to the function for communicating the generated response to the user.

[1387] "Means of recording" refers to a function for saving questions and their corresponding answers in a database.

[1388] A "natural language processing model" is an algorithm or program that analyzes human language and converts it into a format that machines can understand.

[1389] A "food delivery service" is a service that delivers meals to a specific location.

[1390] A "dialogue log" is data that records a series of interactions between a user and a system.

[1391] This invention relates to a system for responding quickly and accurately to user inquiries, particularly in food delivery services. Specific embodiments thereof are described below.

[1392] System configuration and operation

[1393] This system primarily consists of user terminals, servers, and databases.

[1394] User actions

[1395] Users submit inquiries from their own devices, such as smartphones. These inquiries are typically entered as text-based questions. For example, specific questions such as "What time will my ordered pizza arrive?" are submitted.

[1396] Processing at the user terminal

[1397] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[1398] Processing on the server

[1399] The server plays a primary role in parsing incoming queries and generating appropriate responses. The server's processing involves the following steps:

[1400] 1. Received:

[1401] The server accepts POST requests to a specific endpoint (for example, / query).

[1402] 2. Analysis:

[1403] The received query is analyzed using a natural language processing (NLP) model. This model could be a generative AI model such as GPT-3 or BERT.

[1404] 3. Answer generation:

[1405] Based on the analysis results, generate the most appropriate answer.

[1406] 4. Submit your response:

[1407] The generated response is formatted in JSON format and sent back to the user's terminal.

[1408] Use of natural language processing models

[1409] The server parses queries using a natural language processing model. This model utilizes, for example, the Transformers library from Hugging Face. This allows the server to understand the user's input question and context and formulate a meaningful response.

[1410] Records and management

[1411] Furthermore, this system records the generated answers and corresponding questions in a database. This allows them to be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[1412] Specific example

[1413] Consider a scenario where a user sends the following inquiry from their device:

[1414] Inquiry: "What time will my ordered pizza arrive?"

[1415] The server receives this query and performs analysis using a natural language processing model. Based on the analysis, the server generates a response similar to the following:

[1416] Answer: "We are currently checking the delivery status. Pizzas are usually delivered within 30 minutes."

[1417] By sending this response back to the user's terminal, the user can obtain quick and accurate information.

[1418] Example of a prompt

[1419] Examples of prompt statements are as follows:

[1420] "Please tell me the delivery status of the pizza I ordered."

[1421] In this way, the embodiment of this invention makes it possible to respond quickly and accurately to inquiries from users.

[1422] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1423] Step 1:

[1424] Users input and submit inquiries using their own devices, such as smartphones. This input includes text-based questions, such as "What is the estimated arrival time for my ordered pizza?". When a user presses an inquiry button on their device, the inquiry content is treated as input data.

[1425] Step 2:

[1426] The user terminal converts the entered query content into JSON format. At this stage, the input data is in text format, and the output data is in JSON format. The terminal formats the input text into a specific format and prepares to send it to the server.

[1427] Step 3:

[1428] The user terminal sends the converted JSON query to the server as a POST request. The input data is formatted JSON, and the request is sent to the appropriate endpoint (e.g., / query) on the server.

[1429] Step 4:

[1430] The server receives POST requests at a specific endpoint. The input data is a query in JSON format, which is then prepared for the necessary parsing processes within the server.

[1431] Step 5:

[1432] The server parses incoming queries using natural language processing models (e.g., GPT-3, BERT). The input data is the query content in JSON format, and the output data is the parsing result. The parsing process uses libraries such as Hugging Face's Transformers library.

[1433] Step 6:

[1434] The server generates an appropriate response based on the analysis results. Based on the analysis results, the AI ​​model selects and generates the most appropriate response. The input data is the analysis results, and the output data is the generated response.

[1435] Step 7:

[1436] The server formats the generated response into JSON format and prepares it for return to the user's terminal. The input data is the generated response, which is then formatted as a JSON response.

[1437] Step 8:

[1438] The server sends a formatted JSON response to the user's terminal as a POST response. The input data is in JSON format and is sent in a format that is easy for the user's terminal to receive.

[1439] Step 9:

[1440] The user terminal parses the JSON response received from the server and converts it into an appropriate format for display to the user. The input data is a JSON response, and the output data is a text response that the user can understand.

[1441] Step 10:

[1442] The user checks the answer displayed on the device. This allows the user to quickly obtain the appropriate answer to the question. The input data is the converted answer, and the output data is usable information based on the user's understanding.

[1443] As described above, the present invention is a system that provides quick and accurate answers to user inquiries in food delivery services.

[1444] 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.

[1445] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses, further incorporating an emotion engine that recognizes user emotions. This system primarily consists of a server, a user terminal, and the user. Specific embodiments are described in detail below.

[1446] System configuration and operation

[1447] User actions

[1448] Users submit inquiries from their devices (PCs, smartphones, etc.). Inquiries are usually entered by the user in text format. For example, they can submit specific questions such as, "What are Python used for?"

[1449] Processing at the user terminal

[1450] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[1451] Processing on the server

[1452] The server plays a key role in parsing incoming queries and generating appropriate responses. Specifically, the process is carried out in the following steps:

[1453] 1. Received:

[1454] The server accepts POST requests to a specific endpoint (for example, / query).

[1455] 2. Analysis:

[1456] The received inquiry is analyzed using a natural language processing (NLP) model. This model often utilizes, for example, industry-standard natural language processing toolkits.

[1457] 3. Emotion analysis:

[1458] An emotion engine is used to analyze the user's emotions contained in their inquiry. For example, based on the wording and context in which the user enters their question, the emotion engine determines whether the user is happy, angry, anxious, etc.

[1459] 4. Answer generation:

[1460] Based on the analysis results, the most appropriate response is generated. By also taking sentiment analysis results into consideration, responses adapted to the user's emotions are generated.

[1461] 5. Submit your response:

[1462] The generated response is formatted in JSON format and sent back to the user's terminal.

[1463] Use of natural language processing models

[1464] The server analyzes queries using a natural language processing model. This model, for example, uses an industry-standard natural language processing toolkit. This allows the server to understand the user's input question and context and formulate a meaningful response.

[1465] Using an Emotion Engine

[1466] The server uses an emotion engine to analyze the user's emotions from their inquiries. The emotion engine analyzes the text data entered by the user and employs algorithms to identify specific emotional states. This allows the server to provide responses tailored to the user's emotions.

[1467] Specific example

[1468] Suppose a user sends the following inquiry from their device:

[1469] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1470] Question: What are Python's uses? (Sentimental state: Interested)

[1471] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response similar to the following:

[1472] Answer: "Python is widely used in data analysis, web development, AI / machine learning, and more. It's also extremely useful in game development and education."

[1473] This response is sent back to the user's terminal in JSON format. In this way, the user can receive quick and accurate information along with an answer that suits their feelings.

[1474] Records and management

[1475] Furthermore, this system records the generated answers and corresponding questions in a database. In addition, user sentiment data is also recorded. This can be used as reference data for future inquiries. This recording function is expected to improve the system's learning and answer accuracy.

[1476] The above describes the embodiments of the present invention. This system makes it possible to respond quickly and accurately to user inquiries and to provide appropriate answers that take into account the user's feelings.

[1477] The following describes the processing flow.

[1478] Step 1:

[1479] Server startup

[1480] The server executes a computer program to launch the Flask application.

[1481] The system enters a request-waiting state at a specific endpoint (e.g., / query).

[1482] Step 2:

[1483] User inquiry submission

[1484] The user enters their inquiry details using a terminal.

[1485] For example, you could enter the question, "What are Python used for?"

[1486] The user's terminal formats the inquiry content in JSON format and sends a POST request to the server's endpoint.

[1487] Step 3:

[1488] Inquiry received

[1489] The server receives the POST request.

[1490] The request data is read and converted from JSON format to a Python dictionary object.

[1491] Step 4:

[1492] Inquiry analysis

[1493] The server extracts the query context and question from the JSON data.

[1494] Example: Extract the context "Python is a programming language used for a wide range of purposes. In particular, it is widely used in data analysis, web development, AI, and machine learning." and the question "What are Python used for?".

[1495] Step 5:

[1496] Emotion analysis

[1497] The server uses an emotion engine to analyze the user's emotional state based on the text they input.

[1498] Example: The user's question is analyzed as indicating interest.

[1499] Step 6:

[1500] Answer generation

[1501] The server inputs the extracted context and questions, along with the sentiment analysis results, into a natural language processing (NLP) model.

[1502] NLP models generate the most appropriate answers.

[1503] Example: The server receives the response, "Python is widely used for data analysis, web development, AI, machine learning, etc."

[1504] Step 7:

[1505] Submit your response

[1506] The server formats the generated response into JSON format.

[1507] This JSON response is sent to the user's device.

[1508] Step 8:

[1509] Display the answer

[1510] The user's terminal displays the received response in JSON format on the screen.

[1511] The user confirms the answer, "Python is widely used for data analysis, web development, AI, and machine learning."

[1512] Step 9:

[1513] Log

[1514] The server stores the questions, their answers, and the user's emotional state in a database.

[1515] This data will be used as reference information to respond to future inquiries.

[1516] The above outlines the specific processing steps of the present invention. This allows users to obtain quick and accurate answers, as well as receive responses that are appropriate to their emotions.

[1517] (Example 2)

[1518] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1519] Conventional inquiry response systems struggled to quickly generate appropriate answers to user inquiries, particularly in providing responses that considered user emotions. Furthermore, there was a lack of effective methods for managing inquiry and response logs. As a result, improvements in user satisfaction and system accuracy were hindered.

[1520] 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.

[1521] In this invention, the server includes means for receiving inquiries from users, means for formatting the received inquiries in JSON format, means for analyzing the formatted inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user in JSON format, and means for recording questions and their corresponding answers in a database. This makes it possible to generate quick and appropriate answers to user inquiries and to provide responses that take into account the user's feelings. Furthermore, it is possible to effectively record and manage conversation logs, and improvements in system accuracy can be expected.

[1522] "Means for receiving user inquiries" refers to a device or program for sending inquiries entered by users in text format to a server via a network and receiving them.

[1523] "Means for formatting received queries into JSON format" refers to a device or program that has the function of converting text-based queries received from a user into JSON, a structured data format.

[1524] "Means for parsing formatted queries" refers to a device or program that uses natural language processing techniques and algorithms to analyze structured JSON query data and understand its meaning and intent.

[1525] "Means for generating answers based on analysis results" refers to a device or program that has the function of automatically generating appropriate answers based on the content of the analyzed inquiry.

[1526] "Means for sending the generated response to the user in JSON format" refers to a device or program that formats the generated response back into JSON format and sends it to the user's terminal via a network.

[1527] "Means for recording questions and corresponding answers in a database" refers to a device or program that has the function of storing user inquiries and their corresponding answers in a database in order to centrally manage them.

[1528] A "natural language processing model" refers to algorithms and technologies used to analyze text data and understand and generate human language.

[1529] "Emotional analysis" is a technology that analyzes and identifies the user's emotional state (joy, anger, anxiety, etc.) contained within text.

[1530] "Means for recording and managing dialogue logs" refers to a device or program for recording all interactions between a user and a system and managing them in a format that can be referenced later.

[1531] Modes for carrying out the invention

[1532] This invention relates to a system that automatically analyzes user inquiries and generates appropriate responses. In particular, by combining it with an emotion engine that recognizes user emotions, it can provide responses that are adapted to the user's emotions. This system mainly consists of a server, a user terminal, and the user.

[1533] System Configuration

[1534] 1. User terminal:

[1535] User terminals include personal computers and smartphones. Users send inquiries to the system through their terminals. Inquiries entered by users are usually in text format, and are submitted by entering the question in an input field on the screen and clicking the submit button.

[1536] 2. Server:

[1537] The server performs the main processing of receiving, parsing, and generating responses to queries sent from user terminals. The server includes the following main components:

[1538] Receiving unit: Receives POST requests at a specific endpoint.

[1539] Formatting section: Formats the received inquiry into JSON format.

[1540] Analysis Unit: Analyzes queries using natural language processing (NLP) models. For example, it uses industry-standard natural language processing toolkits (e.g., SpaCy or NLTK).

[1541] Sentiment Analysis Unit: Uses an emotion engine to analyze the user's emotions included in the inquiry. For example, it uses a standard sentiment analysis algorithm.

[1542] Response generation unit: Based on the analysis results and sentiment analysis results, it generates appropriate responses using a generation AI model (e.g., GPT-3).

[1543] Transmission unit: Formats the generated response into JSON format and sends it to the user's terminal.

[1544] Records Management Department: Records inquiries, responses, and emotional data in a database.

[1545] Specific example

[1546] Suppose a user sends the following inquiry from their device:

[1547] Context: "Python is a widely used programming language, particularly in data analysis, web development, and AI / machine learning."

[1548] Question: What are Python's uses? (Sentimental state: Interested)

[1549] The server receives this query and processes it using the following steps:

[1550] 1. The receiving unit receives POST requests to a specific endpoint.

[1551] 2. The formatting section formats the received text into JSON format.

[1552] 3. The analysis unit analyzes the query using an NLP model.

[1553] 4. The emotion analysis unit analyzes the user's emotions.

[1554] 5. The response generation unit inputs prompt text into the generation AI model to generate a response.

[1555] 6. The sending unit sends the generated response in JSON format to the user's terminal.

[1556] 7. The Records Management Department will record inquiries and responses in the database.

[1557] Example of a prompt

[1558] The following is an example of a prompt:

[1559] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[1560] In this way, the system can provide prompt and appropriate answers to user inquiries, and also respond in a way that is sensitive to the user's feelings. This makes it possible to improve both user satisfaction and the accuracy of the system.

[1561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1562] Program processing flow

[1563] Step 1:

[1564] The user sends a query from their terminal to the system. Specifically, the user uses their computer to type "What are Python used for?" into the chat box and clicks the send button. The input is a text-based query. The output is that the query text is stored on the terminal.

[1565] Step 2:

[1566] The terminal formats user input into JSON format. Specifically, the query content (text) and the current timestamp are converted into JSON data. The input for this step is the query text entered by the user, and the output is the formatted JSON data.

[1567] Step 3:

[1568] The terminal sends formatted JSON data to the server. Specifically, the terminal sends an HTTP POST request to a specific endpoint on the server (e.g., / query). The input for this step is query data in JSON format, and the output is the request data received on the server side.

[1569] Step 4:

[1570] The server receives a POST request at a specific endpoint. Specifically, the server extracts JSON data from the request body and prepares it for parsing. The input for this step is JSON data sent from the terminal, and the output is data in a parsable format.

[1571] Step 5:

[1572] The server sends the received JSON data to a natural language processing (NLP) model for analysis. Specifically, the server uses industry-standard NLP toolkits (e.g., SpaCy or NLTK) to understand the structure and intent of the text. The input for this step is formalized query data, and the output is structured data as a result of the analysis.

[1573] Step 6:

[1574] The server uses an emotion engine to analyze the user's emotions contained in the query. Specifically, the emotion engine analyzes the user's query text and determines a specific emotional state. The input for this step is the query text, and the output is the emotion analysis result.

[1575] Step 7:

[1576] The server inputs prompt sentences into the generative AI model based on the results of NLP analysis and sentiment analysis, and generates a response. Specifically, the server sends the following prompt sentences to the generative AI model (e.g., GPT-3):

[1577] "The user is in an interested state and has asked the following question: What are Python's uses? Please generate an appropriate answer."

[1578] The input for this step is a prompt message containing the analysis results and sentiment analysis results, and the output is the generated response text.

[1579] Step 8:

[1580] The server formats the generated response into JSON format and sends it to the user's terminal. Specifically, the server converts the generated text response into a JSON object and returns it as an HTTP response. The input for this step is the generated response text, and the output is formatted JSON data.

[1581] Step 9:

[1582] The server records queries, generated responses, and sentiment data in a database. Specifically, the server performs INSERT operations on the database to persist query-response pairs. The inputs to this step are query data, response data, and their sentiment analysis results, and the output is the records stored in the database.

[1583] (Application Example 2)

[1584] 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".

[1585] While conventional systems could automatically generate appropriate answers to user inquiries, they lacked the ability to consider user emotions. Furthermore, no system existed that could generate advertising messages tailored to the user's emotions based on their inquiries. Therefore, there was a need for a mechanism that could provide effective advertising that resonated with users' emotions and improve the user experience.

[1586] 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 inquiries from users, means for analyzing the received inquiries, means for generating answers based on the analysis results, means for sending the generated answers to the user, means for recording questions and corresponding answers in a database, means for analyzing the user's emotions from the inquiries, means for generating appropriate advertising messages based on the results of the emotion analysis, and means for sending the generated advertising messages to the user. This makes it possible to provide appropriate answers and advertising messages that take the user's emotions into consideration.

[1587] "Means of receiving user inquiries" refers to a function that incorporates user-entered questions and comments into the system.

[1588] "Means for analyzing received inquiries" refers to a function that uses natural language processing (NLP) models to understand and analyze the content of text data received from users.

[1589] "Means for generating answers based on analysis results" refers to a function that automatically creates appropriate answers according to the analyzed inquiry content.

[1590] "Means for sending generated responses to users" refers to a function for sending automatically generated responses back to the user's device in real time.

[1591] "Means for recording questions and corresponding answers in a database" refers to a function that stores user inquiries and the system's responses in a database for future reference and analysis.

[1592] "Methods for analyzing user emotions from inquiries" refers to a function that analyzes the content of a user's inquiry and identifies the emotions contained within it (for example, joy, anxiety, anger, etc.).

[1593] "Means for generating appropriate advertising messages based on sentiment analysis results" refers to a function that automatically creates advertising messages adapted to the user's emotions, taking into account the results of sentiment analysis.

[1594] "Means for sending generated advertising messages to users" refers to the function for sending generated advertising messages to the user's device.

[1595] A "natural language processing model" refers to machine learning algorithms and tools used to analyze text data and understand its meaning and context.

[1596] This invention is a system that analyzes user inquiries and automatically generates appropriate responses and advertising messages according to the user's emotions. Specific embodiments of this system are described in detail below.

[1597] System Configuration

[1598] User actions

[1599] Users submit inquiries from devices such as smartphones. Inquiries are typically entered by the user in text format. For example, they can submit specific questions such as, "Is this new product really useful? I'm a little worried."

[1600] Processing at the user terminal

[1601] The user's terminal formats the query content in JSON format and sends a POST request to the server. This format includes the query context and the specific question.

[1602] Processing on the server

[1603] Received

[1604] The server accepts POST requests to a specific endpoint (e.g., / query). Received queries are recorded in the database.

[1605] analysis

[1606] The server analyzes incoming queries using a natural language processing (NLP) model. Specifically, it uses a model from the Transformer library to understand the context of the query.

[1607] Emotion analysis

[1608] The server uses an emotion engine to analyze the user's emotions contained in the inquiry. For example, it uses Hugging Face's emotion analysis pipeline to determine whether the user is interested, anxious, angry, etc.

[1609] Response and advertising message generation

[1610] Based on the analysis results, the server generates responses. It also considers the sentiment analysis results to generate advertising messages tailored to the user's emotions. For example, if the user is feeling anxious, it will generate a message that provides reassurance.

[1611] send

[1612] The generated responses and advertising messages are formatted in JSON format and sent back to the user's device.

[1613] Hardware and software to be used

[1614] This system primarily uses the following hardware and software:

[1615] Hardware: Smartphones, servers

[1616] Software: Python, Transformers (Hugging Face), TextBlob

[1617] Data format: JSON

[1618] Specific example

[1619] For example, suppose a user sends the following inquiry from their device:

[1620] Example of a user inquiry: "Is this new product really useful? I'm a little worried."

[1621] The server receives this query and performs analysis using a natural language processing model and sentiment engine. Based on the analysis, the server generates a response and advertising message like the following:

[1622] Example of a generated response: "We understand your concerns. This product has received very positive reviews. We believe you will be reassured once you review the detailed information and customer feedback."

[1623] Example of a prompt:

[1624] User: Will this new product really be useful? I'm a little worried.

[1625] System: We understand your concerns. This product has received very high ratings. We believe you will be reassured if you review the detailed information and customer reviews.

[1626] The above describes the embodiments of the present invention. This system enables prompt and accurate responses to user inquiries and provides appropriate answers and advertising messages that take into account the user's emotions.

[1627] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1628] Step 1:

[1629] Users input and submit inquiries in text format from devices such as smartphones. The user's input is then formatted in JSON format as both the context of the inquiry and the specific question. For example, a user might input the question, "Is this new product really useful? I'm a little worried." Input: User's text inquiry. Output: Inquiry formatted in JSON format.

[1630] Step 2:

[1631] The terminal sends a formatted query as a POST request to the server. The server accepts POST requests at a specific endpoint (e.g., / query). Input: A query in JSON format. Output: The request that reached the server's specific endpoint.

[1632] Step 3:

[1633] The server receives the incoming query and records it in the database. Next, it analyzes the query content using a natural language processing (NLP) model. For this analysis, a model from the Transformers library, for example, is used to understand the context of the query. Input: Query data in JSON format. Output: Text analysis data with context understood.

[1634] Step 4:

[1635] The server uses an emotion engine to identify the user's emotions from the inquiry content. It utilizes Hugging Face's emotion analysis pipeline to analyze whether the user is experiencing emotions such as interest, anxiety, joy, or anger. Input: Analyzed text data. Output: User's emotional state information.

[1636] Step 5:

[1637] The server automatically generates appropriate responses based on the analysis results. It also generates advertising messages tailored to the user's emotions based on the sentiment analysis results. For example, if the user is feeling anxious, it generates a message to provide reassurance. Input: Contextual analysis data and emotional state information. Output: User-appropriate responses and advertising messages.

[1638] Step 6:

[1639] The generated responses and advertising messages are formatted in JSON format and sent back to the device. The server sends the generated messages to the user's device. Input: Responses and advertising messages. Output: Return messages in JSON format.

[1640] Step 7:

[1641] The device displays the response and advertising message received from the server. The user can review this and then make further inquiries or utilize the provided information. Input: JSON-formatted message from the server. Output: Response and advertising message displayed on the device.

[1642] 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.

[1643] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[1644] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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."

[1651] 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.

[1652] 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.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] The following is further disclosed regarding the embodiments described above.

[1664] (Claim 1)

[1665] A means of receiving inquiries from users,

[1666] A means of analyzing received inquiries,

[1667] A means for generating an answer based on the analysis results,

[1668] A means of sending the generated response to the user,

[1669] A means for recording questions and their corresponding answers in a database,

[1670] A system that includes this.

[1671] (Claim 2)

[1672] The system according to claim 1, comprising means for analyzing a query using a natural language processing model and generating an answer.

[1673] (Claim 3)

[1674] The system according to claim 1, comprising means for recording and managing a log of conversations, including inquiries and responses.

[1675] "Example 1"

[1676] (Claim 1)

[1677] A means of receiving inquiries from users,

[1678] A method for formatting received inquiries into JSON format,

[1679] A means of sending formatted data to a server,

[1680] A means of analyzing received inquiries,

[1681] A means for generating an answer based on the analysis results,

[1682] A method for formatting the generated response into JSON format,

[1683] A means of returning a formatted response to the user's terminal,

[1684] A means for recording questions and their corresponding answers in a database,

[1685] A system that includes this.

[1686] (Claim 2)

[1687] The system according to claim 1, comprising means for analyzing a query using a natural language processing model and generating an answer.

[1688] (Claim 3)

[1689] The system according to claim 1, comprising means for recording and managing a log of conversations, including inquiries and responses.

[1690] "Application Example 1"

[1691] (Claim 1)

[1692] A means of receiving inquiries from users,

[1693] A means of analyzing received inquiries,

[1694] A means for generating an answer based on the analysis results,

[1695] A means of sending the generated response to the user,

[1696] A means for recording questions and their corresponding answers in a database,

[1697] A system including means for analyzing inquiries regarding food delivery services and generating responses.

[1698] (Claim 2)

[1699] The system according to claim 1, comprising means for analyzing a query using a natural language processing model and generating an answer.

[1700] (Claim 3)

[1701] The system according to claim 1, comprising means for recording and managing a log of conversations, including inquiries and responses.

[1702] "Example 2 of combining an emotion engine"

[1703] (Claim 1)

[1704] A means of receiving inquiries from users,

[1705] A method for formatting received inquiries into JSON format,

[1706] A means of parsing a formatted query,

[1707] A means for generating an answer based on the analysis results,

[1708] A means of sending the generated response to the user in JSON format,

[1709] A means for recording questions and their corresponding answers in a database,

[1710] A system that includes this.

[1711] (Claim 2)

[1712] The system according to claim 1, comprising means for analyzing a query using a natural language processing model and generating an answer.

[1713] (Claim 3)

[1714] The system according to claim 1, comprising means for analyzing the user's emotions included in an inquiry.

[1715] (Claim 4)

[1716] The system according to claim 1, comprising means for generating a response based on analysis results and sentiment analysis results.

[1717] (Claim 5)

[1718] The system according to claim 1, comprising means for recording and managing a log of conversations, including inquiries and responses.

[1719] "Application example 2 when combining with an emotional engine"

[1720] (Claim 1)

[1721] A means of receiving inquiries from users,

[1722] A means of analyzing received inquiries,

[1723] A means for generating an answer based on the analysis results,

[1724] A means of sending the generated response to the user,

[1725] A means for recording questions and their corresponding answers in a database,

[1726] Methods for analyzing user emotions from inquiries,

[1727] A means of generating appropriate advertising messages based on the results of sentiment analysis,

[1728] A means of sending the generated advertising message to the user,

[1729] A system that includes this.

[1730] (Claim 2)

[1731] The system according to claim 1, comprising means for analyzing a query using a natural language processing model and generating an answer.

[1732] (Claim 3)

[1733] The system according to claim 1, comprising means for recording and managing a log of conversations, including inquiries and responses. [Explanation of symbols]

[1734] 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 users, A means of analyzing received inquiries, A means for generating an answer based on the analysis results, A means of sending the generated response to the user, A means for recording questions and their corresponding answers in a database, A system that includes this.

2. The system according to claim 1, comprising means for analyzing a query using a natural language processing model and generating an answer.

3. The system according to claim 1, comprising means for recording and managing a log of conversations, including inquiries and responses.

Images