system

Abstract

Provide a system. [Solution] means for receiving a message from a user; natural language processing means for analyzing received messages; means for querying a database based on the analysis results; means for generating a response to the user based on the database query results; means for transmitting the generated answer to the user; A system including:

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] Prices vary widely among real estate businesses, and malicious add-on fees are often seen, so there is a need for a way for users to understand fair real estate prices and deal with unscrupulous businesses. Another issue is the lack of a system that allows users to easily obtain real estate-related questions and market information. To solve these issues and improve transparency regarding real estate prices, a consultation service that users can easily access is needed. [Means for solving the problem]

[0005] The present invention provides a system including a means for receiving messages from users, a natural language processing means for analyzing the received messages, a means for querying a database based on the analysis results, a means for generating a response to the user based on the database query results, and a means for sending the generated response to the user. This system allows users to easily resolve questions about real estate prices and obtain appropriate price information. Furthermore, by recording users' messages and responses using a log system, data useful for preventing and improving future problems is accumulated. Furthermore, this system also includes a terminal including a means for sending users' messages and receiving and displaying responses from the server, allowing users to use the service through an intuitive and easy-to-use interface.

[0006] A "user" is someone who uses the system to obtain information about real estate or to ask for advice.

[0007] The "means for receiving a message" refers to an interface or device for receiving a message sent by a user.

[0008] "Natural language processing means" refers to technology or systems that analyze received messages and understand their content and intent.

[0009] A "database querying means" is a system or method for retrieving information from relevant databases based on the results of the analysis.

[0010] "Means for generating a response to the user" refers to techniques and methods for constructing a response to the user based on information obtained from a database.

[0011] The "means for transmitting an answer to a user" refers to an interface or device for transmitting the generated answer to a user.

[0012] "Log System" refers to a system for recording and storing user messages and the system's responses to those messages.

[0013] A "terminal" is an apparatus or device that allows a user to input and send messages, and receive and display replies from a server. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention provides a ChatBot-style service that allows users to consult about real estate prices and price fluctuations by agents. Detailed embodiments of the invention are described below.

[0036] Server processing

[0037] 1. Receiving a message from a user

[0038] The server receives messages sent by users. The user enters a question about real estate on their device and presses the send button. The message is sent to the server as an HTTP request, and the server receives it.

[0039] 2. Message Analysis

[0040] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. For example, if a message is sent saying, "What is the average price for a 2LDK apartment in the neighborhood?", the NLP engine analyzes the message and extracts information about "2LDK" and "area."

[0041] 3. Database Query

[0042] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0043] 4. Generating answers for users

[0044] The server generates a response to the user based on the acquired data. For example, it averages the acquired price data and generates a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0045] 5. Submit your response

[0046] The server generates a response and sends it to the user, who receives it and displays it in the chat box.

[0047] 6. Logging

[0048] Additionally, the server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or improvements.

[0049] Processing by the terminal

[0050] 1. Enter your message

[0051] Users use the ChatBot interface on their device to input questions about real estate. The input message is temporarily saved and sent to the server when the send button is pressed.

[0052] 2. Sending a Message

[0053] The terminal sends the message entered by the user to the server as an HTTP request, and then waits for a response from the server.

[0054] 3. View Answers

[0055] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0056] User

[0057] 1. Enter your question

[0058] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[0059] 2. Verify the information

[0060] Within a few seconds, the server will return a response to the chat screen, allowing the user to confirm the information. For example, the average price for a 2LDK apartment in this area is 150,000 yen.

[0061] This system allows users to easily resolve questions about real estate prices and obtain accurate price information. In addition, messages and responses are recorded on the server, which helps prevent future problems and improve the system.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[0065] Step 2:

[0066] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[0067] Step 3:

[0068] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[0069] Step 4:

[0070] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent, for example, extracting information about "2LDK" and "area."

[0071] Step 5:

[0072] The server queries a real estate price database based on the analysis results, for example, searching for price data for "2LDK" properties in the specified area.

[0073] Step 6:

[0074] The server receives the database query results and generates a response to the user based on the retrieved data. For example, it creates a response such as, "The average price for a 2LDK apartment in this area is 150,000 yen."

[0075] Step 7:

[0076] The server generates an answer and sends it to the user, which is sent to the user's device as an HTTP response.

[0077] Step 8:

[0078] The terminal receives the answer from the server and displays it in the chat box. The user can then confirm the displayed answer.

[0079] Step 9:

[0080] The server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0081] Example 1

[0082] 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."

[0083] Conventional real estate price information systems have had problems such as taking a long time to receive an appropriate answer after a user inputs a question, and the accuracy of the answers being low. Also, if the user's messages and answers are not recorded in the system, it is difficult to troubleshoot or improve the system later.

[0084] 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.

[0085] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, means for querying a data store based on the analysis results, means for using a generative AI model to generate answers to the users based on the data store query results, and means for sending the generated answers to the users. This allows users to quickly obtain real estate price information with high accuracy, and since the user's messages and answers are recorded, it makes future troubleshooting and system improvements easier.

[0086] "User" refers to a person who uses the System to request information about real estate prices.

[0087] "Message" refers to text information that a user enters into the system and sends to the server.

[0088] "Means for receiving" refers to an interface or function for receiving messages sent by users at the server.

[0089] "Natural language processing means" refers to the technology or algorithm that analyzes messages received by the server and understands the user's intent and content.

[0090] "Data Store" means a database or storage device that stores real estate pricing information and other related data.

[0091] "Means for querying" refers to the functionality for searching the data store based on the analysis results and obtaining the required information.

[0092] A "generative AI model" refers to an artificial intelligence technology that automatically generates answers to users based on information obtained from a data store.

[0093] "Means for sending" refers to a communication interface or function for sending the generated answer back to the user.

[0094] "Log system" refers to a recording device or system that records user messages and system responses for later reference and analysis.

[0095] "Terminal" refers to a device on which a user inputs and sends messages and receives and displays responses from a server. Examples include a smartphone, tablet, or personal computer.

[0096] This invention is a system that provides a chatbot-style service that allows users to consult about real estate prices and price fluctuations by agents. A specific implementation method of this system will be described in detail.

[0097] System configuration

[0098] The system consists of a user device, a server, a data store, a generative AI model, a natural language processing (NLP) engine, and a log system.

[0099] Terminal

[0100] Users can access the system by entering questions using devices such as smartphones, tablets, and personal computers. They can then use the chatbot interface displayed on the device's browser to enter their questions and click the send button. As a specific example, messages can be sent using the AJAX or Fetch API provided by the web browser.

[0101] server

[0102] The server receives messages from users as HTTP requests. To analyze the received messages, it uses an NLP engine such as Google® Cloud Natural Language API or IBM Watson® Natural Language Understanding. Based on the information extracted from the analyzed messages, the server queries a data store that stores real estate price information. This query uses a database system such as MySQL® or PostgreSQL.

[0103] Datastore

[0104] The data store is a database that holds information on real estate prices and market rates by region. The server searches this data store based on the analysis results and obtains the necessary information.

[0105] Generative AI Models

[0106] The server generates a response to the user based on the information retrieved from the data store. This response can be generated using a generative AI model such as OpenAI (registered trademark) GPT-3 (registered trademark). For example, a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen" may be generated.

[0107] Sending a response to the user

[0108] The generated answer is sent from the server to the user's device as an HTTP response. The device displays the received answer in a chat box. HTML, JavaScript (registered trademark), CSS, etc. are used for display.

[0109] Log System

[0110] The server records the user's message and the system's response to it in a log system, using systems such as ElasticSearch® or Splunk, which makes it easier to troubleshoot and improve the system later.

[0111] Specific examples

[0112] When a user types "What is the average rental price for a 3LDK apartment in Shinjuku Ward?" into the chatbot interface on their device and presses the send button, the process goes as follows: The server receives this message and uses an NLP engine to extract the information "Shinjuku Ward" and "3LDK." The server then queries the data store based on this information to obtain corresponding real estate price information. Based on the information obtained, the server uses a generative AI model to generate an answer such as "The average rental price for a 3LDK apartment in Shinjuku Ward is 200,000 yen," and sends it to the user's device. The user can view this in the chat box.

[0113] Prompt Sentence Examples

[0114] Here is an example of a prompt to input to the generative AI model:

[0115] "What is the average rental price for a 3LDK apartment in Shinjuku Ward?"

[0116] Based on this prompt, the AI ​​model retrieves the appropriate data and provides information.

[0117] In this way, the system allows users to quickly and accurately resolve questions about property prices.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] The user types a question into the chatbot interface on the device.

[0121] Specific operation: The user enters a question, for example, "What is the average rent price for a 3LDK apartment in Shinjuku Ward?" and clicks the send button. The data entered is the user's question text, and the click event of the send button is the trigger.

[0122] Step 2:

[0123] The terminal sends the message entered by the user to the server as an HTTP request.

[0124] Specific operation: The browser or application on the device uses AJAX or the Fetch API to send the input message to the server as an HTTP POST request. The input data is the user's question message, and the output is an HTTP request.

[0125] Step 3:

[0126] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent.

[0127] How it works: The server calls an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding to analyze the message. The input data is the user's question, and the output is the analyzed intent and keywords (e.g., "Shinjuku Ward" and "3LDK").

[0128] Step 4:

[0129] The server queries the data store based on the analysis results.

[0130] Specific operation: The server queries a database such as MySQL or PostgreSQL to retrieve real estate price information that matches the specified conditions (e.g., "Shinjuku Ward" and "3LDK"). The input data is the analysis result of the NLP engine, and the output is the real estate price information retrieved from the database.

[0131] Step 5:

[0132] Based on the data acquired by the server, a generative AI model is used to generate answers for the user.

[0133] Specific operation: The server calls a generative AI model (e.g., OpenAI GPT-3) and generates an answer based on the acquired real estate price information. The input data is real estate price information acquired from the database, and the output is the generated answer (e.g., "The average rent for a 3LDK apartment in Shinjuku Ward is 200,000 yen").

[0134] Step 6:

[0135] The server sends the generated answer to the user's terminal as an HTTP response.

[0136] Specific operation: The server includes the generated answer in an HTTP response and sends it back to the terminal. The input data is the generated answer text, and the output is the HTTP response.

[0137] Step 7:

[0138] The terminal displays the response received from the server in the chat box.

[0139] Specific operation: The device parses the response received from the server and displays it in the chat box using HTML and JavaScript. The input data is the response text in the HTTP response, and the output is the text displayed in the browser.

[0140] Step 8:

[0141] The server records the user's message and the system's response in a log system.

[0142] Specific operation: The server records user messages and generated answers in a log system such as ElasticSearch or Splunk. The input data is the user's question message and the generated answer, and the output is the data saved as a log.

[0143] (Application example 1)

[0144] 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."

[0145] Existing systems that provide users with real estate information make it difficult for users to easily obtain information in real time. Even if users visit a store in person, they cannot instantly check detailed real-time real estate information. As a result, users often feel uneasy because they do not have enough information when making decisions about real estate.

[0146] 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.

[0147] In this invention, the server includes means for receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, and means for inputting and displaying a message using a user interface of the smart glasses, thereby enabling users to obtain real estate information in real time through the smart glasses in a store and make quick and accurate decisions.

[0148] The "means for receiving a message from a user" is an interface for receiving a message input by a user in digital form.

[0149] "Natural language processing means for analyzing received messages" refers to a natural language processing engine for analyzing received messages and understanding the user's intent and content.

[0150] "Means for querying a database based on the analysis results" is a function for searching related databases based on the analysis results of natural language processing and obtaining the necessary information.

[0151] "Means for generating an answer to a user based on database query results" refers to the process of creating an appropriate answer to a user's question based on information retrieved from a database.

[0152] The "means for transmitting the generated answer to the user" refers to a communication means for transmitting the generated answer to the user.

[0153] "Means for inputting and displaying messages using a user interface of the smart glasses" refers to an interface that allows a user to input a message using the smart glasses and have the response displayed on the display.

[0154] "Means for recording user messages and responses in a log system" refers to a system for saving and recording messages entered by users and the system's responses to those messages.

[0155] The "means for receiving a response from the server and displaying it on the smart glasses" refers to a method for receiving a response sent from the server on the smart glasses and visually conveying it to the user.

[0156] This invention is a system that allows users to obtain real estate information in real time using smart glasses. The system includes a server, smart glasses, a natural language processing (NLP) engine, a database, a log system, etc.

[0157] Server processing

[0158] The server performs the process using the following main methods:

[0159] 1. Message Receiving Method

[0160] Receives messages entered by the user through the interface of the smart glasses, which are then sent to the server via the Internet as HTTP requests.

[0161] 2. Natural Language Processing Methods

[0162] The received message is passed to an NLP engine (such as spaCy), which analyzes the content of the user's question. For example, a question like "What is the average price for a 2LDK apartment in the neighborhood?" is analyzed, and related keywords (such as "2LDK" and "area") are extracted.

[0163] 3. Database query methods

[0164] Based on the information extracted by the NLP engine, the system queries a real estate price database to retrieve relevant information, including past transaction prices, current market prices, and market rates.

[0165] 4. Answer generation means

[0166] Based on the information retrieved from the database, the system automatically generates answers to be provided to the user. For example, it generates an answer such as, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0167] 5. Method of sending responses

[0168] The generated answers are sent over the internet to the smart glasses and displayed to the user.

[0169] Processing by terminal (smart glasses)

[0170] The smart glasses have the following features:

[0171] 1. Enter and send a message

[0172] The user can input messages by voice or text through the smart glasses interface, and the input messages are sent to the server.

[0173] 2. Receiving and Displaying Responses

[0174] The smart glasses receive the response sent from the server and display it on the display. For example, information such as "The average market price for a 2LDK apartment in this area is 150,000 yen" is visually displayed.

[0175] Log System

[0176] The server records the user's messages and responses in a log system, which provides useful data for future troubleshooting and system improvement.

[0177] Program processing explanation

[0178] The system is implemented using a Python program, the requests library, and an NLP processor (e.g., spaCy). Messages sent by users through the smart glasses are parsed by the server using natural language processing and queried against the relevant real estate database. Answers are then generated based on the retrieved data and sent to the user.

[0179] Prompt Sentence Examples

[0180] Below are some example prompts used for generative AI models (e.g., GPT-3):

[0181] "The user asks through the smart glasses, 'What is the average price for a 3LDK apartment in the neighborhood?' Generate an answer in the following format. Example answer: 'The average price for a 3LDK apartment in this neighborhood is 250,000 yen.'"

[0182] The above configuration allows users to obtain real estate information in real time through smart glasses in a store, enabling them to make quick and accurate decisions.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] Users use the smart glasses' interface to input real estate-related questions. Voice input or text input is supported, and the input message is temporarily stored on the device. For example, a user might input, "What is the market price for a 3LDK apartment in the neighborhood?" The input text is sent to the server in the form of an HTTP request.

[0186] Step 2:

[0187] The server receives an HTTP request sent by a user. The received message is then passed to a natural language processing (NLP) engine for analysis. The NLP engine then understands the content and intent of the message and extracts necessary keywords (e.g., "3LDK" or "neighborhood"). The results of this analysis are input to the next processing step.

[0188] Step 3:

[0189] The server uses the results of the natural language processing engine's analysis to query a real estate price database. For example, it might search the database based on the keywords "3LDK" and "neighborhood" to retrieve related property information. The query results serve as input for the next processing step.

[0190] Step 4:

[0191] The server generates a response to the user based on information retrieved from the database. For example, it can average multiple property data from the search results to automatically generate a response such as "The average market price for a 3LDK apartment in this area is 250,000 yen." This generated response becomes the input for the next processing step.

[0192] Step 5:

[0193] The server then sends the generated answer as an HTTP response to the user's smart glasses. The data is received by the device, and the result is displayed in a chat box or on the smart glasses' display. A message such as "The average market price for a 3LDK apartment in this area is 250,000 yen" is displayed.

[0194] Step 6:

[0195] The server records the message entered by the user and the generated response in a log system. This saves data for future troubleshooting and system improvement. For example, the input message "What is the average price for a 3LDK apartment in the neighborhood?" and the generated response "The average price for a 3LDK apartment in this area is 250,000 yen" are recorded in the log.

[0196] The above is the basic processing flow of this system, and details of the specific operations and inputs / outputs at each step.

[0197] 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.

[0198] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[0199] Server processing

[0200] 1. Receiving a message from a user

[0201] The server receives messages sent by users. The user types a question about real estate from their device and presses the send button. For example, if the user types, "What is the average price for a 2LDK apartment in the neighborhood?", the message is sent to the server as an HTTP request and received.

[0202] 2. Message Analysis

[0203] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. The analysis results include information about the "2LDK" and "area."

[0204] 3. Emotion Recognition by Emotion Engine

[0205] The server simultaneously uses an emotion engine to recognize emotions from the user's message, such as whether the user is angry or confused, based on the message context and specific keywords.

[0206] 4. Database Query

[0207] Based on the analysis results, the server queries a real estate price database. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0208] 5. Generating Answers for the User

[0209] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0210] 6. Submit your response

[0211] The server generates a response and sends it to the user, which is then sent to the user's device as an HTTP response.

[0212] 7. Logging

[0213] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0214] Processing by the terminal

[0215] 1. Enter your message

[0216] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then hit send.

[0217] 2. Sending a Message

[0218] The terminal sends the user's input message to the server as an HTTP request, and then waits for a response from the server.

[0219] 3. View Answers

[0220] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0221] User

[0222] 1. Enter your question

[0223] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[0224] 2. Verify the information

[0225] Within a few seconds, the server will send a response to the chat screen, which the user can confirm. For example, the user may receive information such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0226] This system allows users to easily resolve questions about real estate prices and receive personalized support that takes their emotions into consideration. Furthermore, all logs are recorded on the server side, accumulating data that will be useful for future problem solving and system improvements.

[0227] The processing flow will be explained below.

[0228] Step 1:

[0229] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[0230] Step 2:

[0231] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[0232] Step 3:

[0233] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[0234] Step 4:

[0235] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent. This analysis includes keyword extraction and context understanding. For example, information about "2LDK" and "area" is extracted.

[0236] Step 5:

[0237] The server uses an emotion engine to recognize emotions from the user's message. For example, it determines the user's emotional state from the message context and specific keywords. For example, emotions such as "confused" or "angry" can be recognized.

[0238] Step 6:

[0239] The server queries a real estate price database based on the analysis and emotion recognition results. Based on the analyzed information, it searches for real estate price information that matches the "area" specified in "2LDK."

[0240] Step 7:

[0241] The server receives the results from the database and generates a response for the user. For example, it creates a response that takes into consideration the user's feelings, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0242] Step 8:

[0243] The server sends the generated answer to the user's terminal as an HTTP response.

[0244] Step 9:

[0245] The device receives the response from the server and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0246] Step 10:

[0247] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0248] This series of processes allows users to quickly resolve their real estate-related questions and receive courteous, sensitive service.

[0249] Example 2

[0250] 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."

[0251] Conventional ChatBot systems use natural language processing technology to understand user intent, but lack the ability to recognize a user's emotional state and provide appropriate responses based on that emotion. They also lack a mechanism for quickly and accurately answering complex questions about real estate prices. As a result, users often receive poor quality information, leading to lower satisfaction levels.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0253] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, emotion recognition means for recognizing emotions from the user's messages, means for querying a database based on the analysis results and the emotion recognition results, means for generating a response to the user based on the database query results and the emotion recognition results, and means for sending the generated response to the user. This makes it possible to provide appropriate responses according to the user's emotional state and to quickly and accurately respond to complex questions about real estate prices.

[0254] The "means for receiving a message from a user" is a function for transferring a message input by a user to a server, and is usually performed via an HTTP request.

[0255] "Natural language processing means for analyzing received messages" refers to engines or algorithms that understand the content of messages received from users and analyze keywords and intent. Examples include Google Cloud Natural Language API and IBM Watson.

[0256] "Emotion recognition means for recognizing emotions from user messages" refers to engines or algorithms for reading emotions from the context of a user's message or specific keywords, and examples include Amazon Comprehend and Microsoft (registered trademark) Azure (registered trademark) Text Analytics.

[0257] The "means for querying a database based on the analysis results and emotion recognition results" is a function for searching and retrieving related data from a database based on the content of a user's request and the recognized emotional state.

[0258] The "means for generating a response to the user based on the database query results and emotion recognition results" refers to an algorithm or engine for generating an appropriate response based on the acquired data and the recognized emotion.

[0259] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it, and is usually performed via an HTTP response.

[0260] "Means for recording user messages, emotional states, and responses in the log system" refers to a function for recording user messages, emotional states, and responses generated by the system, for future use in data analysis and system improvement.

[0261] The "means for sending a user's message and receiving and displaying a response from the server" refers to the interface and function on the terminal side that sends the user's input to the server and receives and displays a response from the server.

[0262] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by real estate agents and receive answers. In particular, we provide a system that can recognize the user's emotional state and provide appropriate answers according to that state.

[0263] Overview of the hardware and software used

[0264] This system operates by combining multiple technological elements, including the following key software and hardware components:

[0265] 1. Natural Language Processing (NLP) Engines: Google Cloud Natural Language API and IBM Watson

[0266] 2. Emotion Recognition Engine: Amazon Comprehend or Microsoft Azure Text Analytics

[0267] 3. Database: MySQL or PostgreSQL

[0268] 4. Log systems: Elasticsearch, Logstash

[0269] 5. Servers and terminals: Web servers (e.g., Apache (registered trademark), Nginx), user terminals (e.g., PCs, smartphones)

[0270] System processing flow

[0271] 1. Enter your message

[0272] Users use the ChatBot interface on their device to input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then press the send button.

[0273] 2. Sending a Message

[0274] The terminal sends the input message to the server as an HTTP request, using the HTTP protocol.

[0275] 3. Receiving and parsing messages

[0276] The server receives messages sent by users. The received messages are passed to a natural language processing engine for analysis. In this analysis process, intent such as "2LDK" or "area" is extracted from the message.

[0277] 4. Emotion recognition

[0278] At the same time, the server uses an emotion recognition engine to determine the user's emotions from the message, such as whether the user is dissatisfied or confused, based on the context of the text and specific keywords.

[0279] 5. Querying the Database

[0280] The server queries a real estate price database based on the analysis results and retrieves relevant real estate price data from the database based on the detected keywords (e.g., "2LDK" and "area").

[0281] 6. Answer Generation

[0282] The server generates an appropriate response to the user based on the acquired data and the results of emotion recognition. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0283] 7. Submit your response

[0284] The server sends the generated answer as an HTTP response to the user's device, where it is displayed.

[0285] 8. Logging

[0286] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0287] Specific examples

[0288] The user inputs a prompt into the chatbot interface, such as "What is the average price for a 2LDK apartment in the neighborhood?". In response, the system operates as follows:

[0289] The server receives the message and analyzes it using a natural language processing engine.

[0290] Recognize user emotions with an emotion recognition engine.

[0291] Based on the analysis results, a database is queried to obtain relevant real estate price data.

[0292] Emotion recognition results are also taken into consideration to generate appropriate answers.

[0293] The answer is sent to the user's terminal, and the necessary data is recorded in the log system.

[0294] In this way, users can easily and quickly obtain information about real estate prices. Furthermore, by incorporating emotion recognition, we can provide better services that take users' emotions into consideration.

[0295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0296] Step 1:

[0297] The server receives a message from the user. The user enters a question on the terminal, such as "What is the average price for a 2LDK apartment in the neighborhood?" and presses the send button. This message is sent to the server via an HTTP request. The input is the user's message in text format, and the output is the message received by the server.

[0298] Step 2:

[0299] The server inputs the received message into a natural language processing (NLP) engine. The NLP engine uses Google Cloud Natural Language API or IBM Watson to analyze keywords and user intent from the input message. Specifically, it extracts information such as "2LDK" and "area." The input is the user message, and the output is the extracted keywords and intent.

[0300] Step 3:

[0301] The server simultaneously uses an emotion recognition engine to recognize emotions from the user's message. It uses Amazon Comprehend and Microsoft Azure Text Analytics to determine emotions (e.g., anger, confusion) from the message text. The input is the user message, and the output is the determined emotional information.

[0302] Step 4:

[0303] The server queries a database based on the analysis results and emotion recognition results. It uses MySQL or PostgreSQL as the database and executes a query to retrieve real estate price information that matches the specified area and property type (2LDK). The input is the analysis results and emotion recognition results, and the output is real estate price data.

[0304] Step 5:

[0305] The server generates a response to the user based on the acquired data and the results of emotion recognition. It provides information such as average market prices in appropriate wording, while also taking into consideration the user's emotional state. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help." The input is data acquired from the database and emotional information, and the output is the generated response text.

[0306] Step 6:

[0307] The server sends the generated answer to the user's terminal as an HTTP response. The sent answer is displayed on the user's terminal. The input is the generated answer text, and the output is the answer displayed on the user's terminal.

[0308] Step 7:

[0309] The server records the user's message, emotional state, and the system-generated answer in a log system. Elasticsearch and Logstash are used to manage this data and use it for later analysis and system improvement. The input is the user's message, emotional information, and the generated answer, and the output is the record in the log system.

[0310] (Application example 2)

[0311] 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."

[0312] While conventional chatbot systems can provide appropriate answers to users' questions about real estate prices, they do not adequately take into account the user's emotional state. Furthermore, they do not take into account the application of new devices such as smart glasses as a means of providing instant customer service in brick-and-mortar stores, and there is a need to improve customer satisfaction.

[0313] 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 receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, means for recognizing the user's emotional state, and means for providing an appropriate response based on the recognized emotional state. This makes it possible to provide appropriate real estate information in real time, even in a physical store, taking into account the user's emotional state.

[0314] The "means for receiving messages from users" is a system that includes a process for sending messages sent by users to a server.

[0315] The "natural language processing means for analyzing received messages" is a system that uses a natural language processing engine to analyze the content of a user's message and understand its intent.

[0316] The "means for querying a database based on the analysis result" is a system that includes a process for searching a database to obtain related data based on the content of the analyzed message.

[0317] The "means for generating a response to a user based on the database query results" is a system that includes a process for generating a response to be provided to a user based on the acquired data and analysis results.

[0318] The "means for sending the generated answer to the user" is a system that includes a process for delivering the generated answer to the user.

[0319] The "means for recognizing the user's emotional state" is a system for identifying the user's emotions from the user's facial expressions, voice, message context, etc.

[0320] A "means for providing appropriate answers based on a recognized emotional state" is a system that includes a process for generating more appropriate and considerate answers based on the user's emotional state.

[0321] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[0322] Server processing

[0323] The server receives messages sent by users and analyzes them using a natural language processing engine. Based on the analysis results and the user's emotional state, it queries a database to generate and send a response. Specifically, it works as follows:

[0324] 1. Receiving a message from a user

[0325] The server receives messages entered by users using smart glasses or smartphones. For example, if a user asks, "What is the average price of a 2LDK apartment in this area?", the message is sent to the server as an HTTP request.

[0326] 2. Message Analysis

[0327] The server passes the received message to a natural language processing engine (e.g., spaCy or BERT) to analyze the user's intent. The analysis results include information about "2LDK" and "area."

[0328] 3. Emotion Recognition by Emotion Engine

[0329] At the same time, the server uses an emotion engine (e.g., OpenCV or Affectiva) to recognize emotions from the user's message and facial expressions. For example, it determines whether the user is interested or anxious based on the message context and specific keywords.

[0330] 4. Database Query

[0331] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0332] 5. Generating Answers for the User

[0333] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The current market price is around 150,000 yen. Please let us know if you need more information."

[0334] 6. Submit your response

[0335] The server then sends the generated answer to the user, which is then sent to the user's terminal as an HTTP response.

[0336] Processing by the terminal

[0337] The device sends messages from the user to the server, receives replies from the server, and displays them. This is done using smart glasses or a smartphone.

[0338] 1. Enter your message

[0339] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the average price for a 2LDK apartment in this area?", and then hit the send button.

[0340] 2. Sending a Message

[0341] The terminal sends the user's input message as an HTTP request to the server, and then waits for a response from the server.

[0342] 3. View Answers

[0343] When the server responds to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The current market price is around 150,000 yen. Please let us know if you need more information."

[0344] User operation

[0345] Users can enter specific questions into the ChatBot's interface and view the answers, allowing them to easily resolve their real estate pricing queries and receive a personal, sensitive response.

[0346] Prompt Sentence Examples

[0347] For example, if a customer asks, "What is the average price for a 2LDK apartment in this area?", the following prompt sentence is input into the generative AI model:

[0348] Question: "What is the average price for a 2LDK apartment in this area?"

[0349] Emotional state: "Curious"

[0350] This prompt is sent to the server, the answer is retrieved, and the answer is displayed on the smart glasses, providing the customer with the information instantly.

[0351] This system allows users to resolve questions about real estate prices and communicate in a way that takes their emotions into consideration. In addition, all logs are recorded on the server side, which can be used to solve problems and improve the system in the future.

[0352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0353] Step 1:

[0354] A user uses smart glasses or a smartphone to input a real estate question, for example, "What is the average price of a 2LDK apartment in this area?" and presses the submit button. This input is sent to the server as an HTTP request. The input is the user's natural language message, and the output is an HTTP request sent to the server.

[0355] Step 2:

[0356] The server processes the received HTTP request and passes it to a natural language processing engine to analyze the user's message. The natural language processing engine (e.g., spaCy or BERT) analyzes the content of the message and understands the intent of the user's question. The input is the user's natural language message, and the output is analyzed data (e.g., property type and area information).

[0357] Step 3:

[0358] At the same time, the server uses an emotion engine to recognize the user's emotional state. The emotion engine (e.g., OpenCV or Affectiva) determines the emotion from the user's facial expression and the message context. The input is the user's facial expression data and the message context, and the output is the user's emotional state.

[0359] Step 4:

[0360] The server queries a real estate price database based on the analysis results and the emotional state. The database provides real estate price information matching the specified area and property type (e.g., "2LDK"). The input is the analysis results, and the output is the related real estate price data.

[0361] Step 5:

[0362] The server generates an appropriate answer for the user based on the acquired data and the results of the emotion engine. For example, it creates an answer in the form of "The current market price is around 150,000 yen. Please let us know if you need more information." The input is real estate data acquired from the database and the user's emotional state, and the output is the generated answer.

[0363] Step 6:

[0364] The server generates an answer and sends it to the user. The answer is sent as an HTTP response and displayed on the terminal. The input is the generated answer, and the output is the HTTP response sent to the user.

[0365] Step 7:

[0366] The terminal receives the response from the server and displays it in the chat box, allowing the user to check the response on the terminal. The input is the HTTP response sent from the server, and the output is the response message displayed on the terminal.

[0367] Through the above processing steps, the user can resolve their questions about real estate prices and receive answers that take their emotions into consideration.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] In the smart glasses 214, 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.

[0383] 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."

[0384] This invention provides a ChatBot-style service that allows users to consult about real estate prices and price fluctuations by agents. Detailed embodiments of the invention are described below.

[0385] Server processing

[0386] 1. Receiving a message from a user

[0387] The server receives messages sent by users. The user enters a question about real estate on their device and presses the send button. The message is sent to the server as an HTTP request, and the server receives it.

[0388] 2. Message Analysis

[0389] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. For example, if a message is sent saying, "What is the average price for a 2LDK apartment in the neighborhood?", the NLP engine analyzes the message and extracts information about "2LDK" and "area."

[0390] 3. Database Query

[0391] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0392] 4. Generating answers for users

[0393] The server generates a response to the user based on the acquired data. For example, it averages the acquired price data and generates a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0394] 5. Submit your response

[0395] The server generates a response and sends it to the user, who receives it and displays it in the chat box.

[0396] 6. Logging

[0397] Additionally, the server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or improvements.

[0398] Processing by the terminal

[0399] 1. Enter your message

[0400] Users use the ChatBot interface on their device to input questions about real estate. The input message is temporarily saved and sent to the server when the send button is pressed.

[0401] 2. Sending a Message

[0402] The terminal sends the message entered by the user to the server as an HTTP request, and then waits for a response from the server.

[0403] 3. View Answers

[0404] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0405] User

[0406] 1. Enter your question

[0407] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[0408] 2. Verify the information

[0409] Within a few seconds, the server will return a response to the chat screen, allowing the user to confirm the information. For example, the average price for a 2LDK apartment in this area is 150,000 yen.

[0410] This system allows users to easily resolve questions about real estate prices and obtain accurate price information. In addition, messages and responses are recorded on the server, which helps prevent future problems and improve the system.

[0411] The processing flow will be explained below.

[0412] Step 1:

[0413] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[0414] Step 2:

[0415] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[0416] Step 3:

[0417] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[0418] Step 4:

[0419] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent, for example, extracting information about "2LDK" and "area."

[0420] Step 5:

[0421] The server queries a real estate price database based on the analysis results, for example, searching for price data for "2LDK" properties in the specified area.

[0422] Step 6:

[0423] The server receives the database query results and generates a response to the user based on the retrieved data. For example, it creates a response such as, "The average price for a 2LDK apartment in this area is 150,000 yen."

[0424] Step 7:

[0425] The server generates an answer and sends it to the user, which is sent to the user's device as an HTTP response.

[0426] Step 8:

[0427] The terminal receives the answer from the server and displays it in the chat box. The user can then confirm the displayed answer.

[0428] Step 9:

[0429] The server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0430] Example 1

[0431] 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."

[0432] Conventional real estate price information systems have had problems such as taking a long time to receive an appropriate answer after a user inputs a question, and the accuracy of the answers being low. Also, if the user's messages and answers are not recorded in the system, it is difficult to troubleshoot or improve the system later.

[0433] 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.

[0434] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, means for querying a data store based on the analysis results, means for using a generative AI model to generate answers to the users based on the data store query results, and means for sending the generated answers to the users. This allows users to quickly obtain real estate price information with high accuracy, and since the user's messages and answers are recorded, it makes future troubleshooting and system improvements easier.

[0435] "User" refers to a person who uses the System to request information about real estate prices.

[0436] "Message" refers to text information that a user enters into the system and sends to the server.

[0437] "Means for receiving" refers to an interface or function for receiving messages sent by users at the server.

[0438] "Natural language processing means" refers to the technology or algorithm that analyzes messages received by the server and understands the user's intent and content.

[0439] "Data Store" means a database or storage device that stores real estate pricing information and other related data.

[0440] "Means for querying" refers to the functionality for searching the data store based on the analysis results and obtaining the required information.

[0441] A "generative AI model" refers to an artificial intelligence technology that automatically generates answers to users based on information obtained from a data store.

[0442] "Means for sending" refers to a communication interface or function for sending the generated answer back to the user.

[0443] "Log system" refers to a recording device or system that records user messages and system responses for later reference and analysis.

[0444] "Terminal" refers to a device on which a user inputs and sends messages and receives and displays responses from a server. Examples include a smartphone, tablet, or personal computer.

[0445] This invention is a system that provides a chatbot-style service that allows users to consult about real estate prices and price fluctuations by agents. A specific implementation method of this system will be described in detail.

[0446] System configuration

[0447] The system consists of a user device, a server, a data store, a generative AI model, a natural language processing (NLP) engine, and a log system.

[0448] Terminal

[0449] Users can access the system by entering questions using devices such as smartphones, tablets, and personal computers. They can then use the chatbot interface displayed on the device's browser to enter their questions and click the send button. As a specific example, messages can be sent using the AJAX or Fetch API provided by the web browser.

[0450] server

[0451] The server receives messages from users as HTTP requests. To parse the messages, it uses an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the information extracted from the parsed messages, the server queries a data store that stores real estate price information. This query is performed using a database system such as MySQL or PostgreSQL.

[0452] Datastore

[0453] The data store is a database that holds information on real estate prices and market rates by region. The server searches this data store based on the analysis results and obtains the necessary information.

[0454] Generative AI Models

[0455] The server generates a response to the user based on the information retrieved from the data store. This response can be generated using a generative AI model such as OpenAI GPT-3. For example, a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen" can be generated.

[0456] Sending a response to the user

[0457] The generated answer is sent from the server to the user's device as an HTTP response. The device displays the received answer in a chat box. HTML, JavaScript, CSS, etc. are used for display.

[0458] Log System

[0459] The server records user messages and the system's responses in a logging system, using systems such as ElasticSearch or Splunk, to facilitate future troubleshooting and system improvements.

[0460] Specific examples

[0461] When a user types "What is the average rental price for a 3LDK apartment in Shinjuku Ward?" into the chatbot interface on their device and presses the send button, the process goes as follows: The server receives this message and uses an NLP engine to extract the information "Shinjuku Ward" and "3LDK." The server then queries the data store based on this information to obtain corresponding real estate price information. Based on the information obtained, the server uses a generative AI model to generate an answer such as "The average rental price for a 3LDK apartment in Shinjuku Ward is 200,000 yen," and sends it to the user's device. The user can view this in the chat box.

[0462] Prompt Sentence Examples

[0463] Here is an example of a prompt to input to the generative AI model:

[0464] "What is the average rental price for a 3LDK apartment in Shinjuku Ward?"

[0465] Based on this prompt, the AI ​​model retrieves the appropriate data and provides information.

[0466] In this way, the system allows users to quickly and accurately resolve questions about property prices.

[0467] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0468] Step 1:

[0469] The user types a question into the chatbot interface on the device.

[0470] Specific operation: The user enters a question, for example, "What is the average rent price for a 3LDK apartment in Shinjuku Ward?" and clicks the send button. The data entered is the user's question text, and the click event of the send button is the trigger.

[0471] Step 2:

[0472] The terminal sends the message entered by the user to the server as an HTTP request.

[0473] Specific operation: The browser or application on the device uses AJAX or the Fetch API to send the input message to the server as an HTTP POST request. The input data is the user's question message, and the output is an HTTP request.

[0474] Step 3:

[0475] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent.

[0476] How it works: The server calls an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding to analyze the message. The input data is the user's question, and the output is the analyzed intent and keywords (e.g., "Shinjuku Ward" and "3LDK").

[0477] Step 4:

[0478] The server queries the data store based on the analysis results.

[0479] Specific operation: The server queries a database such as MySQL or PostgreSQL to retrieve real estate price information that matches the specified conditions (e.g., "Shinjuku Ward" and "3LDK"). The input data is the analysis result of the NLP engine, and the output is the real estate price information retrieved from the database.

[0480] Step 5:

[0481] Based on the data acquired by the server, a generative AI model is used to generate answers for the user.

[0482] Specific operation: The server calls a generative AI model (e.g., OpenAI GPT-3) and generates an answer based on the acquired real estate price information. The input data is real estate price information acquired from the database, and the output is the generated answer (e.g., "The average rent for a 3LDK apartment in Shinjuku Ward is 200,000 yen").

[0483] Step 6:

[0484] The server sends the generated answer to the user's terminal as an HTTP response.

[0485] Specific operation: The server includes the generated answer in an HTTP response and sends it back to the terminal. The input data is the generated answer text, and the output is the HTTP response.

[0486] Step 7:

[0487] The terminal displays the response received from the server in the chat box.

[0488] Specific operation: The device parses the response received from the server and displays it in the chat box using HTML and JavaScript. The input data is the response text in the HTTP response, and the output is the text displayed in the browser.

[0489] Step 8:

[0490] The server records the user's message and the system's response in a log system.

[0491] Specific operation: The server records user messages and generated answers in a log system such as ElasticSearch or Splunk. The input data is the user's question message and the generated answer, and the output is the data saved as a log.

[0492] (Application example 1)

[0493] 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."

[0494] Existing systems that provide users with real estate information make it difficult for users to easily obtain information in real time. Even if users visit a store in person, they cannot instantly check detailed real-time real estate information. As a result, users often feel uneasy because they do not have enough information when making decisions about real estate.

[0495] 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.

[0496] In this invention, the server includes means for receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, and means for inputting and displaying a message using a user interface of the smart glasses, thereby enabling users to obtain real estate information in real time through the smart glasses in a store and make quick and accurate decisions.

[0497] The "means for receiving a message from a user" is an interface for receiving a message input by a user in digital form.

[0498] "Natural language processing means for analyzing received messages" refers to a natural language processing engine for analyzing received messages and understanding the user's intent and content.

[0499] "Means for querying a database based on the analysis results" is a function for searching related databases based on the analysis results of natural language processing and obtaining the necessary information.

[0500] "Means for generating an answer to a user based on database query results" refers to the process of creating an appropriate answer to a user's question based on information retrieved from a database.

[0501] The "means for transmitting the generated answer to the user" refers to a communication means for transmitting the generated answer to the user.

[0502] "Means for inputting and displaying messages using a user interface of the smart glasses" refers to an interface that allows a user to input a message using the smart glasses and have the response displayed on the display.

[0503] "Means for recording user messages and responses in a log system" refers to a system for saving and recording messages entered by users and the system's responses to those messages.

[0504] The "means for receiving a response from the server and displaying it on the smart glasses" refers to a method for receiving a response sent from the server on the smart glasses and visually conveying it to the user.

[0505] This invention is a system that allows users to obtain real estate information in real time using smart glasses. The system includes a server, smart glasses, a natural language processing (NLP) engine, a database, a log system, etc.

[0506] Server processing

[0507] The server performs the process using the following main methods:

[0508] 1. Message Receiving Method

[0509] Receives messages entered by the user through the interface of the smart glasses, which are then sent to the server via the Internet as HTTP requests.

[0510] 2. Natural Language Processing Methods

[0511] The received message is passed to an NLP engine (such as spaCy), which analyzes the content of the user's question. For example, a question like "What is the average price for a 2LDK apartment in the neighborhood?" is analyzed, and related keywords (such as "2LDK" and "area") are extracted.

[0512] 3. Database query methods

[0513] Based on the information extracted by the NLP engine, the system queries a real estate price database to retrieve relevant information, including past transaction prices, current market prices, and market rates.

[0514] 4. Answer generation means

[0515] Based on the information retrieved from the database, the system automatically generates answers to be provided to the user. For example, it generates an answer such as, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0516] 5. Method of sending responses

[0517] The generated answers are sent over the internet to the smart glasses and displayed to the user.

[0518] Processing by terminal (smart glasses)

[0519] The smart glasses have the following features:

[0520] 1. Enter and send a message

[0521] The user can input messages by voice or text through the smart glasses interface, and the input messages are sent to the server.

[0522] 2. Receiving and Displaying Responses

[0523] The smart glasses receive the response sent from the server and display it on the display. For example, information such as "The average market price for a 2LDK apartment in this area is 150,000 yen" is visually displayed.

[0524] Log System

[0525] The server records the user's messages and responses in a log system, which provides useful data for future troubleshooting and system improvement.

[0526] Program processing explanation

[0527] The system is implemented using a Python program, the requests library, and an NLP processor (e.g., spaCy). Messages sent by users through the smart glasses are parsed by the server using natural language processing and queried against the relevant real estate database. Answers are then generated based on the retrieved data and sent to the user.

[0528] Prompt Sentence Examples

[0529] Below are some example prompts used for generative AI models (e.g., GPT-3):

[0530] "The user asks through the smart glasses, 'What is the average price for a 3LDK apartment in the neighborhood?' Generate an answer in the following format. Example answer: 'The average price for a 3LDK apartment in this neighborhood is 250,000 yen.'"

[0531] The above configuration allows users to obtain real estate information in real time through smart glasses in a store, enabling them to make quick and accurate decisions.

[0532] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0533] Step 1:

[0534] Users use the smart glasses' interface to input real estate-related questions. Voice input or text input is supported, and the input message is temporarily stored on the device. For example, a user might input, "What is the market price for a 3LDK apartment in the neighborhood?" The input text is sent to the server in the form of an HTTP request.

[0535] Step 2:

[0536] The server receives an HTTP request sent by a user. The received message is then passed to a natural language processing (NLP) engine for analysis. The NLP engine then understands the content and intent of the message and extracts necessary keywords (e.g., "3LDK" or "neighborhood"). The results of this analysis are input to the next processing step.

[0537] Step 3:

[0538] The server uses the results of the natural language processing engine's analysis to query a real estate price database. For example, it might search the database based on the keywords "3LDK" and "neighborhood" to retrieve related property information. The query results serve as input for the next processing step.

[0539] Step 4:

[0540] The server generates a response to the user based on information retrieved from the database. For example, it can average multiple property data from the search results to automatically generate a response such as "The average market price for a 3LDK apartment in this area is 250,000 yen." This generated response becomes the input for the next processing step.

[0541] Step 5:

[0542] The server then sends the generated answer as an HTTP response to the user's smart glasses. The data is received by the device, and the result is displayed in a chat box or on the smart glasses' display. A message such as "The average market price for a 3LDK apartment in this area is 250,000 yen" is displayed.

[0543] Step 6:

[0544] The server records the message entered by the user and the generated response in a log system. This saves data for future troubleshooting and system improvement. For example, the input message "What is the average price for a 3LDK apartment in the neighborhood?" and the generated response "The average price for a 3LDK apartment in this area is 250,000 yen" are recorded in the log.

[0545] The above is the basic processing flow of this system, and details of the specific operations and inputs / outputs at each step.

[0546] 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.

[0547] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[0548] Server processing

[0549] 1. Receiving a message from a user

[0550] The server receives messages sent by users. The user types a question about real estate from their device and presses the send button. For example, if the user types, "What is the average price for a 2LDK apartment in the neighborhood?", the message is sent to the server as an HTTP request and received.

[0551] 2. Message Analysis

[0552] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. The analysis results include information about the "2LDK" and "area."

[0553] 3. Emotion Recognition by Emotion Engine

[0554] The server simultaneously uses an emotion engine to recognize emotions from the user's message, such as whether the user is angry or confused, based on the message context and specific keywords.

[0555] 4. Database Query

[0556] Based on the analysis results, the server queries a real estate price database. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0557] 5. Generating Answers for the User

[0558] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0559] 6. Submit your response

[0560] The server generates a response and sends it to the user, which is then sent to the user's device as an HTTP response.

[0561] 7. Logging

[0562] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0563] Processing by the terminal

[0564] 1. Enter your message

[0565] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then hit send.

[0566] 2. Sending a Message

[0567] The terminal sends the user's input message to the server as an HTTP request, and then waits for a response from the server.

[0568] 3. View Answers

[0569] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0570] User

[0571] 1. Enter your question

[0572] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[0573] 2. Verify the information

[0574] Within a few seconds, the server will send a response to the chat screen, which the user can confirm. For example, the user may receive information such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0575] This system allows users to easily resolve questions about real estate prices and receive personalized support that takes their emotions into consideration. Furthermore, all logs are recorded on the server side, accumulating data that will be useful for future problem solving and system improvements.

[0576] The processing flow will be explained below.

[0577] Step 1:

[0578] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[0579] Step 2:

[0580] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[0581] Step 3:

[0582] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[0583] Step 4:

[0584] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent. This analysis includes keyword extraction and context understanding. For example, information about "2LDK" and "area" is extracted.

[0585] Step 5:

[0586] The server uses an emotion engine to recognize emotions from the user's message. For example, it determines the user's emotional state from the message context and specific keywords. For example, emotions such as "confused" or "angry" can be recognized.

[0587] Step 6:

[0588] The server queries a real estate price database based on the analysis and emotion recognition results. Based on the analyzed information, it searches for real estate price information that matches the "area" specified in "2LDK."

[0589] Step 7:

[0590] The server receives the results from the database and generates a response for the user. For example, it creates a response that takes into consideration the user's feelings, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0591] Step 8:

[0592] The server sends the generated answer to the user's terminal as an HTTP response.

[0593] Step 9:

[0594] The device receives the response from the server and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0595] Step 10:

[0596] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0597] This series of processes allows users to quickly resolve their real estate-related questions and receive courteous, sensitive service.

[0598] Example 2

[0599] 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."

[0600] Conventional ChatBot systems use natural language processing technology to understand user intent, but lack the ability to recognize a user's emotional state and provide appropriate responses based on that emotion. They also lack a mechanism for quickly and accurately answering complex questions about real estate prices. As a result, users often receive poor quality information, leading to lower satisfaction levels.

[0601] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0602] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, emotion recognition means for recognizing emotions from the user's messages, means for querying a database based on the analysis results and the emotion recognition results, means for generating a response to the user based on the database query results and the emotion recognition results, and means for sending the generated response to the user. This makes it possible to provide appropriate responses according to the user's emotional state and to quickly and accurately respond to complex questions about real estate prices.

[0603] The "means for receiving a message from a user" is a function for transferring a message input by a user to a server, and is usually performed via an HTTP request.

[0604] "Natural language processing means for analyzing received messages" refers to engines or algorithms that understand the content of messages received from users and analyze keywords and intent. Examples include Google Cloud Natural Language API and IBM Watson.

[0605] "Emotion recognition means that recognize emotions from user messages" refers to engines or algorithms that read emotions from the context of a user's message or specific keywords. Examples include Amazon Comprehend and Microsoft Azure Text Analytics.

[0606] The "means for querying a database based on the analysis results and emotion recognition results" is a function for searching and retrieving related data from a database based on the content of a user's request and the recognized emotional state.

[0607] The "means for generating a response to the user based on the database query results and emotion recognition results" refers to an algorithm or engine for generating an appropriate response based on the acquired data and the recognized emotion.

[0608] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it, and is usually performed via an HTTP response.

[0609] "Means for recording user messages, emotional states, and responses in the log system" refers to a function for recording user messages, emotional states, and responses generated by the system, for future use in data analysis and system improvement.

[0610] The "means for sending a user's message and receiving and displaying a response from the server" refers to the interface and function on the terminal side that sends the user's input to the server and receives and displays a response from the server.

[0611] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by real estate agents and receive answers. In particular, we provide a system that can recognize the user's emotional state and provide appropriate answers according to that state.

[0612] Overview of the hardware and software used

[0613] This system operates by combining multiple technological elements, including the following key software and hardware components:

[0614] 1. Natural Language Processing (NLP) Engines: Google Cloud Natural Language API and IBM Watson

[0615] 2. Emotion Recognition Engine: Amazon Comprehend or Microsoft Azure Text Analytics

[0616] 3. Database: MySQL or PostgreSQL

[0617] 4. Log systems: Elasticsearch, Logstash

[0618] 5. Servers and terminals: Web servers (e.g., Apache, Nginx), user terminals (e.g., PCs, smartphones)

[0619] System processing flow

[0620] 1. Enter your message

[0621] Users use the ChatBot interface on their device to input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then press the send button.

[0622] 2. Sending a Message

[0623] The terminal sends the input message to the server as an HTTP request, using the HTTP protocol.

[0624] 3. Receiving and parsing messages

[0625] The server receives messages sent by users. The received messages are passed to a natural language processing engine for analysis. In this analysis process, intent such as "2LDK" or "area" is extracted from the message.

[0626] 4. Emotion recognition

[0627] At the same time, the server uses an emotion recognition engine to determine the user's emotions from the message, such as whether the user is dissatisfied or confused, based on the context of the text and specific keywords.

[0628] 5. Querying the Database

[0629] The server queries a real estate price database based on the analysis results and retrieves relevant real estate price data from the database based on the detected keywords (e.g., "2LDK" and "area").

[0630] 6. Answer Generation

[0631] The server generates an appropriate response to the user based on the acquired data and the results of emotion recognition. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0632] 7. Submit your response

[0633] The server sends the generated answer as an HTTP response to the user's device, where it is displayed.

[0634] 8. Logging

[0635] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0636] Specific examples

[0637] The user inputs a prompt into the chatbot interface, such as "What is the average price for a 2LDK apartment in the neighborhood?". In response, the system operates as follows:

[0638] The server receives the message and analyzes it using a natural language processing engine.

[0639] Recognize user emotions with an emotion recognition engine.

[0640] Based on the analysis results, a database is queried to obtain relevant real estate price data.

[0641] Emotion recognition results are also taken into consideration to generate appropriate answers.

[0642] The answer is sent to the user's terminal, and the necessary data is recorded in the log system.

[0643] In this way, users can easily and quickly obtain information about real estate prices. Furthermore, by incorporating emotion recognition, we can provide better services that take users' emotions into consideration.

[0644] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0645] Step 1:

[0646] The server receives a message from the user. The user enters a question on the terminal, such as "What is the average price for a 2LDK apartment in the neighborhood?" and presses the send button. This message is sent to the server via an HTTP request. The input is the user's message in text format, and the output is the message received by the server.

[0647] Step 2:

[0648] The server inputs the received message into a natural language processing (NLP) engine. The NLP engine uses Google Cloud Natural Language API or IBM Watson to analyze keywords and user intent from the input message. Specifically, it extracts information such as "2LDK" and "area." The input is the user message, and the output is the extracted keywords and intent.

[0649] Step 3:

[0650] The server simultaneously uses an emotion recognition engine to recognize emotions from the user's message. It uses Amazon Comprehend and Microsoft Azure Text Analytics to determine emotions (e.g., anger, confusion) from the message text. The input is the user message, and the output is the determined emotional information.

[0651] Step 4:

[0652] The server queries a database based on the analysis results and emotion recognition results. It uses MySQL or PostgreSQL as the database and executes a query to retrieve real estate price information that matches the specified area and property type (2LDK). The input is the analysis results and emotion recognition results, and the output is real estate price data.

[0653] Step 5:

[0654] The server generates a response to the user based on the acquired data and the results of emotion recognition. It provides information such as average market prices in appropriate wording, while also taking into consideration the user's emotional state. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help." The input is data acquired from the database and emotional information, and the output is the generated response text.

[0655] Step 6:

[0656] The server sends the generated answer to the user's terminal as an HTTP response. The sent answer is displayed on the user's terminal. The input is the generated answer text, and the output is the answer displayed on the user's terminal.

[0657] Step 7:

[0658] The server records the user's message, emotional state, and the system-generated answer in a log system. Elasticsearch and Logstash are used to manage this data and use it for later analysis and system improvement. The input is the user's message, emotional information, and the generated answer, and the output is the record in the log system.

[0659] (Application example 2)

[0660] 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."

[0661] While conventional chatbot systems can provide appropriate answers to users' questions about real estate prices, they do not adequately take into account the user's emotional state. Furthermore, they do not take into account the application of new devices such as smart glasses as a means of providing instant customer service in brick-and-mortar stores, and there is a need to improve customer satisfaction.

[0662] 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 receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, means for recognizing the user's emotional state, and means for providing an appropriate response based on the recognized emotional state. This makes it possible to provide appropriate real estate information in real time, even in a physical store, taking into account the user's emotional state.

[0663] The "means for receiving messages from users" is a system that includes a process for sending messages sent by users to a server.

[0664] The "natural language processing means for analyzing received messages" is a system that uses a natural language processing engine to analyze the content of a user's message and understand its intent.

[0665] The "means for querying a database based on the analysis result" is a system that includes a process for searching a database to obtain related data based on the content of the analyzed message.

[0666] The "means for generating a response to a user based on the database query results" is a system that includes a process for generating a response to be provided to a user based on the acquired data and analysis results.

[0667] The "means for sending the generated answer to the user" is a system that includes a process for delivering the generated answer to the user.

[0668] The "means for recognizing the user's emotional state" is a system for identifying the user's emotions from the user's facial expressions, voice, message context, etc.

[0669] A "means for providing appropriate answers based on a recognized emotional state" is a system that includes a process for generating more appropriate and considerate answers based on the user's emotional state.

[0670] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[0671] Server processing

[0672] The server receives messages sent by users and analyzes them using a natural language processing engine. Based on the analysis results and the user's emotional state, it queries a database to generate and send a response. Specifically, it works as follows:

[0673] 1. Receiving a message from a user

[0674] The server receives messages entered by users using smart glasses or smartphones. For example, if a user asks, "What is the average price of a 2LDK apartment in this area?", the message is sent to the server as an HTTP request.

[0675] 2. Message Analysis

[0676] The server passes the received message to a natural language processing engine (e.g., spaCy or BERT) to analyze the user's intent. The analysis results include information about "2LDK" and "area."

[0677] 3. Emotion Recognition by Emotion Engine

[0678] At the same time, the server uses an emotion engine (e.g., OpenCV or Affectiva) to recognize emotions from the user's message and facial expressions. For example, it determines whether the user is interested or anxious based on the message context and specific keywords.

[0679] 4. Database Query

[0680] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0681] 5. Generating Answers for the User

[0682] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The current market price is around 150,000 yen. Please let us know if you need more information."

[0683] 6. Submit your response

[0684] The server then sends the generated answer to the user, which is then sent to the user's terminal as an HTTP response.

[0685] Processing by the terminal

[0686] The device sends messages from the user to the server, receives replies from the server, and displays them. This is done using smart glasses or a smartphone.

[0687] 1. Enter your message

[0688] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the average price for a 2LDK apartment in this area?", and then hit the send button.

[0689] 2. Sending a Message

[0690] The terminal sends the user's input message as an HTTP request to the server, and then waits for a response from the server.

[0691] 3. View Answers

[0692] When the server responds to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The current market price is around 150,000 yen. Please let us know if you need more information."

[0693] User operation

[0694] Users can enter specific questions into the ChatBot's interface and view the answers, allowing them to easily resolve their real estate pricing queries and receive a personal, sensitive response.

[0695] Prompt Sentence Examples

[0696] For example, if a customer asks, "What is the average price for a 2LDK apartment in this area?", the following prompt sentence is input into the generative AI model:

[0697] Question: "What is the average price for a 2LDK apartment in this area?"

[0698] Emotional state: "Curious"

[0699] This prompt is sent to the server, the answer is retrieved, and the answer is displayed on the smart glasses, providing the customer with the information instantly.

[0700] This system allows users to resolve questions about real estate prices and communicate in a way that takes their emotions into consideration. In addition, all logs are recorded on the server side, which can be used to solve problems and improve the system in the future.

[0701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0702] Step 1:

[0703] A user uses smart glasses or a smartphone to input a real estate question, for example, "What is the average price of a 2LDK apartment in this area?" and presses the submit button. This input is sent to the server as an HTTP request. The input is the user's natural language message, and the output is an HTTP request sent to the server.

[0704] Step 2:

[0705] The server processes the received HTTP request and passes it to a natural language processing engine to analyze the user's message. The natural language processing engine (e.g., spaCy or BERT) analyzes the content of the message and understands the intent of the user's question. The input is the user's natural language message, and the output is analyzed data (e.g., property type and area information).

[0706] Step 3:

[0707] At the same time, the server uses an emotion engine to recognize the user's emotional state. The emotion engine (e.g., OpenCV or Affectiva) determines the emotion from the user's facial expression and the message context. The input is the user's facial expression data and the message context, and the output is the user's emotional state.

[0708] Step 4:

[0709] The server queries a real estate price database based on the analysis results and the emotional state. The database provides real estate price information matching the specified area and property type (e.g., "2LDK"). The input is the analysis results, and the output is the related real estate price data.

[0710] Step 5:

[0711] The server generates an appropriate answer for the user based on the acquired data and the results of the emotion engine. For example, it creates an answer in the form of "The current market price is around 150,000 yen. Please let us know if you need more information." The input is real estate data acquired from the database and the user's emotional state, and the output is the generated answer.

[0712] Step 6:

[0713] The server generates an answer and sends it to the user. The answer is sent as an HTTP response and displayed on the terminal. The input is the generated answer, and the output is the HTTP response sent to the user.

[0714] Step 7:

[0715] The terminal receives the response from the server and displays it in the chat box, allowing the user to check the response on the terminal. The input is the HTTP response sent from the server, and the output is the response message displayed on the terminal.

[0716] Through the above processing steps, the user can resolve their questions about real estate prices and receive answers that take their emotions into consideration.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] [Third embodiment]

[0721] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0722] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0723] 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).

[0724] 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.

[0725] 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.

[0726] 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).

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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."

[0733] This invention provides a ChatBot-style service that allows users to consult about real estate prices and price fluctuations by agents. Detailed embodiments of the invention are described below.

[0734] Server processing

[0735] 1. Receiving a message from a user

[0736] The server receives messages sent by users. The user enters a question about real estate on their device and presses the send button. The message is sent to the server as an HTTP request, and the server receives it.

[0737] 2. Message Analysis

[0738] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. For example, if a message is sent saying, "What is the average price for a 2LDK apartment in the neighborhood?", the NLP engine analyzes the message and extracts information about "2LDK" and "area."

[0739] 3. Database Query

[0740] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0741] 4. Generating answers for users

[0742] The server generates a response to the user based on the acquired data. For example, it averages the acquired price data and generates a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0743] 5. Submit your response

[0744] The server generates a response and sends it to the user, who receives it and displays it in the chat box.

[0745] 6. Logging

[0746] Additionally, the server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or improvements.

[0747] Processing by the terminal

[0748] 1. Enter your message

[0749] Users use the ChatBot interface on their device to input questions about real estate. The input message is temporarily saved and sent to the server when the send button is pressed.

[0750] 2. Sending a Message

[0751] The terminal sends the message entered by the user to the server as an HTTP request, and then waits for a response from the server.

[0752] 3. View Answers

[0753] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0754] User

[0755] 1. Enter your question

[0756] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[0757] 2. Verify the information

[0758] Within a few seconds, the server will return a response to the chat screen, allowing the user to confirm the information. For example, the average price for a 2LDK apartment in this area is 150,000 yen.

[0759] This system allows users to easily resolve questions about real estate prices and obtain accurate price information. In addition, messages and responses are recorded on the server, which helps prevent future problems and improve the system.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[0763] Step 2:

[0764] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[0765] Step 3:

[0766] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[0767] Step 4:

[0768] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent, for example, extracting information about "2LDK" and "area."

[0769] Step 5:

[0770] The server queries a real estate price database based on the analysis results, for example, searching for price data for "2LDK" properties in the specified area.

[0771] Step 6:

[0772] The server receives the database query results and generates a response to the user based on the retrieved data. For example, it creates a response such as, "The average price for a 2LDK apartment in this area is 150,000 yen."

[0773] Step 7:

[0774] The server generates an answer and sends it to the user, which is sent to the user's device as an HTTP response.

[0775] Step 8:

[0776] The terminal receives the answer from the server and displays it in the chat box. The user can then confirm the displayed answer.

[0777] Step 9:

[0778] The server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0779] Example 1

[0780] 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."

[0781] Conventional real estate price information systems have had problems such as taking a long time to receive an appropriate answer after a user inputs a question, and the accuracy of the answers being low. Also, if the user's messages and answers are not recorded in the system, it is difficult to troubleshoot or improve the system later.

[0782] 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.

[0783] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, means for querying a data store based on the analysis results, means for using a generative AI model to generate answers to the users based on the data store query results, and means for sending the generated answers to the users. This allows users to quickly obtain real estate price information with high accuracy, and since the user's messages and answers are recorded, it makes future troubleshooting and system improvements easier.

[0784] "User" refers to a person who uses the System to request information about real estate prices.

[0785] "Message" refers to text information that a user enters into the system and sends to the server.

[0786] "Means for receiving" refers to an interface or function for receiving messages sent by users at the server.

[0787] "Natural language processing means" refers to the technology or algorithm that analyzes messages received by the server and understands the user's intent and content.

[0788] "Data Store" means a database or storage device that stores real estate pricing information and other related data.

[0789] "Means for querying" refers to the functionality for searching the data store based on the analysis results and obtaining the required information.

[0790] A "generative AI model" refers to an artificial intelligence technology that automatically generates answers to users based on information obtained from a data store.

[0791] "Means for sending" refers to a communication interface or function for sending the generated answer back to the user.

[0792] "Log system" refers to a recording device or system that records user messages and system responses for later reference and analysis.

[0793] "Terminal" refers to a device on which a user inputs and sends messages and receives and displays responses from a server. Examples include a smartphone, tablet, or personal computer.

[0794] This invention is a system that provides a chatbot-style service that allows users to consult about real estate prices and price fluctuations by agents. A specific implementation method of this system will be described in detail.

[0795] System configuration

[0796] The system consists of a user device, a server, a data store, a generative AI model, a natural language processing (NLP) engine, and a log system.

[0797] Terminal

[0798] Users can access the system by entering questions using devices such as smartphones, tablets, and personal computers. They can then use the chatbot interface displayed on the device's browser to enter their questions and click the send button. As a specific example, messages can be sent using the AJAX or Fetch API provided by the web browser.

[0799] server

[0800] The server receives messages from users as HTTP requests. To parse the messages, it uses an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the information extracted from the parsed messages, the server queries a data store that stores real estate price information. This query is performed using a database system such as MySQL or PostgreSQL.

[0801] Datastore

[0802] The data store is a database that holds information on real estate prices and market rates by region. The server searches this data store based on the analysis results and obtains the necessary information.

[0803] Generative AI Models

[0804] The server generates a response to the user based on the information retrieved from the data store. This response can be generated using a generative AI model such as OpenAI GPT-3. For example, a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen" can be generated.

[0805] Sending a response to the user

[0806] The generated answer is sent from the server to the user's device as an HTTP response. The device displays the received answer in a chat box. HTML, JavaScript, CSS, etc. are used for display.

[0807] Log System

[0808] The server records user messages and the system's responses in a logging system, using systems such as ElasticSearch or Splunk, to facilitate future troubleshooting and system improvements.

[0809] Specific examples

[0810] When a user types "What is the average rental price for a 3LDK apartment in Shinjuku Ward?" into the chatbot interface on their device and presses the send button, the process goes as follows: The server receives this message and uses an NLP engine to extract the information "Shinjuku Ward" and "3LDK." The server then queries the data store based on this information to obtain corresponding real estate price information. Based on the information obtained, the server uses a generative AI model to generate an answer such as "The average rental price for a 3LDK apartment in Shinjuku Ward is 200,000 yen," and sends it to the user's device. The user can view this in the chat box.

[0811] Prompt Sentence Examples

[0812] Here is an example of a prompt to input to the generative AI model:

[0813] "What is the average rental price for a 3LDK apartment in Shinjuku Ward?"

[0814] Based on this prompt, the AI ​​model retrieves the appropriate data and provides information.

[0815] In this way, the system allows users to quickly and accurately resolve questions about property prices.

[0816] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0817] Step 1:

[0818] The user types a question into the chatbot interface on the device.

[0819] Specific operation: The user enters a question, for example, "What is the average rent price for a 3LDK apartment in Shinjuku Ward?" and clicks the send button. The data entered is the user's question text, and the click event of the send button is the trigger.

[0820] Step 2:

[0821] The terminal sends the message entered by the user to the server as an HTTP request.

[0822] Specific operation: The browser or application on the device uses AJAX or the Fetch API to send the input message to the server as an HTTP POST request. The input data is the user's question message, and the output is an HTTP request.

[0823] Step 3:

[0824] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent.

[0825] How it works: The server calls an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding to analyze the message. The input data is the user's question, and the output is the analyzed intent and keywords (e.g., "Shinjuku Ward" and "3LDK").

[0826] Step 4:

[0827] The server queries the data store based on the analysis results.

[0828] Specific operation: The server queries a database such as MySQL or PostgreSQL to retrieve real estate price information that matches the specified conditions (e.g., "Shinjuku Ward" and "3LDK"). The input data is the analysis result of the NLP engine, and the output is the real estate price information retrieved from the database.

[0829] Step 5:

[0830] Based on the data acquired by the server, a generative AI model is used to generate answers for the user.

[0831] Specific operation: The server calls a generative AI model (e.g., OpenAI GPT-3) and generates an answer based on the acquired real estate price information. The input data is real estate price information acquired from the database, and the output is the generated answer (e.g., "The average rent for a 3LDK apartment in Shinjuku Ward is 200,000 yen").

[0832] Step 6:

[0833] The server sends the generated answer to the user's terminal as an HTTP response.

[0834] Specific operation: The server includes the generated answer in an HTTP response and sends it back to the terminal. The input data is the generated answer text, and the output is the HTTP response.

[0835] Step 7:

[0836] The terminal displays the response received from the server in the chat box.

[0837] Specific operation: The device parses the response received from the server and displays it in the chat box using HTML and JavaScript. The input data is the response text in the HTTP response, and the output is the text displayed in the browser.

[0838] Step 8:

[0839] The server records the user's message and the system's response in a log system.

[0840] Specific operation: The server records user messages and generated answers in a log system such as ElasticSearch or Splunk. The input data is the user's question message and the generated answer, and the output is the data saved as a log.

[0841] (Application example 1)

[0842] 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."

[0843] Existing systems that provide users with real estate information make it difficult for users to easily obtain information in real time. Even if users visit a store in person, they cannot instantly check detailed real-time real estate information. As a result, users often feel uneasy because they do not have enough information when making decisions about real estate.

[0844] 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.

[0845] In this invention, the server includes means for receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, and means for inputting and displaying a message using a user interface of the smart glasses, thereby enabling users to obtain real estate information in real time through the smart glasses in a store and make quick and accurate decisions.

[0846] The "means for receiving a message from a user" is an interface for receiving a message input by a user in digital form.

[0847] "Natural language processing means for analyzing received messages" refers to a natural language processing engine for analyzing received messages and understanding the user's intent and content.

[0848] "Means for querying a database based on the analysis results" is a function for searching related databases based on the analysis results of natural language processing and obtaining the necessary information.

[0849] "Means for generating an answer to a user based on database query results" refers to the process of creating an appropriate answer to a user's question based on information retrieved from a database.

[0850] The "means for transmitting the generated answer to the user" refers to a communication means for transmitting the generated answer to the user.

[0851] "Means for inputting and displaying messages using a user interface of the smart glasses" refers to an interface that allows a user to input a message using the smart glasses and have the response displayed on the display.

[0852] "Means for recording user messages and responses in a log system" refers to a system for saving and recording messages entered by users and the system's responses to those messages.

[0853] The "means for receiving a response from the server and displaying it on the smart glasses" refers to a method for receiving a response sent from the server on the smart glasses and visually conveying it to the user.

[0854] This invention is a system that allows users to obtain real estate information in real time using smart glasses. The system includes a server, smart glasses, a natural language processing (NLP) engine, a database, a log system, etc.

[0855] Server processing

[0856] The server performs the process using the following main methods:

[0857] 1. Message Receiving Method

[0858] Receives messages entered by the user through the interface of the smart glasses, which are then sent to the server via the Internet as HTTP requests.

[0859] 2. Natural Language Processing Methods

[0860] The received message is passed to an NLP engine (such as spaCy), which analyzes the content of the user's question. For example, a question like "What is the average price for a 2LDK apartment in the neighborhood?" is analyzed, and related keywords (such as "2LDK" and "area") are extracted.

[0861] 3. Database query methods

[0862] Based on the information extracted by the NLP engine, the system queries a real estate price database to retrieve relevant information, including past transaction prices, current market prices, and market rates.

[0863] 4. Answer generation means

[0864] Based on the information retrieved from the database, the system automatically generates answers to be provided to the user. For example, it generates an answer such as, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[0865] 5. Method of sending responses

[0866] The generated answers are sent over the internet to the smart glasses and displayed to the user.

[0867] Processing by terminal (smart glasses)

[0868] The smart glasses have the following features:

[0869] 1. Enter and send a message

[0870] The user can input messages by voice or text through the smart glasses interface, and the input messages are sent to the server.

[0871] 2. Receiving and Displaying Responses

[0872] The smart glasses receive the response sent from the server and display it on the display. For example, information such as "The average market price for a 2LDK apartment in this area is 150,000 yen" is visually displayed.

[0873] Log System

[0874] The server records the user's messages and responses in a log system, which provides useful data for future troubleshooting and system improvement.

[0875] Program processing explanation

[0876] The system is implemented using a Python program, the requests library, and an NLP processor (e.g., spaCy). Messages sent by users through the smart glasses are parsed by the server using natural language processing and queried against the relevant real estate database. Answers are then generated based on the retrieved data and sent to the user.

[0877] Prompt Sentence Examples

[0878] Below are some example prompts used for generative AI models (e.g., GPT-3):

[0879] "The user asks through the smart glasses, 'What is the average price for a 3LDK apartment in the neighborhood?' Generate an answer in the following format. Example answer: 'The average price for a 3LDK apartment in this neighborhood is 250,000 yen.'"

[0880] The above configuration allows users to obtain real estate information in real time through smart glasses in a store, enabling them to make quick and accurate decisions.

[0881] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0882] Step 1:

[0883] Users use the smart glasses' interface to input real estate-related questions. Voice input or text input is supported, and the input message is temporarily stored on the device. For example, a user might input, "What is the market price for a 3LDK apartment in the neighborhood?" The input text is sent to the server in the form of an HTTP request.

[0884] Step 2:

[0885] The server receives an HTTP request sent by a user. The received message is then passed to a natural language processing (NLP) engine for analysis. The NLP engine then understands the content and intent of the message and extracts necessary keywords (e.g., "3LDK" or "neighborhood"). The results of this analysis are input to the next processing step.

[0886] Step 3:

[0887] The server uses the results of the natural language processing engine's analysis to query a real estate price database. For example, it might search the database based on the keywords "3LDK" and "neighborhood" to retrieve related property information. The query results serve as input for the next processing step.

[0888] Step 4:

[0889] The server generates a response to the user based on information retrieved from the database. For example, it can average multiple property data from the search results to automatically generate a response such as "The average market price for a 3LDK apartment in this area is 250,000 yen." This generated response becomes the input for the next processing step.

[0890] Step 5:

[0891] The server then sends the generated answer as an HTTP response to the user's smart glasses. The data is received by the device, and the result is displayed in a chat box or on the smart glasses' display. A message such as "The average market price for a 3LDK apartment in this area is 250,000 yen" is displayed.

[0892] Step 6:

[0893] The server records the message entered by the user and the generated response in a log system. This saves data for future troubleshooting and system improvement. For example, the input message "What is the average price for a 3LDK apartment in the neighborhood?" and the generated response "The average price for a 3LDK apartment in this area is 250,000 yen" are recorded in the log.

[0894] The above is the basic processing flow of this system, and details of the specific operations and inputs / outputs at each step.

[0895] 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.

[0896] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[0897] Server processing

[0898] 1. Receiving a message from a user

[0899] The server receives messages sent by users. The user types a question about real estate from their device and presses the send button. For example, if the user types, "What is the average price for a 2LDK apartment in the neighborhood?", the message is sent to the server as an HTTP request and received.

[0900] 2. Message Analysis

[0901] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. The analysis results include information about the "2LDK" and "area."

[0902] 3. Emotion Recognition by Emotion Engine

[0903] The server simultaneously uses an emotion engine to recognize emotions from the user's message, such as whether the user is angry or confused, based on the message context and specific keywords.

[0904] 4. Database Query

[0905] Based on the analysis results, the server queries a real estate price database. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[0906] 5. Generating Answers for the User

[0907] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0908] 6. Submit your response

[0909] The server generates a response and sends it to the user, which is then sent to the user's device as an HTTP response.

[0910] 7. Logging

[0911] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0912] Processing by the terminal

[0913] 1. Enter your message

[0914] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then hit send.

[0915] 2. Sending a Message

[0916] The terminal sends the user's input message to the server as an HTTP request, and then waits for a response from the server.

[0917] 3. View Answers

[0918] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0919] User

[0920] 1. Enter your question

[0921] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[0922] 2. Verify the information

[0923] Within a few seconds, the server will send a response to the chat screen, which the user can confirm. For example, the user may receive information such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0924] This system allows users to easily resolve questions about real estate prices and receive personalized support that takes their emotions into consideration. Furthermore, all logs are recorded on the server side, accumulating data that will be useful for future problem solving and system improvements.

[0925] The processing flow will be explained below.

[0926] Step 1:

[0927] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[0928] Step 2:

[0929] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[0930] Step 3:

[0931] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[0932] Step 4:

[0933] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent. This analysis includes keyword extraction and context understanding. For example, information about "2LDK" and "area" is extracted.

[0934] Step 5:

[0935] The server uses an emotion engine to recognize emotions from the user's message. For example, it determines the user's emotional state from the message context and specific keywords. For example, emotions such as "confused" or "angry" can be recognized.

[0936] Step 6:

[0937] The server queries a real estate price database based on the analysis and emotion recognition results. Based on the analyzed information, it searches for real estate price information that matches the "area" specified in "2LDK."

[0938] Step 7:

[0939] The server receives the results from the database and generates a response for the user. For example, it creates a response that takes into consideration the user's feelings, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0940] Step 8:

[0941] The server sends the generated answer to the user's terminal as an HTTP response.

[0942] Step 9:

[0943] The device receives the response from the server and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0944] Step 10:

[0945] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0946] This series of processes allows users to quickly resolve their real estate-related questions and receive courteous, sensitive service.

[0947] Example 2

[0948] 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."

[0949] Conventional ChatBot systems use natural language processing technology to understand user intent, but lack the ability to recognize a user's emotional state and provide appropriate responses based on that emotion. They also lack a mechanism for quickly and accurately answering complex questions about real estate prices. As a result, users often receive poor quality information, leading to lower satisfaction levels.

[0950] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0951] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, emotion recognition means for recognizing emotions from the user's messages, means for querying a database based on the analysis results and the emotion recognition results, means for generating a response to the user based on the database query results and the emotion recognition results, and means for sending the generated response to the user. This makes it possible to provide appropriate responses according to the user's emotional state and to quickly and accurately respond to complex questions about real estate prices.

[0952] The "means for receiving a message from a user" is a function for transferring a message input by a user to a server, and is usually performed via an HTTP request.

[0953] "Natural language processing means for analyzing received messages" refers to engines or algorithms that understand the content of messages received from users and analyze keywords and intent. Examples include Google Cloud Natural Language API and IBM Watson.

[0954] "Emotion recognition means that recognize emotions from user messages" refers to engines or algorithms that read emotions from the context of a user's message or specific keywords. Examples include Amazon Comprehend and Microsoft Azure Text Analytics.

[0955] The "means for querying a database based on the analysis results and emotion recognition results" is a function for searching and retrieving related data from a database based on the content of a user's request and the recognized emotional state.

[0956] The "means for generating a response to the user based on the database query results and emotion recognition results" refers to an algorithm or engine for generating an appropriate response based on the acquired data and the recognized emotion.

[0957] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it, and is usually performed via an HTTP response.

[0958] "Means for recording user messages, emotional states, and responses in the log system" refers to a function for recording user messages, emotional states, and responses generated by the system, for future use in data analysis and system improvement.

[0959] The "means for sending a user's message and receiving and displaying a response from the server" refers to the interface and function on the terminal side that sends the user's input to the server and receives and displays a response from the server.

[0960] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by real estate agents and receive answers. In particular, we provide a system that can recognize the user's emotional state and provide appropriate answers according to that state.

[0961] Overview of the hardware and software used

[0962] This system operates by combining multiple technological elements, including the following key software and hardware components:

[0963] 1. Natural Language Processing (NLP) Engines: Google Cloud Natural Language API and IBM Watson

[0964] 2. Emotion Recognition Engine: Amazon Comprehend or Microsoft Azure Text Analytics

[0965] 3. Database: MySQL or PostgreSQL

[0966] 4. Log systems: Elasticsearch, Logstash

[0967] 5. Servers and terminals: Web servers (e.g., Apache, Nginx), user terminals (e.g., PCs, smartphones)

[0968] System processing flow

[0969] 1. Enter your message

[0970] Users use the ChatBot interface on their device to input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then press the send button.

[0971] 2. Sending a Message

[0972] The terminal sends the input message to the server as an HTTP request, using the HTTP protocol.

[0973] 3. Receiving and parsing messages

[0974] The server receives messages sent by users. The received messages are passed to a natural language processing engine for analysis. In this analysis process, intent such as "2LDK" or "area" is extracted from the message.

[0975] 4. Emotion recognition

[0976] At the same time, the server uses an emotion recognition engine to determine the user's emotions from the message, such as whether the user is dissatisfied or confused, based on the context of the text and specific keywords.

[0977] 5. Querying the Database

[0978] The server queries a real estate price database based on the analysis results and retrieves relevant real estate price data from the database based on the detected keywords (e.g., "2LDK" and "area").

[0979] 6. Answer Generation

[0980] The server generates an appropriate response to the user based on the acquired data and the results of emotion recognition. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[0981] 7. Submit your response

[0982] The server sends the generated answer as an HTTP response to the user's device, where it is displayed.

[0983] 8. Logging

[0984] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[0985] Specific examples

[0986] The user inputs a prompt into the chatbot interface, such as "What is the average price for a 2LDK apartment in the neighborhood?". In response, the system operates as follows:

[0987] The server receives the message and analyzes it using a natural language processing engine.

[0988] Recognize user emotions with an emotion recognition engine.

[0989] Based on the analysis results, a database is queried to obtain relevant real estate price data.

[0990] Emotion recognition results are also taken into consideration to generate appropriate answers.

[0991] The answer is sent to the user's terminal, and the necessary data is recorded in the log system.

[0992] In this way, users can easily and quickly obtain information about real estate prices. Furthermore, by incorporating emotion recognition, we can provide better services that take users' emotions into consideration.

[0993] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0994] Step 1:

[0995] The server receives a message from the user. The user enters a question on the terminal, such as "What is the average price for a 2LDK apartment in the neighborhood?" and presses the send button. This message is sent to the server via an HTTP request. The input is the user's message in text format, and the output is the message received by the server.

[0996] Step 2:

[0997] The server inputs the received message into a natural language processing (NLP) engine. The NLP engine uses Google Cloud Natural Language API or IBM Watson to analyze keywords and user intent from the input message. Specifically, it extracts information such as "2LDK" and "area." The input is the user message, and the output is the extracted keywords and intent.

[0998] Step 3:

[0999] The server simultaneously uses an emotion recognition engine to recognize emotions from the user's message. It uses Amazon Comprehend and Microsoft Azure Text Analytics to determine emotions (e.g., anger, confusion) from the message text. The input is the user message, and the output is the determined emotional information.

[1000] Step 4:

[1001] The server queries a database based on the analysis results and emotion recognition results. It uses MySQL or PostgreSQL as the database and executes a query to retrieve real estate price information that matches the specified area and property type (2LDK). The input is the analysis results and emotion recognition results, and the output is real estate price data.

[1002] Step 5:

[1003] The server generates a response to the user based on the acquired data and the results of emotion recognition. It provides information such as average market prices in appropriate wording, while also taking into consideration the user's emotional state. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help." The input is data acquired from the database and emotional information, and the output is the generated response text.

[1004] Step 6:

[1005] The server sends the generated answer to the user's terminal as an HTTP response. The sent answer is displayed on the user's terminal. The input is the generated answer text, and the output is the answer displayed on the user's terminal.

[1006] Step 7:

[1007] The server records the user's message, emotional state, and the system-generated answer in a log system. Elasticsearch and Logstash are used to manage this data and use it for later analysis and system improvement. The input is the user's message, emotional information, and the generated answer, and the output is the record in the log system.

[1008] (Application example 2)

[1009] 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."

[1010] While conventional chatbot systems can provide appropriate answers to users' questions about real estate prices, they do not adequately take into account the user's emotional state. Furthermore, they do not take into account the application of new devices such as smart glasses as a means of providing instant customer service in brick-and-mortar stores, and there is a need to improve customer satisfaction.

[1011] 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 receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, means for recognizing the user's emotional state, and means for providing an appropriate response based on the recognized emotional state. This makes it possible to provide appropriate real estate information in real time, even in a physical store, taking into account the user's emotional state.

[1012] The "means for receiving messages from users" is a system that includes a process for sending messages sent by users to a server.

[1013] The "natural language processing means for analyzing received messages" is a system that uses a natural language processing engine to analyze the content of a user's message and understand its intent.

[1014] The "means for querying a database based on the analysis result" is a system that includes a process for searching a database to obtain related data based on the content of the analyzed message.

[1015] The "means for generating a response to a user based on the database query results" is a system that includes a process for generating a response to be provided to a user based on the acquired data and analysis results.

[1016] The "means for sending the generated answer to the user" is a system that includes a process for delivering the generated answer to the user.

[1017] The "means for recognizing the user's emotional state" is a system for identifying the user's emotions from the user's facial expressions, voice, message context, etc.

[1018] A "means for providing appropriate answers based on a recognized emotional state" is a system that includes a process for generating more appropriate and considerate answers based on the user's emotional state.

[1019] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[1020] Server processing

[1021] The server receives messages sent by users and analyzes them using a natural language processing engine. Based on the analysis results and the user's emotional state, it queries a database to generate and send a response. Specifically, it works as follows:

[1022] 1. Receiving a message from a user

[1023] The server receives messages entered by users using smart glasses or smartphones. For example, if a user asks, "What is the average price of a 2LDK apartment in this area?", the message is sent to the server as an HTTP request.

[1024] 2. Message Analysis

[1025] The server passes the received message to a natural language processing engine (e.g., spaCy or BERT) to analyze the user's intent. The analysis results include information about "2LDK" and "area."

[1026] 3. Emotion Recognition by Emotion Engine

[1027] At the same time, the server uses an emotion engine (e.g., OpenCV or Affectiva) to recognize emotions from the user's message and facial expressions. For example, it determines whether the user is interested or anxious based on the message context and specific keywords.

[1028] 4. Database Query

[1029] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[1030] 5. Generating Answers for the User

[1031] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The current market price is around 150,000 yen. Please let us know if you need more information."

[1032] 6. Submit your response

[1033] The server then sends the generated answer to the user, which is then sent to the user's terminal as an HTTP response.

[1034] Processing by the terminal

[1035] The device sends messages from the user to the server, receives replies from the server, and displays them. This is done using smart glasses or a smartphone.

[1036] 1. Enter your message

[1037] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the average price for a 2LDK apartment in this area?", and then hit the send button.

[1038] 2. Sending a Message

[1039] The terminal sends the user's input message as an HTTP request to the server, and then waits for a response from the server.

[1040] 3. View Answers

[1041] When the server responds to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The current market price is around 150,000 yen. Please let us know if you need more information."

[1042] User operation

[1043] Users can enter specific questions into the ChatBot's interface and view the answers, allowing them to easily resolve their real estate pricing queries and receive a personal, sensitive response.

[1044] Prompt Sentence Examples

[1045] For example, if a customer asks, "What is the average price for a 2LDK apartment in this area?", the following prompt sentence is input into the generative AI model:

[1046] Question: "What is the average price for a 2LDK apartment in this area?"

[1047] Emotional state: "Curious"

[1048] This prompt is sent to the server, the answer is retrieved, and the answer is displayed on the smart glasses, providing the customer with the information instantly.

[1049] This system allows users to resolve questions about real estate prices and communicate in a way that takes their emotions into consideration. In addition, all logs are recorded on the server side, which can be used to solve problems and improve the system in the future.

[1050] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1051] Step 1:

[1052] A user uses smart glasses or a smartphone to input a real estate question, for example, "What is the average price of a 2LDK apartment in this area?" and presses the submit button. This input is sent to the server as an HTTP request. The input is the user's natural language message, and the output is an HTTP request sent to the server.

[1053] Step 2:

[1054] The server processes the received HTTP request and passes it to a natural language processing engine to analyze the user's message. The natural language processing engine (e.g., spaCy or BERT) analyzes the content of the message and understands the intent of the user's question. The input is the user's natural language message, and the output is analyzed data (e.g., property type and area information).

[1055] Step 3:

[1056] At the same time, the server uses an emotion engine to recognize the user's emotional state. The emotion engine (e.g., OpenCV or Affectiva) determines the emotion from the user's facial expression and the message context. The input is the user's facial expression data and the message context, and the output is the user's emotional state.

[1057] Step 4:

[1058] The server queries a real estate price database based on the analysis results and the emotional state. The database provides real estate price information matching the specified area and property type (e.g., "2LDK"). The input is the analysis results, and the output is the related real estate price data.

[1059] Step 5:

[1060] The server generates an appropriate answer for the user based on the acquired data and the results of the emotion engine. For example, it creates an answer in the form of "The current market price is around 150,000 yen. Please let us know if you need more information." The input is real estate data acquired from the database and the user's emotional state, and the output is the generated answer.

[1061] Step 6:

[1062] The server generates an answer and sends it to the user. The answer is sent as an HTTP response and displayed on the terminal. The input is the generated answer, and the output is the HTTP response sent to the user.

[1063] Step 7:

[1064] The terminal receives the response from the server and displays it in the chat box, allowing the user to check the response on the terminal. The input is the HTTP response sent from the server, and the output is the response message displayed on the terminal.

[1065] Through the above processing steps, the user can resolve their questions about real estate prices and receive answers that take their emotions into consideration.

[1066] 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.

[1067] 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.

[1068] 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.

[1069] [Fourth embodiment]

[1070] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1071] 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.

[1072] 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).

[1073] 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.

[1074] 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.

[1075] 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).

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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.

[1081] 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.

[1082] 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."

[1083] This invention provides a ChatBot-style service that allows users to consult about real estate prices and price fluctuations by agents. Detailed embodiments of the invention are described below.

[1084] Server processing

[1085] 1. Receiving a message from a user

[1086] The server receives messages sent by users. The user enters a question about real estate on their device and presses the send button. The message is sent to the server as an HTTP request, and the server receives it.

[1087] 2. Message Analysis

[1088] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. For example, if a message is sent saying, "What is the average price for a 2LDK apartment in the neighborhood?", the NLP engine analyzes the message and extracts information about "2LDK" and "area."

[1089] 3. Database Query

[1090] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[1091] 4. Generating answers for users

[1092] The server generates a response to the user based on the acquired data. For example, it averages the acquired price data and generates a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen."

[1093] 5. Submit your response

[1094] The server generates a response and sends it to the user, who receives it and displays it in the chat box.

[1095] 6. Logging

[1096] Additionally, the server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or improvements.

[1097] Processing by the terminal

[1098] 1. Enter your message

[1099] Users can use the ChatBot interface on their device to input questions about real estate. The input message is temporarily saved and sent to the server when the send button is pressed.

[1100] 2. Sending a Message

[1101] The terminal sends the message entered by the user to the server as an HTTP request, and then waits for a response from the server.

[1102] 3. View Answers

[1103] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, a message such as "The average market price for a 2LDK apartment in this area is 150,000 yen" may be displayed.

[1104] User

[1105] 1. Enter your question

[1106] The user enters a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[1107] 2. Verify the information

[1108] Within a few seconds, the server will return a response to the chat screen, allowing the user to confirm the information. For example, the average price for a 2LDK apartment in this area is 150,000 yen.

[1109] This system allows users to easily resolve questions about real estate prices and obtain accurate price information. In addition, messages and responses are recorded on the server, which helps prevent future problems and improve the system.

[1110] The processing flow will be explained below.

[1111] Step 1:

[1112] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[1113] Step 2:

[1114] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[1115] Step 3:

[1116] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[1117] Step 4:

[1118] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent, for example, extracting information about "2LDK" and "area."

[1119] Step 5:

[1120] The server queries a real estate price database based on the analysis results, for example, searching for price data for "2LDK" properties in the specified area.

[1121] Step 6:

[1122] The server receives the database query results and generates a response to the user based on the retrieved data. For example, it creates a response such as, "The average price for a 2LDK apartment in this area is 150,000 yen."

[1123] Step 7:

[1124] The server generates an answer and sends it to the user, which is sent to the user's device as an HTTP response.

[1125] Step 8:

[1126] The terminal receives the answer from the server and displays it in the chat box. The user can then confirm the displayed answer.

[1127] Step 9:

[1128] The server records the user's message and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[1129] Example 1

[1130] 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."

[1131] Conventional real estate price information systems have had problems such as taking a long time to receive an appropriate answer after a user inputs a question, and the accuracy of the answers being low. Also, if the user's messages and answers are not recorded in the system, it is difficult to troubleshoot or improve the system later.

[1132] 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.

[1133] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, means for querying a data store based on the analysis results, means for using a generative AI model to generate answers to the users based on the data store query results, and means for sending the generated answers to the users. This allows users to quickly obtain real estate price information with high accuracy, and since the user's messages and answers are recorded, it makes future troubleshooting and system improvements easier.

[1134] "User" refers to a person who uses the System to request information about real estate prices.

[1135] "Message" refers to text information that a user enters into the system and sends to the server.

[1136] "Means for receiving" refers to an interface or function for receiving messages sent by users at the server.

[1137] "Natural language processing means" refers to the technology or algorithm that analyzes messages received by the server and understands the user's intent and content.

[1138] "Data Store" means a database or storage device that stores real estate pricing information and other related data.

[1139] "Means for querying" refers to the functionality for searching the data store based on the analysis results and obtaining the required information.

[1140] A "generative AI model" refers to an artificial intelligence technology that automatically generates answers to users based on information obtained from a data store.

[1141] "Means for sending" refers to a communication interface or function for sending the generated answer back to the user.

[1142] "Log system" refers to a recording device or system that records user messages and system responses for later reference and analysis.

[1143] "Terminal" refers to a device on which a user inputs and sends messages and receives and displays responses from a server. Examples include a smartphone, tablet, or personal computer.

[1144] This invention is a system that provides a chatbot-style service that allows users to consult about real estate prices and price fluctuations by agents. A specific implementation method of this system will be described in detail.

[1145] System configuration

[1146] The system consists of a user device, a server, a data store, a generative AI model, a natural language processing (NLP) engine, and a log system.

[1147] Terminal

[1148] Users can access the system by entering questions using devices such as smartphones, tablets, and personal computers. They can then use the chatbot interface displayed on the device's browser to enter their questions and click the send button. As a specific example, messages can be sent using the AJAX or Fetch API provided by the web browser.

[1149] server

[1150] The server receives messages from users as HTTP requests. To parse the messages, it uses an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the information extracted from the parsed messages, the server queries a data store that stores real estate price information. This query is performed using a database system such as MySQL or PostgreSQL.

[1151] Datastore

[1152] The data store is a database that holds information on real estate prices and market rates by region. The server searches this data store based on the analysis results and obtains the necessary information.

[1153] Generative AI Models

[1154] The server generates a response to the user based on the information retrieved from the data store. This response can be generated using a generative AI model such as OpenAI GPT-3. For example, a response such as "The average market price for a 2LDK apartment in this area is 150,000 yen" can be generated.

[1155] Sending a response to the user

[1156] The generated answer is sent from the server to the user's device as an HTTP response. The device displays the received answer in a chat box. HTML, JavaScript, CSS, etc. are used for display.

[1157] Log System

[1158] The server records user messages and the system's responses in a logging system, using systems such as ElasticSearch or Splunk, to facilitate future troubleshooting and system improvements.

[1159] Specific examples

[1160] When a user types "What is the average rental price for a 3LDK apartment in Shinjuku Ward?" into the chatbot interface on their device and presses the send button, the process goes as follows: The server receives this message and uses an NLP engine to extract the information "Shinjuku Ward" and "3LDK." The server then queries the data store based on this information to obtain corresponding real estate price information. Based on the information obtained, the server uses a generative AI model to generate an answer such as "The average rental price for a 3LDK apartment in Shinjuku Ward is 200,000 yen," and sends it to the user's device. The user can view this in the chat box.

[1161] Prompt Sentence Examples

[1162] Here is an example of a prompt to input to the generative AI model:

[1163] "What is the average rental price for a 3LDK apartment in Shinjuku Ward?"

[1164] Based on this prompt, the AI ​​model retrieves the appropriate data and provides information.

[1165] In this way, the system allows users to quickly and accurately resolve questions about property prices.

[1166] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1167] Step 1:

[1168] The user types a question into the chatbot interface on the device.

[1169] Specific operation: The user enters a question, for example, "What is the average rent price for a 3LDK apartment in Shinjuku Ward?" and clicks the send button. The data entered is the user's question text, and the click event of the send button is the trigger.

[1170] Step 2:

[1171] The terminal sends the message entered by the user to the server as an HTTP request.

[1172] Specific operation: The browser or application on the device uses AJAX or the Fetch API to send the input message to the server as an HTTP POST request. The input data is the user's question message, and the output is an HTTP request.

[1173] Step 3:

[1174] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent.

[1175] How it works: The server calls an NLP engine such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding to analyze the message. The input data is the user's question, and the output is the analyzed intent and keywords (e.g., "Shinjuku Ward" and "3LDK").

[1176] Step 4:

[1177] The server queries the data store based on the analysis results.

[1178] Specific operation: The server queries a database such as MySQL or PostgreSQL to retrieve real estate price information that matches the specified conditions (e.g., "Shinjuku Ward" and "3LDK"). The input data is the analysis result of the NLP engine, and the output is the real estate price information retrieved from the database.

[1179] Step 5:

[1180] Based on the data acquired by the server, a generative AI model is used to generate answers for the user.

[1181] Specific operation: The server calls a generative AI model (e.g., OpenAI GPT-3) and generates an answer based on the acquired real estate price information. The input data is real estate price information acquired from the database, and the output is the generated answer (e.g., "The average rent for a 3LDK apartment in Shinjuku Ward is 200,000 yen").

[1182] Step 6:

[1183] The server sends the generated answer to the user's terminal as an HTTP response.

[1184] Specific operation: The server includes the generated answer in an HTTP response and sends it back to the terminal. The input data is the generated answer text, and the output is the HTTP response.

[1185] Step 7:

[1186] The terminal displays the response received from the server in the chat box.

[1187] Specific operation: The device parses the response received from the server and displays it in the chat box using HTML and JavaScript. The input data is the response text in the HTTP response, and the output is the text displayed in the browser.

[1188] Step 8:

[1189] The server records the user's message and the system's response in a log system.

[1190] Specific operation: The server records user messages and generated answers in a log system such as ElasticSearch or Splunk. The input data is the user's question message and the generated answer, and the output is the data saved as a log.

[1191] (Application example 1)

[1192] 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."

[1193] Existing systems that provide users with real estate information make it difficult for users to easily obtain information in real time. Even if users visit a store in person, they cannot instantly check detailed real-time real estate information. As a result, users often feel uneasy because they do not have enough information when making decisions about real estate.

[1194] 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.

[1195] In this invention, the server includes means for receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, and means for inputting and displaying a message using a user interface of the smart glasses, thereby enabling users to obtain real estate information in real time through the smart glasses in a store and make quick and accurate decisions.

[1196] The "means for receiving a message from a user" is an interface for receiving a message input by a user in digital form.

[1197] "Natural language processing means for analyzing received messages" refers to a natural language processing engine for analyzing received messages and understanding the user's intent and content.

[1198] "Means for querying a database based on the analysis results" is a function for searching related databases based on the analysis results of natural language processing and obtaining the necessary information.

[1199] "Means for generating an answer to a user based on database query results" refers to the process of creating an appropriate answer to a user's question based on information retrieved from a database.

[1200] The "means for transmitting the generated answer to the user" refers to a communication means for transmitting the generated answer to the user.

[1201] "Means for inputting and displaying messages using a user interface of the smart glasses" refers to an interface that allows a user to input a message using the smart glasses and have the response displayed on the display.

[1202] "Means for recording user messages and responses in a log system" refers to a system for saving and recording messages entered by users and the system's responses to those messages.

[1203] The "means for receiving a response from the server and displaying it on the smart glasses" refers to a method for receiving a response sent from the server on the smart glasses and visually conveying it to the user.

[1204] This invention is a system that allows users to obtain real estate information in real time using smart glasses. The system includes a server, smart glasses, a natural language processing (NLP) engine, a database, a log system, etc.

[1205] Server processing

[1206] The server performs the process using the following main methods:

[1207] 1. Message Receiving Method

[1208] Receives messages entered by the user through the interface of the smart glasses, which are then sent to the server via the Internet as HTTP requests.

[1209] 2. Natural Language Processing Methods

[1210] The received message is passed to an NLP engine (such as spaCy), which analyzes the content of the user's question. For example, a question like "What is the average price for a 2LDK apartment in the neighborhood?" is analyzed, and related keywords (such as "2LDK" and "area") are extracted.

[1211] 3. Database query methods

[1212] Based on the information extracted by the NLP engine, the system queries a real estate price database to retrieve relevant information, including past transaction prices, current market prices, and market rates.

[1213] 4. Answer generation means

[1214] Based on the information retrieved from the database, the system automatically generates answers to be provided to the user. For example, it generates an answer such as, "The average market price for a 2LDK apartment in this area is 150,000 yen."

[1215] 5. Method of sending responses

[1216] The generated answers are sent over the internet to the smart glasses and displayed to the user.

[1217] Processing by terminal (smart glasses)

[1218] The smart glasses have the following features:

[1219] 1. Enter and send a message

[1220] The user can input messages by voice or text through the smart glasses interface, and the input messages are sent to the server.

[1221] 2. Receiving and Displaying Responses

[1222] The smart glasses receive the response sent from the server and display it on the display. For example, information such as "The average market price for a 2LDK apartment in this area is 150,000 yen" is visually displayed.

[1223] Log System

[1224] The server records the user's messages and responses in a log system, which provides useful data for future troubleshooting and system improvement.

[1225] Program processing explanation

[1226] The system is implemented using a Python program, the requests library, and an NLP processor (e.g., spaCy). Messages sent by users through the smart glasses are parsed by the server using natural language processing and queried against the relevant real estate database. Answers are then generated based on the retrieved data and sent to the user.

[1227] Prompt Sentence Examples

[1228] Below are some example prompts used for generative AI models (e.g., GPT-3):

[1229] "The user asks through the smart glasses, 'What is the average price for a 3LDK apartment in the neighborhood?' Generate an answer in the following format. Example answer: 'The average price for a 3LDK apartment in this neighborhood is 250,000 yen.'"

[1230] The above configuration allows users to obtain real estate information in real time through smart glasses in a store, enabling them to make quick and accurate decisions.

[1231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1232] Step 1:

[1233] Users use the smart glasses' interface to input real estate-related questions. Voice input or text input is supported, and the input message is temporarily stored on the device. For example, a user might input, "What is the market price for a 3LDK apartment in the neighborhood?" The input text is sent to the server in the form of an HTTP request.

[1234] Step 2:

[1235] The server receives an HTTP request sent by a user. The received message is then passed to a natural language processing (NLP) engine for analysis. The NLP engine then understands the content and intent of the message and extracts necessary keywords (e.g., "3LDK" or "neighborhood"). The results of this analysis are input to the next processing step.

[1236] Step 3:

[1237] The server uses the results of the natural language processing engine's analysis to query a real estate price database. For example, it might search the database based on the keywords "3LDK" and "neighborhood" to retrieve related property information. The query results serve as input for the next processing step.

[1238] Step 4:

[1239] The server generates a response to the user based on information retrieved from the database. For example, it can average multiple property data from the search results to automatically generate a response such as "The average market price for a 3LDK apartment in this area is 250,000 yen." This generated response becomes the input for the next processing step.

[1240] Step 5:

[1241] The server then sends the generated answer as an HTTP response to the user's smart glasses. The data is received by the device, and the result is displayed in a chat box or on the smart glasses' display. A message such as "The average market price for a 3LDK apartment in this area is 250,000 yen" is displayed.

[1242] Step 6:

[1243] The server records the message entered by the user and the generated response in a log system. This saves data for future troubleshooting and system improvement. For example, the input message "What is the average price for a 3LDK apartment in the neighborhood?" and the generated response "The average price for a 3LDK apartment in this area is 250,000 yen" are recorded in the log.

[1244] The above is the basic processing flow of this system, and details of the specific operations and inputs / outputs at each step.

[1245] 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.

[1246] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[1247] Server processing

[1248] 1. Receiving a message from a user

[1249] The server receives messages sent by users. The user types a question about real estate from their device and presses the send button. For example, if the user types, "What is the average price for a 2LDK apartment in the neighborhood?", the message is sent to the server as an HTTP request and received.

[1250] 2. Message Analysis

[1251] The server passes the received message to a natural language processing (NLP) engine to analyze the user's intent. The analysis results include information about the "2LDK" and "area."

[1252] 3. Emotion Recognition by Emotion Engine

[1253] The server simultaneously uses an emotion engine to recognize emotions from the user's message, such as whether the user is angry or confused, based on the message context and specific keywords.

[1254] 4. Database Query

[1255] Based on the analysis results, the server queries a real estate price database. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[1256] 5. Generating Answers for the User

[1257] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[1258] 6. Submit your response

[1259] The server generates a response and sends it to the user, which is then sent to the user's device as an HTTP response.

[1260] 7. Logging

[1261] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[1262] Processing by the terminal

[1263] 1. Enter your message

[1264] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then hit send.

[1265] 2. Sending a Message

[1266] The terminal sends the user's input message to the server as an HTTP request, and then waits for a response from the server.

[1267] 3. View Answers

[1268] When the server returns an answer to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[1269] User

[1270] 1. Enter your question

[1271] The user types a specific question into the ChatBot's interface, for example, "What is the average price for a 2LDK apartment in the neighborhood?", and then presses the send button.

[1272] 2. Verify the information

[1273] Within a few seconds, the server will send a response to the chat screen, which the user can confirm. For example, the user may receive information such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[1274] This system allows users to easily resolve questions about real estate prices and receive personalized support that takes their emotions into consideration. Furthermore, all logs are recorded on the server side, accumulating data that will be useful for future problem solving and system improvements.

[1275] The processing flow will be explained below.

[1276] Step 1:

[1277] The user enters a question into the ChatBot interface on their device and presses the "Send" button. For example, they might enter, "What is the average price for a 2LDK apartment in the neighborhood?"

[1278] Step 2:

[1279] The terminal receives the user's input message and sends it to the server as an HTTP request, which includes the user's question.

[1280] Step 3:

[1281] The server receives the HTTP request and prepares to parse the message, then logs the received message in the log system.

[1282] Step 4:

[1283] The server passes the message to a natural language processing (NLP) engine to analyze the user's intent. This analysis includes keyword extraction and context understanding. For example, information about "2LDK" and "area" is extracted.

[1284] Step 5:

[1285] The server uses an emotion engine to recognize emotions from the user's message. For example, it determines the user's emotional state from the message context and specific keywords. For example, emotions such as "confused" or "angry" can be recognized.

[1286] Step 6:

[1287] The server queries a real estate price database based on the analysis and emotion recognition results. Based on the analyzed information, it searches for real estate price information that matches the "area" specified in "2LDK."

[1288] Step 7:

[1289] The server receives the results from the database and generates a response for the user. For example, it creates a response that takes into consideration the user's feelings, such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[1290] Step 8:

[1291] The server sends the generated answer to the user's terminal as an HTTP response.

[1292] Step 9:

[1293] The device receives the response from the server and displays it in the chat box. For example, it might say, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[1294] Step 10:

[1295] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[1296] This series of processes allows users to quickly resolve their real estate-related questions and receive courteous, sensitive service.

[1297] Example 2

[1298] 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."

[1299] Conventional ChatBot systems use natural language processing technology to understand user intent, but lack the ability to recognize a user's emotional state and provide appropriate responses based on that emotion. They also lack a mechanism for quickly and accurately answering complex questions about real estate prices. As a result, users often receive poor quality information, leading to lower satisfaction levels.

[1300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1301] In this invention, the server includes means for receiving messages from users, natural language processing means for analyzing the received messages, emotion recognition means for recognizing emotions from the user's messages, means for querying a database based on the analysis results and the emotion recognition results, means for generating a response to the user based on the database query results and the emotion recognition results, and means for sending the generated response to the user. This makes it possible to provide appropriate responses according to the user's emotional state and to quickly and accurately respond to complex questions about real estate prices.

[1302] The "means for receiving a message from a user" is a function for transferring a message input by a user to a server, and is usually performed via an HTTP request.

[1303] "Natural language processing means for analyzing received messages" refers to engines or algorithms that understand the content of messages received from users and analyze keywords and intent. Examples include Google Cloud Natural Language API and IBM Watson.

[1304] "Emotion recognition means that recognize emotions from user messages" refers to engines or algorithms that read emotions from the context of a user's message or specific keywords. Examples include Amazon Comprehend and Microsoft Azure Text Analytics.

[1305] The "means for querying a database based on the analysis results and emotion recognition results" is a function for searching and retrieving related data from a database based on the content of a user's request and the recognized emotional state.

[1306] The "means for generating a response to the user based on the database query results and emotion recognition results" refers to an algorithm or engine for generating an appropriate response based on the acquired data and the recognized emotion.

[1307] The "means for transmitting the generated answer to the user" is a function for transferring the generated answer to the user's terminal and displaying it, and is usually performed via an HTTP response.

[1308] "Means for recording user messages, emotional states, and responses in the log system" refers to a function for recording user messages, emotional states, and responses generated by the system, for future use in data analysis and system improvement.

[1309] The "means for sending a user's message and receiving and displaying a response from the server" refers to the interface and function on the terminal side that sends the user's input to the server and receives and displays a response from the server.

[1310] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by real estate agents and receive answers. In particular, we provide a system that can recognize the user's emotional state and provide appropriate answers according to that state.

[1311] Overview of the hardware and software used

[1312] This system operates by combining multiple technological elements, including the following key software and hardware components:

[1313] 1. Natural Language Processing (NLP) Engines: Google Cloud Natural Language API and IBM Watson

[1314] 2. Emotion Recognition Engine: Amazon Comprehend or Microsoft Azure Text Analytics

[1315] 3. Database: MySQL or PostgreSQL

[1316] 4. Log systems: Elasticsearch, Logstash

[1317] 5. Servers and terminals: Web servers (e.g., Apache, Nginx), user terminals (e.g., PCs, smartphones)

[1318] System processing flow

[1319] 1. Enter your message

[1320] Users use the ChatBot interface on their device to input a real estate question, such as "What is the going rate for a 2LDK apartment in the neighborhood?", and then press the send button.

[1321] 2. Sending a Message

[1322] The terminal sends the input message to the server as an HTTP request, using the HTTP protocol.

[1323] 3. Receiving and parsing messages

[1324] The server receives messages sent by users. The received messages are passed to a natural language processing engine for analysis. In this analysis process, intent such as "2LDK" or "area" is extracted from the message.

[1325] 4. Emotion recognition

[1326] At the same time, the server uses an emotion recognition engine to determine the user's emotions from the message, such as whether the user is dissatisfied or confused, based on the context of the text and specific keywords.

[1327] 5. Querying the Database

[1328] The server queries a real estate price database based on the analysis results and retrieves relevant real estate price data from the database based on the detected keywords (e.g., "2LDK" and "area").

[1329] 6. Answer Generation

[1330] The server generates an appropriate response to the user based on the acquired data and the results of emotion recognition. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help."

[1331] 7. Submit your response

[1332] The server sends the generated answer as an HTTP response to the user's device, where it is displayed.

[1333] 8. Logging

[1334] The server records the user's message, emotional state, and the system's response in a log system, which provides data that can be used later in case of problems or to improve the system.

[1335] Specific examples

[1336] The user inputs a prompt into the chatbot interface, such as "What is the average price for a 2LDK apartment in the neighborhood?". In response, the system operates as follows:

[1337] The server receives the message and analyzes it using a natural language processing engine.

[1338] Recognize user emotions with an emotion recognition engine.

[1339] Based on the analysis results, a database is queried to obtain relevant real estate price data.

[1340] Emotion recognition results are also taken into consideration to generate appropriate answers.

[1341] The answer is sent to the user's terminal, and the necessary data is recorded in the log system.

[1342] In this way, users can easily and quickly obtain information about real estate prices. Furthermore, by incorporating emotion recognition, we can provide better services that take users' emotions into consideration.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1:

[1345] The server receives a message from the user. The user enters a question on the terminal, such as "What is the average price for a 2LDK apartment in the neighborhood?" and presses the send button. This message is sent to the server via an HTTP request. The input is the user's message in text format, and the output is the message received by the server.

[1346] Step 2:

[1347] The server inputs the received message into a natural language processing (NLP) engine. The NLP engine uses Google Cloud Natural Language API or IBM Watson to analyze keywords and user intent from the input message. Specifically, it extracts information such as "2LDK" and "area." The input is the user message, and the output is the extracted keywords and intent.

[1348] Step 3:

[1349] The server simultaneously uses an emotion recognition engine to recognize emotions from the user's message. It uses Amazon Comprehend and Microsoft Azure Text Analytics to determine emotions (e.g., anger, confusion) from the message text. The input is the user message, and the output is the determined emotional information.

[1350] Step 4:

[1351] The server queries a database based on the analysis results and emotion recognition results. It uses MySQL or PostgreSQL as the database and executes a query to retrieve real estate price information that matches the specified area and property type (2LDK). The input is the analysis results and emotion recognition results, and the output is real estate price data.

[1352] Step 5:

[1353] The server generates a response to the user based on the acquired data and the results of emotion recognition. It provides information such as average market prices in appropriate wording, while also taking into consideration the user's emotional state. For example, it might generate a response such as, "The average market price for a 2LDK apartment in this area is 150,000 yen. Please contact us if you need any help." The input is data acquired from the database and emotional information, and the output is the generated response text.

[1354] Step 6:

[1355] The server sends the generated answer to the user's terminal as an HTTP response. The sent answer is displayed on the user's terminal. The input is the generated answer text, and the output is the answer displayed on the user's terminal.

[1356] Step 7:

[1357] The server records the user's message, emotional state, and the system-generated answer in a log system. Elasticsearch and Logstash are used to manage this data and use it for later analysis and system improvement. The input is the user's message, emotional information, and the generated answer, and the output is the record in the log system.

[1358] (Application example 2)

[1359] 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."

[1360] While conventional chatbot systems can provide appropriate answers to users' questions about real estate prices, they do not adequately take into account the user's emotional state. Furthermore, they do not take into account the application of new devices such as smart glasses as a means of providing instant customer service in brick-and-mortar stores, and there is a need to improve customer satisfaction.

[1361] 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 receiving a message from a user, natural language processing means for analyzing the received message, means for querying a database based on the analysis result, means for generating a response to the user based on the database query result, means for sending the generated response to the user, means for recognizing the user's emotional state, and means for providing an appropriate response based on the recognized emotional state. This makes it possible to provide appropriate real estate information in real time, even in a physical store, taking into account the user's emotional state.

[1362] The "means for receiving messages from users" is a system that includes a process for sending messages sent by users to a server.

[1363] The "natural language processing means for analyzing received messages" is a system that uses a natural language processing engine to analyze the content of a user's message and understand its intent.

[1364] The "means for querying a database based on the analysis result" is a system that includes a process for searching a database to obtain related data based on the content of the analyzed message.

[1365] The "means for generating a response to a user based on the database query results" is a system that includes a process for generating a response to be provided to a user based on the acquired data and analysis results.

[1366] The "means for sending the generated answer to the user" is a system that includes a process for delivering the generated answer to the user.

[1367] The "means for recognizing the user's emotional state" is a system for identifying the user's emotions from the user's facial expressions, voice, message context, etc.

[1368] A "means for providing appropriate answers based on a recognized emotional state" is a system that includes a process for generating more appropriate and considerate answers based on the user's emotional state.

[1369] This invention relates to a ChatBot system that allows users to ask questions about real estate prices and price fluctuations by agents and receive answers. In particular, we provide a system that incorporates an emotion engine that can recognize the user's emotional state and provide appropriate answers according to that state. Below, we will describe in detail the embodiments of this invention.

[1370] Server processing

[1371] The server receives messages sent by users and analyzes them using a natural language processing engine. Based on the analysis results and the user's emotional state, it queries a database to generate and send a response. Specifically, it works as follows:

[1372] 1. Receiving a message from a user

[1373] The server receives messages entered by users using smart glasses or smartphones. For example, if a user asks, "What is the average price of a 2LDK apartment in this area?", the message is sent to the server as an HTTP request.

[1374] 2. Message Analysis

[1375] The server passes the received message to a natural language processing engine (e.g., spaCy or BERT) to analyze the user's intent. The analysis results include information about "2LDK" and "area."

[1376] 3. Emotion Recognition by Emotion Engine

[1377] At the same time, the server uses an emotion engine (e.g., OpenCV or Affectiva) to recognize emotions from the user's message and facial expressions. For example, it determines whether the user is interested or anxious based on the message context and specific keywords.

[1378] 4. Database Query

[1379] The server then queries a real estate price database based on the analysis results. For example, it retrieves real estate price information that matches the specified area and property type (2LDK). This data includes past transaction prices, current market prices, and market rates.

[1380] 5. Generating Answers for the User

[1381] The server generates a response to the user based on the acquired data and the results of the emotion engine. For example, it creates a response that takes the user's emotions into consideration, such as, "The current market price is around 150,000 yen. Please let us know if you need more information."

[1382] 6. Submit your response

[1383] The server then sends the generated answer to the user, which is then sent to the user's terminal as an HTTP response.

[1384] Processing by the terminal

[1385] The device sends messages from the user to the server, receives replies from the server, and displays them. This is done using smart glasses or a smartphone.

[1386] 1. Enter your message

[1387] Using the ChatBot interface on their device, users can input a real estate question, such as "What is the average price for a 2LDK apartment in this area?", and then hit the send button.

[1388] 2. Sending a Message

[1389] The terminal sends the user's input message as an HTTP request to the server, and then waits for a response from the server.

[1390] 3. View Answers

[1391] When the server responds to the user's question, the device receives it and displays it in the chat box. For example, it might say, "The current market price is around 150,000 yen. Please let us know if you need more information."

[1392] User operation

[1393] Users can enter specific questions into the ChatBot's interface and view the answers, allowing them to easily resolve their real estate pricing queries and receive a personal, sensitive response.

[1394] Prompt Sentence Examples

[1395] For example, if a customer asks, "What is the average price for a 2LDK apartment in this area?", the following prompt sentence is input into the generative AI model:

[1396] Question: "What is the average price for a 2LDK apartment in this area?"

[1397] Emotional state: "Curious"

[1398] This prompt is sent to the server, the answer is retrieved, and the answer is displayed on the smart glasses, providing the customer with the information instantly.

[1399] This system allows users to resolve questions about real estate prices and communicate in a way that takes their emotions into consideration. In addition, all logs are recorded on the server side, which can be used to solve problems and improve the system in the future.

[1400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1401] Step 1:

[1402] A user uses smart glasses or a smartphone to input a real estate question, for example, "What is the average price of a 2LDK apartment in this area?" and presses the submit button. This input is sent to the server as an HTTP request. The input is the user's natural language message, and the output is an HTTP request sent to the server.

[1403] Step 2:

[1404] The server processes the received HTTP request and passes it to a natural language processing engine to analyze the user's message. The natural language processing engine (e.g., spaCy or BERT) analyzes the content of the message and understands the intent of the user's question. The input is the user's natural language message, and the output is analyzed data (e.g., property type and area information).

[1405] Step 3:

[1406] At the same time, the server uses an emotion engine to recognize the user's emotional state. The emotion engine (e.g., OpenCV or Affectiva) determines the emotion from the user's facial expression and the message context. The input is the user's facial expression data and the message context, and the output is the user's emotional state.

[1407] Step 4:

[1408] The server queries a real estate price database based on the analysis results and the emotional state. The database provides real estate price information matching the specified area and property type (e.g., "2LDK"). The input is the analysis results, and the output is the related real estate price data.

[1409] Step 5:

[1410] The server generates an appropriate answer for the user based on the acquired data and the results of the emotion engine. For example, it creates an answer in the form of "The current market price is around 150,000 yen. Please let us know if you need more information." The input is real estate data acquired from the database and the user's emotional state, and the output is the generated answer.

[1411] Step 6:

[1412] The server generates an answer and sends it to the user. The answer is sent as an HTTP response and displayed on the terminal. The input is the generated answer, and the output is the HTTP response sent to the user.

[1413] Step 7:

[1414] The terminal receives the response from the server and displays it in the chat box, allowing the user to check the response on the terminal. The input is the HTTP response sent from the server, and the output is the response message displayed on the terminal.

[1415] Through the above processing steps, the user can resolve their questions about real estate prices and receive answers that take their emotions into consideration.

[1416] 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.

[1417] 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.

[1418] 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 robot 414.

[1419] 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.

[1420] FIG. 9 illustrates 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 behaviors 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.

[1421] 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.

[1422] 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).

[1423] 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.

[1424] 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."

[1425] 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.

[1426] 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).

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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.

[1437] The following is further disclosed regarding the above embodiment.

[1438] (Claim 1)

[1439] means for receiving a message from a user;

[1440] natural language processing means for analyzing received messages;

[1441] means for querying a database based on the analysis results;

[1442] means for generating a response to the user based on the database query results;

[1443] means for transmitting the generated answer to the user;

[1444] A system including:

[1445] (Claim 2)

[1446] 10. The system of claim 1, further comprising means for recording user messages and responses in a log system.

[1447] (Claim 3)

[1448] 10. The system of claim 1, further comprising a terminal including means for sending a user's message and receiving and displaying a reply from the server.

[1449] "Example 1"

[1450] (Claim 1)

[1451] means for receiving a message from a user;

[1452] natural language processing means for analyzing received messages;

[1453] means for querying a data store based on the analysis results;

[1454] means for using a generative AI model to generate an answer for a user based on the data store query results;

[1455] means for transmitting the generated answer to the user;

[1456] A system including:

[1457] (Claim 2)

[1458] 10. The system of claim 1, further comprising means for recording user messages and responses in a log system.

[1459] (Claim 3)

[1460] 10. The system of claim 1, further comprising a terminal including means for sending a user's message and receiving and displaying a reply from the server.

[1461] "Application Example 1"

[1462] (Claim 1)

[1463] means for receiving a message from a user;

[1464] natural language processing means for analyzing received messages;

[1465] means for querying a database based on the analysis results;

[1466] means for generating a response to the user based on the database query results;

[1467] means for transmitting the generated answer to the user;

[1468] means for inputting and displaying messages using a user interface of the smart glasses;

[1469] A system including:

[1470] (Claim 2)

[1471] 10. The system of claim 1, further comprising means for recording user messages and responses in a log system.

[1472] (Claim 3)

[1473] 10. The system of claim 1, further comprising a terminal including means for sending a user's message and receiving a reply from the server for display on the smart glasses.

[1474] "Example 2: Combining Emotion Engines"

[1475] (Claim 1)

[1476] means for receiving a message from a user;

[1477] natural language processing means for analyzing received messages;

[1478] emotion recognition means for recognizing emotions from a user's message;

[1479] means for querying the database based on the analysis results and emotion recognition results;

[1480] means for generating a response to the user based on the database query results and the emotion recognition results;

[1481] means for transmitting the generated answer to the user;

[1482] A system including:

[1483] (Claim 2)

[1484] 10. The system of claim 1, further comprising means for recording the user's messages, emotional states, and responses in a log system.

[1485] (Claim 3)

[1486] 10. The system of claim 1, further comprising a terminal including means for sending a user's message and receiving and displaying a reply from the server.

[1487] "Application example 2 when combining emotion engines"

[1488] (Claim 1)

[1489] means for receiving a message from a user;

[1490] natural language processing means for analyzing received messages;

[1491] means for querying a database based on the analysis results;

[1492] means for generating a response to the user based on the database query results;

[1493] means for transmitting the generated answer to the user;

[1494] means for recognizing the emotional state of a user;

[1495] a means for providing an appropriate response based on the perceived emotional state;

[1496] A system including:

[1497] (Claim 2)

[1498] 10. The system of claim 1, further comprising means for recording user messages and responses in a log system.

[1499] (Claim 3)

[1500] 10. The system of claim 1, further comprising a terminal including means for sending a user's message and receiving and displaying a reply from the server. [Explanation of symbols]

[1501] 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. means for receiving a message from a user; natural language processing means for analyzing received messages; means for querying a database based on the analysis results; means for generating a response to the user based on the database query results; means for transmitting the generated answer to the user; A system including:

2. 10. The system of claim 1, further comprising means for recording user messages and responses in a log system.

3. 10. The system of claim 1, further comprising a terminal including means for sending a user's message and for receiving and displaying a reply from the server.

Images