System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a query from a user; means for analyzing the query to identify a corresponding intent and entity; means for retrieving relevant information from a database based on the identified intent and entity; means for generating a response to the query based on the retrieved information; and means for transmitting the generated response to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] A problem with conventional internal inquiry systems is that users must expend a great deal of time and effort searching for various pieces of information. In particular, when manually searching and retrieving information from multiple different systems and databases, users must go through cumbersome and inefficient procedures. Furthermore, depending on the content of the inquiry, simply referencing related pages may not be sufficient, making it difficult to obtain a specific answer. The present invention aims to solve these problems and provide a system that allows users to obtain information smoothly and quickly. [Means for solving the problem]

[0005] The present invention is a system including means for accepting a query from a user, means for analyzing the query and identifying a corresponding intent and entity, means for retrieving related information from a database based on the identified intent and entity, means for generating an answer to the query based on the retrieved information, and means for transmitting the generated answer to a user terminal. According to the present invention, it is possible to provide an accurate and prompt answer to the query content, thereby improving user convenience. Furthermore, by using a natural language processing model to analyze the query, it is possible to identify the intent and entity with high accuracy, and generate a more specific and useful answer.

[0006] A "user" is a person who queries the system and obtains information.

[0007] An "inquiry" is a question or request that a user enters into the system.

[0008] The "receiving means" refers to a method or device by which the system receives inquiries from users.

[0009] "Analysis" is the process of interpreting the received inquiry and understanding its meaning and intent.

[0010] "Intent" refers to the primary purpose or information sought that is extracted from a user's query.

[0011] An "entity" is a word or phrase that refers to a specific object or attribute in a query.

[0012] An "identification means" is a method or device that finds intent and entities from a received query.

[0013] A "means for retrieving information from a database" is a method or apparatus for searching and retrieving relevant information from a database based on the specified intent and entity.

[0014] The "means for generating an answer" refers to a method or device that uses the acquired information to create an answer to provide to the user.

[0015] The "transmitting means" refers to a method or device for transferring the generated answer to the user terminal.

[0016] The "system" refers to a comprehensive collection of devices and methods that includes the above means and provides appropriate answers to user inquiries.

[0017] A "natural language processing model" is a computational model that uses machine learning and statistical methods to analyze user inquiries and understand the meaning and structure of words.

[0018] A "user terminal" is a device such as a computer or smartphone that a user uses to access the system and make inquiries. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention relates to a system for quickly and accurately responding to inquiries from users. Specific embodiments of the system will be described below.

[0041] System Overview

[0042] The system of the present invention consists of a user, a terminal, and a server. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, retrieves appropriate information from a database, generates a response, and sends it to the terminal. The terminal then displays the generated response to the user.

[0043] Example of a system

[0044] User operations

[0045] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[0046] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[0047] Device operation

[0048] 1. The terminal generates an HTTP request to send the entered query to the server.

[0049] The terminal converts the query content into JSON format and sends it to the server.

[0050] Server Operations

[0051] 1. The server receives the HTTP request and analyzes the query.

[0052] The server uses natural language processing models to identify the intent and entities contained in the query.

[0053] For example, identify "payroll (intent)" and "new employee (entity)."

[0054] 2. The server retrieves relevant information from a database based on the identified intent and entity.

[0055] The server generates database queries to search and retrieve the required information.

[0056] 3. The server generates an appropriate response based on the information obtained.

[0057] The server organizes the information and generates an answer in a format that is easy for the user to understand.

[0058] 4. The server sends the generated response in JSON format to the device.

[0059] The server generates an HTTP response and sends the answer back to the terminal.

[0060] Terminal operation (again)

[0061] 1. The device analyzes the response received from the server and displays it to the user.

[0062] The terminal parses the JSON response and displays it in the chatbot interface.

[0063] Specific examples

[0064] Example 1: Payroll enquiry

[0065] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[0066] 2. The device sends this query to the server.

[0067] 3. The server parses the query and identifies the "payroll (intent)" and the "new employee (entity)."

[0068] 4. The server retrieves the relevant information from the database and generates a response such as: "New employee salary is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[0069] 5. The server sends the generated response to the terminal.

[0070] 6. The device displays the received response on the chatbot interface.

[0071] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The user enters a query into the chatbot interface on their device.

[0075] For example, enter "I would like to know about payroll calculations for new employees."

[0076] Step 2:

[0077] The terminal captures the entered query and generates an HTTP request.

[0078] The query content is converted to JSON format and sent to the server.

[0079] Step 3:

[0080] The server receives an HTTP request.

[0081] Use a web framework such as Flask or Django to parse the request content.

[0082] Step 4:

[0083] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[0084] Use NLP models to identify the intent and entities of a query.

[0085] Step 5:

[0086] The server retrieves relevant information from a database based on the identified intent and entity.

[0087] Use SQL or NoSQL to execute queries and extract the required information.

[0088] Step 6:

[0089] Based on the information acquired by the server, an answer is generated in a format that is easy for the user to understand.

[0090] Organize information and construct sentences that fit the context.

[0091] Step 7:

[0092] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[0093] The response content contains the answer.

[0094] Step 8:

[0095] The device parses the JSON response received from the server and displays it in the chatbot interface.

[0096] The user reads the displayed answers from the terminal.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] Conventional systems have had difficulty responding to user inquiries quickly and accurately. Furthermore, there are issues with analysis accuracy and answer generation, which can lead to a decline in the quality of the user experience. In response to these issues, the present invention aims to provide a system that responds to user inquiries quickly and accurately.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for analyzing the query and using a natural language processing model to identify a corresponding intent and entity, means for retrieving related information from a database based on the identified intent and entity, and means for generating an answer to the query based on the retrieved information using a template engine, thereby enabling the server to provide a quick and accurate answer to the user's query.

[0102] A "user" is a user who makes an inquiry to the system.

[0103] A "query" is a question or request that a user enters into the system to request specific information.

[0104] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes a personal computer, a smartphone, etc.

[0105] A "server" is a computer system that analyzes queries, obtains and processes the necessary information, and provides it to users.

[0106] The "JSON format" is a text format that expresses data in JavaScript (registered trademark) Object Notation (JSON), and is lightweight and suitable for data exchange.

[0107] An "HTTP request" is a request based on a communication protocol that allows a terminal to request specific processing or information from a server.

[0108] A "natural language processing model" is an algorithm or mathematical model that understands and analyzes human language and is used to identify query intent and entities.

[0109] "Intent" is the purpose or request behind a user's query.

[0110] An "entity" is an important item or concept included in a user's query.

[0111] A "database" is a data management system that systematically stores specific information and allows it to be quickly searched and retrieved as needed.

[0112] A "template engine" is a system for formatting dynamically generated content and displaying it in an appropriate way for the user.

[0113] An "HTTP response" is a response sent from a server to a terminal, and includes results and data in response to a request.

[0114] A "generative AI model" is an artificial intelligence algorithm that learns from large amounts of data and generates new data and answers.

[0115] The present invention relates to a system for responding to inquiries from users quickly and accurately. The system is composed of users, terminals, and a server. A specific embodiment of the system will be described below.

[0116] User Inquiry

[0117] Users access a terminal and input inquiries through the chatbot interface. The terminal can be a PC, smartphone, or other device. The chatbot interface is configured as a web browser or a dedicated application.

[0118] Terminal handling

[0119] The terminal acquires the query entered by the user and converts the data into JSON format. The converted data is sent to the server as an HTTP request. To generate the HTTP request, JavaScript's JSON.stringify method or the fetch API is used.

[0120] Server Processing

[0121] The server analyzes the HTTP request received from the terminal and extracts JSON data. This analysis is performed using the Python json module, etc. The server then uses a natural language processing model (e.g., GPT-3 (registered trademark)) to identify the intent and entities contained in the query. This process is performed using the Python transformers library.

[0122] Information Acquisition and Answer Generation

[0123] The server generates a database query based on the identified intent and entity, and retrieves the required information from the database. The database may be MySQL (registered trademark) or PostgreSQL. A Python library such as sqlalchemy or psycopg2 is used to generate the database query.

[0124] Next, the server uses a template engine (e.g., Jinja2) to generate a response based on the acquired information. The generated response is then converted back to JSON format and sent to the terminal as an HTTP response.

[0125] Displaying answers to users

[0126] The terminal parses the HTTP response received from the server and extracts the JSON data. The extracted data is displayed on the chatbot interface. To display the data, JavaScript's JSON.parse method and DOM manipulation are used.

[0127] Specific operation example

[0128] A specific example of the operation of this system is shown below.

[0129] Example 1: Payroll enquiry

[0130] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[0131] 2. The device converts this query into JSON format and sends it to the server as an HTTP request.

[0132] 3. The server receives the request and uses a natural language processing model to identify the "payroll intent" and the "new employee entity."

[0133] 4. The server generates a database query based on the identified intent and entities to retrieve the required information.

[0134] 5. The server generates a response based on the information it has obtained, such as: "A new employee's salary is the sum of their base salary and various allowances. For details, please refer to your company's payroll policy."

[0135] 6. The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0136] 7. The device analyzes the received response and displays it on the chatbot interface.

[0137] Prompt Sentence Examples

[0138] Here are some example prompts to input to the generative AI model:

[0139] How do I calculate the salary of a new employee?

[0140] I would like to know about pay deductions if I am late.

[0141] Please tell me the details of the year-end adjustment.

[0142] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model and a template engine, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1:

[0145] Users open the chatbot interface on their device and enter their query.

[0146] Specific behavior: The user enters a specific address in the browser URL bar to open the chatbot page, clicks the text box, enters "I want to know about payroll calculations for new employees," and presses the "Submit" button.

[0147] Input: Text data entered by the user.

[0148] Output: The query data sent to the user's device.

[0149] Step 2:

[0150] The terminal acquires the query entered by the user and converts the data into JSON format.

[0151] Specific behavior: Converts text data to JSON using JavaScript's JSON.stringify method.

[0152] Input: Text data entered by the user.

[0153] Output: Query data converted to JSON format.

[0154] Step 3:

[0155] The terminal sends the converted JSON data to the server as an HTTP request.

[0156] Specific operation: Send a request using the fetch API or axios library.

[0157] Input: Query data converted to JSON format.

[0158] Output: The HTTP request sent to the server.

[0159] Step 4:

[0160] The server analyzes the HTTP request received from the terminal and extracts the JSON data.

[0161] Specific operation: Uses Python's json module to parse the HTTP request and extract the JSON data.

[0162] Input: HTTP request.

[0163] Output: The extracted JSON data.

[0164] Step 5:

[0165] The server uses a natural language processing model (generative AI model) to analyze the query content and identify the intent and entity.

[0166] What it does: Using the Python transformers library, we invoke the model to parse the text data, for example, identifying "payroll (intent)" and "new employee (entity)."

[0167] Input: The extracted JSON data.

[0168] Output: Identified intents and entities.

[0169] Step 6:

[0170] The server generates database queries based on the identified intent and entities to retrieve the required information.

[0171] Specific operations: Generate queries using Python libraries such as sqlalchemy and psycopg2, establish database connections, and execute the queries.

[0172] Input: Identified intents and entities.

[0173] Output: Relevant information retrieved from the database.

[0174] Step 7:

[0175] The server generates a response using a template engine (e.g. Jinja2) based on the retrieved information.

[0176] What it does: Uses a template engine to format the retrieved data and generate an answer, such as "The salary for a new employee is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[0177] Input: Relevant information retrieved from the database.

[0178] Output: The generated answer to display to the user.

[0179] Step 8:

[0180] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0181] What it does: Serialize the answer into JSON data using Python's json module, and create an HTTP response using a web framework such as Flask or Django.

[0182] Input: The generated answer.

[0183] Output: The HTTP response sent from the server to the device.

[0184] Step 9:

[0185] The terminal analyzes the HTTP response received from the server and extracts the JSON data.

[0186] Specific behavior: Parses the response using JavaScript's JSON.parse method.

[0187] Input: The HTTP response from the server.

[0188] Output: The extracted JSON data.

[0189] Step 10:

[0190] The terminal displays the extracted data in a chatbot interface.

[0191] Specific behavior: Uses JavaScript methods to manipulate the DOM and displays the answer in a text box.

[0192] Input: The extracted JSON data.

[0193] Output: The answer displayed on the user's terminal.

[0194] (Application example 1)

[0195] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0196] Current security services require a fast and accurate response when users report an emergency. However, many systems take a long time to respond to inquiries, resulting in delays before users can obtain appropriate countermeasures. There are also technical challenges in understanding the content of inquiries and generating accurate responses. Therefore, a system that can respond quickly and accurately is needed to ensure user safety.

[0197] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0198] In this invention, the server includes means for accepting inquiries from users, means for analyzing the inquiries and identifying corresponding intentions and entities, means for retrieving related information from a database based on the identified intentions and entities, means for generating an answer to the inquiry based on the retrieved information, means for transmitting the generated answer to a user terminal, means for the user to report an emergency, and means for generating appropriate measures in response to the emergency and notifying the user. This makes it possible to respond quickly and accurately to user inquiries and to quickly provide appropriate measures, particularly in emergency situations.

[0199] A "means for accepting user inquiries" is an interface that allows a user to receive input from the system to request information or report a problem.

[0200] "Means for analyzing inquiries and identifying the corresponding intent and entity" refers to a method for analyzing the content of an inquiry received from a user using technologies such as natural language processing and recognizing the purpose (intent) and target (entity) behind the inquiry.

[0201] The "means for obtaining relevant information from a database" is a method for searching and extracting necessary information from a pre-built database based on the identified intent and entity.

[0202] The "means for generating a response to an inquiry based on acquired information" refers to a means for creating a specific and meaningful response to a user's inquiry using information acquired from a database.

[0203] "Means for transmitting the generated answer to the user terminal" refers to a method for transmitting the generated answer to the terminal (such as a smartphone or PC) used by the user.

[0204] "Means for users to report an emergency" refers to an input method that allows users to quickly notify the system when danger or trouble occurs.

[0205] "Means for generating appropriate countermeasures in response to an emergency and notifying the user" refers to a method for generating countermeasures including information and instructions that are most appropriate for the situation when an emergency occurs and notifying the user of them.

[0206] MODE FOR CARRYING OUT THE INVENTION

[0207] System Overview

[0208] This invention is a system for quickly and accurately responding to user inquiries. The system consists of a user terminal, a server, and a database. The user terminal provides a chatbot interface, and the server analyzes the inquiry and retrieves appropriate information from the database to provide the user with an answer. The system also includes functions specialized for reporting and responding to emergency situations.

[0209] Hardware and software used

[0210] Hardware:

[0211] Smartphone (user device)

[0212] Server (cloud-based)

[0213] software:

[0214] Chatbot interface (application installed on the user's device)

[0215] Natural language processing models (e.g., Google® BERT)

[0216] Database (e.g. MySQL)

[0217] Processing flow

[0218] User operations

[0219] Users use a security app installed on their smartphone to report a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[0220] Device operation

[0221] The smartphone receives this query and sends it to the server for analysis. The device converts the query into JSON format and sends it as an HTTP request.

[0222] Server Operations

[0223] The server interprets the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query's intent (e.g., emergency report) and entity (e.g., suspicious person). The server then searches a database to retrieve relevant information based on the identified intent and entity. Based on this information, the server generates an appropriate response for the user and sends it back to the terminal in JSON format.

[0224] Reoperate the device

[0225] The smartphone analyzes the response received from the server and displays it to the user, for example, "Please call the police immediately. A security team is on the way to the scene."

[0226] Specific examples

[0227] The user types "There is a suspicious person loitering around the house" into the device. The device sends this query to the server. The server analyzes the query and identifies the "emergency report (intent)" and the "suspicious person (entity)". The server retrieves relevant information from the database and generates a response saying "Please call the police immediately. A security team is on the way to the scene." The server sends this response to the device, which displays it to the user.

[0228] Prompt Sentence Examples

[0229] An example prompt is:

[0230] We would like to report the following as an emergency:

[0231] "There's a suspicious person hanging around the house."

[0232] Seek advice including appropriate measures.

[0233] This system allows users to make inquiries and emergency reports quickly and accurately and receive appropriate responses.

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1:

[0236] A user launches a security app on their smartphone and reports a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[0237] (Input) The inquiry entered by the user.

[0238] (Output) The inquiry is sent to the terminal.

[0239] Step 2:

[0240] The terminal converts the received inquiry content into JSON format and sends it to the server as an HTTP request.

[0241] (Input) The inquiry entered by the user.

[0242] (Output) The query content is converted to JSON format and an HTTP request is sent to the server.

[0243] Step 3:

[0244] The server parses the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query intent and entities.

[0245] (Input) The HTTP request received by the server (query content in JSON format).

[0246] (Output) The query intent and entities are identified and stored as internal data.

[0247] Step 4:

[0248] Based on the identified intent and entity, the server searches a database to retrieve relevant information.

[0249] (Input) The intent and entity identified by the server.

[0250] (Output) Relevant information is retrieved from the database and stored as internal data.

[0251] Step 5:

[0252] The server generates an appropriate response to the query based on the information it has acquired, converts the response into JSON format, and sends it to the device.

[0253] (Input) Information retrieved from the database.

[0254] (Output) The appropriate response is generated and sent to the terminal in JSON format.

[0255] Step 6:

[0256] The device parses the JSON response received from the server and displays it in the chatbot interface, for example, "Please call the police immediately. A security team is on the way."

[0257] (Input) The JSON response received from the server.

[0258] (Output) The parsed answer is displayed in the chatbot interface.

[0259] This process allows users to make inquiries quickly and accurately and receive appropriate responses.

[0260] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0261] The present invention relates to a system that not only responds to user inquiries quickly and accurately, but also recognizes the user's emotions and generates appropriate answers based on those emotions. Specific embodiments of this system will be described below.

[0262] System Overview

[0263] The system of the present invention comprises a user, a terminal, a server, and an emotion engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and also recognizes the user's emotion using the emotion engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal then displays the generated response to the user.

[0264] Example of a system

[0265] User operations

[0266] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[0267] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[0268] Device operation

[0269] 1. The device generates an HTTP request to send the input query along with the emotion engine to the server.

[0270] The query content is converted to JSON format and sent to the server.

[0271] Server Operations

[0272] 1. The server receives the HTTP request and analyzes the query.

[0273] The server uses a natural language processing (NLP) model to identify the intent and entities contained in the query.

[0274] For example, identify "payroll (intent)" and "new employee (entity)."

[0275] 2. The server uses an emotion engine to recognize the user's emotions.

[0276] For example, the user's emotions may be identified as being in a state of "anxiety" or "doubt."

[0277] 3. The server retrieves relevant information from a database based on the identified intent and entity.

[0278] The server generates database queries to search and retrieve the required information.

[0279] 4. Based on the information obtained, the server adjusts the answer according to the user's feelings and generates an answer in an easy-to-understand format.

[0280] For example, include gentle language and detailed explanations that will ease anxiety.

[0281] 5. The server converts the generated answer into JSON format and returns it to the device as an HTTP response.

[0282] The response content includes answers that take emotions into consideration.

[0283] Terminal operation (again)

[0284] 1. The device analyzes the response received from the server and displays it to the user.

[0285] The terminal parses the JSON response and displays it in the chatbot interface.

[0286] Specific examples

[0287] Example 1: Payroll enquiry

[0288] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[0289] 2. The device sends this query to the server.

[0290] 3. The server analyzes the query, identifies the "payroll calculation (intent)" and the "new employee (entity)," and uses the emotion engine to recognize the user's emotion as "anxiety."

[0291] 4. The server retrieves the relevant information from the database and generates an emotionally sensitive response such as: "A new employee's salary is the sum of their base salary and various allowances. Please refer to our company's payroll policy for details. If you have any questions, please feel free to contact us."

[0292] 5. The server sends the generated response to the terminal.

[0293] 6. The device displays the received response on the chatbot interface.

[0294] As described above, the system of the present invention can provide quick and accurate answers to user inquiries while also taking into consideration the user's feelings, thereby significantly improving user convenience and satisfaction.

[0295] The processing flow will be explained below.

[0296] Step 1:

[0297] The user enters a query into the chatbot interface on their device.

[0298] For example, enter "I would like to know about payroll calculations for new employees."

[0299] Step 2:

[0300] The terminal captures the entered query and generates an HTTP request.

[0301] The query content is converted to JSON format and sent to the server.

[0302] Step 3:

[0303] The server receives an HTTP request.

[0304] Use a web framework such as Flask or Django to parse the request content.

[0305] Step 4:

[0306] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[0307] Use NLP models to identify the intent and entities of a query.

[0308] For example, identify "payroll (intent)" and "new employee (entity)."

[0309] Step 5:

[0310] The server passes the extracted query text to an emotion engine to analyze the user's emotions.

[0311] For example, identify emotions such as "anxiety" or "doubt."

[0312] Step 6:

[0313] The server retrieves relevant information from a database based on the identified intent, entity, and user sentiment.

[0314] Use SQL or NoSQL to run queries and extract the information you need.

[0315] Step 7:

[0316] Based on the information acquired by the server, a response to the query is generated.

[0317] Organize information, construct sentences that are appropriate to the context, and take user emotions into consideration.

[0318] For example, include gentle language and detailed explanations to ease anxiety.

[0319] Step 8:

[0320] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[0321] The response content includes answers that take emotions into consideration.

[0322] Step 9:

[0323] The device parses the JSON response received from the server and displays it in the chatbot interface.

[0324] The user reads the displayed answers from the terminal.

[0325] Example 2

[0326] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0327] In today's information society, it is important for businesses to respond quickly and accurately to diverse user inquiries. However, current inquiry systems often provide uniform answers without considering the user's emotions. This can result in a decline in user satisfaction and trust. Furthermore, responses that do not recognize emotions may not fully resolve the user's concerns or questions.

[0328] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for recognizing the user's emotion based on the identified intention and entity, means for acquiring related information from a database based on the recognized emotion, means for generating an answer based on the acquired information and the recognized emotion, and means for transmitting the generated answer to the user terminal. This makes it possible to provide an answer that takes the user's emotions into consideration. Specifically, if the user is feeling anxious or uncertain, an answer can be provided using careful explanations and gentle expressions that will ease the user's anxiety or doubts, which is expected to improve user satisfaction and reliability.

[0329] A "user" is a subject who makes an inquiry to the system and is the subject to whom information is provided.

[0330] A "terminal" refers to a device used by a user, which is used to input inquiries and display responses.

[0331] The "server" refers to the central component of the system that analyzes queries, identifies intent and entities, recognizes emotions, retrieves corresponding information from a database, and generates answers.

[0332] A "query" refers to a user's request for information from the system.

[0333] "Intent" refers to the purpose or intent behind a user's query.

[0334] "Entity" refers to a specific object or item referred to in a query.

[0335] An "emotion engine" refers to software or algorithms that have the ability to analyze and identify emotions contained in user queries.

[0336] "Relevant information" refers to information in the database that is necessary to provide an appropriate response to a query.

[0337] "Database" refers to a digital storage system for storing and managing related information.

[0338] "Answer" refers to information generated by a server and provided in response to a user's inquiry.

[0339] "Natural Language Processing Model" refers to machine learning algorithms and techniques for analyzing queries and identifying intent and entities.

[0340] MODE FOR CARRYING OUT THE INVENTION

[0341] The system of the present invention aims not only to respond quickly and accurately to inquiries from users, but also to recognize the user's emotions and generate appropriate answers based on those emotions.

[0342] System Configuration

[0343] The system of the present invention is realized by the cooperation of a user, a terminal, a server, and an emotion engine. Each element operates as follows.

[0344] User operations

[0345] Users make inquiries through the chatbot interface on their devices, which are entered in text format and sent to the device.

[0346] As a specific example, consider the case where a user inputs "I would like to know about payroll calculations for new employees." This inquiry is received by the terminal.

[0347] Device operation

[0348] The device converts the received query into JSON format and sends it to the server as an HTTP request using software such as the JavaScript fetch API and the Python requests library.

[0349] Server Operations

[0350] The server performs the following process:

[0351] 1. Receiving and parsing the request

[0352] The server receives HTTP requests using Apache (registered trademark) or Nginx and analyzes the query content using a natural language processing model (e.g., SpaCy or BERT), thereby identifying the intent and entity contained in the query.

[0353] 2. Recognizing User Emotions

[0354] The server uses an emotion engine (e.g., Google Natural Language API or Microsoft® Text Analytics API) to recognize the user's emotion. For example, the user's emotion is identified as "anxiety."

[0355] 3. Retrieving relevant information from the database

[0356] The server retrieves relevant information from a database (e.g. MySQL or PostgreSQL) based on the intent and entities specified, generating queries to find the required information.

[0357] 4. Generating Emotion-Based Answers

[0358] The server generates an answer based on the acquired information, taking into consideration the user's emotions. By using a template engine (e.g., Jinja2), it creates an answer that includes appropriate expressions according to the emotion. The generated answer is converted into JSON format and sent back to the terminal as an HTTP response.

[0359] Reoperate the device

[0360] The device analyzes the response received from the server and displays it on the chatbot interface, allowing the user to obtain an answer to their inquiry.

[0361] Prompt Sentence Examples

[0362] An example of a specific prompt sentence would be, "Please tell me about the payroll calculation for new employees." The server can analyze the sentiment of this query and generate an appropriate answer.

[0363] result

[0364] The system of the present invention is capable of providing answers that take into consideration the user's feelings, and is expected to improve user satisfaction and reliability. Furthermore, by using this system, companies can achieve efficient and effective customer support.

[0365] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0366] Step 1:

[0367] The user inputs a query into the terminal.

[0368] The user opens the chatbot interface on their device and types, "I'd like to know about payroll calculations for new employees."

[0369] This input is sent to the terminal and stored in the terminal's memory.

[0370] Step 2:

[0371] The terminal converts the input into JSON format and sends it to the server.

[0372] The terminal converts the received query into JSON format using JavaScript's fetch API or Python's requests library.

[0373] The converted data is as follows:

[0374] json

[0375] {

[0376] "query": "I want to know about payroll calculations for new employees"

[0377] }

[0378] The terminal generates this JSON data as an HTTP request and sends it to the server.

[0379] Step 3:

[0380] The server receives the request and parses the query.

[0381] The server uses Apache or Nginx to receive HTTP requests.

[0382] The request is processed on the server using the Python Flask framework.

[0383] Analyze the received JSON data and identify the inquiry content.

[0384] Use natural language processing models (e.g., SpaCy or BERT) to identify query intent and entities.

[0385] Input: "I want to know about payroll calculations for new employees."

[0386] Output: "Payroll (Intent)", "New Employee (Entity)"

[0387] Step 4:

[0388] The server uses an emotion engine to recognize the user's emotion.

[0389] The server uses the Google Natural Language API and Microsoft Text Analytics API to analyze user sentiment.

[0390] Input: "I want to know about payroll calculations for new employees."

[0391] Output: Sentiment score indicating "anxiety"

[0392] The server identifies the user's emotion from the API response and recognizes it as "anxiety."

[0393] Step 5:

[0394] The server retrieves the relevant information from a database.

[0395] The server queries the database based on the intent and the entity.

[0396] For example, if you are using a PostgreSQL database, run a query like this:

[0397] SELECT FROM salary_policy WHERE category = 'New Employee';

[0398] Inputs: "Payroll (Intent)", "New Employee (Entity)"

[0399] Output: Applicable salary information

[0400] Step 6:

[0401] The server generates a response according to the emotion and sends it to the device.

[0402] The server uses a template engine (e.g. Jinja2) to generate answers that take the user's feelings into consideration.

[0403] For example, "A new employee's salary is the sum of their basic salary and various allowances. For details, please refer to our company's payroll policy. If you have any questions, please feel free to contact us."

[0404] This generated response is converted into JSON format and sent to the terminal as an HTTP response.

[0405] Input: relevant salary information, sentiment score indicating "anxiety"

[0406] Output: Emotionally sensitive answers

[0407] Step 7:

[0408] The terminal displays the answer to the user.

[0409] The device analyzes the answers received from the server and displays them on the chatbot interface.

[0410] Input: Emotionally sensitive answers

[0411] Output: The answer displayed to the user

[0412] (Application example 2)

[0413] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0414] Conventional chatbots and automated response systems can respond to user inquiries quickly and accurately, but they often do not generate responses that take user emotions into consideration, which can result in lower satisfaction. Therefore, there is a need for systems that can recognize user emotions and generate and adjust appropriate responses based on those emotions. Especially on online shopping sites, providing responses to product-related inquiries that take user emotions into consideration can increase purchasing motivation and improve customer support.

[0415] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for acquiring related information from a database based on the identified intention and entity, means for generating an answer to the inquiry based on the acquired information, means for recognizing the user's emotions and adjusting the answer based on the recognition, and means for transmitting the generated answer to the user terminal. This enables a personalized answer that takes the user's emotions into consideration.

[0416] A "user" is a user who makes an inquiry to the system.

[0417] The "means for accepting an inquiry" is an interface function that accepts input such as text or voice from the user and sends it to the analysis process.

[0418] The "means for analyzing inquiries" refers to natural language processing models and algorithms that analyze the content of the received inquiry and extract intent and entities from it.

[0419] "Intent" is a concept that indicates the type of purpose or request that a user wants to achieve from a system.

[0420] An "entity" is a word or phrase that indicates a specific element or object contained in a user's query.

[0421] The "means for obtaining related information" is a function for searching and obtaining appropriate information from a database based on the analyzed intent and entity.

[0422] The "means for generating an answer" refers to an algorithm or program that generates an answer to a user's inquiry based on the acquired information.

[0423] "Means for recognizing the user's emotions and adjusting responses based on those emotions" refers to a function that uses an emotion recognition engine to identify the user's emotions and corrects and adjusts responses in a way that takes those emotions into consideration.

[0424] The "means for transmitting the answer to the user terminal" refers to a communication and display function for transmitting the generated answer to the user's terminal and displaying it in a format that is easy for the user to view.

[0425] A "natural language processing model" is a computational model that analyzes text data to understand the meaning and structure of language and extract information such as intent and entities.

[0426] An "emotion recognition engine" is a machine learning model or algorithm that identifies emotions from a user's text or voice characteristics and outputs that state.

[0427] A "database" is a digital storage system that stores and manages relevant information to generate answers to inquiries.

[0428] A "user terminal" is a device used by a user to enter inquiries and receive responses, and includes smartphones, tablets, PCs, etc.

[0429] The present invention relates to a system that quickly provides appropriate answers to inquiries from users, recognizes the emotions of the users, and adjusts the answers based on the emotions. Specific embodiments of the system are described in detail below.

[0430] System Overview

[0431] The system of the present invention comprises a user, a terminal, a server, and an emotion recognition engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and further recognizes the user's emotion using the emotion recognition engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal displays the generated response to the user.

[0432] User operations

[0433] The user accesses a terminal and inputs a query through the chatbot interface. For example, the user inputs, "Are these shoes waterproof?"

[0434] Terminal handling

[0435] The device sends the input query to the server along with the emotion recognition engine. To do this, it generates an HTTP request, and the query content is converted to JSON format and sent to the server.

[0436] Server Processing

[0437] The server receives the HTTP request and analyzes the query using a natural language processing (NLP) model, for example, to identify the intent and entities contained in the query.

[0438] The server then uses an emotion recognition engine to recognize the user's emotion, for example, identifying the user's emotion as anxiety.

[0439] The server then retrieves relevant information from a database based on the identified intent and entity, generating database queries to search and retrieve the required information.

[0440] The system then tailors the responses to take into account the perceived emotions and generates specific answers, for example, creating a reassuring answer for a user who is feeling anxious.

[0441] The generated answer is converted to JSON format and sent back to the device as an HTTP response, which includes an emotionally sensitive answer.

[0442] Terminal handling (again)

[0443] The terminal parses the answer received from the server and displays it to the user. It parses the JSON response and generates an answer that is displayed in the chatbot interface.

[0444] Example

[0445] For example, if a user types "Are these shoes waterproof?" into a device, the server analyzes the query and identifies the "waterproof performance of the shoes (intent)" and "shoes (entity)." The emotion recognition engine then recognizes the user's emotion as "anxiety." The server retrieves relevant information from the database, generates an emotion-sensitive response such as "These shoes are made with high-quality waterproof material, so you can wear them safely even on rainy days," and sends it to the device, which then displays it to the user.

[0446] Prompt Sentence Examples

[0447] User Question: "Are these shoes waterproof?"

[0448] As described above, the system of the present invention can provide quick and accurate answers to user inquiries, and can increase user satisfaction by generating answers that take into consideration the user's feelings.

[0449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0450] Step 1:

[0451] A user opens the chatbot interface using a terminal and inputs a query. For example, the user inputs "Are these shoes waterproof?". The input data is a string.

[0452] Step 2:

[0453] The terminal accepts the input query and generates an HTTP request to send it to the server. The query content is converted to JSON format and sent to the server. The input data is the user's query text, and the output data is the HTTP request in JSON format.

[0454] Step 3:

[0455] The server receives an HTTP request and analyzes the query. It uses a natural language processing (NLP) model to identify intents and entities from the query. For example, "Shoe waterproofing" and "Shoes" are identified. The input data is the user's query text, and the output data is a pair of intents and entities.

[0456] Step 4:

[0457] The server uses an emotion recognition engine to recognize the user's emotion. The emotion recognition engine infers the emotion from the user's text and outputs an emotional state such as "anxiety" or "excitement." For example, the user's emotion is identified as "anxiety." The input data is the user's query text, and the output data is the user's emotional state.

[0458] Step 5:

[0459] The server retrieves relevant information from the database based on the identified intent and entity. It generates a database query to search and retrieve the required information. For example, information on waterproof shoes is retrieved. The input data is the intent-entity pair, and the output data is the related information.

[0460] Step 6:

[0461] The server generates an answer based on the acquired information and the user's emotions. For example, it creates an answer that takes emotions into consideration, such as "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data are the relevant information and the user's emotional state, and the output data is the generated answer.

[0462] Step 7:

[0463] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response. Finally, the response sent from the server is received. The input data is the generated response, and the output data is the JSON format HTTP response.

[0464] Step 8:

[0465] The terminal analyzes the answer received from the server and displays it to the user. It parses the JSON response and displays the generated answer on the chatbot interface. For example, the answer might be, "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data is the HTTP response in JSON format, and the output data is the text displayed to the user.

[0466] As a result, the system of the present invention can quickly and accurately respond to user inquiries and provide answers that take into consideration the user's feelings, which is expected to improve user satisfaction and increase purchasing motivation.

[0467] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0468] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0469] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0470] [Second embodiment]

[0471] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0472] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0473] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0474] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0475] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0476] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0477] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0478] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0479] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0480] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0481] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0482] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0483] The present invention relates to a system for quickly and accurately responding to inquiries from users. Specific embodiments of the system will be described below.

[0484] System Overview

[0485] The system of the present invention consists of a user, a terminal, and a server. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, retrieves appropriate information from a database, generates a response, and sends it to the terminal. The terminal then displays the generated response to the user.

[0486] Example of a system

[0487] User operations

[0488] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[0489] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[0490] Device operation

[0491] 1. The terminal generates an HTTP request to send the entered query to the server.

[0492] The terminal converts the query content into JSON format and sends it to the server.

[0493] Server Operations

[0494] 1. The server receives the HTTP request and analyzes the query.

[0495] The server uses natural language processing models to identify the intent and entities contained in the query.

[0496] For example, identify "payroll (intent)" and "new employee (entity)."

[0497] 2. The server retrieves relevant information from a database based on the identified intent and entity.

[0498] The server generates database queries to search and retrieve the required information.

[0499] 3. The server generates an appropriate response based on the information obtained.

[0500] The server organizes the information and generates an answer in a format that is easy for the user to understand.

[0501] 4. The server sends the generated response in JSON format to the device.

[0502] The server generates an HTTP response and sends the answer back to the terminal.

[0503] Terminal operation (again)

[0504] 1. The device analyzes the response received from the server and displays it to the user.

[0505] The terminal parses the JSON response and displays it in the chatbot interface.

[0506] Specific examples

[0507] Example 1: Payroll enquiry

[0508] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

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

[0510] 3. The server parses the query and identifies the "payroll (intent)" and the "new employee (entity)."

[0511] 4. The server retrieves the relevant information from the database and generates a response such as: "New employee salary is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[0512] 5. The server sends the generated response to the terminal.

[0513] 6. The device displays the received response on the chatbot interface.

[0514] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] The user enters a query into the chatbot interface on their device.

[0518] For example, enter "I would like to know about payroll calculations for new employees."

[0519] Step 2:

[0520] The terminal captures the entered query and generates an HTTP request.

[0521] The query content is converted to JSON format and sent to the server.

[0522] Step 3:

[0523] The server receives an HTTP request.

[0524] Use a web framework such as Flask or Django to parse the request content.

[0525] Step 4:

[0526] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[0527] Use NLP models to identify the intent and entities of a query.

[0528] Step 5:

[0529] The server retrieves relevant information from a database based on the identified intent and entity.

[0530] Use SQL or NoSQL to execute queries and extract the required information.

[0531] Step 6:

[0532] Based on the information acquired by the server, an answer is generated in a format that is easy for the user to understand.

[0533] Organize information and construct sentences that fit the context.

[0534] Step 7:

[0535] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[0536] The response content contains the answer.

[0537] Step 8:

[0538] The device parses the JSON response received from the server and displays it in the chatbot interface.

[0539] The user reads the displayed answers from the terminal.

[0540] Example 1

[0541] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] Conventional systems have had difficulty responding to user inquiries quickly and accurately. Furthermore, there are issues with analysis accuracy and answer generation, which can lead to a decline in the quality of the user experience. In response to these issues, the present invention aims to provide a system that responds to user inquiries quickly and accurately.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0544] In this invention, the server includes means for analyzing the query and using a natural language processing model to identify a corresponding intent and entity, means for retrieving related information from a database based on the identified intent and entity, and means for generating an answer to the query based on the retrieved information using a template engine, thereby enabling the server to provide a quick and accurate answer to the user's query.

[0545] A "user" is a user who makes an inquiry to the system.

[0546] A "query" is a question or request that a user enters into the system to request specific information.

[0547] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes a personal computer, a smartphone, etc.

[0548] A "server" is a computer system that analyzes queries, obtains and processes the necessary information, and provides it to users.

[0549] The "JSON format" is a text format that represents data in JavaScript Object Notation (JSON), and is lightweight and suitable for data exchange.

[0550] An "HTTP request" is a request based on a communication protocol that allows a terminal to request specific processing or information from a server.

[0551] A "natural language processing model" is an algorithm or mathematical model that understands and analyzes human language and is used to identify query intent and entities.

[0552] "Intent" is the purpose or request behind a user's query.

[0553] An "entity" is an important item or concept included in a user's query.

[0554] A "database" is a data management system that systematically stores specific information and allows it to be quickly searched and retrieved as needed.

[0555] A "template engine" is a system for formatting dynamically generated content and displaying it in an appropriate way for the user.

[0556] An "HTTP response" is a response sent from a server to a terminal, and includes results and data in response to a request.

[0557] A "generative AI model" is an artificial intelligence algorithm that learns from large amounts of data and generates new data and answers.

[0558] The present invention relates to a system for responding to inquiries from users quickly and accurately. The system is composed of users, terminals, and a server. A specific embodiment of the system will be described below.

[0559] User Inquiry

[0560] Users access a terminal and input inquiries through the chatbot interface. The terminal can be a PC, smartphone, or other device. The chatbot interface is configured as a web browser or a dedicated application.

[0561] Terminal handling

[0562] The terminal acquires the query entered by the user and converts the data into JSON format. The converted data is sent to the server as an HTTP request. To generate the HTTP request, JavaScript's JSON.stringify method or the fetch API is used.

[0563] Server Processing

[0564] The server parses the HTTP request received from the device and extracts JSON data. This parsing is done using Python's json module, for example. The server then uses a natural language processing model (e.g., GPT-3) to identify the intent and entities contained in the query. This process is done using Python's transformers library.

[0565] Information Acquisition and Answer Generation

[0566] The server generates a database query based on the identified intent and entity, and retrieves the required information from the database. The database can be MySQL or PostgreSQL. Python libraries such as sqlalchemy and psycopg2 are used to generate the database query.

[0567] Next, the server uses a template engine (e.g., Jinja2) to generate a response based on the acquired information. The generated response is then converted back to JSON format and sent to the terminal as an HTTP response.

[0568] Displaying answers to users

[0569] The terminal parses the HTTP response received from the server and extracts the JSON data. The extracted data is displayed on the chatbot interface. To display the data, JavaScript's JSON.parse method and DOM manipulation are used.

[0570] Specific operation example

[0571] A specific example of the operation of this system is shown below.

[0572] Example 1: Payroll enquiry

[0573] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[0574] 2. The device converts this query into JSON format and sends it to the server as an HTTP request.

[0575] 3. The server receives the request and uses a natural language processing model to identify the "payroll intent" and the "new employee entity."

[0576] 4. The server generates a database query based on the identified intent and entities to retrieve the required information.

[0577] 5. The server generates a response based on the information it has obtained, such as: "A new employee's salary is the sum of their base salary and various allowances. For details, please refer to your company's payroll policy."

[0578] 6. The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0579] 7. The device analyzes the received response and displays it on the chatbot interface.

[0580] Prompt Sentence Examples

[0581] Here are some example prompts to input to the generative AI model:

[0582] How do I calculate the salary of a new employee?

[0583] I would like to know about pay deductions if I am late.

[0584] Please tell me the details of the year-end adjustment.

[0585] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model and a template engine, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[0586] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0587] Step 1:

[0588] Users open the chatbot interface on their device and enter their query.

[0589] Specific behavior: The user enters a specific address in the browser URL bar to open the chatbot page, clicks the text box, enters "I want to know about payroll calculations for new employees," and presses the "Submit" button.

[0590] Input: Text data entered by the user.

[0591] Output: The query data sent to the user's device.

[0592] Step 2:

[0593] The terminal acquires the query entered by the user and converts the data into JSON format.

[0594] Specific behavior: Converts text data to JSON using JavaScript's JSON.stringify method.

[0595] Input: Text data entered by the user.

[0596] Output: Query data converted to JSON format.

[0597] Step 3:

[0598] The terminal sends the converted JSON data to the server as an HTTP request.

[0599] Specific operation: Send a request using the fetch API or axios library.

[0600] Input: Query data converted to JSON format.

[0601] Output: The HTTP request sent to the server.

[0602] Step 4:

[0603] The server analyzes the HTTP request received from the terminal and extracts the JSON data.

[0604] Specific operation: Uses Python's json module to parse the HTTP request and extract the JSON data.

[0605] Input: HTTP request.

[0606] Output: The extracted JSON data.

[0607] Step 5:

[0608] The server uses a natural language processing model (generative AI model) to analyze the query content and identify the intent and entity.

[0609] What it does: Using the Python transformers library, we invoke the model to parse the text data, for example, identifying "payroll (intent)" and "new employee (entity)."

[0610] Input: The extracted JSON data.

[0611] Output: Identified intents and entities.

[0612] Step 6:

[0613] The server generates database queries based on the identified intent and entities to retrieve the required information.

[0614] Specific operations: Generate queries using Python libraries such as sqlalchemy and psycopg2, establish database connections, and execute the queries.

[0615] Input: Identified intents and entities.

[0616] Output: Relevant information retrieved from the database.

[0617] Step 7:

[0618] The server generates a response using a template engine (e.g. Jinja2) based on the retrieved information.

[0619] What it does: Uses a template engine to format the retrieved data and generate an answer, such as "The salary for a new employee is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[0620] Input: Relevant information retrieved from the database.

[0621] Output: The generated answer to display to the user.

[0622] Step 8:

[0623] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0624] What it does: Serialize the answer into JSON data using Python's json module, and create an HTTP response using a web framework such as Flask or Django.

[0625] Input: The generated answer.

[0626] Output: The HTTP response sent from the server to the device.

[0627] Step 9:

[0628] The terminal analyzes the HTTP response received from the server and extracts the JSON data.

[0629] Specific behavior: Parses the response using JavaScript's JSON.parse method.

[0630] Input: The HTTP response from the server.

[0631] Output: The extracted JSON data.

[0632] Step 10:

[0633] The terminal displays the extracted data in a chatbot interface.

[0634] Specific behavior: Uses JavaScript methods to manipulate the DOM and displays the answer in a text box.

[0635] Input: The extracted JSON data.

[0636] Output: The answer displayed on the user's terminal.

[0637] (Application example 1)

[0638] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0639] Current security services require a fast and accurate response when users report an emergency. However, many systems take a long time to respond to inquiries, resulting in delays before users can obtain appropriate countermeasures. There are also technical challenges in understanding the content of inquiries and generating accurate responses. Therefore, a system that can respond quickly and accurately is needed to ensure user safety.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0641] In this invention, the server includes means for accepting inquiries from users, means for analyzing the inquiries and identifying corresponding intentions and entities, means for retrieving related information from a database based on the identified intentions and entities, means for generating an answer to the inquiry based on the retrieved information, means for transmitting the generated answer to a user terminal, means for the user to report an emergency, and means for generating appropriate measures in response to the emergency and notifying the user. This makes it possible to respond quickly and accurately to user inquiries and to quickly provide appropriate measures, particularly in emergency situations.

[0642] A "means for accepting user inquiries" is an interface that allows a user to receive input from the system to request information or report a problem.

[0643] "Means for analyzing inquiries and identifying the corresponding intent and entity" refers to a method for analyzing the content of an inquiry received from a user using technologies such as natural language processing and recognizing the purpose (intent) and target (entity) behind the inquiry.

[0644] The "means for obtaining relevant information from a database" is a method for searching and extracting necessary information from a pre-built database based on the identified intent and entity.

[0645] The "means for generating a response to an inquiry based on acquired information" refers to a means for creating a specific and meaningful response to a user's inquiry using information acquired from a database.

[0646] "Means for transmitting the generated answer to the user terminal" refers to a method for transmitting the generated answer to the terminal (such as a smartphone or PC) used by the user.

[0647] "Means for users to report an emergency" refers to an input method that allows users to quickly notify the system when danger or trouble occurs.

[0648] "Means for generating appropriate countermeasures in response to an emergency and notifying the user" refers to a method for generating countermeasures including information and instructions that are most appropriate for the situation when an emergency occurs and notifying the user of them.

[0649] MODE FOR CARRYING OUT THE INVENTION

[0650] System Overview

[0651] This invention is a system for quickly and accurately responding to user inquiries. The system consists of a user terminal, a server, and a database. The user terminal provides a chatbot interface, and the server analyzes the inquiry and retrieves appropriate information from the database to provide the user with an answer. The system also includes functions specialized for reporting and responding to emergency situations.

[0652] Hardware and software used

[0653] Hardware:

[0654] Smartphone (user device)

[0655] Server (cloud-based)

[0656] software:

[0657] Chatbot interface (application installed on the user's device)

[0658] Natural language processing models (e.g., Google BERT)

[0659] Database (e.g. MySQL)

[0660] Processing flow

[0661] User operations

[0662] Users use a security app installed on their smartphone to report a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[0663] Device operation

[0664] The smartphone receives this query and sends it to the server for analysis. The device converts the query into JSON format and sends it as an HTTP request.

[0665] Server Operations

[0666] The server interprets the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query's intent (e.g., emergency report) and entity (e.g., suspicious person). The server then searches a database to retrieve relevant information based on the identified intent and entity. Based on this information, the server generates an appropriate response for the user and sends it back to the terminal in JSON format.

[0667] Reoperate the device

[0668] The smartphone analyzes the response received from the server and displays it to the user, for example, "Please call the police immediately. A security team is on the way to the scene."

[0669] Specific examples

[0670] The user types "There is a suspicious person loitering around the house" into the device. The device sends this query to the server. The server analyzes the query and identifies the "emergency report (intent)" and the "suspicious person (entity)". The server retrieves relevant information from the database and generates a response saying "Please call the police immediately. A security team is on the way to the scene." The server sends this response to the device, which displays it to the user.

[0671] Prompt Sentence Examples

[0672] An example prompt is:

[0673] We would like to report the following as an emergency:

[0674] "There's a suspicious person hanging around the house."

[0675] Seek advice including appropriate measures.

[0676] This system allows users to make inquiries and emergency reports quickly and accurately and receive appropriate responses.

[0677] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0678] Step 1:

[0679] A user launches a security app on their smartphone and reports a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[0680] (Input) The inquiry entered by the user.

[0681] (Output) The inquiry is sent to the terminal.

[0682] Step 2:

[0683] The terminal converts the received inquiry content into JSON format and sends it to the server as an HTTP request.

[0684] (Input) The inquiry entered by the user.

[0685] (Output) The query content is converted to JSON format and an HTTP request is sent to the server.

[0686] Step 3:

[0687] The server parses the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query intent and entities.

[0688] (Input) The HTTP request received by the server (query content in JSON format).

[0689] (Output) The query intent and entities are identified and stored as internal data.

[0690] Step 4:

[0691] Based on the identified intent and entity, the server searches a database to retrieve relevant information.

[0692] (Input) The intent and entity identified by the server.

[0693] (Output) Relevant information is retrieved from the database and stored as internal data.

[0694] Step 5:

[0695] The server generates an appropriate response to the query based on the information it has acquired, converts the response into JSON format, and sends it to the device.

[0696] (Input) Information retrieved from the database.

[0697] (Output) The appropriate response is generated and sent to the terminal in JSON format.

[0698] Step 6:

[0699] The device parses the JSON response received from the server and displays it in the chatbot interface, for example, "Please call the police immediately. A security team is on the way."

[0700] (Input) The JSON response received from the server.

[0701] (Output) The parsed answer is displayed in the chatbot interface.

[0702] This process allows users to make inquiries quickly and accurately and receive appropriate responses.

[0703] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0704] The present invention relates to a system that not only responds to user inquiries quickly and accurately, but also recognizes the user's emotions and generates appropriate answers based on those emotions. Specific embodiments of this system will be described below.

[0705] System Overview

[0706] The system of the present invention comprises a user, a terminal, a server, and an emotion engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and also recognizes the user's emotion using the emotion engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal then displays the generated response to the user.

[0707] Example of a system

[0708] User operations

[0709] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[0710] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[0711] Device operation

[0712] 1. The device generates an HTTP request to send the input query along with the emotion engine to the server.

[0713] The query content is converted to JSON format and sent to the server.

[0714] Server Operations

[0715] 1. The server receives the HTTP request and analyzes the query.

[0716] The server uses a natural language processing (NLP) model to identify the intent and entities contained in the query.

[0717] For example, identify "payroll (intent)" and "new employee (entity)."

[0718] 2. The server uses an emotion engine to recognize the user's emotions.

[0719] For example, the user's emotions may be identified as being in a state of "anxiety" or "doubt."

[0720] 3. The server retrieves relevant information from a database based on the identified intent and entity.

[0721] The server generates database queries to search and retrieve the required information.

[0722] 4. Based on the information obtained, the server adjusts the answer according to the user's feelings and generates an answer in an easy-to-understand format.

[0723] For example, include gentle language and detailed explanations that will ease anxiety.

[0724] 5. The server converts the generated answer into JSON format and returns it to the device as an HTTP response.

[0725] The response content includes answers that take emotions into consideration.

[0726] Terminal operation (again)

[0727] 1. The device analyzes the response received from the server and displays it to the user.

[0728] The terminal parses the JSON response and displays it in the chatbot interface.

[0729] Specific examples

[0730] Example 1: Payroll enquiry

[0731] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[0732] 2. The device sends this query to the server.

[0733] 3. The server analyzes the query, identifies the "payroll calculation (intent)" and the "new employee (entity)," and uses the emotion engine to recognize the user's emotion as "anxiety."

[0734] 4. The server retrieves the relevant information from the database and generates an emotionally sensitive response such as: "A new employee's salary is the sum of their base salary and various allowances. Please refer to our company's payroll policy for details. If you have any questions, please feel free to contact us."

[0735] 5. The server sends the generated response to the terminal.

[0736] 6. The device displays the received response on the chatbot interface.

[0737] As described above, the system of the present invention can provide quick and accurate answers to user inquiries while also taking into consideration the user's feelings, thereby significantly improving user convenience and satisfaction.

[0738] The processing flow will be explained below.

[0739] Step 1:

[0740] The user enters a query into the chatbot interface on their device.

[0741] For example, enter "I would like to know about payroll calculations for new employees."

[0742] Step 2:

[0743] The terminal captures the entered query and generates an HTTP request.

[0744] The query content is converted to JSON format and sent to the server.

[0745] Step 3:

[0746] The server receives an HTTP request.

[0747] Use a web framework such as Flask or Django to parse the request content.

[0748] Step 4:

[0749] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[0750] Use NLP models to identify the intent and entities of a query.

[0751] For example, identify "payroll (intent)" and "new employee (entity)."

[0752] Step 5:

[0753] The server passes the extracted query text to an emotion engine to analyze the user's emotions.

[0754] For example, identify emotions such as "anxiety" or "doubt."

[0755] Step 6:

[0756] The server retrieves relevant information from a database based on the identified intent, entity, and user sentiment.

[0757] Use SQL or NoSQL to run queries and extract the information you need.

[0758] Step 7:

[0759] Based on the information acquired by the server, a response to the query is generated.

[0760] Organize information, construct sentences that are appropriate to the context, and take user emotions into consideration.

[0761] For example, include gentle language and detailed explanations to ease anxiety.

[0762] Step 8:

[0763] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[0764] The response content includes answers that take emotions into consideration.

[0765] Step 9:

[0766] The device parses the JSON response received from the server and displays it in the chatbot interface.

[0767] The user reads the displayed answers from the terminal.

[0768] Example 2

[0769] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0770] In today's information society, it is important for businesses to respond quickly and accurately to diverse user inquiries. However, current inquiry systems often provide uniform answers without considering the user's emotions. This can result in a decline in user satisfaction and trust. Furthermore, responses that do not recognize emotions may not fully resolve the user's concerns or questions.

[0771] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for recognizing the user's emotion based on the identified intention and entity, means for acquiring related information from a database based on the recognized emotion, means for generating an answer based on the acquired information and the recognized emotion, and means for transmitting the generated answer to the user terminal. This makes it possible to provide an answer that takes the user's emotions into consideration. Specifically, if the user is feeling anxious or uncertain, an answer can be provided using careful explanations and gentle expressions that will ease the user's anxiety or doubts, which is expected to improve user satisfaction and reliability.

[0772] A "user" is a subject who makes an inquiry to the system and is the subject to whom information is provided.

[0773] A "terminal" refers to a device used by a user, which is used to input inquiries and display responses.

[0774] The "server" refers to the central component of the system that analyzes queries, identifies intent and entities, recognizes emotions, retrieves corresponding information from a database, and generates answers.

[0775] A "query" refers to a user's request for information from the system.

[0776] "Intent" refers to the purpose or intent behind a user's query.

[0777] "Entity" refers to a specific object or item referred to in a query.

[0778] An "emotion engine" refers to software or algorithms that have the ability to analyze and identify emotions contained in user queries.

[0779] "Relevant information" refers to information in the database that is necessary to provide an appropriate response to a query.

[0780] "Database" refers to a digital storage system for storing and managing related information.

[0781] "Answer" refers to information generated by a server and provided in response to a user's inquiry.

[0782] "Natural Language Processing Model" refers to machine learning algorithms and techniques for analyzing queries and identifying intent and entities.

[0783] MODE FOR CARRYING OUT THE INVENTION

[0784] The system of the present invention aims not only to respond quickly and accurately to inquiries from users, but also to recognize the user's emotions and generate appropriate answers based on those emotions.

[0785] System Configuration

[0786] The system of the present invention is realized by the cooperation of a user, a terminal, a server, and an emotion engine. Each element operates as follows.

[0787] User operations

[0788] Users make inquiries through the chatbot interface on their devices, which are entered in text format and sent to the device.

[0789] As a specific example, consider the case where a user inputs "I would like to know about payroll calculations for new employees." This inquiry is received by the terminal.

[0790] Device operation

[0791] The device converts the received query into JSON format and sends it to the server as an HTTP request using software such as the JavaScript fetch API and the Python requests library.

[0792] Server Operations

[0793] The server performs the following process:

[0794] 1. Receiving and parsing the request

[0795] The server receives HTTP requests using Apache or Nginx and analyzes the query using a natural language processing model (e.g., SpaCy or BERT), thereby identifying the intent and entity contained in the query.

[0796] 2. Recognizing User Emotions

[0797] The server uses an emotion engine (e.g., Google Natural Language API or Microsoft Text Analytics API) to recognize the user's emotion. For example, the user's emotion is identified as "anxiety."

[0798] 3. Retrieving relevant information from the database

[0799] The server retrieves relevant information from a database (e.g. MySQL or PostgreSQL) based on the intent and entities specified, generating queries to find the required information.

[0800] 4. Generating Emotion-Based Answers

[0801] The server generates an answer based on the acquired information, taking into consideration the user's emotions. By using a template engine (e.g., Jinja2), it creates an answer that includes appropriate expressions according to the emotion. The generated answer is converted into JSON format and sent back to the terminal as an HTTP response.

[0802] Reoperate the device

[0803] The device analyzes the response received from the server and displays it on the chatbot interface, allowing the user to obtain an answer to their inquiry.

[0804] Prompt Sentence Examples

[0805] An example of a specific prompt sentence would be, "Please tell me about the payroll calculation for new employees." The server can analyze the sentiment of this query and generate an appropriate answer.

[0806] result

[0807] The system of the present invention is capable of providing answers that take into consideration the user's feelings, and is expected to improve user satisfaction and reliability. Furthermore, by using this system, companies can achieve efficient and effective customer support.

[0808] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0809] Step 1:

[0810] The user inputs a query into the terminal.

[0811] The user opens the chatbot interface on their device and types, "I'd like to know about payroll calculations for new employees."

[0812] This input is sent to the terminal and stored in the terminal's memory.

[0813] Step 2:

[0814] The terminal converts the input into JSON format and sends it to the server.

[0815] The terminal converts the received query into JSON format using JavaScript's fetch API or Python's requests library.

[0816] The converted data is as follows:

[0817] json

[0818] {

[0819] "query": "I want to know about payroll calculations for new employees"

[0820] }

[0821] The terminal generates this JSON data as an HTTP request and sends it to the server.

[0822] Step 3:

[0823] The server receives the request and parses the query.

[0824] The server uses Apache or Nginx to receive HTTP requests.

[0825] The request is processed on the server using the Python Flask framework.

[0826] Analyze the received JSON data and identify the inquiry content.

[0827] Use natural language processing models (e.g., SpaCy or BERT) to identify query intent and entities.

[0828] Input: "I want to know about payroll calculations for new employees."

[0829] Output: "Payroll (Intent)", "New Employee (Entity)"

[0830] Step 4:

[0831] The server uses an emotion engine to recognize the user's emotion.

[0832] The server uses the Google Natural Language API and Microsoft Text Analytics API to analyze user sentiment.

[0833] Input: "I want to know about payroll calculations for new employees."

[0834] Output: Sentiment score indicating "anxiety"

[0835] The server identifies the user's emotion from the API response and recognizes it as "anxiety."

[0836] Step 5:

[0837] The server retrieves the relevant information from a database.

[0838] The server queries the database based on the intent and the entity.

[0839] For example, if you are using a PostgreSQL database, run a query like this:

[0840] SELECT FROM salary_policy WHERE category = 'New Employee';

[0841] Inputs: "Payroll (Intent)", "New Employee (Entity)"

[0842] Output: Applicable salary information

[0843] Step 6:

[0844] The server generates a response according to the emotion and sends it to the device.

[0845] The server uses a template engine (e.g. Jinja2) to generate answers that take the user's feelings into consideration.

[0846] For example, "A new employee's salary is the sum of their basic salary and various allowances. For details, please refer to our company's payroll policy. If you have any questions, please feel free to contact us."

[0847] This generated response is converted into JSON format and sent to the terminal as an HTTP response.

[0848] Input: relevant salary information, sentiment score indicating "anxiety"

[0849] Output: Emotionally sensitive answers

[0850] Step 7:

[0851] The terminal displays the answer to the user.

[0852] The device analyzes the answers received from the server and displays them on the chatbot interface.

[0853] Input: Emotionally sensitive answers

[0854] Output: The answer displayed to the user

[0855] (Application example 2)

[0856] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0857] Conventional chatbots and automated response systems can respond to user inquiries quickly and accurately, but they often do not generate responses that take user emotions into consideration, which can result in lower satisfaction. Therefore, there is a need for systems that can recognize user emotions and generate and adjust appropriate responses based on those emotions. Especially on online shopping sites, providing responses to product-related inquiries that take user emotions into consideration can increase purchasing motivation and improve customer support.

[0858] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for acquiring related information from a database based on the identified intention and entity, means for generating an answer to the inquiry based on the acquired information, means for recognizing the user's emotions and adjusting the answer based on the recognition, and means for transmitting the generated answer to the user terminal. This enables a personalized answer that takes the user's emotions into consideration.

[0859] A "user" is a user who makes an inquiry to the system.

[0860] The "means for accepting an inquiry" is an interface function that accepts input such as text or voice from the user and sends it to the analysis process.

[0861] The "means for analyzing inquiries" refers to natural language processing models and algorithms that analyze the content of the received inquiry and extract intent and entities from it.

[0862] "Intent" is a concept that indicates the type of purpose or request that a user wants to achieve from a system.

[0863] An "entity" is a word or phrase that indicates a specific element or object contained in a user's query.

[0864] The "means for obtaining related information" is a function for searching and obtaining appropriate information from a database based on the analyzed intent and entity.

[0865] The "means for generating an answer" refers to an algorithm or program that generates an answer to a user's inquiry based on the acquired information.

[0866] "Means for recognizing the user's emotions and adjusting responses based on those emotions" refers to a function that uses an emotion recognition engine to identify the user's emotions and corrects and adjusts responses in a way that takes those emotions into consideration.

[0867] The "means for transmitting the answer to the user terminal" refers to a communication and display function for transmitting the generated answer to the user's terminal and displaying it in a format that is easy for the user to view.

[0868] A "natural language processing model" is a computational model that analyzes text data to understand the meaning and structure of language and extract information such as intent and entities.

[0869] An "emotion recognition engine" is a machine learning model or algorithm that identifies emotions from a user's text or voice characteristics and outputs that state.

[0870] A "database" is a digital storage system that stores and manages relevant information to generate answers to inquiries.

[0871] A "user terminal" is a device used by a user to enter inquiries and receive responses, and includes smartphones, tablets, PCs, etc.

[0872] The present invention relates to a system that quickly provides appropriate answers to inquiries from users, recognizes the emotions of the users, and adjusts the answers based on the emotions. Specific embodiments of the system are described in detail below.

[0873] System Overview

[0874] The system of the present invention comprises a user, a terminal, a server, and an emotion recognition engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and further recognizes the user's emotion using the emotion recognition engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal displays the generated response to the user.

[0875] User operations

[0876] The user accesses a terminal and inputs a query through the chatbot interface. For example, the user inputs, "Are these shoes waterproof?"

[0877] Terminal handling

[0878] The device sends the input query to the server along with the emotion recognition engine. To do this, it generates an HTTP request, and the query content is converted to JSON format and sent to the server.

[0879] Server Processing

[0880] The server receives the HTTP request and analyzes the query using a natural language processing (NLP) model, for example, to identify the intent and entities contained in the query.

[0881] The server then uses an emotion recognition engine to recognize the user's emotion, for example, identifying the user's emotion as anxiety.

[0882] The server then retrieves relevant information from a database based on the identified intent and entity, generating database queries to search and retrieve the required information.

[0883] The system then tailors the responses to take into account the perceived emotions and generates specific answers, for example, creating a reassuring answer for a user who is feeling anxious.

[0884] The generated answer is converted to JSON format and sent back to the device as an HTTP response, which includes an emotionally sensitive answer.

[0885] Terminal handling (again)

[0886] The terminal parses the answer received from the server and displays it to the user. It parses the JSON response and generates an answer that is displayed in the chatbot interface.

[0887] Example

[0888] For example, if a user types "Are these shoes waterproof?" into a device, the server analyzes the query and identifies the "waterproof performance of the shoes (intent)" and "shoes (entity)." The emotion recognition engine then recognizes the user's emotion as "anxiety." The server retrieves relevant information from the database, generates an emotion-sensitive response such as "These shoes are made with high-quality waterproof material, so you can wear them safely even on rainy days," and sends it to the device, which then displays it to the user.

[0889] Prompt Sentence Examples

[0890] User Question: "Are these shoes waterproof?"

[0891] As described above, the system of the present invention can provide quick and accurate answers to user inquiries, and can increase user satisfaction by generating answers that take into consideration the user's feelings.

[0892] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0893] Step 1:

[0894] A user opens the chatbot interface using a terminal and inputs a query. For example, the user inputs "Are these shoes waterproof?". The input data is a string.

[0895] Step 2:

[0896] The terminal accepts the input query and generates an HTTP request to send it to the server. The query content is converted to JSON format and sent to the server. The input data is the user's query text, and the output data is the HTTP request in JSON format.

[0897] Step 3:

[0898] The server receives an HTTP request and analyzes the query. It uses a natural language processing (NLP) model to identify intents and entities from the query. For example, "Shoe waterproofing" and "Shoes" are identified. The input data is the user's query text, and the output data is a pair of intents and entities.

[0899] Step 4:

[0900] The server uses an emotion recognition engine to recognize the user's emotion. The emotion recognition engine infers the emotion from the user's text and outputs an emotional state such as "anxiety" or "excitement." For example, the user's emotion is identified as "anxiety." The input data is the user's query text, and the output data is the user's emotional state.

[0901] Step 5:

[0902] The server retrieves relevant information from the database based on the identified intent and entity. It generates a database query to search and retrieve the required information. For example, information on waterproof shoes is retrieved. The input data is the intent-entity pair, and the output data is the related information.

[0903] Step 6:

[0904] The server generates an answer based on the acquired information and the user's emotions. For example, it creates an answer that takes emotions into consideration, such as "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data are the relevant information and the user's emotional state, and the output data is the generated answer.

[0905] Step 7:

[0906] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response. Finally, the response sent from the server is received. The input data is the generated response, and the output data is the JSON format HTTP response.

[0907] Step 8:

[0908] The terminal analyzes the answer received from the server and displays it to the user. It parses the JSON response and displays the generated answer on the chatbot interface. For example, the answer might be, "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data is the HTTP response in JSON format, and the output data is the text displayed to the user.

[0909] As a result, the system of the present invention can quickly and accurately respond to user inquiries and provide answers that take into consideration the user's feelings, which is expected to improve user satisfaction and increase purchasing motivation.

[0910] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0911] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0912] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0913] [Third embodiment]

[0914] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0915] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0916] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0917] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0918] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0919] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0920] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0921] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0922] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0923] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0924] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0925] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0926] The present invention relates to a system for quickly and accurately responding to inquiries from users. Specific embodiments of the system will be described below.

[0927] System Overview

[0928] The system of the present invention consists of a user, a terminal, and a server. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, retrieves appropriate information from a database, generates a response, and sends it to the terminal. The terminal then displays the generated response to the user.

[0929] Example of a system

[0930] User operations

[0931] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[0932] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[0933] Device operation

[0934] 1. The terminal generates an HTTP request to send the entered query to the server.

[0935] The terminal converts the query content into JSON format and sends it to the server.

[0936] Server Operations

[0937] 1. The server receives the HTTP request and analyzes the query.

[0938] The server uses natural language processing models to identify the intent and entities contained in the query.

[0939] For example, identify "payroll (intent)" and "new employee (entity)."

[0940] 2. The server retrieves relevant information from a database based on the identified intent and entity.

[0941] The server generates database queries to search and retrieve the required information.

[0942] 3. The server generates an appropriate response based on the information obtained.

[0943] The server organizes the information and generates an answer in a format that is easy for the user to understand.

[0944] 4. The server sends the generated response in JSON format to the device.

[0945] The server generates an HTTP response and sends the answer back to the terminal.

[0946] Terminal operation (again)

[0947] 1. The device analyzes the response received from the server and displays it to the user.

[0948] The terminal parses the JSON response and displays it in the chatbot interface.

[0949] Specific examples

[0950] Example 1: Payroll enquiry

[0951] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[0952] 2. The device sends this query to the server.

[0953] 3. The server parses the query and identifies the "payroll (intent)" and the "new employee (entity)."

[0954] 4. The server retrieves the relevant information from the database and generates a response such as: "New employee salary is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[0955] 5. The server sends the generated response to the terminal.

[0956] 6. The device displays the received response on the chatbot interface.

[0957] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] The user enters a query into the chatbot interface on their device.

[0961] For example, enter "I would like to know about payroll calculations for new employees."

[0962] Step 2:

[0963] The terminal captures the entered query and generates an HTTP request.

[0964] The query content is converted to JSON format and sent to the server.

[0965] Step 3:

[0966] The server receives an HTTP request.

[0967] Use a web framework such as Flask or Django to parse the request content.

[0968] Step 4:

[0969] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[0970] Use NLP models to identify the intent and entities of a query.

[0971] Step 5:

[0972] The server retrieves relevant information from a database based on the identified intent and entity.

[0973] Use SQL or NoSQL to execute queries and extract the required information.

[0974] Step 6:

[0975] Based on the information acquired by the server, an answer is generated in a format that is easy for the user to understand.

[0976] Organize information and construct sentences that fit the context.

[0977] Step 7:

[0978] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[0979] The response content contains the answer.

[0980] Step 8:

[0981] The device parses the JSON response received from the server and displays it in the chatbot interface.

[0982] The user reads the displayed answers from the terminal.

[0983] Example 1

[0984] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0985] Conventional systems have had difficulty responding to user inquiries quickly and accurately. Furthermore, there are issues with analysis accuracy and answer generation, which can lead to a decline in the quality of the user experience. In response to these issues, the present invention aims to provide a system that responds to user inquiries quickly and accurately.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0987] In this invention, the server includes means for analyzing the query and using a natural language processing model to identify a corresponding intent and entity, means for retrieving related information from a database based on the identified intent and entity, and means for generating an answer to the query based on the retrieved information using a template engine, thereby enabling the server to provide a quick and accurate answer to the user's query.

[0988] A "user" is a user who makes an inquiry to the system.

[0989] A "query" is a question or request that a user enters into the system to request specific information.

[0990] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes a personal computer, a smartphone, etc.

[0991] A "server" is a computer system that analyzes queries, obtains and processes the necessary information, and provides it to users.

[0992] The "JSON format" is a text format that represents data in JavaScript Object Notation (JSON), and is lightweight and suitable for data exchange.

[0993] An "HTTP request" is a request based on a communication protocol that allows a terminal to request specific processing or information from a server.

[0994] A "natural language processing model" is an algorithm or mathematical model that understands and analyzes human language and is used to identify query intent and entities.

[0995] "Intent" is the purpose or request behind a user's query.

[0996] An "entity" is an important item or concept included in a user's query.

[0997] A "database" is a data management system that systematically stores specific information and allows it to be quickly searched and retrieved as needed.

[0998] A "template engine" is a system for formatting dynamically generated content and displaying it in an appropriate way for the user.

[0999] An "HTTP response" is a response sent from a server to a terminal, and includes results and data in response to a request.

[1000] A "generative AI model" is an artificial intelligence algorithm that learns from large amounts of data and generates new data and answers.

[1001] The present invention relates to a system for responding to inquiries from users quickly and accurately. The system is composed of users, terminals, and a server. A specific embodiment of the system will be described below.

[1002] User Inquiry

[1003] Users access a terminal and input inquiries through the chatbot interface. The terminal can be a PC, smartphone, or other device. The chatbot interface is configured as a web browser or a dedicated application.

[1004] Terminal handling

[1005] The terminal acquires the query entered by the user and converts the data into JSON format. The converted data is sent to the server as an HTTP request. To generate the HTTP request, JavaScript's JSON.stringify method or the fetch API is used.

[1006] Server Processing

[1007] The server parses the HTTP request received from the device and extracts JSON data. This parsing is done using Python's json module, for example. The server then uses a natural language processing model (e.g., GPT-3) to identify the intent and entities contained in the query. This process is done using Python's transformers library.

[1008] Information Acquisition and Answer Generation

[1009] The server generates a database query based on the identified intent and entity, and retrieves the required information from the database. The database can be MySQL or PostgreSQL. Python libraries such as sqlalchemy and psycopg2 are used to generate the database query.

[1010] Next, the server uses a template engine (e.g., Jinja2) to generate a response based on the acquired information. The generated response is then converted back to JSON format and sent to the terminal as an HTTP response.

[1011] Displaying answers to users

[1012] The terminal parses the HTTP response received from the server and extracts the JSON data. The extracted data is displayed on the chatbot interface. To display the data, JavaScript's JSON.parse method and DOM manipulation are used.

[1013] Specific operation example

[1014] A specific example of the operation of this system is shown below.

[1015] Example 1: Payroll enquiry

[1016] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[1017] 2. The device converts this query into JSON format and sends it to the server as an HTTP request.

[1018] 3. The server receives the request and uses a natural language processing model to identify the "payroll intent" and the "new employee entity."

[1019] 4. The server generates a database query based on the identified intent and entities to retrieve the required information.

[1020] 5. The server generates a response based on the information it has obtained, such as: "A new employee's salary is the sum of their base salary and various allowances. For details, please refer to your company's payroll policy."

[1021] 6. The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[1022] 7. The device analyzes the received response and displays it on the chatbot interface.

[1023] Prompt Sentence Examples

[1024] Here are some example prompts to input to the generative AI model:

[1025] How do I calculate the salary of a new employee?

[1026] I would like to know about pay deductions if I am late.

[1027] Please tell me the details of the year-end adjustment.

[1028] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model and a template engine, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[1029] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1030] Step 1:

[1031] Users open the chatbot interface on their device and enter their query.

[1032] Specific behavior: The user enters a specific address in the browser URL bar to open the chatbot page, clicks the text box, enters "I want to know about payroll calculations for new employees," and presses the "Submit" button.

[1033] Input: Text data entered by the user.

[1034] Output: The query data sent to the user's device.

[1035] Step 2:

[1036] The terminal acquires the query entered by the user and converts the data into JSON format.

[1037] Specific behavior: Converts text data to JSON using JavaScript's JSON.stringify method.

[1038] Input: Text data entered by the user.

[1039] Output: Query data converted to JSON format.

[1040] Step 3:

[1041] The terminal sends the converted JSON data to the server as an HTTP request.

[1042] Specific operation: Send a request using the fetch API or axios library.

[1043] Input: Query data converted to JSON format.

[1044] Output: The HTTP request sent to the server.

[1045] Step 4:

[1046] The server analyzes the HTTP request received from the terminal and extracts the JSON data.

[1047] Specific operation: Uses Python's json module to parse the HTTP request and extract the JSON data.

[1048] Input: HTTP request.

[1049] Output: The extracted JSON data.

[1050] Step 5:

[1051] The server uses a natural language processing model (generative AI model) to analyze the query content and identify the intent and entity.

[1052] What it does: Using the Python transformers library, we invoke the model to parse the text data, for example, identifying "payroll (intent)" and "new employee (entity)."

[1053] Input: The extracted JSON data.

[1054] Output: Identified intents and entities.

[1055] Step 6:

[1056] The server generates database queries based on the identified intent and entities to retrieve the required information.

[1057] Specific operations: Generate queries using Python libraries such as sqlalchemy and psycopg2, establish database connections, and execute the queries.

[1058] Input: Identified intents and entities.

[1059] Output: Relevant information retrieved from the database.

[1060] Step 7:

[1061] The server generates a response using a template engine (e.g. Jinja2) based on the retrieved information.

[1062] What it does: Uses a template engine to format the retrieved data and generate an answer, such as "The salary for a new employee is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[1063] Input: Relevant information retrieved from the database.

[1064] Output: The generated answer to display to the user.

[1065] Step 8:

[1066] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[1067] What it does: Serialize the answer into JSON data using Python's json module, and create an HTTP response using a web framework such as Flask or Django.

[1068] Input: The generated answer.

[1069] Output: The HTTP response sent from the server to the device.

[1070] Step 9:

[1071] The terminal analyzes the HTTP response received from the server and extracts the JSON data.

[1072] Specific behavior: Parses the response using JavaScript's JSON.parse method.

[1073] Input: The HTTP response from the server.

[1074] Output: The extracted JSON data.

[1075] Step 10:

[1076] The terminal displays the extracted data in a chatbot interface.

[1077] Specific behavior: Uses JavaScript methods to manipulate the DOM and displays the answer in a text box.

[1078] Input: The extracted JSON data.

[1079] Output: The answer displayed on the user's terminal.

[1080] (Application example 1)

[1081] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1082] Current security services require a fast and accurate response when users report an emergency. However, many systems take a long time to respond to inquiries, resulting in delays before users can obtain appropriate countermeasures. There are also technical challenges in understanding the content of inquiries and generating accurate responses. Therefore, a system that can respond quickly and accurately is needed to ensure user safety.

[1083] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1084] In this invention, the server includes means for accepting inquiries from users, means for analyzing the inquiries and identifying corresponding intentions and entities, means for retrieving related information from a database based on the identified intentions and entities, means for generating an answer to the inquiry based on the retrieved information, means for transmitting the generated answer to a user terminal, means for the user to report an emergency, and means for generating appropriate measures in response to the emergency and notifying the user. This makes it possible to respond quickly and accurately to user inquiries and to quickly provide appropriate measures, particularly in emergency situations.

[1085] A "means for accepting user inquiries" is an interface that allows a user to receive input from the system to request information or report a problem.

[1086] "Means for analyzing inquiries and identifying the corresponding intent and entity" refers to a method for analyzing the content of an inquiry received from a user using technologies such as natural language processing and recognizing the purpose (intent) and target (entity) behind the inquiry.

[1087] The "means for obtaining relevant information from a database" is a method for searching and extracting necessary information from a pre-built database based on the identified intent and entity.

[1088] The "means for generating a response to an inquiry based on acquired information" refers to a means for creating a specific and meaningful response to a user's inquiry using information acquired from a database.

[1089] "Means for transmitting the generated answer to the user terminal" refers to a method for transmitting the generated answer to the terminal (such as a smartphone or PC) used by the user.

[1090] "Means for users to report an emergency" refers to an input method that allows users to quickly notify the system when danger or trouble occurs.

[1091] "Means for generating appropriate countermeasures in response to an emergency and notifying the user" refers to a method for generating countermeasures including information and instructions that are most appropriate for the situation when an emergency occurs and notifying the user of them.

[1092] MODE FOR CARRYING OUT THE INVENTION

[1093] System Overview

[1094] This invention is a system for quickly and accurately responding to user inquiries. The system consists of a user terminal, a server, and a database. The user terminal provides a chatbot interface, and the server analyzes the inquiry and retrieves appropriate information from the database to provide the user with an answer. The system also includes functions specialized for reporting and responding to emergency situations.

[1095] Hardware and software used

[1096] Hardware:

[1097] Smartphone (user device)

[1098] Server (cloud-based)

[1099] software:

[1100] Chatbot interface (application installed on the user's device)

[1101] Natural language processing models (e.g., Google BERT)

[1102] Database (e.g. MySQL)

[1103] Processing flow

[1104] User operations

[1105] Users use a security app installed on their smartphone to report a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[1106] Device operation

[1107] The smartphone receives this query and sends it to the server for analysis. The device converts the query into JSON format and sends it as an HTTP request.

[1108] Server Operations

[1109] The server interprets the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query's intent (e.g., emergency report) and entity (e.g., suspicious person). The server then searches a database to retrieve relevant information based on the identified intent and entity. Based on this information, the server generates an appropriate response for the user and sends it back to the terminal in JSON format.

[1110] Reoperate the device

[1111] The smartphone analyzes the response received from the server and displays it to the user, for example, "Please call the police immediately. A security team is on the way to the scene."

[1112] Specific examples

[1113] The user types "There is a suspicious person loitering around the house" into the device. The device sends this query to the server. The server analyzes the query and identifies the "emergency report (intent)" and the "suspicious person (entity)". The server retrieves relevant information from the database and generates a response saying "Please call the police immediately. A security team is on the way to the scene." The server sends this response to the device, which displays it to the user.

[1114] Prompt Sentence Examples

[1115] An example prompt is:

[1116] We would like to report the following as an emergency:

[1117] "There's a suspicious person hanging around the house."

[1118] Seek advice including appropriate measures.

[1119] This system allows users to make inquiries and emergency reports quickly and accurately and receive appropriate responses.

[1120] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1121] Step 1:

[1122] A user launches a security app on their smartphone and reports a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[1123] (Input) The inquiry entered by the user.

[1124] (Output) The inquiry is sent to the terminal.

[1125] Step 2:

[1126] The terminal converts the received inquiry content into JSON format and sends it to the server as an HTTP request.

[1127] (Input) The inquiry entered by the user.

[1128] (Output) The query content is converted to JSON format and an HTTP request is sent to the server.

[1129] Step 3:

[1130] The server parses the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query intent and entities.

[1131] (Input) The HTTP request received by the server (query content in JSON format).

[1132] (Output) The query intent and entities are identified and stored as internal data.

[1133] Step 4:

[1134] Based on the identified intent and entity, the server searches a database to retrieve relevant information.

[1135] (Input) The intent and entity identified by the server.

[1136] (Output) Relevant information is retrieved from the database and stored as internal data.

[1137] Step 5:

[1138] The server generates an appropriate response to the query based on the information it has acquired, converts the response into JSON format, and sends it to the device.

[1139] (Input) Information retrieved from the database.

[1140] (Output) The appropriate response is generated and sent to the terminal in JSON format.

[1141] Step 6:

[1142] The device parses the JSON response received from the server and displays it in the chatbot interface, for example, "Please call the police immediately. A security team is on the way."

[1143] (Input) The JSON response received from the server.

[1144] (Output) The parsed answer is displayed in the chatbot interface.

[1145] This process allows users to make inquiries quickly and accurately and receive appropriate responses.

[1146] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1147] The present invention relates to a system that not only responds to user inquiries quickly and accurately, but also recognizes the user's emotions and generates appropriate answers based on those emotions. Specific embodiments of this system will be described below.

[1148] System Overview

[1149] The system of the present invention comprises a user, a terminal, a server, and an emotion engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and also recognizes the user's emotion using the emotion engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal then displays the generated response to the user.

[1150] Example of a system

[1151] User operations

[1152] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[1153] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[1154] Device operation

[1155] 1. The device generates an HTTP request to send the input query along with the emotion engine to the server.

[1156] The query content is converted to JSON format and sent to the server.

[1157] Server Operations

[1158] 1. The server receives the HTTP request and analyzes the query.

[1159] The server uses a natural language processing (NLP) model to identify the intent and entities contained in the query.

[1160] For example, identify "payroll (intent)" and "new employee (entity)."

[1161] 2. The server uses an emotion engine to recognize the user's emotions.

[1162] For example, the user's emotions may be identified as being in a state of "anxiety" or "doubt."

[1163] 3. The server retrieves relevant information from a database based on the identified intent and entity.

[1164] The server generates database queries to search and retrieve the required information.

[1165] 4. Based on the information obtained, the server adjusts the answer according to the user's feelings and generates an answer in an easy-to-understand format.

[1166] For example, include gentle language and detailed explanations that will ease anxiety.

[1167] 5. The server converts the generated answer into JSON format and returns it to the device as an HTTP response.

[1168] The response content includes answers that take emotions into consideration.

[1169] Terminal operation (again)

[1170] 1. The device analyzes the response received from the server and displays it to the user.

[1171] The terminal parses the JSON response and displays it in the chatbot interface.

[1172] Specific examples

[1173] Example 1: Payroll enquiry

[1174] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[1175] 2. The device sends this query to the server.

[1176] 3. The server analyzes the query, identifies the "payroll calculation (intent)" and the "new employee (entity)," and uses the emotion engine to recognize the user's emotion as "anxiety."

[1177] 4. The server retrieves the relevant information from the database and generates an emotionally sensitive response such as: "A new employee's salary is the sum of their base salary and various allowances. Please refer to our company's payroll policy for details. If you have any questions, please feel free to contact us."

[1178] 5. The server sends the generated response to the terminal.

[1179] 6. The device displays the received response on the chatbot interface.

[1180] As described above, the system of the present invention can provide quick and accurate answers to user inquiries while also taking into consideration the user's feelings, thereby significantly improving user convenience and satisfaction.

[1181] The processing flow will be explained below.

[1182] Step 1:

[1183] The user enters a query into the chatbot interface on their device.

[1184] For example, enter "I would like to know about payroll calculations for new employees."

[1185] Step 2:

[1186] The terminal captures the entered query and generates an HTTP request.

[1187] The query content is converted to JSON format and sent to the server.

[1188] Step 3:

[1189] The server receives an HTTP request.

[1190] Use a web framework such as Flask or Django to parse the request content.

[1191] Step 4:

[1192] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[1193] Use NLP models to identify the intent and entities of a query.

[1194] For example, identify "payroll (intent)" and "new employee (entity)."

[1195] Step 5:

[1196] The server passes the extracted query text to an emotion engine to analyze the user's emotions.

[1197] For example, identify emotions such as "anxiety" or "doubt."

[1198] Step 6:

[1199] The server retrieves relevant information from a database based on the identified intent, entity, and user sentiment.

[1200] Use SQL or NoSQL to run queries and extract the information you need.

[1201] Step 7:

[1202] Based on the information acquired by the server, a response to the query is generated.

[1203] Organize information, construct sentences that are appropriate to the context, and take user emotions into consideration.

[1204] For example, include gentle language and detailed explanations to ease anxiety.

[1205] Step 8:

[1206] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[1207] The response content includes answers that take emotions into consideration.

[1208] Step 9:

[1209] The device parses the JSON response received from the server and displays it in the chatbot interface.

[1210] The user reads the displayed answers from the terminal.

[1211] Example 2

[1212] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1213] In today's information society, it is important for businesses to respond quickly and accurately to diverse user inquiries. However, current inquiry systems often provide uniform answers without considering the user's emotions. This can result in a decline in user satisfaction and trust. Furthermore, responses that do not recognize emotions may not fully resolve the user's concerns or questions.

[1214] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for recognizing the user's emotion based on the identified intention and entity, means for acquiring related information from a database based on the recognized emotion, means for generating an answer based on the acquired information and the recognized emotion, and means for transmitting the generated answer to the user terminal. This makes it possible to provide an answer that takes the user's emotions into consideration. Specifically, if the user is feeling anxious or uncertain, an answer can be provided using careful explanations and gentle expressions that will ease the user's anxiety or doubts, which is expected to improve user satisfaction and reliability.

[1215] A "user" is a subject who makes an inquiry to the system and is the subject to whom information is provided.

[1216] A "terminal" refers to a device used by a user, which is used to input inquiries and display responses.

[1217] The "server" refers to the central component of the system that analyzes queries, identifies intent and entities, recognizes emotions, retrieves corresponding information from a database, and generates answers.

[1218] A "query" refers to a user's request for information from the system.

[1219] "Intent" refers to the purpose or intent behind a user's query.

[1220] "Entity" refers to a specific object or item referred to in a query.

[1221] An "emotion engine" refers to software or algorithms that have the ability to analyze and identify emotions contained in user queries.

[1222] "Relevant information" refers to information in the database that is necessary to provide an appropriate response to a query.

[1223] "Database" refers to a digital storage system for storing and managing related information.

[1224] "Answer" refers to information generated by a server and provided in response to a user's inquiry.

[1225] "Natural Language Processing Model" refers to machine learning algorithms and techniques for analyzing queries and identifying intent and entities.

[1226] MODE FOR CARRYING OUT THE INVENTION

[1227] The system of the present invention aims not only to respond quickly and accurately to inquiries from users, but also to recognize the user's emotions and generate appropriate answers based on those emotions.

[1228] System Configuration

[1229] The system of the present invention is realized by the cooperation of a user, a terminal, a server, and an emotion engine. Each element operates as follows.

[1230] User operations

[1231] Users make inquiries through the chatbot interface on their devices, which are entered in text format and sent to the device.

[1232] As a specific example, consider the case where a user inputs "I would like to know about payroll calculations for new employees." This inquiry is received by the terminal.

[1233] Device operation

[1234] The device converts the received query into JSON format and sends it to the server as an HTTP request using software such as the JavaScript fetch API and the Python requests library.

[1235] Server Operations

[1236] The server performs the following process:

[1237] 1. Receiving and parsing the request

[1238] The server receives HTTP requests using Apache or Nginx and analyzes the query using a natural language processing model (e.g., SpaCy or BERT), thereby identifying the intent and entity contained in the query.

[1239] 2. Recognizing User Emotions

[1240] The server uses an emotion engine (e.g., Google Natural Language API or Microsoft Text Analytics API) to recognize the user's emotion. For example, the user's emotion is identified as "anxiety."

[1241] 3. Retrieving relevant information from the database

[1242] The server retrieves relevant information from a database (e.g. MySQL or PostgreSQL) based on the intent and entities specified, generating queries to find the required information.

[1243] 4. Generating Emotion-Based Answers

[1244] The server generates an answer based on the acquired information, taking into consideration the user's emotions. By using a template engine (e.g., Jinja2), it creates an answer that includes appropriate expressions according to the emotion. The generated answer is converted into JSON format and sent back to the terminal as an HTTP response.

[1245] Reoperate the device

[1246] The device analyzes the response received from the server and displays it on the chatbot interface, allowing the user to obtain an answer to their inquiry.

[1247] Prompt Sentence Examples

[1248] An example of a specific prompt sentence would be, "Please tell me about the payroll calculation for new employees." The server can analyze the sentiment of this query and generate an appropriate answer.

[1249] result

[1250] The system of the present invention is capable of providing answers that take into consideration the user's feelings, and is expected to improve user satisfaction and reliability. Furthermore, by using this system, companies can achieve efficient and effective customer support.

[1251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1252] Step 1:

[1253] The user inputs a query into the terminal.

[1254] The user opens the chatbot interface on their device and types, "I'd like to know about payroll calculations for new employees."

[1255] This input is sent to the terminal and stored in the terminal's memory.

[1256] Step 2:

[1257] The terminal converts the input into JSON format and sends it to the server.

[1258] The terminal converts the received query into JSON format using JavaScript's fetch API or Python's requests library.

[1259] The converted data is as follows:

[1260] json

[1261] {

[1262] "query": "I want to know about payroll calculations for new employees"

[1263] }

[1264] The terminal generates this JSON data as an HTTP request and sends it to the server.

[1265] Step 3:

[1266] The server receives the request and parses the query.

[1267] The server uses Apache or Nginx to receive HTTP requests.

[1268] The request is processed on the server using the Python Flask framework.

[1269] Analyze the received JSON data and identify the inquiry content.

[1270] Use natural language processing models (e.g., SpaCy or BERT) to identify query intent and entities.

[1271] Input: "I want to know about payroll calculations for new employees."

[1272] Output: "Payroll (Intent)", "New Employee (Entity)"

[1273] Step 4:

[1274] The server uses an emotion engine to recognize the user's emotion.

[1275] The server uses the Google Natural Language API and Microsoft Text Analytics API to analyze user sentiment.

[1276] Input: "I want to know about payroll calculations for new employees."

[1277] Output: Sentiment score indicating "anxiety"

[1278] The server identifies the user's emotion from the API response and recognizes it as "anxiety."

[1279] Step 5:

[1280] The server retrieves the relevant information from a database.

[1281] The server queries the database based on the intent and the entity.

[1282] For example, if you are using a PostgreSQL database, run a query like this:

[1283] SELECT FROM salary_policy WHERE category = 'New Employee';

[1284] Inputs: "Payroll (Intent)", "New Employee (Entity)"

[1285] Output: Applicable salary information

[1286] Step 6:

[1287] The server generates a response according to the emotion and sends it to the device.

[1288] The server uses a template engine (e.g. Jinja2) to generate answers that take the user's feelings into consideration.

[1289] For example, "A new employee's salary is the sum of their basic salary and various allowances. For details, please refer to our company's payroll policy. If you have any questions, please feel free to contact us."

[1290] This generated response is converted into JSON format and sent to the terminal as an HTTP response.

[1291] Input: relevant salary information, sentiment score indicating "anxiety"

[1292] Output: Emotionally sensitive answers

[1293] Step 7:

[1294] The terminal displays the answer to the user.

[1295] The device analyzes the answers received from the server and displays them on the chatbot interface.

[1296] Input: Emotionally sensitive answers

[1297] Output: The answer displayed to the user

[1298] (Application example 2)

[1299] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1300] Conventional chatbots and automated response systems can respond to user inquiries quickly and accurately, but they often do not generate responses that take user emotions into consideration, which can result in lower satisfaction. Therefore, there is a need for systems that can recognize user emotions and generate and adjust appropriate responses based on those emotions. Especially on online shopping sites, providing responses to product-related inquiries that take user emotions into consideration can increase purchasing motivation and improve customer support.

[1301] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for acquiring related information from a database based on the identified intention and entity, means for generating an answer to the inquiry based on the acquired information, means for recognizing the user's emotions and adjusting the answer based on the recognition, and means for transmitting the generated answer to the user terminal. This enables a personalized answer that takes the user's emotions into consideration.

[1302] A "user" is a user who makes an inquiry to the system.

[1303] The "means for accepting an inquiry" is an interface function that accepts input such as text or voice from the user and sends it to the analysis process.

[1304] The "means for analyzing inquiries" refers to natural language processing models and algorithms that analyze the content of the received inquiry and extract intent and entities from it.

[1305] "Intent" is a concept that indicates the type of purpose or request that a user wants to achieve from a system.

[1306] An "entity" is a word or phrase that indicates a specific element or object contained in a user's query.

[1307] The "means for obtaining related information" is a function for searching and obtaining appropriate information from a database based on the analyzed intent and entity.

[1308] The "means for generating an answer" refers to an algorithm or program that generates an answer to a user's inquiry based on the acquired information.

[1309] "Means for recognizing the user's emotions and adjusting responses based on those emotions" refers to a function that uses an emotion recognition engine to identify the user's emotions and corrects and adjusts responses in a way that takes those emotions into consideration.

[1310] The "means for transmitting the answer to the user terminal" refers to a communication and display function for transmitting the generated answer to the user's terminal and displaying it in a format that is easy for the user to view.

[1311] A "natural language processing model" is a computational model that analyzes text data to understand the meaning and structure of language and extract information such as intent and entities.

[1312] An "emotion recognition engine" is a machine learning model or algorithm that identifies emotions from a user's text or voice characteristics and outputs that state.

[1313] A "database" is a digital storage system that stores and manages relevant information to generate answers to inquiries.

[1314] A "user terminal" is a device used by a user to enter inquiries and receive responses, and includes smartphones, tablets, PCs, etc.

[1315] The present invention relates to a system that quickly provides appropriate answers to inquiries from users, recognizes the emotions of the users, and adjusts the answers based on the emotions. Specific embodiments of the system are described in detail below.

[1316] System Overview

[1317] The system of the present invention comprises a user, a terminal, a server, and an emotion recognition engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and further recognizes the user's emotion using the emotion recognition engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal displays the generated response to the user.

[1318] User operations

[1319] The user accesses a terminal and inputs a query through the chatbot interface. For example, the user inputs, "Are these shoes waterproof?"

[1320] Terminal handling

[1321] The device sends the input query to the server along with the emotion recognition engine. To do this, it generates an HTTP request, and the query content is converted to JSON format and sent to the server.

[1322] Server Processing

[1323] The server receives the HTTP request and analyzes the query using a natural language processing (NLP) model, for example, to identify the intent and entities contained in the query.

[1324] The server then uses an emotion recognition engine to recognize the user's emotion, for example, identifying the user's emotion as anxiety.

[1325] The server then retrieves relevant information from a database based on the identified intent and entity, generating database queries to search and retrieve the required information.

[1326] The system then tailors the responses to take into account the perceived emotions and generates specific answers, for example, creating a reassuring answer for a user who is feeling anxious.

[1327] The generated answer is converted to JSON format and sent back to the device as an HTTP response, which includes an emotionally sensitive answer.

[1328] Terminal handling (again)

[1329] The terminal parses the answer received from the server and displays it to the user. It parses the JSON response and generates an answer that is displayed in the chatbot interface.

[1330] Example

[1331] For example, if a user types "Are these shoes waterproof?" into a device, the server analyzes the query and identifies the "waterproof performance of the shoes (intent)" and "shoes (entity)." The emotion recognition engine then recognizes the user's emotion as "anxiety." The server retrieves relevant information from the database, generates an emotion-sensitive response such as "These shoes are made with high-quality waterproof material, so you can wear them safely even on rainy days," and sends it to the device, which then displays it to the user.

[1332] Prompt Sentence Examples

[1333] User Question: "Are these shoes waterproof?"

[1334] As described above, the system of the present invention can provide quick and accurate answers to user inquiries, and can increase user satisfaction by generating answers that take into consideration the user's feelings.

[1335] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1336] Step 1:

[1337] A user opens the chatbot interface using a terminal and inputs a query. For example, the user inputs "Are these shoes waterproof?". The input data is a string.

[1338] Step 2:

[1339] The terminal accepts the input query and generates an HTTP request to send it to the server. The query content is converted to JSON format and sent to the server. The input data is the user's query text, and the output data is the HTTP request in JSON format.

[1340] Step 3:

[1341] The server receives an HTTP request and analyzes the query. It uses a natural language processing (NLP) model to identify intents and entities from the query. For example, "Shoe waterproofing" and "Shoes" are identified. The input data is the user's query text, and the output data is a pair of intents and entities.

[1342] Step 4:

[1343] The server uses an emotion recognition engine to recognize the user's emotion. The emotion recognition engine infers the emotion from the user's text and outputs an emotional state such as "anxiety" or "excitement." For example, the user's emotion is identified as "anxiety." The input data is the user's query text, and the output data is the user's emotional state.

[1344] Step 5:

[1345] The server retrieves relevant information from the database based on the identified intent and entity. It generates a database query to search and retrieve the required information. For example, information on waterproof shoes is retrieved. The input data is the intent-entity pair, and the output data is the related information.

[1346] Step 6:

[1347] The server generates an answer based on the acquired information and the user's emotions. For example, it creates an answer that takes emotions into consideration, such as "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data are the relevant information and the user's emotional state, and the output data is the generated answer.

[1348] Step 7:

[1349] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response. Finally, the response sent from the server is received. The input data is the generated response, and the output data is the JSON format HTTP response.

[1350] Step 8:

[1351] The terminal analyzes the answer received from the server and displays it to the user. It parses the JSON response and displays the generated answer on the chatbot interface. For example, the answer might be, "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data is the HTTP response in JSON format, and the output data is the text displayed to the user.

[1352] As a result, the system of the present invention can quickly and accurately respond to user inquiries and provide answers that take into consideration the user's feelings, which is expected to improve user satisfaction and increase purchasing motivation.

[1353] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1354] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1355] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1356] [Fourth embodiment]

[1357] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1358] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1359] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1360] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1361] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1362] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1363] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1364] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1365] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1366] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1367] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1368] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1369] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1370] The present invention relates to a system for quickly and accurately responding to inquiries from users. Specific embodiments of the system will be described below.

[1371] System Overview

[1372] The system of the present invention consists of a user, a terminal, and a server. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, retrieves appropriate information from a database, generates a response, and sends it to the terminal. The terminal then displays the generated response to the user.

[1373] Example of a system

[1374] User operations

[1375] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[1376] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[1377] Device operation

[1378] 1. The terminal generates an HTTP request to send the entered query to the server.

[1379] The terminal converts the query content into JSON format and sends it to the server.

[1380] Server Operations

[1381] 1. The server receives the HTTP request and analyzes the query.

[1382] The server uses natural language processing models to identify the intent and entities contained in the query.

[1383] For example, identify "payroll (intent)" and "new employee (entity)."

[1384] 2. The server retrieves relevant information from a database based on the identified intent and entity.

[1385] The server generates database queries to search and retrieve the required information.

[1386] 3. The server generates an appropriate response based on the information obtained.

[1387] The server organizes the information and generates an answer in a format that is easy for the user to understand.

[1388] 4. The server sends the generated response in JSON format to the device.

[1389] The server generates an HTTP response and sends the answer back to the terminal.

[1390] Terminal operation (again)

[1391] 1. The device analyzes the response received from the server and displays it to the user.

[1392] The terminal parses the JSON response and displays it in the chatbot interface.

[1393] Specific examples

[1394] Example 1: Payroll enquiry

[1395] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[1396] 2. The device sends this query to the server.

[1397] 3. The server parses the query and identifies the "payroll (intent)" and the "new employee (entity)."

[1398] 4. The server retrieves the relevant information from the database and generates a response such as: "New employee salary is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[1399] 5. The server sends the generated response to the terminal.

[1400] 6. The device displays the received response on the chatbot interface.

[1401] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[1402] The processing flow will be explained below.

[1403] Step 1:

[1404] The user enters a query into the chatbot interface on their device.

[1405] For example, enter "I would like to know about payroll calculations for new employees."

[1406] Step 2:

[1407] The terminal captures the entered query and generates an HTTP request.

[1408] The query content is converted to JSON format and sent to the server.

[1409] Step 3:

[1410] The server receives an HTTP request.

[1411] Use a web framework such as Flask or Django to parse the request content.

[1412] Step 4:

[1413] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[1414] Use NLP models to identify the intent and entities of a query.

[1415] Step 5:

[1416] The server retrieves relevant information from a database based on the identified intent and entity.

[1417] Use SQL or NoSQL to execute queries and extract the required information.

[1418] Step 6:

[1419] Based on the information acquired by the server, an answer is generated in a format that is easy for the user to understand.

[1420] Organize information and construct sentences that fit the context.

[1421] Step 7:

[1422] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[1423] The response content contains the answer.

[1424] Step 8:

[1425] The device parses the JSON response received from the server and displays it in the chatbot interface.

[1426] The user reads the displayed answers from the terminal.

[1427] Example 1

[1428] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1429] Conventional systems have had difficulty responding to user inquiries quickly and accurately. Furthermore, there are issues with analysis accuracy and answer generation, which can lead to a decline in the quality of the user experience. In response to these issues, the present invention aims to provide a system that responds to user inquiries quickly and accurately.

[1430] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1431] In this invention, the server includes means for analyzing the query and using a natural language processing model to identify a corresponding intent and entity, means for retrieving related information from a database based on the identified intent and entity, and means for generating an answer to the query based on the retrieved information using a template engine, thereby enabling the server to provide a quick and accurate answer to the user's query.

[1432] A "user" is a user who makes an inquiry to the system.

[1433] A "query" is a question or request that a user enters into the system to request specific information.

[1434] A "terminal" is a device through which a user inputs an inquiry and communicates with a server, and includes a personal computer, a smartphone, etc.

[1435] A "server" is a computer system that analyzes queries, obtains and processes the necessary information, and provides it to users.

[1436] The "JSON format" is a text format that represents data in JavaScript Object Notation (JSON), and is lightweight and suitable for data exchange.

[1437] An "HTTP request" is a request based on a communication protocol that allows a terminal to request specific processing or information from a server.

[1438] A "natural language processing model" is an algorithm or mathematical model that understands and analyzes human language and is used to identify query intent and entities.

[1439] "Intent" is the purpose or request behind a user's query.

[1440] An "entity" is an important item or concept included in a user's query.

[1441] A "database" is a data management system that systematically stores specific information and allows it to be quickly searched and retrieved as needed.

[1442] A "template engine" is a system for formatting dynamically generated content and displaying it in an appropriate way for the user.

[1443] An "HTTP response" is a response sent from a server to a terminal, and includes results and data in response to a request.

[1444] A "generative AI model" is an artificial intelligence algorithm that learns from large amounts of data and generates new data and answers.

[1445] The present invention relates to a system for responding to inquiries from users quickly and accurately. The system is composed of users, terminals, and a server. A specific embodiment of the system will be described below.

[1446] User Inquiry

[1447] Users access a terminal and input inquiries through the chatbot interface. The terminal can be a PC, smartphone, or other device. The chatbot interface is configured as a web browser or a dedicated application.

[1448] Terminal handling

[1449] The terminal acquires the query entered by the user and converts the data into JSON format. The converted data is sent to the server as an HTTP request. To generate the HTTP request, JavaScript's JSON.stringify method or the fetch API is used.

[1450] Server Processing

[1451] The server parses the HTTP request received from the device and extracts JSON data. This parsing is done using Python's json module, for example. The server then uses a natural language processing model (e.g., GPT-3) to identify the intent and entities contained in the query. This process is done using Python's transformers library.

[1452] Information Acquisition and Answer Generation

[1453] The server generates a database query based on the identified intent and entity, and retrieves the required information from the database. The database can be MySQL or PostgreSQL. Python libraries such as sqlalchemy and psycopg2 are used to generate the database query.

[1454] Next, the server uses a template engine (e.g., Jinja2) to generate a response based on the acquired information. The generated response is then converted back to JSON format and sent to the terminal as an HTTP response.

[1455] Displaying answers to users

[1456] The terminal parses the HTTP response received from the server and extracts the JSON data. The extracted data is displayed on the chatbot interface. To display the data, JavaScript's JSON.parse method and DOM manipulation are used.

[1457] Specific operation example

[1458] A specific example of the operation of this system is shown below.

[1459] Example 1: Payroll enquiry

[1460] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[1461] 2. The device converts this query into JSON format and sends it to the server as an HTTP request.

[1462] 3. The server receives the request and uses a natural language processing model to identify the "payroll intent" and the "new employee entity."

[1463] 4. The server generates a database query based on the identified intent and entities to retrieve the required information.

[1464] 5. The server generates a response based on the information it has obtained, such as: "A new employee's salary is the sum of their base salary and various allowances. For details, please refer to your company's payroll policy."

[1465] 6. The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[1466] 7. The device analyzes the received response and displays it on the chatbot interface.

[1467] Prompt Sentence Examples

[1468] Here are some example prompts to input to the generative AI model:

[1469] How do I calculate the salary of a new employee?

[1470] I would like to know about pay deductions if I am late.

[1471] Please tell me the details of the year-end adjustment.

[1472] As described above, the system of the present invention can provide quick and accurate answers to user inquiries. Furthermore, by using a natural language processing model and a template engine, the accuracy of the inquiry content can be improved, thereby enhancing the quality of service provided to users.

[1473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1474] Step 1:

[1475] Users open the chatbot interface on their device and enter their query.

[1476] Specific behavior: The user enters a specific address in the browser URL bar to open the chatbot page, clicks the text box, enters "I want to know about payroll calculations for new employees," and presses the "Submit" button.

[1477] Input: Text data entered by the user.

[1478] Output: The query data sent to the user's device.

[1479] Step 2:

[1480] The terminal acquires the query entered by the user and converts the data into JSON format.

[1481] Specific behavior: Converts text data to JSON using JavaScript's JSON.stringify method.

[1482] Input: Text data entered by the user.

[1483] Output: Query data converted to JSON format.

[1484] Step 3:

[1485] The terminal sends the converted JSON data to the server as an HTTP request.

[1486] Specific operation: Send a request using the fetch API or axios library.

[1487] Input: Query data converted to JSON format.

[1488] Output: The HTTP request sent to the server.

[1489] Step 4:

[1490] The server analyzes the HTTP request received from the terminal and extracts the JSON data.

[1491] Specific operation: Uses Python's json module to parse the HTTP request and extract the JSON data.

[1492] Input: HTTP request.

[1493] Output: The extracted JSON data.

[1494] Step 5:

[1495] The server uses a natural language processing model (generative AI model) to analyze the query content and identify the intent and entity.

[1496] What it does: Using the Python transformers library, we invoke the model to parse the text data, for example, identifying "payroll (intent)" and "new employee (entity)."

[1497] Input: The extracted JSON data.

[1498] Output: Identified intents and entities.

[1499] Step 6:

[1500] The server generates database queries based on the identified intent and entities to retrieve the required information.

[1501] Specific operations: Generate queries using Python libraries such as sqlalchemy and psycopg2, establish database connections, and execute the queries.

[1502] Input: Identified intents and entities.

[1503] Output: Relevant information retrieved from the database.

[1504] Step 7:

[1505] The server generates a response using a template engine (e.g. Jinja2) based on the retrieved information.

[1506] What it does: Uses a template engine to format the retrieved data and generate an answer, such as "The salary for a new employee is the sum of base salary and various allowances. Please refer to your company's payroll policy for details."

[1507] Input: Relevant information retrieved from the database.

[1508] Output: The generated answer to display to the user.

[1509] Step 8:

[1510] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[1511] What it does: Serialize the answer into JSON data using Python's json module, and create an HTTP response using a web framework such as Flask or Django.

[1512] Input: The generated answer.

[1513] Output: The HTTP response sent from the server to the device.

[1514] Step 9:

[1515] The terminal analyzes the HTTP response received from the server and extracts the JSON data.

[1516] Specific behavior: Parses the response using JavaScript's JSON.parse method.

[1517] Input: The HTTP response from the server.

[1518] Output: The extracted JSON data.

[1519] Step 10:

[1520] The terminal displays the extracted data in a chatbot interface.

[1521] Specific behavior: Uses JavaScript methods to manipulate the DOM and displays the answer in a text box.

[1522] Input: The extracted JSON data.

[1523] Output: The answer displayed on the user's terminal.

[1524] (Application example 1)

[1525] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1526] Current security services require a fast and accurate response when users report an emergency. However, many systems take a long time to respond to inquiries, resulting in delays before users can obtain appropriate countermeasures. There are also technical challenges in understanding the content of inquiries and generating accurate responses. Therefore, a system that can respond quickly and accurately is needed to ensure user safety.

[1527] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1528] In this invention, the server includes means for accepting inquiries from users, means for analyzing the inquiries and identifying corresponding intentions and entities, means for retrieving related information from a database based on the identified intentions and entities, means for generating an answer to the inquiry based on the retrieved information, means for transmitting the generated answer to a user terminal, means for the user to report an emergency, and means for generating appropriate measures in response to the emergency and notifying the user. This makes it possible to respond quickly and accurately to user inquiries and to quickly provide appropriate measures, particularly in emergency situations.

[1529] A "means for accepting user inquiries" is an interface that allows a user to receive input from the system to request information or report a problem.

[1530] "Means for analyzing inquiries and identifying the corresponding intent and entity" refers to a method for analyzing the content of an inquiry received from a user using technologies such as natural language processing and recognizing the purpose (intent) and target (entity) behind the inquiry.

[1531] The "means for obtaining relevant information from a database" is a method for searching and extracting necessary information from a pre-built database based on the identified intent and entity.

[1532] The "means for generating a response to an inquiry based on acquired information" refers to a means for creating a specific and meaningful response to a user's inquiry using information acquired from a database.

[1533] "Means for transmitting the generated answer to the user terminal" refers to a method for transmitting the generated answer to the terminal (such as a smartphone or PC) used by the user.

[1534] "Means for users to report an emergency" refers to an input method that allows users to quickly notify the system when danger or trouble occurs.

[1535] "Means for generating appropriate countermeasures in response to an emergency and notifying the user" refers to a method for generating countermeasures including information and instructions that are most appropriate for the situation when an emergency occurs and notifying the user of them.

[1536] MODE FOR CARRYING OUT THE INVENTION

[1537] System Overview

[1538] This invention is a system for quickly and accurately responding to user inquiries. The system consists of a user terminal, a server, and a database. The user terminal provides a chatbot interface, and the server analyzes the inquiry and retrieves appropriate information from the database to provide the user with an answer. The system also includes functions specialized for reporting and responding to emergency situations.

[1539] Hardware and software used

[1540] Hardware:

[1541] Smartphone (user device)

[1542] Server (cloud-based)

[1543] software:

[1544] Chatbot interface (application installed on the user's device)

[1545] Natural language processing models (e.g., Google BERT)

[1546] Database (e.g. MySQL)

[1547] Processing flow

[1548] User operations

[1549] Users use a security app installed on their smartphone to report a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[1550] Device operation

[1551] The smartphone receives this query and sends it to the server for analysis. The device converts the query into JSON format and sends it as an HTTP request.

[1552] Server Operations

[1553] The server interprets the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query's intent (e.g., emergency report) and entity (e.g., suspicious person). The server then searches a database to retrieve relevant information based on the identified intent and entity. Based on this information, the server generates an appropriate response for the user and sends it back to the terminal in JSON format.

[1554] Reoperate the device

[1555] The smartphone analyzes the response received from the server and displays it to the user, for example, "Please call the police immediately. A security team is on the way to the scene."

[1556] Specific examples

[1557] The user types "There is a suspicious person loitering around the house" into the device. The device sends this query to the server. The server analyzes the query and identifies the "emergency report (intent)" and the "suspicious person (entity)". The server retrieves relevant information from the database and generates a response saying "Please call the police immediately. A security team is on the way to the scene." The server sends this response to the device, which displays it to the user.

[1558] Prompt Sentence Examples

[1559] An example prompt is:

[1560] We would like to report the following as an emergency:

[1561] "There's a suspicious person hanging around the house."

[1562] Seek advice including appropriate measures.

[1563] This system allows users to make inquiries and emergency reports quickly and accurately and receive appropriate responses.

[1564] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1565] Step 1:

[1566] A user launches a security app on their smartphone and reports a query or emergency through the chatbot interface, for example, by typing, "There's a suspicious person hanging around my house."

[1567] (Input) The inquiry entered by the user.

[1568] (Output) The inquiry is sent to the terminal.

[1569] Step 2:

[1570] The terminal converts the received inquiry content into JSON format and sends it to the server as an HTTP request.

[1571] (Input) The inquiry entered by the user.

[1572] (Output) The query content is converted to JSON format and an HTTP request is sent to the server.

[1573] Step 3:

[1574] The server parses the received HTTP request and analyzes the query using a natural language processing model (e.g., Google BERT). This analysis identifies the query intent and entities.

[1575] (Input) The HTTP request received by the server (query content in JSON format).

[1576] (Output) The query intent and entities are identified and stored as internal data.

[1577] Step 4:

[1578] Based on the identified intent and entity, the server searches a database to retrieve relevant information.

[1579] (Input) The intent and entity identified by the server.

[1580] (Output) Relevant information is retrieved from the database and stored as internal data.

[1581] Step 5:

[1582] The server generates an appropriate response to the query based on the information it has acquired, converts the response into JSON format, and sends it to the device.

[1583] (Input) Information retrieved from the database.

[1584] (Output) The appropriate response is generated and sent to the terminal in JSON format.

[1585] Step 6:

[1586] The device parses the JSON response received from the server and displays it in the chatbot interface, for example, "Please call the police immediately. A security team is on the way."

[1587] (Input) The JSON response received from the server.

[1588] (Output) The parsed answer is displayed in the chatbot interface.

[1589] This process allows users to make inquiries quickly and accurately and receive appropriate responses.

[1590] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1591] The present invention relates to a system that not only responds to user inquiries quickly and accurately, but also recognizes the user's emotions and generates appropriate answers based on those emotions. Specific embodiments of this system will be described below.

[1592] System Overview

[1593] The system of the present invention comprises a user, a terminal, a server, and an emotion engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and also recognizes the user's emotion using the emotion engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal then displays the generated response to the user.

[1594] Example of a system

[1595] User operations

[1596] 1. The user accesses the terminal and inputs a query through the chatbot interface.

[1597] For example, the user inputs, "I would like to know about payroll calculations for new employees."

[1598] Device operation

[1599] 1. The device generates an HTTP request to send the input query along with the emotion engine to the server.

[1600] The query content is converted to JSON format and sent to the server.

[1601] Server Operations

[1602] 1. The server receives the HTTP request and analyzes the query.

[1603] The server uses a natural language processing (NLP) model to identify the intent and entities contained in the query.

[1604] For example, identify "payroll (intent)" and "new employee (entity)."

[1605] 2. The server uses an emotion engine to recognize the user's emotions.

[1606] For example, the user's emotions may be identified as being in a state of "anxiety" or "doubt."

[1607] 3. The server retrieves relevant information from a database based on the identified intent and entity.

[1608] The server generates database queries to search and retrieve the required information.

[1609] 4. Based on the information obtained, the server adjusts the answer according to the user's feelings and generates an answer in an easy-to-understand format.

[1610] For example, include gentle language and detailed explanations that will ease anxiety.

[1611] 5. The server converts the generated answer into JSON format and returns it to the device as an HTTP response.

[1612] The response content includes answers that take emotions into consideration.

[1613] Terminal operation (again)

[1614] 1. The device analyzes the response received from the server and displays it to the user.

[1615] The terminal parses the JSON response and displays it in the chatbot interface.

[1616] Specific examples

[1617] Example 1: Payroll enquiry

[1618] 1. The user types into the terminal, "I would like to know about payroll calculations for new employees."

[1619] 2. The device sends this query to the server.

[1620] 3. The server analyzes the query, identifies the "payroll calculation (intent)" and the "new employee (entity)," and uses the emotion engine to recognize the user's emotion as "anxiety."

[1621] 4. The server retrieves the relevant information from the database and generates an emotionally sensitive response such as: "A new employee's salary is the sum of their base salary and various allowances. Please refer to our company's payroll policy for details. If you have any questions, please feel free to contact us."

[1622] 5. The server sends the generated response to the terminal.

[1623] 6. The device displays the received response on the chatbot interface.

[1624] As described above, the system of the present invention can provide quick and accurate answers to user inquiries while also taking into consideration the user's feelings, thereby significantly improving user convenience and satisfaction.

[1625] The processing flow will be explained below.

[1626] Step 1:

[1627] The user enters a query into the chatbot interface on their device.

[1628] For example, enter "I would like to know about payroll calculations for new employees."

[1629] Step 2:

[1630] The terminal captures the entered query and generates an HTTP request.

[1631] The query content is converted to JSON format and sent to the server.

[1632] Step 3:

[1633] The server receives an HTTP request.

[1634] Use a web framework such as Flask or Django to parse the request content.

[1635] Step 4:

[1636] The server extracts the query from the parsed request and passes it to a natural language processing (NLP) model.

[1637] Use NLP models to identify the intent and entities of a query.

[1638] For example, identify "payroll (intent)" and "new employee (entity)."

[1639] Step 5:

[1640] The server passes the extracted query text to an emotion engine to analyze the user's emotions.

[1641] For example, identify emotions such as "anxiety" or "doubt."

[1642] Step 6:

[1643] The server retrieves relevant information from a database based on the identified intent, entity, and user sentiment.

[1644] Use SQL or NoSQL to run queries and extract the information you need.

[1645] Step 7:

[1646] Based on the information acquired by the server, a response to the query is generated.

[1647] Organize information, construct sentences that are appropriate to the context, and take user emotions into consideration.

[1648] For example, include gentle language and detailed explanations to ease anxiety.

[1649] Step 8:

[1650] The server converts the generated answer into JSON format and sends it back to the device as an HTTP response.

[1651] The response content includes answers that take emotions into consideration.

[1652] Step 9:

[1653] The device parses the JSON response received from the server and displays it in the chatbot interface.

[1654] The user reads the displayed answers from the terminal.

[1655] Example 2

[1656] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1657] In today's information society, it is important for businesses to respond quickly and accurately to diverse user inquiries. However, current inquiry systems often provide uniform answers without considering the user's emotions. This can result in a decline in user satisfaction and trust. Furthermore, responses that do not recognize emotions may not fully resolve the user's concerns or questions.

[1658] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for recognizing the user's emotion based on the identified intention and entity, means for acquiring related information from a database based on the recognized emotion, means for generating an answer based on the acquired information and the recognized emotion, and means for transmitting the generated answer to the user terminal. This makes it possible to provide an answer that takes the user's emotions into consideration. Specifically, if the user is feeling anxious or uncertain, an answer can be provided using careful explanations and gentle expressions that will ease the user's anxiety or doubts, which is expected to improve user satisfaction and reliability.

[1659] A "user" is a subject who makes an inquiry to the system and is the subject to whom information is provided.

[1660] A "terminal" refers to a device used by a user, which is used to input inquiries and display responses.

[1661] The "server" refers to the central component of the system that analyzes queries, identifies intent and entities, recognizes emotions, retrieves corresponding information from a database, and generates answers.

[1662] A "query" refers to a user's request for information from the system.

[1663] "Intent" refers to the purpose or intent behind a user's query.

[1664] "Entity" refers to a specific object or item referred to in a query.

[1665] An "emotion engine" refers to software or algorithms that have the ability to analyze and identify emotions contained in user queries.

[1666] "Relevant information" refers to information in the database that is necessary to provide an appropriate response to a query.

[1667] "Database" refers to a digital storage system for storing and managing related information.

[1668] "Answer" refers to information generated by a server and provided in response to a user's inquiry.

[1669] "Natural Language Processing Model" refers to machine learning algorithms and techniques for analyzing queries and identifying intent and entities.

[1670] MODE FOR CARRYING OUT THE INVENTION

[1671] The system of the present invention aims not only to respond quickly and accurately to inquiries from users, but also to recognize the user's emotions and generate appropriate answers based on those emotions.

[1672] System Configuration

[1673] The system of the present invention is realized by the cooperation of a user, a terminal, a server, and an emotion engine. Each element operates as follows.

[1674] User operations

[1675] Users make inquiries through the chatbot interface on their devices, which are entered in text format and sent to the device.

[1676] As a specific example, consider the case where a user inputs "I would like to know about payroll calculations for new employees." This inquiry is received by the terminal.

[1677] Device operation

[1678] The device converts the received query into JSON format and sends it to the server as an HTTP request using software such as the JavaScript fetch API and the Python requests library.

[1679] Server Operations

[1680] The server performs the following process:

[1681] 1. Receiving and parsing the request

[1682] The server receives HTTP requests using Apache or Nginx and analyzes the query using a natural language processing model (e.g., SpaCy or BERT), thereby identifying the intent and entity contained in the query.

[1683] 2. Recognizing User Emotions

[1684] The server uses an emotion engine (e.g., Google Natural Language API or Microsoft Text Analytics API) to recognize the user's emotion. For example, the user's emotion is identified as "anxiety."

[1685] 3. Retrieving relevant information from the database

[1686] The server retrieves relevant information from a database (e.g. MySQL or PostgreSQL) based on the intent and entities specified, generating queries to find the required information.

[1687] 4. Generating Emotion-Based Answers

[1688] The server generates an answer based on the acquired information, taking into consideration the user's emotions. By using a template engine (e.g., Jinja2), it creates an answer that includes appropriate expressions according to the emotion. The generated answer is converted into JSON format and sent back to the terminal as an HTTP response.

[1689] Reoperate the device

[1690] The device analyzes the response received from the server and displays it on the chatbot interface, allowing the user to obtain an answer to their inquiry.

[1691] Prompt Sentence Examples

[1692] An example of a specific prompt sentence would be, "Please tell me about the payroll calculation for new employees." The server can analyze the sentiment of this query and generate an appropriate answer.

[1693] result

[1694] The system of the present invention is capable of providing answers that take into consideration the user's feelings, and is expected to improve user satisfaction and reliability. Furthermore, by using this system, companies can achieve efficient and effective customer support.

[1695] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1696] Step 1:

[1697] The user inputs a query into the terminal.

[1698] The user opens the chatbot interface on their device and types, "I'd like to know about payroll calculations for new employees."

[1699] This input is sent to the terminal and stored in the terminal's memory.

[1700] Step 2:

[1701] The terminal converts the input into JSON format and sends it to the server.

[1702] The terminal converts the received query into JSON format using JavaScript's fetch API or Python's requests library.

[1703] The converted data is as follows:

[1704] json

[1705] {

[1706] "query": "I want to know about payroll calculations for new employees"

[1707] }

[1708] The terminal generates this JSON data as an HTTP request and sends it to the server.

[1709] Step 3:

[1710] The server receives the request and parses the query.

[1711] The server uses Apache or Nginx to receive HTTP requests.

[1712] The request is processed on the server using the Python Flask framework.

[1713] Analyze the received JSON data and identify the inquiry content.

[1714] Use natural language processing models (e.g., SpaCy or BERT) to identify query intent and entities.

[1715] Input: "I want to know about payroll calculations for new employees."

[1716] Output: "Payroll (Intent)", "New Employee (Entity)"

[1717] Step 4:

[1718] The server uses an emotion engine to recognize the user's emotion.

[1719] The server uses the Google Natural Language API and Microsoft Text Analytics API to analyze user sentiment.

[1720] Input: "I want to know about payroll calculations for new employees."

[1721] Output: Sentiment score indicating "anxiety"

[1722] The server identifies the user's emotion from the API response and recognizes it as "anxiety."

[1723] Step 5:

[1724] The server retrieves the relevant information from a database.

[1725] The server queries the database based on the intent and the entity.

[1726] For example, if you are using a PostgreSQL database, run a query like this:

[1727] SELECT FROM salary_policy WHERE category = 'New Employee';

[1728] Inputs: "Payroll (Intent)", "New Employee (Entity)"

[1729] Output: Applicable salary information

[1730] Step 6:

[1731] The server generates a response according to the emotion and sends it to the device.

[1732] The server uses a template engine (e.g. Jinja2) to generate answers that take the user's feelings into consideration.

[1733] For example, "A new employee's salary is the sum of their basic salary and various allowances. For details, please refer to our company's payroll policy. If you have any questions, please feel free to contact us."

[1734] This generated response is converted into JSON format and sent to the terminal as an HTTP response.

[1735] Input: relevant salary information, sentiment score indicating "anxiety"

[1736] Output: Emotionally sensitive answers

[1737] Step 7:

[1738] The terminal displays the answer to the user.

[1739] The device analyzes the answers received from the server and displays them on the chatbot interface.

[1740] Input: Emotionally sensitive answers

[1741] Output: The answer displayed to the user

[1742] (Application example 2)

[1743] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1744] Conventional chatbots and automated response systems can respond to user inquiries quickly and accurately, but they often do not generate responses that take user emotions into consideration, which can result in lower satisfaction. Therefore, there is a need for systems that can recognize user emotions and generate and adjust appropriate responses based on those emotions. Especially on online shopping sites, providing responses to product-related inquiries that take user emotions into consideration can increase purchasing motivation and improve customer support.

[1745] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for analyzing the inquiry and identifying the corresponding intention and entity, means for acquiring related information from a database based on the identified intention and entity, means for generating an answer to the inquiry based on the acquired information, means for recognizing the user's emotions and adjusting the answer based on the recognition, and means for transmitting the generated answer to the user terminal. This enables a personalized answer that takes the user's emotions into consideration.

[1746] A "user" is a user who makes an inquiry to the system.

[1747] The "means for accepting an inquiry" is an interface function that accepts input such as text or voice from the user and sends it to the analysis process.

[1748] The "means for analyzing inquiries" refers to natural language processing models and algorithms that analyze the content of the received inquiry and extract intent and entities from it.

[1749] "Intent" is a concept that indicates the type of purpose or request that a user wants to achieve from a system.

[1750] An "entity" is a word or phrase that indicates a specific element or object contained in a user's query.

[1751] The "means for obtaining related information" is a function for searching and obtaining appropriate information from a database based on the analyzed intent and entity.

[1752] The "means for generating an answer" refers to an algorithm or program that generates an answer to a user's inquiry based on the acquired information.

[1753] "Means for recognizing the user's emotions and adjusting responses based on those emotions" refers to a function that uses an emotion recognition engine to identify the user's emotions and corrects and adjusts responses in a way that takes those emotions into consideration.

[1754] The "means for transmitting the answer to the user terminal" refers to a communication and display function for transmitting the generated answer to the user's terminal and displaying it in a format that is easy for the user to view.

[1755] A "natural language processing model" is a computational model that analyzes text data to understand the meaning and structure of language and extract information such as intent and entities.

[1756] An "emotion recognition engine" is a machine learning model or algorithm that identifies emotions from a user's text or voice characteristics and outputs that state.

[1757] A "database" is a digital storage system that stores and manages relevant information to generate answers to inquiries.

[1758] A "user terminal" is a device used by a user to enter inquiries and receive responses, and includes smartphones, tablets, PCs, etc.

[1759] The present invention relates to a system that quickly provides appropriate answers to inquiries from users, recognizes the emotions of the users, and adjusts the answers based on the emotions. Specific embodiments of the system are described in detail below.

[1760] System Overview

[1761] The system of the present invention comprises a user, a terminal, a server, and an emotion recognition engine. The user makes a query through the chatbot interface of the terminal, and the terminal sends the query to the server. The server analyzes the query, identifies the corresponding intent and entity, and further recognizes the user's emotion using the emotion recognition engine. The server then retrieves relevant information from a database, adjusts and generates a response based on the obtained emotion information, and sends it to the terminal. The terminal displays the generated response to the user.

[1762] User operations

[1763] The user accesses a terminal and inputs a query through the chatbot interface. For example, the user inputs, "Are these shoes waterproof?"

[1764] Terminal handling

[1765] The device sends the input query to the server along with the emotion recognition engine. To do this, it generates an HTTP request, and the query content is converted to JSON format and sent to the server.

[1766] Server Processing

[1767] The server receives the HTTP request and analyzes the query using a natural language processing (NLP) model, for example, to identify the intent and entities contained in the query.

[1768] The server then uses an emotion recognition engine to recognize the user's emotion, for example, identifying the user's emotion as anxiety.

[1769] The server then retrieves relevant information from a database based on the identified intent and entity, generating database queries to search and retrieve the required information.

[1770] The system then tailors the responses to take into account the perceived emotions and generates specific answers, for example, creating a reassuring answer for a user who is feeling anxious.

[1771] The generated answer is converted to JSON format and sent back to the device as an HTTP response, which includes an emotionally sensitive answer.

[1772] Terminal handling (again)

[1773] The terminal parses the answer received from the server and displays it to the user. It parses the JSON response and generates an answer that is displayed in the chatbot interface.

[1774] Example

[1775] For example, if a user types "Are these shoes waterproof?" into a device, the server analyzes the query and identifies the "waterproof performance of the shoes (intent)" and "shoes (entity)." The emotion recognition engine then recognizes the user's emotion as "anxiety." The server retrieves relevant information from the database, generates an emotion-sensitive response such as "These shoes are made with high-quality waterproof material, so you can wear them safely even on rainy days," and sends it to the device, which then displays it to the user.

[1776] Prompt Sentence Examples

[1777] User Question: "Are these shoes waterproof?"

[1778] As described above, the system of the present invention can provide quick and accurate answers to user inquiries, and can increase user satisfaction by generating answers that take into consideration the user's feelings.

[1779] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1780] Step 1:

[1781] A user opens the chatbot interface using a terminal and inputs a query. For example, the user inputs "Are these shoes waterproof?". The input data is a string.

[1782] Step 2:

[1783] The terminal accepts the input query and generates an HTTP request to send it to the server. The query content is converted to JSON format and sent to the server. The input data is the user's query text, and the output data is the HTTP request in JSON format.

[1784] Step 3:

[1785] The server receives an HTTP request and analyzes the query. It uses a natural language processing (NLP) model to identify intents and entities from the query. For example, "Shoe waterproofing" and "Shoes" are identified. The input data is the user's query text, and the output data is a pair of intents and entities.

[1786] Step 4:

[1787] The server uses an emotion recognition engine to recognize the user's emotion. The emotion recognition engine infers the emotion from the user's text and outputs an emotional state such as "anxiety" or "excitement." For example, the user's emotion is identified as "anxiety." The input data is the user's query text, and the output data is the user's emotional state.

[1788] Step 5:

[1789] The server retrieves relevant information from the database based on the identified intent and entity. It generates a database query to search and retrieve the required information. For example, information on waterproof shoes is retrieved. The input data is the intent-entity pair, and the output data is the related information.

[1790] Step 6:

[1791] The server generates an answer based on the acquired information and the user's emotions. For example, it creates an answer that takes emotions into consideration, such as "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data are the relevant information and the user's emotional state, and the output data is the generated answer.

[1792] Step 7:

[1793] The server converts the generated response into JSON format and sends it to the terminal as an HTTP response. Finally, the response sent from the server is received. The input data is the generated response, and the output data is the JSON format HTTP response.

[1794] Step 8:

[1795] The terminal analyzes the answer received from the server and displays it to the user. It parses the JSON response and displays the generated answer on the chatbot interface. For example, the answer might be, "These shoes are made of high-quality waterproof material, so you can wear them safely even on rainy days." The input data is the HTTP response in JSON format, and the output data is the text displayed to the user.

[1796] As a result, the system of the present invention can quickly and accurately respond to user inquiries and provide answers that take into consideration the user's feelings, which is expected to improve user satisfaction and increase purchasing motivation.

[1797] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1798] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1799] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1800] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1801] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1802] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1803] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1804] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1805] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1806] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1807] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1808] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1809] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1810] 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.

[1811] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1812] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1813] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1814] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1815] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1816] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1817] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1818] The following is further disclosed regarding the above embodiment.

[1819] (Claim 1)

[1820] A means for accepting inquiries from users;

[1821] means for analyzing the query and identifying a corresponding intent and entity;

[1822] a means for retrieving relevant information from a database based on the identified intent and entity;

[1823] means for generating a response to the inquiry based on the acquired information;

[1824] means for transmitting the generated answer to a user terminal;

[1825] A system including:

[1826] (Claim 2)

[1827] 10. The system of claim 1, further comprising means for using a natural language processing model to analyze the query.

[1828] (Claim 3)

[1829] 2. The system according to claim 1, further comprising means for transmitting a query received from a user terminal to a server.

[1830] "Example 1"

[1831] (Claim 1)

[1832] A means for accepting inquiries from users;

[1833] means for converting the query into a JSON format;

[1834] means for transmitting the converted query as an HTTP request to a server;

[1835] means for analyzing the query and using a natural language processing model to identify corresponding intents and entities;

[1836] a means for retrieving relevant information from a database based on the identified intent and entity;

[1837] a means for generating an answer to the inquiry based on the acquired information using a template engine;

[1838] A means of converting the generated answers into JSON format;

[1839] means for transmitting the generated answer to a user terminal;

[1840] A system including:

[1841] (Claim 2)

[1842] 10. The system of claim 1, wherein the system uses a generative AI model to analyze the query.

[1843] (Claim 3)

[1844] 2. The system according to claim 1, further comprising means for transmitting a query received from a user terminal to a server.

[1845] "Application Example 1"

[1846] (Claim 1)

[1847] A means for accepting inquiries from users;

[1848] means for analyzing the query and identifying a corresponding intent and entity;

[1849] a means for retrieving relevant information from a database based on the identified intent and entity;

[1850] means for generating a response to the inquiry based on the acquired information;

[1851] means for transmitting the generated answer to a user terminal;

[1852] a means for a user to report an emergency;

[1853] A means for generating appropriate measures in response to an emergency and notifying the user thereof;

[1854] A system including:

[1855] (Claim 2)

[1856] 10. The system of claim 1, further comprising means for using a natural language processing model to analyze the query.

[1857] (Claim 3)

[1858] 2. The system according to claim 1, further comprising means for transmitting a query received from a user terminal to a server.

[1859] "Example 2: Combining Emotion Engines"

[1860] (Claim 1)

[1861] A means for accepting inquiries from users;

[1862] means for analyzing the query and identifying a corresponding intent and entity;

[1863] means for recognizing a user's emotion based on the identified intent and entity;

[1864] means for retrieving relevant information from a database based on the recognized emotion;

[1865] means for generating an answer according to the acquired information and the recognized emotion;

[1866] means for transmitting the generated answer to a user terminal;

[1867] A system including:

[1868] (Claim 2)

[1869] 10. The system of claim 1, further comprising means for using a natural language processing model to analyze the query.

[1870] (Claim 3)

[1871] 2. The system according to claim 1, further comprising means for transmitting a query received from a user terminal to a server.

[1872] "Application example 2 when combining emotion engines"

[1873] (Claim 1)

[1874] A means for accepting inquiries from users;

[1875] means for analyzing the query and identifying a corresponding intent and entity;

[1876] a means for retrieving relevant information from a database based on the identified intent and entity;

[1877] means for generating a response to the inquiry based on the acquired information;

[1878] a means for recognizing a user's emotions and tailoring responses accordingly;

[1879] means for transmitting the generated answer to a user terminal;

[1880] A system including:

[1881] (Claim 2)

[1882] 10. The system of claim 1, further comprising means for using a natural language processing model to analyze the query.

[1883] (Claim 3)

[1884] 2. The system according to claim 1, further comprising means for transmitting a query received from a user terminal to a server. [Explanation of symbols]

[1885] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for accepting inquiries from users; means for analyzing the query and identifying a corresponding intent and entity; a means for retrieving relevant information from a database based on the identified intent and entity; means for generating a response to the inquiry based on the acquired information; means for transmitting the generated answer to a user terminal; A system including:

2. 10. The system of claim 1, further comprising means for using a natural language processing model to analyze the query.

3. 2. The system according to claim 1, further comprising means for transmitting a query received from a user terminal to a server.

Images