System

Abstract

A system is provided.SOLUTION: A system comprising: means for hearing player needs and conditions using conversational artificial intelligence; means for generating proxy artificial intelligence and conducting negotiations based on player needs and conditions; RetrievalAugmentGeneration means for analyzing market trends and past negotiation data; means for providing generated trading information to users; and means for accumulating negotiation data and market trend data and conducting self-learning.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the real estate industry, negotiations between players not only consume a significant amount of time and resources, but also make follow-up on negotiations extremely difficult. It is also not easy for each player to find the best deal that meets their individual needs and conditions. The current situation calls for more efficient negotiations and fairer transactions. Conventional systems have limited means of resolving these issues, making it difficult to expect efficient and fair transactions. The present invention aims to provide a new system that solves these problems. [Means for solving the problem]

[0005] The present invention solves the aforementioned problems by the following means. Conversational AI listens to the requests and conditions of each player in the real estate industry, and a proxy AI automatically negotiates based on that information. Furthermore, market trends and past negotiation data are analyzed using the Retrieval Augment Generation method, and optimal transaction information is provided to the user. The proxy AI self-learns based on accumulated negotiation data and market trend data, improving its negotiation skills. This aims to achieve efficient and fair transactions.

[0006] "Conversational AI" is an AI that uses natural language processing to understand a user's requests and requirements and store them in a database.

[0007] A "surrogate AI" is an AI that automatically negotiates with other surrogate AIs based on the user's requests and conditions.

[0008] "Retrieval Augment Generation" is a method of collecting and analyzing market trends and past negotiation data to generate optimal trading information for users.

[0009] "Users" are players involved in real estate transactions and end consumers.

[0010] "Players" are those involved in the real estate industry, such as landowners, construction companies, building material manufacturers, developers, real estate dealers, and financial institutions.

[0011] The "automated negotiation platform" is a system that uses proxy artificial intelligence to automatically negotiate in real estate transactions.

[0012] The "database" is an information storage system for storing and managing player requests and conditions, negotiation data, and market trend data.

[0013] "Learning" is the process by which the surrogate AI uses past negotiation data and market trend data to improve and enhance its negotiation skills.

[0014] "Market trends" refers to information such as current and past price fluctuations in the real estate market, the balance of supply and demand, and transaction trends.

[0015] "Negotiation" refers to the exchanges that take place in real estate transactions to determine the price, conditions, delivery date, etc. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

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

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

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

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate dealers, financial institutions, and consumers), and then each player's proxy AI automatically negotiates based on those conditions. Below are details of the program's processing and a specific example.

[0038] Program processing details:

[0039] The system of the present invention operates as follows.

[0040] 1. A user accesses the server

[0041] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[0042] Server: Verifies the user's credentials and starts the session.

[0043] 2. Listen to users' requests and requirements

[0044] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0045] Server: Receives the input data, analyzes the information using a natural language processing (NLP) module, and stores it in a database.

[0046] 3. Creating a proxy AI and starting negotiations

[0047] Server: Based on the user's input information, it generates artificial intelligence representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0048] Server: Loads the user's requests and conditions into each proxy AI and initiates negotiations.

[0049] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[0050] 4. Market trend analysis and information provision using the RAG method

[0051] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0052] Server: Provides the acquired important transaction information to the user and the surrogate AI. The surrogate AI utilizes this information to optimize negotiation strategies.

[0053] 5. Review and feedback on negotiation results

[0054] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[0055] User: Review the negotiation results and provide feedback if necessary.

[0056] Server: Stores user feedback in a database.

[0057] 6. Data accumulation and self-learning

[0058] Server: Stores data on negotiations and market trends, updating the dataset for self-learning by the surrogate AI.

[0059] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[0060] Server: Monitors the learning process and updates the AI ​​model as needed.

[0061] Examples:

[0062] Step 1: Enter your request

[0063] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0064] Server: "The data entered by the user has been parsed and saved to the database."

[0065] Step 2: Negotiation begins with surrogate AI

[0066] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[0067] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0068] Step 3: Market trend analysis and information provision

[0069] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0070] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0071] Step 4: Review and feedback on negotiation results

[0072] Server: "Negotiation completed. User notified of outcome."

[0073] User: "Review the results and provide feedback."

[0074] Step 5: Data accumulation and learning

[0075] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[0076] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] User: Access the server and log in.

[0080] Server: Validates the user's credentials and initiates a session.

[0081] Step 2:

[0082] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0083] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0084] Server: Stores the analyzed requests and conditions in a database.

[0085] Step 3:

[0086] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0087] Server: Loads each surrogate AI with the relevant player's information, wishes and conditions.

[0088] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[0089] Proxy AI: Builds a negotiation strategy using an internal algorithm based on the received conditions.

[0090] Step 4:

[0091] Proxy AI: Proceeds negotiations based on each player's conditions (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[0092] Server: Records the progress of negotiations in a database in real time.

[0093] Step 5:

[0094] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0095] Server: Provides acquired important transaction information to the proxy AI.

[0096] Proxy AI: Optimizes negotiation tactics based on the information provided and continues negotiations.

[0097] Step 6:

[0098] Server: Once the negotiation is complete, aggregate all results and notify the user.

[0099] User: Review the negotiation results and provide feedback if necessary.

[0100] Server: Stores user feedback in a database.

[0101] Step 7:

[0102] Server: Stores negotiation data and market trend data in a proprietary database.

[0103] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[0104] Server: Monitors the learning process and updates the AI ​​model as needed.

[0105] Proxy AI: Reflects learning results in the next negotiation.

[0106] Example 1

[0107] 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."

[0108] In conventional real estate transactions, negotiations between each player (landowner, construction company, building materials manufacturer, developer, real estate dealer, financial institution, and consumer) often do not proceed efficiently due to their complexity and time-consuming efforts. Furthermore, the progress and success rate of negotiations depend on the subjective judgment of each player, making it difficult to achieve a fair transaction. Furthermore, conventional systems using artificial intelligence have the problem of not being able to adequately analyze information or optimize strategies, resulting in poor transaction outcomes. The present invention aims to solve these problems and realize efficient and fair real estate transactions.

[0109] 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.

[0110] In this invention, the server includes means for using a conversational AI to hear the user's requests and conditions, means for generating a proxy AI and negotiating based on the user's requests and conditions, means for acquiring and expanding information for analyzing market trends and past negotiation data, means for providing the generated transaction information to the user, means for accumulating negotiation data and market trend data and for self-learning, means for the user to access and log in to the system using a web browser or application, means for analyzing the requests and conditions entered by the user using natural language processing and storing them in a database, means for the proxy AI to communicate with other proxy AIs to strategically advance negotiations, means for extracting important transaction information and providing it to the proxy AI and the user, and means for notifying the user of the negotiation results and receiving feedback, thereby enabling fast and efficient negotiations and fair transactions.

[0111] "Conversational artificial intelligence" is a system that uses artificial intelligence technology to converse with users in natural language and gather their requests and requirements.

[0112] "Proxy AI" is a program or system that uses AI technology to negotiate on behalf of each player.

[0113] "Information retrieval augmentation generation means" is a means of collecting and analyzing market trends and past negotiation data using the Retrieval Augment Generation (RAG) method.

[0114] "Transaction Information" refers to data relating to the results of player negotiations and market trends, and is information provided to users.

[0115] "Self-learning" is the process by which artificial intelligence uses machine learning algorithms to learn and improve its performance based on past negotiation data and market trend data.

[0116] A "web browser" is software for viewing web pages on the Internet.

[0117] An "application" is a software program designed to accomplish a particular purpose.

[0118] "Natural language processing" is a technology that processes human language using a computer to perform semantic analysis and information extraction.

[0119] A "database" is an information collection system that systematically stores data and enables it to be searched and managed.

[0120] "Feedback" refers to the results of negotiations and opinions and evaluations from users regarding their use of the system, and is information that can be used to help with future improvements and adjustments.

[0121] This invention is a system in which a conversational AI listens to the requests and conditions of each player in a real estate transaction (land owner, construction company, building material manufacturer, developer, real estate dealer, financial institution, consumer), and then a proxy AI for each player automatically negotiates based on those conditions. This system operates as follows.

[0122] 1. Hardware and software used

[0123] Hardware: Servers, devices (devices that run the web browsers and specialized applications used by users), and network infrastructure.

[0124] Software: Conversational artificial intelligence (natural language processing), surrogate artificial intelligence (machine learning algorithms), database management systems (SQL databases, NoSQL databases), web browsers (Google Chrome, Mozilla Firefox), dedicated applications.

[0125] 2. Data processing and calculation

[0126] server

[0127] Credential validation: The credentials entered by the user at login are checked against a database to verify their validity.

[0128] Natural language processing: The requests and conditions entered by the user are analyzed using a natural language processing module (e.g., spaCy or NLTK), converted into structured data, and stored in the database.

[0129] Generate surrogate AI: Based on user input data, generate surrogate AI for the relevant player using machine learning libraries such as TensorFlow or PyTorch.

[0130] RAG information analysis: We use the Retrieval Augmented Generation (RAG) method to analyze market trends and past negotiation data. Specifically, we use external data collected using scraping techniques to analyze current market trends in real time.

[0131] Notification of important information: Important transaction information obtained as a result of analysis is compiled and provided to the agent AI and users in real time.

[0132] proxy AI

[0133] Communication and negotiation: Communicate with other agent AIs via RESTful APIs, share their requests and conditions, and proceed with negotiations. Use internal algorithms to find the optimal solution for the negotiation.

[0134] Self-learning: Negotiation data and market trend data are self-learned using machine learning algorithms, and reflected in the next negotiation.

[0135] Terminal

[0136] Providing a user interface: Providing an interface for users to access the system and input their requests and requirements. Specifically, this includes form entry, button operations, etc.

[0137] Display notifications: Display the negotiation results and important information sent from the server to the user.

[0138] 3. Specific Examples

[0139] Input of user requests

[0140] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0141] Server: "The data entered by the user has been parsed and saved to the database."

[0142] Negotiations begin with proxy AI

[0143] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[0144] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0145] Market trend analysis and information provision

[0146] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0147] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0148] Confirmation and feedback of negotiation results

[0149] Server: "Negotiation completed. User notified of outcome."

[0150] User: "Review the results and provide feedback."

[0151] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Processing Steps

[0154] Step 1: User Access and Login

[0155] input:

[0156] The user accesses the system's URL through a web browser or application and enters their user ID and password on the login screen.

[0157] Specific behavior:

[0158] Terminal: Launch a web browser or application and access the system URL. The login screen will appear.

[0159] User: Enter your user ID and password on the login screen and click the "Login" button.

[0160] Server: Receives the entered user ID and password and checks the authentication information against the database. If authentication is successful, the session starts and the home screen is displayed.

[0161] output:

[0162] The home screen appears, allowing the user to access the system's features.

[0163] Step 2: Enter your requirements and requirements

[0164] input:

[0165] The user enters their requests and conditions (budget, location, desired property type, construction period, etc.) into the input form on the home screen and clicks the submit button.

[0166] Specific behavior:

[0167] User: Enter requirements such as "Budget: within 200 million yen," "Location: Tokyo," and "Construction period: 1 year" into the input form on the home screen, and click the submit button.

[0168] Terminal: Sends the input form data to the server.

[0169] Server: Analyzes the received data using a natural language processing (NLP) module (e.g., spaCy or NLTK) and stores the analyzed structured data in a database.

[0170] output:

[0171] The structured data is saved in a database, which triggers the next processing step.

[0172] Step 3: Create and configure a surrogate AI

[0173] input:

[0174] Data on user requests and requirements stored on the server.

[0175] Specific behavior:

[0176] Server: Based on the user's input data, it generates surrogate AI for the relevant players (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.) using machine learning libraries such as TensorFlow and PyTorch.

[0177] Server: Loads the user's requests and conditions into the generated surrogate AI.

[0178] output:

[0179] Multiple proxy AIs are generated and loaded with the user's requests and conditions.

[0180] Step 4: Negotiation begins with surrogate AI

[0181] input:

[0182] User requests and conditions loaded into each surrogate AI.

[0183] Specific behavior:

[0184] Delegate AI: Communicates with other Delegate AIs via RESTful APIs, shares their requests and conditions, and uses internal algorithms to advance negotiations.

[0185] For example, a land owner AI might propose the condition "can be sold for 150 million yen" to another proxy AI, and the construction company AI might respond "can be constructed within the budget."

[0186] output:

[0187] Negotiations continue to progress and optimal terms are found.

[0188] Step 5: Analyze market trends and provide information

[0189] input:

[0190] Market trend information and past negotiation data collected by the server.

[0191] Specific behavior:

[0192] Server: Analyzes market trends and historical negotiation data using Retrieval Augmented Generation (RAG) techniques, specifically scraping data from external data sources and performing real-time analysis.

[0193] Server: Extracts important transaction information obtained as a result of the analysis and provides it to the proxy AI and the user.

[0194] For example, information such as "land prices in Tokyo have increased 10% compared to the previous year" is collected as a current market trend, and this information is notified to the proxy AI.

[0195] output:

[0196] Key transaction information is obtained, and the surrogate AI optimizes the negotiation strategy based on it.

[0197] Step 6: Review and feedback on negotiation results

[0198] input:

[0199] Negotiation result data and user feedback information.

[0200] Specific behavior:

[0201] Server: Once the negotiation is complete, the server consolidates all the results and notifies the user via email or in-app notification.

[0202] User: After receiving the notification, log back into the system to check the negotiation results and provide feedback if necessary.

[0203] For example, the user may input, "The negotiation process went smoothly, but I'm dissatisfied because it was over budget."

[0204] output:

[0205] The negotiation results and feedback information confirmed by the user are stored in a database.

[0206] Step 7: Data accumulation and self-learning

[0207] input:

[0208] Negotiation data and feedback information.

[0209] Specific behavior:

[0210] Server: Records negotiation data and feedback information in a database and prepares for the next negotiation.

[0211] Surrogate AI: Acquires new data and uses machine learning algorithms (e.g., reinforcement learning) to self-learn and improve negotiation tactics.

[0212] Server: Monitors the learning progress and adjusts the algorithm parameters as needed.

[0213] output:

[0214] Deputy AI with improved negotiation skills and updated systems.

[0215] (Application example 1)

[0216] 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."

[0217] Existing negotiation systems in the real estate industry have faced challenges such as the difficulty of reconciling the diverse requests and conditions between each player and the complexity of efficiently conducting optimal transactions. Furthermore, supply chain management and appropriate price negotiations are important for procuring materials within a factory, but doing this manually takes time and effort. This leads to problems such as a lack of negotiating power and an increased risk of human error.

[0218] 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.

[0219] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, Retrieval Augment Generation means for analyzing market trends and past negotiation data, means for allowing a user to input material requirements and automatically negotiate with suppliers in the procurement of materials within a factory, and means for selecting the most suitable supplier based on the material requirements and optimizing prices. This enables efficient and optimal transactions in line with the player's requests, making material procurement more efficient and reducing costs.

[0220] "Conversational AI" is AI that can have natural conversations with users via voice and text.

[0221] A "surrogate AI" is an AI generated to negotiate with other surrogate AIs based on the user's requests and conditions.

[0222] "Retrieval Augment Generation Method" is a method for automatically generating transaction information by analyzing past negotiation data and market trends.

[0223] "In-factory material procurement" is the process of properly securing materials and parts necessary for factory production activities.

[0224] "Material requirements" are the specific conditions and specifications for the materials to be procured, such as quantity, quality, and delivery date.

[0225] "Supplier" means a supplier that supplies materials and parts to the factory.

[0226] "Market trends" refers to information that refers to general trends such as the current market state and price fluctuations.

[0227] "Price optimization" is the process of procuring materials of the required quality and quantity at the optimal price while keeping costs down.

[0228] This invention is a system for in-factory material procurement and supply chain management that uses conversational AI to hear the requests and conditions of players (factory personnel, suppliers) and then uses proxy AI to efficiently automate negotiations. An embodiment of this system is shown below.

[0229] System Overview

[0230] The server is configured using the following hardware and software.

[0231] Hardware: High-performance servers, IoT devices in factories

[0232] software:

[0233] Natural Language Processing (NLP) modules (e.g., spaCy, NLTK)

[0234] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0235] Database (e.g. MySQL, MongoDB)

[0236] Libraries suitable for implementing Retrieval Augment Generation (RAG) techniques (e.g., Transformers)

[0237] Processing flow

[0238] User Input and Data Analysis

[0239] Using a terminal, factory personnel input material requirements (e.g., quantity, quality, delivery date). The server analyzes this information using a natural language processing (NLP) module and stores it in a database, allowing the input requirements to be treated as concrete data.

[0240] Creation of a surrogate AI and the start of negotiations

[0241] Based on the analyzed data, the server generates surrogate AIs for the relevant suppliers. Each surrogate AI loads the user's requirements and initiates automatic negotiations with the suppliers.

[0242] Market trend analysis

[0243] The server uses the RAG methodology to collect and analyze market trends and past negotiation data, thereby understanding current market prices and trends and providing information that can be used in negotiations.

[0244] Notification and optimization of negotiation results

[0245] After the negotiation is completed, the server notifies the user of the results in real time. The user can then review the results and enter feedback as needed. This allows the user to obtain quotes and delivery terms from the most suitable suppliers.

[0246] Specific examples

[0247] For example, a factory worker enters the following prompt:

[0248] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[0249] Based on this prompt, the server analyzes the information and generates a suitable supplier's surrogate AI. The surrogate AI then negotiates with other surrogate AIs, grasps market trends using the RAG method, and proposes the optimal price and delivery date. Finally, the negotiation results are notified to the factory staff in real time for confirmation and feedback.

[0250] This invention significantly improves the efficiency of material procurement within factories, reducing costs and strengthening supply chain risk management.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1:

[0253] A user uses a terminal to input material requirements, including specific conditions such as quantity, quality, and delivery date, and the input information is sent from the terminal to the server.

[0254] Input: Material requirements (e.g. quantity, quality, delivery date)

[0255] Output: Material requirements sent to the server

[0256] Specific behavior:

[0257] The factory worker enters the following as the prompt:

[0258] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[0259] The server receives this information and proceeds to the next step.

[0260] Step 2:

[0261] The server uses a natural language processing (NLP) module to analyze the material requirements submitted by the user. This analysis converts the requirements into a format that can be stored in a database. Once the analysis is complete, the data is stored in the database.

[0262] Input: Material requirements submitted by the user

[0263] Output: The parsed data and how it is stored in the database

[0264] Specific behavior:

[0265] The server uses an NLP module (e.g., spaCy, NLTK) to parse the prompt sentence and break it down into the elements "aluminum materials," "1,000 units," "A grade or higher," and "within 3 weeks." The parsed data is stored in a database.

[0266] Step 3:

[0267] The server generates surrogate artificial intelligence (AI) for the relevant suppliers based on the analyzed data, and simultaneously loads the user's requirements into each surrogate AI to initiate negotiations with the suppliers.

[0268] Input: Analyzed material requirements

[0269] Output: Generated surrogate AI and data for starting negotiations

[0270] Specific behavior:

[0271] The server uses the analyzed data to generate a surrogate AI for an appropriate supplier, and loads the requirement of "procure 1,000 units of A-grade aluminum materials within three weeks" into the surrogate AI, which then begins negotiations with the supplier.

[0272] Step 4:

[0273] The server uses Retrieval Augment Generation (RAG) techniques to analyze market trends and past negotiation data, and based on this, it understands current market prices and trends and provides useful information for negotiations to the surrogate AI.

[0274] Input: Market trend data, past negotiation data

[0275] Output: Market price and trend information provided to the surrogate AI

[0276] Specific behavior:

[0277] The server uses RAG techniques (e.g., the Transformers library) to analyze market trends and extract information such as "the current market price is X yen per unit." This information is fed back to the proxy AI and used during negotiations.

[0278] Step 5:

[0279] Once the negotiation is complete, the server notifies the user of the results in real time. The user can then review the results and provide feedback if necessary. This feedback is also stored in the database and used for future negotiations.

[0280] Input: Negotiation results, user feedback

[0281] Output: Negotiation results communicated to the user and feedback stored in a database

[0282] Specific behavior:

[0283] The server receives the negotiation results from the proxy AI and notifies the user of the information that "the quote from a specific supplier is Y yen, and the delivery time is Z weeks." The user checks the results and enters feedback such as "the delivery time is too short," which is then saved in the database.

[0284] This series of steps significantly improves the efficiency of material procurement within the factory and enables transactions to be made with the most suitable supplier.

[0285] 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.

[0286] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and a proxy AI automatically negotiates based on that information. Furthermore, this invention combines an emotion engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. Details of the program's processing and specific examples are provided below.

[0287] Program processing details:

[0288] The system of the present invention operates as follows.

[0289] 1. A user accesses the server

[0290] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[0291] Server: Verifies the user's credentials and starts the session.

[0292] 2. Listen to users' requests and requirements

[0293] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0294] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0295] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[0296] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[0297] 3. Creating a proxy AI and starting negotiations

[0298] Server: Based on user input, it generates surrogate AI for related players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0299] Server: Loads each surrogate AI with the user's requests, conditions, and emotional data, and initiates negotiations.

[0300] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[0301] 4. Market trend analysis and information provision using the RAG method

[0302] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0303] Server: Provides the acquired important transaction information to the user and the surrogate AI, which then uses this information to optimize negotiation strategies.

[0304] 5. Review and feedback on negotiation results

[0305] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[0306] User: Review the negotiation results and provide feedback if necessary.

[0307] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[0308] Server: Stores user feedback and emotion data in a database.

[0309] 6. Data accumulation and self-learning

[0310] Server: Accumulates negotiation data, sentiment data, and market trend data to update the dataset for self-learning by the surrogate AI.

[0311] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[0312] Server: Monitors the learning process and updates the AI ​​model as needed.

[0313] Examples:

[0314] Step 1: Enter your request

[0315] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0316] Server: "The data entered by the user has been parsed and saved to the database."

[0317] Emotion Engine: "Analyzes the user's facial expressions and generates emotion data."

[0318] Step 2: Negotiation begins with surrogate AI

[0319] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests and sentiment data..."

[0320] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0321] Step 3: Market trend analysis and information provision

[0322] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0323] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0324] Step 4: Review and feedback on negotiation results

[0325] Server: "Negotiation completed. User notified of outcome."

[0326] User: "Review the results and provide feedback."

[0327] Emotion Engine: "We analyzed users' emotions regarding the negotiation outcome and generated satisfaction data."

[0328] Step 5: Data accumulation and learning

[0329] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[0330] The system of the present invention is a new means for further improving the efficiency of negotiations and realizing fair transactions by using user emotional information.

[0331] The processing flow will be explained below.

[0332] Step 1:

[0333] User: Access the server and log in.

[0334] Server: Validates the user's credentials and initiates a session.

[0335] Step 2:

[0336] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0337] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0338] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[0339] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[0340] Step 3:

[0341] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0342] Server: Loads each surrogate AI with relevant player information, desires, conditions, and emotion data.

[0343] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[0344] Proxy AI: An internal algorithm builds a negotiation strategy based on the received conditions and emotional data.

[0345] Step 4:

[0346] Proxy AI: Proceed with negotiations based on each player's conditions and emotional data (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[0347] Server: Records the progress of negotiations in a database in real time.

[0348] Step 5:

[0349] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0350] Server: Provides acquired important transaction information to the proxy AI.

[0351] Surrogate AI: Optimizes negotiation tactics based on provided information and emotional data and continues negotiations.

[0352] Step 6:

[0353] Server: Once the negotiation is complete, aggregate all results and notify the user.

[0354] User: Review the negotiation results and provide feedback if necessary.

[0355] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[0356] Server: Stores user feedback and emotion data in a database.

[0357] Step 7:

[0358] Server: Stores negotiation data, market trend data, and sentiment data in a proprietary database.

[0359] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[0360] Server: Monitors the learning process and updates the AI ​​model as needed.

[0361] Proxy AI: Reflects learning results in the next negotiation.

[0362] Example 2

[0363] 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."

[0364] Conventional real estate transaction systems have difficulty in properly gathering the requests and conditions of each party and conducting negotiations efficiently. Furthermore, they are unable to take into account the user's feelings during the negotiation process, resulting in problems with fairness and inefficiency in transactions. Furthermore, conventional systems are unable to fully utilize market trends and past negotiation data, making it difficult to formulate optimal negotiation strategies.

[0365] 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.

[0366] In this invention, the server includes means for listening to the player's requests and conditions using a conversational AI, means for generating emotion data using an emotion processing engine that recognizes the user's emotions, and means for generating a proxy AI and negotiating based on the player's requests and conditions, thereby improving the efficiency of negotiations and enabling fair transactions that take into account the user's emotional information.

[0367] "Conversational AI" refers to AI that has the ability to listen to the player's requests and conditions, understand them, and respond appropriately.

[0368] An "emotion processing engine" refers to an engine that analyzes a user's facial expressions, tone of voice, etc., and generates emotional data about the user.

[0369] "Proxy AI" refers to an AI that negotiates with other proxy AIs based on the player's requests and conditions.

[0370] "Retrieval Augment Generation Means" refers to the method and means for retrieving information and generating additional information based on that information.

[0371] "Generated transaction information" refers to detailed information regarding transactions created through negotiations between proxy AIs.

[0372] "Market Trend Data" means data regarding current and historical market movements and trading trends.

[0373] "Self-learning" refers to the process by which artificial intelligence uses past and newly acquired data to improve its performance.

[0374] This invention is a system in which conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and then a proxy AI automatically negotiates based on that information. Furthermore, it combines an emotion processing engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. This system utilizes advanced AI technology to realize efficient and fair real estate transactions.

[0375] Hardware and software used

[0376] This system uses the following hardware and software:

[0377] server:

[0378] Various AI modules are executed using servers with high-speed processing capabilities, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[0379] Device:

[0380] Users access the system using devices such as PCs, smartphones, and tablets. These devices are connected to the Internet and users log in to the system via a web browser.

[0381] Conversational Artificial Intelligence:

[0382] Google Dialogflow and IBM Watson Assistant are used as natural language processing (NLP) modules to listen to and analyze user requests and conditions.

[0383] Emotion Processing Engine:

[0384] Microsoft Azure Emotion API and Amazon Rekognition are used as engines to analyze the user's facial expressions and tone of voice.

[0385] Deputy AI:

[0386] It is developed using machine learning libraries such as TensorFlow and PyTorch, which allows automatic negotiations to be performed on behalf of each player.

[0387] Market Analysis:

[0388] It uses Retrieval Augment Generation (RAG) techniques, specifically using Hugging Face's Transformers library to analyze market trends and historical negotiation data.

[0389] Specific examples

[0390] Step 1: Enter your request

[0391] The user enters their request into an on-screen form, such as "I'd like to purchase land in Tokyo for less than 200 million yen. I would like the construction period to be one year." The server receives this information and analyzes it using a natural language processing module. At the same time, the emotion processing engine generates emotion data from the user's facial expressions and stores this data in a database.

[0392] Step 2: Negotiation begins with surrogate AI

[0393] The server generates AIs for the landowner, construction company, building materials manufacturer, developer, real estate agent, and financial institution. These AIs receive user requests and emotional data and begin negotiations with other AIs. For example, the landowner AI adjusts the price of the land, and the construction company AI proposes the construction period.

[0394] Step 3: Market trend analysis and information provision

[0395] The server analyzes the latest market trends using the RAG method and provides key points to the surrogate AI, which then uses the information to negotiate and present the optimal terms.

[0396] Step 4: Review and feedback on negotiation results

[0397] When the negotiation is over, the server compiles all the results and notifies the user. The user checks the results and enters feedback. The emotion processing engine analyzes the user's feelings about the negotiation results and generates satisfaction data. This data is stored on the server and used for the next negotiation.

[0398] Step 5: Data accumulation and learning

[0399] The server accumulates negotiation data and emotional data and updates the dataset for the surrogate AI to self-learn. The surrogate AI uses machine learning algorithms to improve its negotiation skills. The server monitors this learning process and updates the AI ​​model as needed.

[0400] Example prompt sentence:

[0401] A user wishes to purchase land in Tokyo for less than 200 million yen. The construction period is within one year. To proceed with this negotiation, please generate AIs for the land owner, construction company, building materials manufacturer, developer, real estate agent, and financial institution, and load them with the user's requests and sentiment data. Use the RAG method to collect appropriate information based on the latest market trends and provide it as a guide for proceeding with the negotiation.

[0402] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0403] Step 1:

[0404] User: Access the system login page using a web browser, enter your user ID and password, and click the login button.

[0405] Input: User ID, Password

[0406] Output: Session ID

[0407] Specific operation: The server authenticates the user ID and password in the database, and if authentication is successful, generates a session ID and returns it to the user.

[0408] Step 2:

[0409] User: After logging in, the user is taken to a form page where they can enter their requests and conditions. They enter their budget, location, desired property type, construction period, etc. into the form and click the submit button.

[0410] Input: Budget, Location, Property Type, Construction Period

[0411] Output: Structured data, sentiment data

[0412] Specific operation: The server receives the input data and analyzes it using a natural language processing (NLP) module. At the same time, the emotion processing engine analyzes the user's facial expressions and tone of voice to generate emotion data. The server then stores the analyzed requests, conditions, and emotion data in a database.

[0413] Step 3:

[0414] Server: Based on user input information, it generates surrogate artificial intelligence (AI) for the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0415] Input: Structured data, sentiment data

[0416] Output: An instance of each surrogate AI

[0417] Specific operation: The server separately generates a landowner AI, a construction company AI, a building materials manufacturer AI, a developer AI, a real estate agent AI, and a financial institution AI, and loads the user's requests, conditions, and emotional data into each of them.

[0418] Step 4:

[0419] Each surrogate AI: Initiates communication with other surrogate AIs, shares their requests and conditions, and advances negotiations.

[0420] Input: User requests and conditions, emotional data

[0421] Output: Negotiation result data

[0422] Specific operation: Each agent AI uses its internal algorithm to formulate a strategy based on the requested requests and conditions, and negotiates with other agent AIs. For example, the landowner AI adjusts the price conditions for the land, and the building materials manufacturer AI estimates the cost of building materials.

[0423] Step 5:

[0424] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0425] Inputs: Market data, historical negotiation data

[0426] Output: Market analysis results

[0427] How it works: The server uses Hugging Face's Transformers library to collect and analyze the latest market trends and important trading information, and provides the results to each agent AI. The agent AI then uses this information to optimize its negotiation strategy.

[0428] Step 6:

[0429] Server: When each proxy AI negotiation is completed, it compiles all the results and notifies the user.

[0430] Input: Negotiation result data

[0431] Output: Final negotiation results, satisfaction data

[0432] Specific operation: The server generates a detailed report of the negotiation results and displays it on the user's dashboard. At the same time, the emotion processing engine analyzes the user's emotions regarding the negotiation results and generates satisfaction data. These data are stored in a database.

[0433] Step 7:

[0434] Server: Accumulates negotiation data, sentiment data, and market trend data, and updates the self-learning dataset.

[0435] Inputs: Negotiation data, sentiment data, market data

[0436] Output: Updated AI model

[0437] How it works: The server stores historical data and uses machine learning algorithms to train the surrogate AI. It monitors the learning process and updates the AI ​​model as needed, for example by training a new model if performance degradation is detected.

[0438] (Application example 2)

[0439] 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."

[0440] Conventional product transactions and procurement negotiations in brick-and-mortar stores are typically conducted manually, resulting in a complex and time-consuming negotiation process that is inefficient. Furthermore, the lack of a means to properly manage emotional influences during negotiations can lead to lower user satisfaction. The present invention aims to solve these problems and provide a new system for achieving efficient and fair transactions.

[0441] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0442] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, means for Retrieval Augment Generation to analyze market trends and past negotiation data, means for providing the generated transaction information to the user, means for analyzing the user's emotions and generating emotion data, and means for accumulating negotiation data, emotion data, and market trend data and performing self-learning. This enables efficient and emotion-conscious transactions in physical stores.

[0443] "Conversational AI" is an AI system that listens to and understands players' requests and conditions in natural language.

[0444] "Proxy AI" is an AI system that automatically negotiates based on the player's requests and conditions.

[0445] "Retrieval Augment Generation Method" refers to a method for analyzing market trends and past negotiation data to acquire and generate relevant information.

[0446] "Emotion data" is the analysis and conversion of a user's emotional information into data.

[0447] "Self-learning" is the process by which the system independently learns and improves its performance based on negotiation data, sentiment data, and market trend data.

[0448] "User" refers to a person who uses the system to negotiate.

[0449] The system for implementing this invention is composed of the following main components. It is realized by the cooperation of a server, a terminal, and a user. Specifically, the server includes a conversational artificial intelligence, a proxy artificial intelligence, a Retrieval Augment Generation (RAG) means, a sentiment analysis engine, and a self-learning function. The terminal receives user input using a smartphone, smart glasses, or the like.

[0450] The server uses conversational AI to listen to the user's requests and conditions and analyzes them using natural language processing. Furthermore, the server generates user emotional data using an emotion analysis engine and provides a surrogate AI that negotiates based on that data. This allows the surrogate AI to negotiate with other surrogate AIs based on the requests and conditions entered by the user, and achieves efficient negotiations by analyzing market trends and past negotiation data using the RAG method.

[0451] The hardware used includes smartphones, smart glasses, and servers, and the software used includes sentiment analysis libraries (e.g., the sentiment analysis module from Transformers) and GPT-2 models (e.g., GPT-2 from the Transformers library).

[0452] As a concrete example, suppose a user uses a smartphone to enter the following prompt sentence:

[0453] "I visited a store in Tokyo to choose a kimono, but I would like it to be offered at a reasonable price."

[0454] First, the server receives the prompt, the conversational AI analyzes the requests and conditions, and the emotion analysis engine analyzes the user's emotions. A surrogate AI is then generated and begins negotiations based on the requests and emotion data. The surrogate AI communicates with other surrogate AIs, analyzes market trends and past data using the RAG method, and proposes optimal trading terms to the user.

[0455] This system will enable efficient and emotionally sensitive transactions in brick-and-mortar stores. For example, when purchasing an expensive wine, customers can input their desired price range using their smartphone, and the AI ​​will automatically facilitate the optimal transaction and suggest discounts and special offers based on emotional analysis.

[0456] Example prompt sentence:

[0457] "The user has made the following request: Request: Offer a new product at a special price. Emotion: Joy. Based on this request, the surrogate AI will suggest an appropriate price."

[0458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0459] Step 1:

[0460] The user inputs their requests and requirements using a smartphone or smart glasses. For example, if they input a prompt such as "I'm visiting a store in Tokyo to choose a kimono, and I'd like it to be offered at a reasonable price," the input data is sent to the server.

[0461] Step 2:

[0462] The server uses conversational AI to listen to the user's requests and requirements. The input data is passed to a natural language analysis module, which analyzes the requests and requirements and converts them into structured data. The results of this analysis are stored on the server.

[0463] Step 3:

[0464] The server's emotion analysis engine generates emotion data based on the user's input. For example, it detects emotions such as joy or anger from the user's input text and stores the emotion data together with the analysis results.

[0465] Step 4:

[0466] The server generates a substitute AI based on the request and emotion data. This substitute AI has data including the user's request and conditions and prepares to communicate with other substitute AIs.

[0467] Step 5:

[0468] The agent AI initiates communication with other agent AIs to strategically advance negotiations. During communication, each agent AI shares data on conditions and market trends with each other and formulates an appropriate negotiation strategy.

[0469] Step 6:

[0470] The server obtains the latest market information using Retrieval Augment Generation, which analyzes market trends and past negotiation data. For example, it obtains market prices and demand trends for expensive products and uses them in negotiations. This information is provided to the agent AI.

[0471] Step 7:

[0472] The generated transaction information is provided to the user through a proxy AI. The transaction information includes negotiated terms, discount information, and special offers. Users can view this information on their smartphones or smart glasses.

[0473] Step 8:

[0474] The server accumulates negotiation and sentiment data and uses a self-learning algorithm to improve the model, enabling more efficient and fairer transactions in the next negotiation.

[0475] Through these steps, the system can enable efficient and emotionally sensitive negotiations, improving the quality of transactions in physical stores.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0491] 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."

[0492] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate dealers, financial institutions, and consumers), and then each player's proxy AI automatically negotiates based on those conditions. Below are details of the program's processing and a specific example.

[0493] Program processing details:

[0494] The system of the present invention operates as follows.

[0495] 1. A user accesses the server

[0496] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[0497] Server: Verifies the user's credentials and starts the session.

[0498] 2. Listen to users' requests and requirements

[0499] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0500] Server: Receives the input data, analyzes the information using a natural language processing (NLP) module, and stores it in a database.

[0501] 3. Creating a proxy AI and starting negotiations

[0502] Server: Based on the user's input information, it generates artificial intelligence representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0503] Server: Loads the user's requests and conditions into each proxy AI and initiates negotiations.

[0504] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[0505] 4. Market trend analysis and information provision using the RAG method

[0506] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0507] Server: Provides the acquired important transaction information to the user and the surrogate AI. The surrogate AI utilizes this information to optimize negotiation strategies.

[0508] 5. Review and feedback on negotiation results

[0509] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[0510] User: Review the negotiation results and provide feedback if necessary.

[0511] Server: Stores user feedback in a database.

[0512] 6. Data accumulation and self-learning

[0513] Server: Stores data on negotiations and market trends, updating the dataset for self-learning by the surrogate AI.

[0514] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[0515] Server: Monitors the learning process and updates the AI ​​model as needed.

[0516] Examples:

[0517] Step 1: Enter your request

[0518] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0519] Server: "The data entered by the user has been parsed and saved to the database."

[0520] Step 2: Negotiation begins with surrogate AI

[0521] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[0522] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0523] Step 3: Market trend analysis and information provision

[0524] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0525] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0526] Step 4: Review and feedback on negotiation results

[0527] Server: "Negotiation completed. User notified of outcome."

[0528] User: "Review the results and provide feedback."

[0529] Step 5: Data accumulation and learning

[0530] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[0531] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[0532] The processing flow will be explained below.

[0533] Step 1:

[0534] User: Access the server and log in.

[0535] Server: Validates the user's credentials and initiates a session.

[0536] Step 2:

[0537] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0538] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0539] Server: Stores the analyzed requests and conditions in a database.

[0540] Step 3:

[0541] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0542] Server: Loads each surrogate AI with the relevant player's information, wishes and conditions.

[0543] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[0544] Proxy AI: Builds a negotiation strategy using an internal algorithm based on the received conditions.

[0545] Step 4:

[0546] Proxy AI: Proceeds negotiations based on each player's conditions (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[0547] Server: Records the progress of negotiations in a database in real time.

[0548] Step 5:

[0549] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0550] Server: Provides acquired important transaction information to the proxy AI.

[0551] Proxy AI: Optimizes negotiation tactics based on the information provided and continues negotiations.

[0552] Step 6:

[0553] Server: Once the negotiation is complete, aggregate all results and notify the user.

[0554] User: Review the negotiation results and provide feedback if necessary.

[0555] Server: Stores user feedback in a database.

[0556] Step 7:

[0557] Server: Stores negotiation data and market trend data in a proprietary database.

[0558] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[0559] Server: Monitors the learning process and updates the AI ​​model as needed.

[0560] Proxy AI: Reflects learning results in the next negotiation.

[0561] Example 1

[0562] 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."

[0563] In conventional real estate transactions, negotiations between each player (landowner, construction company, building materials manufacturer, developer, real estate dealer, financial institution, and consumer) often do not proceed efficiently due to their complexity and time-consuming efforts. Furthermore, the progress and success rate of negotiations depend on the subjective judgment of each player, making it difficult to achieve a fair transaction. Furthermore, conventional systems using artificial intelligence have the problem of not being able to adequately analyze information or optimize strategies, resulting in poor transaction outcomes. The present invention aims to solve these problems and realize efficient and fair real estate transactions.

[0564] 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.

[0565] In this invention, the server includes means for using a conversational AI to hear the user's requests and conditions, means for generating a proxy AI and negotiating based on the user's requests and conditions, means for acquiring and expanding information for analyzing market trends and past negotiation data, means for providing the generated transaction information to the user, means for accumulating negotiation data and market trend data and for self-learning, means for the user to access and log in to the system using a web browser or application, means for analyzing the requests and conditions entered by the user using natural language processing and storing them in a database, means for the proxy AI to communicate with other proxy AIs to strategically advance negotiations, means for extracting important transaction information and providing it to the proxy AI and the user, and means for notifying the user of the negotiation results and receiving feedback, thereby enabling fast and efficient negotiations and fair transactions.

[0566] "Conversational artificial intelligence" is a system that uses artificial intelligence technology to converse with users in natural language and gather their requests and requirements.

[0567] "Proxy AI" is a program or system that uses AI technology to negotiate on behalf of each player.

[0568] "Information retrieval augmentation generation means" is a means of collecting and analyzing market trends and past negotiation data using the Retrieval Augment Generation (RAG) method.

[0569] "Transaction Information" refers to data relating to the results of player negotiations and market trends, and is information provided to users.

[0570] "Self-learning" is the process by which artificial intelligence uses machine learning algorithms to learn and improve its performance based on past negotiation data and market trend data.

[0571] A "web browser" is software for viewing web pages on the Internet.

[0572] An "application" is a software program designed to accomplish a particular purpose.

[0573] "Natural language processing" is a technology that processes human language using a computer to perform semantic analysis and information extraction.

[0574] A "database" is an information collection system that systematically stores data and enables it to be searched and managed.

[0575] "Feedback" refers to the results of negotiations and opinions and evaluations from users regarding their use of the system, and is information that can be used to help with future improvements and adjustments.

[0576] This invention is a system in which a conversational AI listens to the requests and conditions of each player in a real estate transaction (land owner, construction company, building material manufacturer, developer, real estate dealer, financial institution, consumer), and then a proxy AI for each player automatically negotiates based on those conditions. This system operates as follows.

[0577] 1. Hardware and software used

[0578] Hardware: Servers, devices (devices that run the web browsers and specialized applications used by users), and network infrastructure.

[0579] Software: Conversational artificial intelligence (natural language processing), surrogate artificial intelligence (machine learning algorithms), database management systems (SQL databases, NoSQL databases), web browsers (Google Chrome, Mozilla Firefox), dedicated applications.

[0580] 2. Data processing and calculation

[0581] server

[0582] Credential validation: The credentials entered by the user at login are checked against a database to verify their validity.

[0583] Natural language processing: The requests and conditions entered by the user are analyzed using a natural language processing module (e.g., spaCy or NLTK), converted into structured data, and stored in the database.

[0584] Generate surrogate AI: Based on user input data, generate surrogate AI for the relevant player using machine learning libraries such as TensorFlow or PyTorch.

[0585] RAG information analysis: We use the Retrieval Augmented Generation (RAG) method to analyze market trends and past negotiation data. Specifically, we use external data collected using scraping techniques to analyze current market trends in real time.

[0586] Notification of important information: Important transaction information obtained as a result of analysis is compiled and provided to the agent AI and users in real time.

[0587] proxy AI

[0588] Communication and negotiation: Communicate with other agent AIs via RESTful APIs, share their requests and conditions, and proceed with negotiations. Use internal algorithms to find the optimal solution for the negotiation.

[0589] Self-learning: Negotiation data and market trend data are self-learned using machine learning algorithms, and reflected in the next negotiation.

[0590] Terminal

[0591] Providing a user interface: Providing an interface for users to access the system and input their requests and requirements. Specifically, this includes form entry, button operations, etc.

[0592] Display notifications: Display the negotiation results and important information sent from the server to the user.

[0593] 3. Specific Examples

[0594] Input of user requests

[0595] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0596] Server: "The data entered by the user has been parsed and saved to the database."

[0597] Negotiations begin with proxy AI

[0598] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[0599] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0600] Market trend analysis and information provision

[0601] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0602] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0603] Confirmation and feedback of negotiation results

[0604] Server: "Negotiation completed. User notified of outcome."

[0605] User: "Review the results and provide feedback."

[0606] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0608] Processing Steps

[0609] Step 1: User Access and Login

[0610] input:

[0611] The user accesses the system's URL through a web browser or application and enters their user ID and password on the login screen.

[0612] Specific behavior:

[0613] Terminal: Launch a web browser or application and access the system URL. The login screen will appear.

[0614] User: Enter your user ID and password on the login screen and click the "Login" button.

[0615] Server: Receives the entered user ID and password and checks the authentication information against the database. If authentication is successful, the session starts and the home screen is displayed.

[0616] output:

[0617] The home screen appears, allowing the user to access the system's features.

[0618] Step 2: Enter your requirements and requirements

[0619] input:

[0620] The user enters their requests and conditions (budget, location, desired property type, construction period, etc.) into the input form on the home screen and clicks the submit button.

[0621] Specific behavior:

[0622] User: Enter requirements such as "Budget: within 200 million yen," "Location: Tokyo," and "Construction period: 1 year" into the input form on the home screen, and click the submit button.

[0623] Terminal: Sends the input form data to the server.

[0624] Server: Analyzes the received data using a natural language processing (NLP) module (e.g., spaCy or NLTK) and stores the analyzed structured data in a database.

[0625] output:

[0626] The structured data is saved in a database, which triggers the next processing step.

[0627] Step 3: Create and configure a surrogate AI

[0628] input:

[0629] Data on user requests and requirements stored on the server.

[0630] Specific behavior:

[0631] Server: Based on the user's input data, it generates surrogate AI for the relevant players (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.) using machine learning libraries such as TensorFlow and PyTorch.

[0632] Server: Loads the user's requests and conditions into the generated surrogate AI.

[0633] output:

[0634] Multiple proxy AIs are generated and loaded with the user's requests and conditions.

[0635] Step 4: Negotiation begins with surrogate AI

[0636] input:

[0637] User requests and conditions loaded into each surrogate AI.

[0638] Specific behavior:

[0639] Delegate AI: Communicates with other Delegate AIs via RESTful APIs, shares their requests and conditions, and uses internal algorithms to advance negotiations.

[0640] For example, a land owner AI might propose the condition "can be sold for 150 million yen" to another proxy AI, and the construction company AI might respond "can be constructed within the budget."

[0641] output:

[0642] Negotiations continue to progress and optimal terms are found.

[0643] Step 5: Analyze market trends and provide information

[0644] input:

[0645] Market trend information and past negotiation data collected by the server.

[0646] Specific behavior:

[0647] Server: Analyzes market trends and historical negotiation data using Retrieval Augmented Generation (RAG) techniques, specifically scraping data from external data sources and performing real-time analysis.

[0648] Server: Extracts important transaction information obtained as a result of the analysis and provides it to the proxy AI and the user.

[0649] For example, information such as "land prices in Tokyo have increased 10% compared to the previous year" is collected as a current market trend, and this information is notified to the proxy AI.

[0650] output:

[0651] Key transaction information is obtained, and the surrogate AI optimizes the negotiation strategy based on it.

[0652] Step 6: Review and feedback on negotiation results

[0653] input:

[0654] Negotiation result data and user feedback information.

[0655] Specific behavior:

[0656] Server: Once the negotiation is complete, the server consolidates all the results and notifies the user via email or in-app notification.

[0657] User: After receiving the notification, log back into the system to check the negotiation results and provide feedback if necessary.

[0658] For example, the user may input, "The negotiation process went smoothly, but I'm dissatisfied because it was over budget."

[0659] output:

[0660] The negotiation results and feedback information confirmed by the user are stored in a database.

[0661] Step 7: Data accumulation and self-learning

[0662] input:

[0663] Negotiation data and feedback information.

[0664] Specific behavior:

[0665] Server: Records negotiation data and feedback information in a database and prepares for the next negotiation.

[0666] Surrogate AI: Acquires new data and uses machine learning algorithms (e.g., reinforcement learning) to self-learn and improve negotiation tactics.

[0667] Server: Monitors the learning progress and adjusts the algorithm parameters as needed.

[0668] output:

[0669] Deputy AI with improved negotiation skills and updated systems.

[0670] (Application example 1)

[0671] 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."

[0672] Existing negotiation systems in the real estate industry have faced challenges such as the difficulty of reconciling the diverse requests and conditions between each player and the complexity of efficiently conducting optimal transactions. Furthermore, supply chain management and appropriate price negotiations are important for procuring materials within a factory, but doing this manually takes time and effort. This leads to problems such as a lack of negotiating power and an increased risk of human error.

[0673] 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.

[0674] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, Retrieval Augment Generation means for analyzing market trends and past negotiation data, means for allowing a user to input material requirements and automatically negotiate with suppliers in the procurement of materials within a factory, and means for selecting the most suitable supplier based on the material requirements and optimizing prices. This enables efficient and optimal transactions in line with the player's requests, making material procurement more efficient and reducing costs.

[0675] "Conversational AI" is AI that can have natural conversations with users via voice and text.

[0676] A "surrogate AI" is an AI generated to negotiate with other surrogate AIs based on the user's requests and conditions.

[0677] "Retrieval Augment Generation Method" is a method for automatically generating transaction information by analyzing past negotiation data and market trends.

[0678] "In-factory material procurement" is the process of properly securing materials and parts necessary for factory production activities.

[0679] "Material requirements" are the specific conditions and specifications for the materials to be procured, such as quantity, quality, and delivery date.

[0680] "Supplier" means a supplier that supplies materials and parts to the factory.

[0681] "Market trends" refers to information that refers to general trends such as the current market state and price fluctuations.

[0682] "Price optimization" is the process of procuring materials of the required quality and quantity at the optimal price while keeping costs down.

[0683] This invention is a system for in-factory material procurement and supply chain management that uses conversational AI to hear the requests and conditions of players (factory personnel, suppliers) and then uses proxy AI to efficiently automate negotiations. An embodiment of this system is shown below.

[0684] System Overview

[0685] The server is configured using the following hardware and software.

[0686] Hardware: High-performance servers, IoT devices in factories

[0687] software:

[0688] Natural Language Processing (NLP) modules (e.g., spaCy, NLTK)

[0689] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0690] Database (e.g. MySQL, MongoDB)

[0691] Libraries suitable for implementing Retrieval Augment Generation (RAG) techniques (e.g., Transformers)

[0692] Processing flow

[0693] User Input and Data Analysis

[0694] Using a terminal, factory personnel input material requirements (e.g., quantity, quality, delivery date). The server analyzes this information using a natural language processing (NLP) module and stores it in a database, allowing the input requirements to be treated as concrete data.

[0695] Creation of a surrogate AI and the start of negotiations

[0696] Based on the analyzed data, the server generates surrogate AIs for the relevant suppliers. Each surrogate AI loads the user's requirements and initiates automatic negotiations with the suppliers.

[0697] Market trend analysis

[0698] The server uses the RAG methodology to collect and analyze market trends and past negotiation data, thereby understanding current market prices and trends and providing information that can be used in negotiations.

[0699] Notification and optimization of negotiation results

[0700] After the negotiation is completed, the server notifies the user of the results in real time. The user can then review the results and enter feedback as needed. This allows the user to obtain quotes and delivery terms from the most suitable suppliers.

[0701] Specific examples

[0702] For example, a factory worker enters the following prompt:

[0703] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[0704] Based on this prompt, the server analyzes the information and generates a suitable supplier's surrogate AI. The surrogate AI then negotiates with other surrogate AIs, grasps market trends using the RAG method, and proposes the optimal price and delivery date. Finally, the negotiation results are notified to the factory staff in real time for confirmation and feedback.

[0705] This invention significantly improves the efficiency of material procurement within factories, reducing costs and strengthening supply chain risk management.

[0706] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0707] Step 1:

[0708] A user uses a terminal to input material requirements, including specific conditions such as quantity, quality, and delivery date, and the input information is sent from the terminal to the server.

[0709] Input: Material requirements (e.g. quantity, quality, delivery date)

[0710] Output: Material requirements sent to the server

[0711] Specific behavior:

[0712] The factory worker enters the following as the prompt:

[0713] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[0714] The server receives this information and proceeds to the next step.

[0715] Step 2:

[0716] The server uses a natural language processing (NLP) module to analyze the material requirements submitted by the user. This analysis converts the requirements into a format that can be stored in a database. Once the analysis is complete, the data is stored in the database.

[0717] Input: Material requirements submitted by the user

[0718] Output: The parsed data and how it is stored in the database

[0719] Specific behavior:

[0720] The server uses an NLP module (e.g., spaCy, NLTK) to parse the prompt sentence and break it down into the elements "aluminum materials," "1,000 units," "A grade or higher," and "within 3 weeks." The parsed data is stored in a database.

[0721] Step 3:

[0722] The server generates surrogate artificial intelligence (AI) for the relevant suppliers based on the analyzed data, and simultaneously loads the user's requirements into each surrogate AI to initiate negotiations with the suppliers.

[0723] Input: Analyzed material requirements

[0724] Output: Generated surrogate AI and data for starting negotiations

[0725] Specific behavior:

[0726] The server uses the analyzed data to generate a surrogate AI for an appropriate supplier, and loads the requirement of "procure 1,000 units of A-grade aluminum materials within three weeks" into the surrogate AI, which then begins negotiations with the supplier.

[0727] Step 4:

[0728] The server uses Retrieval Augment Generation (RAG) techniques to analyze market trends and past negotiation data, and based on this, it understands current market prices and trends and provides useful information for negotiations to the surrogate AI.

[0729] Input: Market trend data, past negotiation data

[0730] Output: Market price and trend information provided to the surrogate AI

[0731] Specific behavior:

[0732] The server uses RAG techniques (e.g., the Transformers library) to analyze market trends and extract information such as "the current market price is X yen per unit." This information is fed back to the proxy AI and used during negotiations.

[0733] Step 5:

[0734] Once the negotiation is complete, the server notifies the user of the results in real time. The user can then review the results and provide feedback if necessary. This feedback is also stored in the database and used for future negotiations.

[0735] Input: Negotiation results, user feedback

[0736] Output: Negotiation results communicated to the user and feedback stored in a database

[0737] Specific behavior:

[0738] The server receives the negotiation results from the proxy AI and notifies the user of the information that "the quote from a specific supplier is Y yen, and the delivery time is Z weeks." The user checks the results and enters feedback such as "the delivery time is too short," which is then saved in the database.

[0739] This series of steps significantly improves the efficiency of material procurement within the factory and enables transactions to be made with the most suitable supplier.

[0740] 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.

[0741] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and a proxy AI automatically negotiates based on that information. Furthermore, this invention combines an emotion engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. Details of the program's processing and specific examples are provided below.

[0742] Program processing details:

[0743] The system of the present invention operates as follows.

[0744] 1. A user accesses the server

[0745] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[0746] Server: Verifies the user's credentials and starts the session.

[0747] 2. Listen to users' requests and requirements

[0748] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0749] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0750] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[0751] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[0752] 3. Creating a proxy AI and starting negotiations

[0753] Server: Based on user input, it generates surrogate AI for related players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0754] Server: Loads each surrogate AI with the user's requests, conditions, and emotional data, and initiates negotiations.

[0755] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[0756] 4. Market trend analysis and information provision using the RAG method

[0757] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0758] Server: Provides the acquired important transaction information to the user and the surrogate AI, which then uses this information to optimize negotiation strategies.

[0759] 5. Review and feedback on negotiation results

[0760] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[0761] User: Review the negotiation results and provide feedback if necessary.

[0762] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[0763] Server: Stores user feedback and emotion data in a database.

[0764] 6. Data accumulation and self-learning

[0765] Server: Accumulates negotiation data, sentiment data, and market trend data to update the dataset for self-learning by the surrogate AI.

[0766] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[0767] Server: Monitors the learning process and updates the AI ​​model as needed.

[0768] Examples:

[0769] Step 1: Enter your request

[0770] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0771] Server: "The data entered by the user has been parsed and saved to the database."

[0772] Emotion Engine: "Analyzes the user's facial expressions and generates emotion data."

[0773] Step 2: Negotiation begins with surrogate AI

[0774] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests and sentiment data..."

[0775] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0776] Step 3: Market trend analysis and information provision

[0777] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0778] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0779] Step 4: Review and feedback on negotiation results

[0780] Server: "Negotiation completed. User notified of outcome."

[0781] User: "Review the results and provide feedback."

[0782] Emotion Engine: "We analyzed users' emotions regarding the negotiation outcome and generated satisfaction data."

[0783] Step 5: Data accumulation and learning

[0784] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[0785] The system of the present invention is a new means for further improving the efficiency of negotiations and realizing fair transactions by using user emotional information.

[0786] The processing flow will be explained below.

[0787] Step 1:

[0788] User: Access the server and log in.

[0789] Server: Validates the user's credentials and initiates a session.

[0790] Step 2:

[0791] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0792] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0793] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[0794] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[0795] Step 3:

[0796] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0797] Server: Loads each surrogate AI with relevant player information, desires, conditions, and emotion data.

[0798] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[0799] Proxy AI: An internal algorithm builds a negotiation strategy based on the received conditions and emotional data.

[0800] Step 4:

[0801] Proxy AI: Proceed with negotiations based on each player's conditions and emotional data (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[0802] Server: Records the progress of negotiations in a database in real time.

[0803] Step 5:

[0804] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0805] Server: Provides acquired important transaction information to the proxy AI.

[0806] Surrogate AI: Optimizes negotiation tactics based on provided information and emotional data and continues negotiations.

[0807] Step 6:

[0808] Server: Once the negotiation is complete, aggregate all results and notify the user.

[0809] User: Review the negotiation results and provide feedback if necessary.

[0810] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[0811] Server: Stores user feedback and emotion data in a database.

[0812] Step 7:

[0813] Server: Stores negotiation data, market trend data, and sentiment data in a proprietary database.

[0814] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[0815] Server: Monitors the learning process and updates the AI ​​model as needed.

[0816] Proxy AI: Reflects learning results in the next negotiation.

[0817] Example 2

[0818] 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."

[0819] Conventional real estate transaction systems have difficulty in properly gathering the requests and conditions of each party and conducting negotiations efficiently. Furthermore, they are unable to take into account the user's feelings during the negotiation process, resulting in problems with fairness and inefficiency in transactions. Furthermore, conventional systems are unable to fully utilize market trends and past negotiation data, making it difficult to formulate optimal negotiation strategies.

[0820] 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.

[0821] In this invention, the server includes means for listening to the player's requests and conditions using a conversational AI, means for generating emotion data using an emotion processing engine that recognizes the user's emotions, and means for generating a proxy AI and negotiating based on the player's requests and conditions, thereby improving the efficiency of negotiations and enabling fair transactions that take into account the user's emotional information.

[0822] "Conversational AI" refers to AI that has the ability to listen to the player's requests and conditions, understand them, and respond appropriately.

[0823] An "emotion processing engine" refers to an engine that analyzes a user's facial expressions, tone of voice, etc., and generates emotional data about the user.

[0824] "Proxy AI" refers to an AI that negotiates with other proxy AIs based on the player's requests and conditions.

[0825] "Retrieval Augment Generation Means" refers to the method and means for retrieving information and generating additional information based on that information.

[0826] "Generated transaction information" refers to detailed information regarding transactions created through negotiations between proxy AIs.

[0827] "Market Trend Data" means data regarding current and historical market movements and trading trends.

[0828] "Self-learning" refers to the process by which artificial intelligence uses past and newly acquired data to improve its performance.

[0829] This invention is a system in which conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and then a proxy AI automatically negotiates based on that information. Furthermore, it combines an emotion processing engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. This system utilizes advanced AI technology to realize efficient and fair real estate transactions.

[0830] Hardware and software used

[0831] This system uses the following hardware and software:

[0832] server:

[0833] Various AI modules are executed using servers with high-speed processing capabilities, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[0834] Device:

[0835] Users access the system using devices such as PCs, smartphones, and tablets. These devices are connected to the Internet and users log in to the system via a web browser.

[0836] Conversational Artificial Intelligence:

[0837] Google Dialogflow and IBM Watson Assistant are used as natural language processing (NLP) modules to listen to and analyze user requests and conditions.

[0838] Emotion Processing Engine:

[0839] Microsoft Azure Emotion API and Amazon Rekognition are used as engines to analyze the user's facial expressions and tone of voice.

[0840] Deputy AI:

[0841] It is developed using machine learning libraries such as TensorFlow and PyTorch, which allows automatic negotiations to be performed on behalf of each player.

[0842] Market Analysis:

[0843] It uses Retrieval Augment Generation (RAG) techniques, specifically using Hugging Face's Transformers library to analyze market trends and historical negotiation data.

[0844] Specific examples

[0845] Step 1: Enter your request

[0846] The user enters their request into an on-screen form, such as "I'd like to purchase land in Tokyo for less than 200 million yen. I would like the construction period to be one year." The server receives this information and analyzes it using a natural language processing module. At the same time, the emotion processing engine generates emotion data from the user's facial expressions and stores this data in a database.

[0847] Step 2: Negotiation begins with surrogate AI

[0848] The server generates AIs for the landowner, construction company, building materials manufacturer, developer, real estate agent, and financial institution. These AIs receive user requests and emotional data and begin negotiations with other AIs. For example, the landowner AI adjusts the price of the land, and the construction company AI proposes the construction period.

[0849] Step 3: Market trend analysis and information provision

[0850] The server analyzes the latest market trends using the RAG method and provides key points to the surrogate AI, which then uses the information to negotiate and present the optimal terms.

[0851] Step 4: Review and feedback on negotiation results

[0852] When the negotiation is over, the server compiles all the results and notifies the user. The user checks the results and enters feedback. The emotion processing engine analyzes the user's feelings about the negotiation results and generates satisfaction data. This data is stored on the server and used for the next negotiation.

[0853] Step 5: Data accumulation and learning

[0854] The server accumulates negotiation data and emotional data and updates the dataset for the surrogate AI to self-learn. The surrogate AI uses machine learning algorithms to improve its negotiation skills. The server monitors this learning process and updates the AI ​​model as needed.

[0855] Example prompt sentence:

[0856] A user wishes to purchase land in Tokyo for less than 200 million yen. The construction period is within one year. To proceed with this negotiation, please generate AIs for the land owner, construction company, building materials manufacturer, developer, real estate agent, and financial institution, and load them with the user's requests and sentiment data. Use the RAG method to collect appropriate information based on the latest market trends and provide it as a guide for proceeding with the negotiation.

[0857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0858] Step 1:

[0859] User: Access the system login page using a web browser, enter your user ID and password, and click the login button.

[0860] Input: User ID, Password

[0861] Output: Session ID

[0862] Specific operation: The server authenticates the user ID and password in the database, and if authentication is successful, generates a session ID and returns it to the user.

[0863] Step 2:

[0864] User: After logging in, the user is taken to a form page where they can enter their requests and conditions. They enter their budget, location, desired property type, construction period, etc. into the form and click the submit button.

[0865] Input: Budget, Location, Property Type, Construction Period

[0866] Output: Structured data, sentiment data

[0867] Specific operation: The server receives the input data and analyzes it using a natural language processing (NLP) module. At the same time, the emotion processing engine analyzes the user's facial expressions and tone of voice to generate emotion data. The server then stores the analyzed requests, conditions, and emotion data in a database.

[0868] Step 3:

[0869] Server: Based on user input information, it generates surrogate artificial intelligence (AI) for the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0870] Input: Structured data, sentiment data

[0871] Output: An instance of each surrogate AI

[0872] Specific operation: The server separately generates a landowner AI, a construction company AI, a building materials manufacturer AI, a developer AI, a real estate agent AI, and a financial institution AI, and loads the user's requests, conditions, and emotional data into each of them.

[0873] Step 4:

[0874] Each surrogate AI: Initiates communication with other surrogate AIs, shares their requests and conditions, and advances negotiations.

[0875] Input: User requests and conditions, emotional data

[0876] Output: Negotiation result data

[0877] Specific operation: Each agent AI uses its internal algorithm to formulate a strategy based on the requested requests and conditions, and negotiates with other agent AIs. For example, the landowner AI adjusts the price conditions for the land, and the building materials manufacturer AI estimates the cost of building materials.

[0878] Step 5:

[0879] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0880] Inputs: Market data, historical negotiation data

[0881] Output: Market analysis results

[0882] How it works: The server uses Hugging Face's Transformers library to collect and analyze the latest market trends and important trading information, and provides the results to each agent AI. The agent AI then uses this information to optimize its negotiation strategy.

[0883] Step 6:

[0884] Server: When each proxy AI negotiation is completed, it compiles all the results and notifies the user.

[0885] Input: Negotiation result data

[0886] Output: Final negotiation results, satisfaction data

[0887] Specific operation: The server generates a detailed report of the negotiation results and displays it on the user's dashboard. At the same time, the emotion processing engine analyzes the user's emotions regarding the negotiation results and generates satisfaction data. These data are stored in a database.

[0888] Step 7:

[0889] Server: Accumulates negotiation data, sentiment data, and market trend data, and updates the self-learning dataset.

[0890] Inputs: Negotiation data, sentiment data, market data

[0891] Output: Updated AI model

[0892] How it works: The server stores historical data and uses machine learning algorithms to train the surrogate AI. It monitors the learning process and updates the AI ​​model as needed, for example by training a new model if performance degradation is detected.

[0893] (Application example 2)

[0894] 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."

[0895] Conventional product transactions and procurement negotiations in brick-and-mortar stores are typically conducted manually, resulting in a complex and time-consuming negotiation process that is inefficient. Furthermore, the lack of a means to properly manage emotional influences during negotiations can lead to lower user satisfaction. The present invention aims to solve these problems and provide a new system for achieving efficient and fair transactions.

[0896] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0897] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, means for Retrieval Augment Generation to analyze market trends and past negotiation data, means for providing the generated transaction information to the user, means for analyzing the user's emotions and generating emotion data, and means for accumulating negotiation data, emotion data, and market trend data and performing self-learning. This enables efficient and emotion-conscious transactions in physical stores.

[0898] "Conversational AI" is an AI system that listens to and understands players' requests and conditions in natural language.

[0899] "Proxy AI" is an AI system that automatically negotiates based on the player's requests and conditions.

[0900] "Retrieval Augment Generation Method" refers to a method for analyzing market trends and past negotiation data to acquire and generate relevant information.

[0901] "Emotion data" is the analysis and conversion of a user's emotional information into data.

[0902] "Self-learning" is the process by which the system independently learns and improves its performance based on negotiation data, sentiment data, and market trend data.

[0903] "User" refers to a person who uses the system to negotiate.

[0904] The system for implementing this invention is composed of the following main components. It is realized by the cooperation of a server, a terminal, and a user. Specifically, the server includes a conversational artificial intelligence, a proxy artificial intelligence, a Retrieval Augment Generation (RAG) means, a sentiment analysis engine, and a self-learning function. The terminal receives user input using a smartphone, smart glasses, or the like.

[0905] The server uses conversational AI to listen to the user's requests and conditions and analyzes them using natural language processing. Furthermore, the server generates user emotional data using an emotion analysis engine and provides a surrogate AI that negotiates based on that data. This allows the surrogate AI to negotiate with other surrogate AIs based on the requests and conditions entered by the user, and achieves efficient negotiations by analyzing market trends and past negotiation data using the RAG method.

[0906] The hardware used includes smartphones, smart glasses, and servers, and the software used includes sentiment analysis libraries (e.g., the sentiment analysis module from Transformers) and GPT-2 models (e.g., GPT-2 from the Transformers library).

[0907] As a concrete example, suppose a user uses a smartphone to enter the following prompt sentence:

[0908] "I visited a store in Tokyo to choose a kimono, but I would like it to be offered at a reasonable price."

[0909] First, the server receives the prompt, the conversational AI analyzes the requests and conditions, and the emotion analysis engine analyzes the user's emotions. A surrogate AI is then generated and begins negotiations based on the requests and emotion data. The surrogate AI communicates with other surrogate AIs, analyzes market trends and past data using the RAG method, and proposes optimal trading terms to the user.

[0910] This system will enable efficient and emotionally sensitive transactions in brick-and-mortar stores. For example, when purchasing an expensive wine, customers can input their desired price range using their smartphone, and the AI ​​will automatically facilitate the optimal transaction and suggest discounts and special offers based on emotional analysis.

[0911] Example prompt sentence:

[0912] "The user has made the following request: Request: Offer a new product at a special price. Emotion: Joy. Based on this request, the surrogate AI will suggest an appropriate price."

[0913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0914] Step 1:

[0915] The user inputs their requests and requirements using a smartphone or smart glasses. For example, if they input a prompt such as "I'm visiting a store in Tokyo to choose a kimono, and I'd like it to be offered at a reasonable price," the input data is sent to the server.

[0916] Step 2:

[0917] The server uses conversational AI to listen to the user's requests and requirements. The input data is passed to a natural language analysis module, which analyzes the requests and requirements and converts them into structured data. The results of this analysis are stored on the server.

[0918] Step 3:

[0919] The server's emotion analysis engine generates emotion data based on the user's input. For example, it detects emotions such as joy or anger from the user's input text and stores the emotion data together with the analysis results.

[0920] Step 4:

[0921] The server generates a substitute AI based on the request and emotion data. This substitute AI has data including the user's request and conditions and prepares to communicate with other substitute AIs.

[0922] Step 5:

[0923] The agent AI initiates communication with other agent AIs to strategically advance negotiations. During communication, each agent AI shares data on conditions and market trends with each other and formulates an appropriate negotiation strategy.

[0924] Step 6:

[0925] The server obtains the latest market information using Retrieval Augment Generation, which analyzes market trends and past negotiation data. For example, it obtains market prices and demand trends for expensive products and uses them in negotiations. This information is provided to the agent AI.

[0926] Step 7:

[0927] The generated transaction information is provided to the user through a proxy AI. The transaction information includes negotiated terms, discount information, and special offers. Users can view this information on their smartphones or smart glasses.

[0928] Step 8:

[0929] The server accumulates negotiation and sentiment data and uses a self-learning algorithm to improve the model, enabling more efficient and fairer transactions in the next negotiation.

[0930] Through these steps, the system can enable efficient and emotionally sensitive negotiations, improving the quality of transactions in physical stores.

[0931] 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.

[0932] 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.

[0933] 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.

[0934] [Third embodiment]

[0935] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0936] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0937] 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).

[0938] 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.

[0939] 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.

[0940] 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).

[0941] 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.

[0942] 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.

[0943] 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.

[0944] 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.

[0945] 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.

[0946] 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."

[0947] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate dealers, financial institutions, and consumers), and then each player's proxy AI automatically negotiates based on those conditions. Below are details of the program's processing and a specific example.

[0948] Program processing details:

[0949] The system of the present invention operates as follows.

[0950] 1. A user accesses the server

[0951] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[0952] Server: Verifies the user's credentials and starts the session.

[0953] 2. Listen to users' requests and requirements

[0954] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0955] Server: Receives the input data, analyzes the information using a natural language processing (NLP) module, and stores it in a database.

[0956] 3. Creating a proxy AI and starting negotiations

[0957] Server: Based on the user's input information, it generates artificial intelligence representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0958] Server: Loads the user's requests and conditions into each proxy AI and initiates negotiations.

[0959] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[0960] 4. Market trend analysis and information provision using the RAG method

[0961] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[0962] Server: Provides the acquired important transaction information to the user and the surrogate AI. The surrogate AI utilizes this information to optimize negotiation strategies.

[0963] 5. Review and feedback on negotiation results

[0964] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[0965] User: Review the negotiation results and provide feedback if necessary.

[0966] Server: Stores user feedback in a database.

[0967] 6. Data accumulation and self-learning

[0968] Server: Stores data on negotiations and market trends, updating the dataset for self-learning by the surrogate AI.

[0969] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[0970] Server: Monitors the learning process and updates the AI ​​model as needed.

[0971] Examples:

[0972] Step 1: Enter your request

[0973] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[0974] Server: "The data entered by the user has been parsed and saved to the database."

[0975] Step 2: Negotiation begins with surrogate AI

[0976] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[0977] Proxy AI: "I will begin negotiations with other Proxy AIs."

[0978] Step 3: Market trend analysis and information provision

[0979] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[0980] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[0981] Step 4: Review and feedback on negotiation results

[0982] Server: "Negotiation completed. User notified of outcome."

[0983] User: "Review the results and provide feedback."

[0984] Step 5: Data accumulation and learning

[0985] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[0986] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] User: Access the server and log in.

[0990] Server: Validates the user's credentials and initiates a session.

[0991] Step 2:

[0992] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[0993] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[0994] Server: Stores the analyzed requests and conditions in a database.

[0995] Step 3:

[0996] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[0997] Server: Loads each surrogate AI with the relevant player's information, wishes and conditions.

[0998] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[0999] Proxy AI: Builds a negotiation strategy using an internal algorithm based on the received conditions.

[1000] Step 4:

[1001] Proxy AI: Proceeds negotiations based on each player's conditions (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[1002] Server: Records the progress of negotiations in a database in real time.

[1003] Step 5:

[1004] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1005] Server: Provides acquired important transaction information to the proxy AI.

[1006] Proxy AI: Optimizes negotiation tactics based on the information provided and continues negotiations.

[1007] Step 6:

[1008] Server: Once the negotiation is complete, aggregate all results and notify the user.

[1009] User: Review the negotiation results and provide feedback if necessary.

[1010] Server: Stores user feedback in a database.

[1011] Step 7:

[1012] Server: Stores negotiation data and market trend data in a proprietary database.

[1013] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[1014] Server: Monitors the learning process and updates the AI ​​model as needed.

[1015] Proxy AI: Reflects learning results in the next negotiation.

[1016] Example 1

[1017] 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."

[1018] In conventional real estate transactions, negotiations between each player (landowner, construction company, building materials manufacturer, developer, real estate dealer, financial institution, and consumer) often do not proceed efficiently due to their complexity and time-consuming efforts. Furthermore, the progress and success rate of negotiations depend on the subjective judgment of each player, making it difficult to achieve a fair transaction. Furthermore, conventional systems using artificial intelligence have the problem of not being able to adequately analyze information or optimize strategies, resulting in poor transaction outcomes. The present invention aims to solve these problems and realize efficient and fair real estate transactions.

[1019] 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.

[1020] In this invention, the server includes means for using a conversational AI to hear the user's requests and conditions, means for generating a proxy AI and negotiating based on the user's requests and conditions, means for acquiring and expanding information for analyzing market trends and past negotiation data, means for providing the generated transaction information to the user, means for accumulating negotiation data and market trend data and for self-learning, means for the user to access and log in to the system using a web browser or application, means for analyzing the requests and conditions entered by the user using natural language processing and storing them in a database, means for the proxy AI to communicate with other proxy AIs to strategically advance negotiations, means for extracting important transaction information and providing it to the proxy AI and the user, and means for notifying the user of the negotiation results and receiving feedback, thereby enabling fast and efficient negotiations and fair transactions.

[1021] "Conversational artificial intelligence" is a system that uses artificial intelligence technology to converse with users in natural language and gather their requests and requirements.

[1022] "Proxy AI" is a program or system that uses AI technology to negotiate on behalf of each player.

[1023] "Information retrieval augmentation generation means" is a means of collecting and analyzing market trends and past negotiation data using the Retrieval Augment Generation (RAG) method.

[1024] "Transaction Information" refers to data relating to the results of player negotiations and market trends, and is information provided to users.

[1025] "Self-learning" is the process by which artificial intelligence uses machine learning algorithms to learn and improve its performance based on past negotiation data and market trend data.

[1026] A "web browser" is software for viewing web pages on the Internet.

[1027] An "application" is a software program designed to accomplish a particular purpose.

[1028] "Natural language processing" is a technology that processes human language using a computer to perform semantic analysis and information extraction.

[1029] A "database" is an information collection system that systematically stores data and enables it to be searched and managed.

[1030] "Feedback" refers to the results of negotiations and opinions and evaluations from users regarding their use of the system, and is information that can be used to help with future improvements and adjustments.

[1031] This invention is a system in which a conversational AI listens to the requests and conditions of each player in a real estate transaction (land owner, construction company, building material manufacturer, developer, real estate dealer, financial institution, consumer), and then a proxy AI for each player automatically negotiates based on those conditions. This system operates as follows.

[1032] 1. Hardware and software used

[1033] Hardware: Servers, devices (devices that run the web browsers and specialized applications used by users), and network infrastructure.

[1034] Software: Conversational artificial intelligence (natural language processing), surrogate artificial intelligence (machine learning algorithms), database management systems (SQL databases, NoSQL databases), web browsers (Google Chrome, Mozilla Firefox), dedicated applications.

[1035] 2. Data processing and calculation

[1036] server

[1037] Credential validation: The credentials entered by the user at login are checked against a database to verify their validity.

[1038] Natural language processing: The requests and conditions entered by the user are analyzed using a natural language processing module (e.g., spaCy or NLTK), converted into structured data, and stored in the database.

[1039] Generate surrogate AI: Based on user input data, generate surrogate AI for the relevant player using machine learning libraries such as TensorFlow or PyTorch.

[1040] RAG information analysis: We use the Retrieval Augmented Generation (RAG) method to analyze market trends and past negotiation data. Specifically, we use external data collected using scraping techniques to analyze current market trends in real time.

[1041] Notification of important information: Important transaction information obtained as a result of analysis is compiled and provided to the agent AI and users in real time.

[1042] proxy AI

[1043] Communication and negotiation: Communicate with other agent AIs via RESTful APIs, share their requests and conditions, and proceed with negotiations. Use internal algorithms to find the optimal solution for the negotiation.

[1044] Self-learning: Negotiation data and market trend data are self-learned using machine learning algorithms, and reflected in the next negotiation.

[1045] Terminal

[1046] Providing a user interface: Providing an interface for users to access the system and input their requests and requirements. Specifically, this includes form entry, button operations, etc.

[1047] Display notifications: Display the negotiation results and important information sent from the server to the user.

[1048] 3. Specific Examples

[1049] Input of user requests

[1050] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[1051] Server: "The data entered by the user has been parsed and saved to the database."

[1052] Negotiations begin with proxy AI

[1053] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[1054] Proxy AI: "I will begin negotiations with other Proxy AIs."

[1055] Market trend analysis and information provision

[1056] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[1057] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[1058] Confirmation and feedback of negotiation results

[1059] Server: "Negotiation completed. User notified of outcome."

[1060] User: "Review the results and provide feedback."

[1061] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[1062] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1063] Processing Steps

[1064] Step 1: User Access and Login

[1065] input:

[1066] The user accesses the system's URL through a web browser or application and enters their user ID and password on the login screen.

[1067] Specific behavior:

[1068] Terminal: Launch a web browser or application and access the system URL. The login screen will appear.

[1069] User: Enter your user ID and password on the login screen and click the "Login" button.

[1070] Server: Receives the entered user ID and password and checks the authentication information against the database. If authentication is successful, the session starts and the home screen is displayed.

[1071] output:

[1072] The home screen appears, allowing the user to access the system's features.

[1073] Step 2: Enter your requirements and requirements

[1074] input:

[1075] The user enters their requests and conditions (budget, location, desired property type, construction period, etc.) into the input form on the home screen and clicks the submit button.

[1076] Specific behavior:

[1077] User: Enter requirements such as "Budget: within 200 million yen," "Location: Tokyo," and "Construction period: 1 year" into the input form on the home screen, and click the submit button.

[1078] Terminal: Sends the input form data to the server.

[1079] Server: Analyzes the received data using a natural language processing (NLP) module (e.g., spaCy or NLTK) and stores the analyzed structured data in a database.

[1080] output:

[1081] The structured data is saved in a database, which triggers the next processing step.

[1082] Step 3: Create and configure a surrogate AI

[1083] input:

[1084] Data on user requests and requirements stored on the server.

[1085] Specific behavior:

[1086] Server: Based on the user's input data, it generates surrogate AI for the relevant players (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.) using machine learning libraries such as TensorFlow and PyTorch.

[1087] Server: Loads the user's requests and conditions into the generated surrogate AI.

[1088] output:

[1089] Multiple proxy AIs are generated and loaded with the user's requests and conditions.

[1090] Step 4: Negotiation begins with surrogate AI

[1091] input:

[1092] User requests and conditions loaded into each surrogate AI.

[1093] Specific behavior:

[1094] Delegate AI: Communicates with other Delegate AIs via RESTful APIs, shares their requests and conditions, and uses internal algorithms to advance negotiations.

[1095] For example, a land owner AI might propose the condition "can be sold for 150 million yen" to another proxy AI, and the construction company AI might respond "can be constructed within the budget."

[1096] output:

[1097] Negotiations continue to progress and optimal terms are found.

[1098] Step 5: Analyze market trends and provide information

[1099] input:

[1100] Market trend information and past negotiation data collected by the server.

[1101] Specific behavior:

[1102] Server: Analyzes market trends and historical negotiation data using Retrieval Augmented Generation (RAG) techniques, specifically scraping data from external data sources and performing real-time analysis.

[1103] Server: Extracts important transaction information obtained as a result of the analysis and provides it to the proxy AI and the user.

[1104] For example, information such as "land prices in Tokyo have increased 10% compared to the previous year" is collected as a current market trend, and this information is notified to the proxy AI.

[1105] output:

[1106] Key transaction information is obtained, and the surrogate AI optimizes the negotiation strategy based on it.

[1107] Step 6: Review and feedback on negotiation results

[1108] input:

[1109] Negotiation result data and user feedback information.

[1110] Specific behavior:

[1111] Server: Once the negotiation is complete, the server consolidates all the results and notifies the user via email or in-app notification.

[1112] User: After receiving the notification, log back into the system to check the negotiation results and provide feedback if necessary.

[1113] For example, the user may input, "The negotiation process went smoothly, but I'm dissatisfied because it was over budget."

[1114] output:

[1115] The negotiation results and feedback information confirmed by the user are stored in a database.

[1116] Step 7: Data accumulation and self-learning

[1117] input:

[1118] Negotiation data and feedback information.

[1119] Specific behavior:

[1120] Server: Records negotiation data and feedback information in a database and prepares for the next negotiation.

[1121] Surrogate AI: Acquires new data and uses machine learning algorithms (e.g., reinforcement learning) to self-learn and improve negotiation tactics.

[1122] Server: Monitors the learning progress and adjusts the algorithm parameters as needed.

[1123] output:

[1124] Deputy AI with improved negotiation skills and updated systems.

[1125] (Application example 1)

[1126] 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."

[1127] Existing negotiation systems in the real estate industry have faced challenges such as the difficulty of reconciling the diverse requests and conditions between each player and the complexity of efficiently conducting optimal transactions. Furthermore, supply chain management and appropriate price negotiations are important for procuring materials within a factory, but doing this manually takes time and effort. This leads to problems such as a lack of negotiating power and an increased risk of human error.

[1128] 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.

[1129] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, Retrieval Augment Generation means for analyzing market trends and past negotiation data, means for allowing a user to input material requirements and automatically negotiate with suppliers in the procurement of materials within a factory, and means for selecting the most suitable supplier based on the material requirements and optimizing prices. This enables efficient and optimal transactions in line with the player's requests, making material procurement more efficient and reducing costs.

[1130] "Conversational AI" is AI that can have natural conversations with users via voice and text.

[1131] A "surrogate AI" is an AI generated to negotiate with other surrogate AIs based on the user's requests and conditions.

[1132] "Retrieval Augment Generation Method" is a method for automatically generating transaction information by analyzing past negotiation data and market trends.

[1133] "In-factory material procurement" is the process of properly securing materials and parts necessary for factory production activities.

[1134] "Material requirements" are the specific conditions and specifications for the materials to be procured, such as quantity, quality, and delivery date.

[1135] "Supplier" means a supplier that supplies materials and parts to the factory.

[1136] "Market trends" refers to information that refers to general trends such as the current market state and price fluctuations.

[1137] "Price optimization" is the process of procuring materials of the required quality and quantity at the optimal price while keeping costs down.

[1138] This invention is a system for in-factory material procurement and supply chain management that uses conversational AI to hear the requests and conditions of players (factory personnel, suppliers) and then uses proxy AI to efficiently automate negotiations. An embodiment of this system is shown below.

[1139] System Overview

[1140] The server is configured using the following hardware and software.

[1141] Hardware: High-performance servers, IoT devices in factories

[1142] software:

[1143] Natural Language Processing (NLP) modules (e.g., spaCy, NLTK)

[1144] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1145] Database (e.g. MySQL, MongoDB)

[1146] Libraries suitable for implementing Retrieval Augment Generation (RAG) techniques (e.g., Transformers)

[1147] Processing flow

[1148] User Input and Data Analysis

[1149] Using a terminal, factory personnel input material requirements (e.g., quantity, quality, delivery date). The server analyzes this information using a natural language processing (NLP) module and stores it in a database, allowing the input requirements to be treated as concrete data.

[1150] Creation of a surrogate AI and the start of negotiations

[1151] Based on the analyzed data, the server generates surrogate AIs for the relevant suppliers. Each surrogate AI loads the user's requirements and initiates automatic negotiations with the suppliers.

[1152] Market trend analysis

[1153] The server uses the RAG methodology to collect and analyze market trends and past negotiation data, thereby understanding current market prices and trends and providing information that can be used in negotiations.

[1154] Notification and optimization of negotiation results

[1155] After the negotiation is completed, the server notifies the user of the results in real time. The user can then review the results and enter feedback as needed. This allows the user to obtain quotes and delivery terms from the most suitable suppliers.

[1156] Specific examples

[1157] For example, a factory worker enters the following prompt:

[1158] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[1159] Based on this prompt, the server analyzes the information and generates a suitable supplier's surrogate AI. The surrogate AI then negotiates with other surrogate AIs, grasps market trends using the RAG method, and proposes the optimal price and delivery date. Finally, the negotiation results are notified to the factory staff in real time for confirmation and feedback.

[1160] This invention significantly improves the efficiency of material procurement within factories, reducing costs and strengthening supply chain risk management.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] A user uses a terminal to input material requirements, including specific conditions such as quantity, quality, and delivery date, and the input information is sent from the terminal to the server.

[1164] Input: Material requirements (e.g. quantity, quality, delivery date)

[1165] Output: Material requirements sent to the server

[1166] Specific behavior:

[1167] The factory worker enters the following as the prompt:

[1168] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[1169] The server receives this information and proceeds to the next step.

[1170] Step 2:

[1171] The server uses a natural language processing (NLP) module to analyze the material requirements submitted by the user. This analysis converts the requirements into a format that can be stored in a database. Once the analysis is complete, the data is stored in the database.

[1172] Input: Material requirements submitted by the user

[1173] Output: The parsed data and how it is stored in the database

[1174] Specific behavior:

[1175] The server uses an NLP module (e.g., spaCy, NLTK) to parse the prompt sentence and break it down into the elements "aluminum materials," "1,000 units," "A grade or higher," and "within 3 weeks." The parsed data is stored in a database.

[1176] Step 3:

[1177] The server generates surrogate artificial intelligence (AI) for the relevant suppliers based on the analyzed data, and simultaneously loads the user's requirements into each surrogate AI to initiate negotiations with the suppliers.

[1178] Input: Analyzed material requirements

[1179] Output: Generated surrogate AI and data for starting negotiations

[1180] Specific behavior:

[1181] The server uses the analyzed data to generate a surrogate AI for an appropriate supplier, and loads the requirement of "procure 1,000 units of A-grade aluminum materials within three weeks" into the surrogate AI, which then begins negotiations with the supplier.

[1182] Step 4:

[1183] The server uses Retrieval Augment Generation (RAG) techniques to analyze market trends and past negotiation data, and based on this, it understands current market prices and trends and provides useful information for negotiations to the surrogate AI.

[1184] Input: Market trend data, past negotiation data

[1185] Output: Market price and trend information provided to the surrogate AI

[1186] Specific behavior:

[1187] The server uses RAG techniques (e.g., the Transformers library) to analyze market trends and extract information such as "the current market price is X yen per unit." This information is fed back to the proxy AI and used during negotiations.

[1188] Step 5:

[1189] Once the negotiation is complete, the server notifies the user of the results in real time. The user can then review the results and provide feedback if necessary. This feedback is also stored in the database and used for future negotiations.

[1190] Input: Negotiation results, user feedback

[1191] Output: Negotiation results communicated to the user and feedback stored in a database

[1192] Specific behavior:

[1193] The server receives the negotiation results from the proxy AI and notifies the user of the information that "the quote from a specific supplier is Y yen, and the delivery time is Z weeks." The user checks the results and enters feedback such as "the delivery time is too short," which is then saved in the database.

[1194] This series of steps significantly improves the efficiency of material procurement within the factory and enables transactions to be made with the most suitable supplier.

[1195] 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.

[1196] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and a proxy AI automatically negotiates based on that information. Furthermore, this invention combines an emotion engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. Details of the program's processing and specific examples are provided below.

[1197] Program processing details:

[1198] The system of the present invention operates as follows.

[1199] 1. A user accesses the server

[1200] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[1201] Server: Verifies the user's credentials and starts the session.

[1202] 2. Listen to users' requests and requirements

[1203] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[1204] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[1205] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[1206] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[1207] 3. Creating a proxy AI and starting negotiations

[1208] Server: Based on user input, it generates surrogate AI for related players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1209] Server: Loads each surrogate AI with the user's requests, conditions, and emotional data, and initiates negotiations.

[1210] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[1211] 4. Market trend analysis and information provision using the RAG method

[1212] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1213] Server: Provides the acquired important transaction information to the user and the surrogate AI, which then uses this information to optimize negotiation strategies.

[1214] 5. Review and feedback on negotiation results

[1215] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[1216] User: Review the negotiation results and provide feedback if necessary.

[1217] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[1218] Server: Stores user feedback and emotion data in a database.

[1219] 6. Data accumulation and self-learning

[1220] Server: Accumulates negotiation data, sentiment data, and market trend data to update the dataset for self-learning by the surrogate AI.

[1221] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[1222] Server: Monitors the learning process and updates the AI ​​model as needed.

[1223] Examples:

[1224] Step 1: Enter your request

[1225] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[1226] Server: "The data entered by the user has been parsed and saved to the database."

[1227] Emotion Engine: "Analyzes the user's facial expressions and generates emotion data."

[1228] Step 2: Negotiation begins with surrogate AI

[1229] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests and sentiment data..."

[1230] Proxy AI: "I will begin negotiations with other Proxy AIs."

[1231] Step 3: Market trend analysis and information provision

[1232] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[1233] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[1234] Step 4: Review and feedback on negotiation results

[1235] Server: "Negotiation completed. User notified of outcome."

[1236] User: "Review the results and provide feedback."

[1237] Emotion Engine: "We analyzed users' emotions regarding the negotiation outcome and generated satisfaction data."

[1238] Step 5: Data accumulation and learning

[1239] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[1240] The system of the present invention is a new means for further improving the efficiency of negotiations and realizing fair transactions by using user emotional information.

[1241] The processing flow will be explained below.

[1242] Step 1:

[1243] User: Access the server and log in.

[1244] Server: Validates the user's credentials and initiates a session.

[1245] Step 2:

[1246] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[1247] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[1248] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[1249] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[1250] Step 3:

[1251] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1252] Server: Loads each surrogate AI with relevant player information, desires, conditions, and emotion data.

[1253] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[1254] Proxy AI: An internal algorithm builds a negotiation strategy based on the received conditions and emotional data.

[1255] Step 4:

[1256] Proxy AI: Proceed with negotiations based on each player's conditions and emotional data (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[1257] Server: Records the progress of negotiations in a database in real time.

[1258] Step 5:

[1259] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1260] Server: Provides acquired important transaction information to the proxy AI.

[1261] Surrogate AI: Optimizes negotiation tactics based on provided information and emotional data and continues negotiations.

[1262] Step 6:

[1263] Server: Once the negotiation is complete, aggregate all results and notify the user.

[1264] User: Review the negotiation results and provide feedback if necessary.

[1265] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[1266] Server: Stores user feedback and emotion data in a database.

[1267] Step 7:

[1268] Server: Stores negotiation data, market trend data, and sentiment data in a proprietary database.

[1269] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[1270] Server: Monitors the learning process and updates the AI ​​model as needed.

[1271] Proxy AI: Reflects learning results in the next negotiation.

[1272] Example 2

[1273] 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."

[1274] Conventional real estate transaction systems have difficulty in properly gathering the requests and conditions of each party and conducting negotiations efficiently. Furthermore, they are unable to take into account the user's feelings during the negotiation process, resulting in problems with fairness and inefficiency in transactions. Furthermore, conventional systems are unable to fully utilize market trends and past negotiation data, making it difficult to formulate optimal negotiation strategies.

[1275] 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.

[1276] In this invention, the server includes means for listening to the player's requests and conditions using a conversational AI, means for generating emotion data using an emotion processing engine that recognizes the user's emotions, and means for generating a proxy AI and negotiating based on the player's requests and conditions, thereby improving the efficiency of negotiations and enabling fair transactions that take into account the user's emotional information.

[1277] "Conversational AI" refers to AI that has the ability to listen to the player's requests and conditions, understand them, and respond appropriately.

[1278] An "emotion processing engine" refers to an engine that analyzes a user's facial expressions, tone of voice, etc., and generates emotional data about the user.

[1279] "Proxy AI" refers to an AI that negotiates with other proxy AIs based on the player's requests and conditions.

[1280] "Retrieval Augment Generation Means" refers to the method and means for retrieving information and generating additional information based on that information.

[1281] "Generated transaction information" refers to detailed information regarding transactions created through negotiations between proxy AIs.

[1282] "Market Trend Data" means data regarding current and historical market movements and trading trends.

[1283] "Self-learning" refers to the process by which artificial intelligence uses past and newly acquired data to improve its performance.

[1284] This invention is a system in which conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and then a proxy AI automatically negotiates based on that information. Furthermore, it combines an emotion processing engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. This system utilizes advanced AI technology to realize efficient and fair real estate transactions.

[1285] Hardware and software used

[1286] This system uses the following hardware and software:

[1287] server:

[1288] Various AI modules are executed using servers with high-speed processing capabilities, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[1289] Device:

[1290] Users access the system using devices such as PCs, smartphones, and tablets. These devices are connected to the Internet and users log in to the system via a web browser.

[1291] Conversational Artificial Intelligence:

[1292] Google Dialogflow and IBM Watson Assistant are used as natural language processing (NLP) modules to listen to and analyze user requests and conditions.

[1293] Emotion Processing Engine:

[1294] Microsoft Azure Emotion API and Amazon Rekognition are used as engines to analyze the user's facial expressions and tone of voice.

[1295] Deputy AI:

[1296] It is developed using machine learning libraries such as TensorFlow and PyTorch, which allows automatic negotiations to be performed on behalf of each player.

[1297] Market Analysis:

[1298] It uses Retrieval Augment Generation (RAG) techniques, specifically using Hugging Face's Transformers library to analyze market trends and historical negotiation data.

[1299] Specific examples

[1300] Step 1: Enter your request

[1301] The user enters their request into an on-screen form, such as "I'd like to purchase land in Tokyo for less than 200 million yen. I would like the construction period to be one year." The server receives this information and analyzes it using a natural language processing module. At the same time, the emotion processing engine generates emotion data from the user's facial expressions and stores this data in a database.

[1302] Step 2: Negotiation begins with surrogate AI

[1303] The server generates AIs for the landowner, construction company, building materials manufacturer, developer, real estate agent, and financial institution. These AIs receive user requests and emotional data and begin negotiations with other AIs. For example, the landowner AI adjusts the price of the land, and the construction company AI proposes the construction period.

[1304] Step 3: Market trend analysis and information provision

[1305] The server analyzes the latest market trends using the RAG method and provides key points to the surrogate AI, which then uses the information to negotiate and present the optimal terms.

[1306] Step 4: Review and feedback on negotiation results

[1307] When the negotiation is over, the server compiles all the results and notifies the user. The user checks the results and enters feedback. The emotion processing engine analyzes the user's feelings about the negotiation results and generates satisfaction data. This data is stored on the server and used for the next negotiation.

[1308] Step 5: Data accumulation and learning

[1309] The server accumulates negotiation data and emotional data and updates the dataset for the surrogate AI to self-learn. The surrogate AI uses machine learning algorithms to improve its negotiation skills. The server monitors this learning process and updates the AI ​​model as needed.

[1310] Example prompt sentence:

[1311] A user wishes to purchase land in Tokyo for less than 200 million yen. The construction period is within one year. To proceed with this negotiation, please generate AIs for the land owner, construction company, building materials manufacturer, developer, real estate agent, and financial institution, and load them with the user's requests and sentiment data. Use the RAG method to collect appropriate information based on the latest market trends and provide it as a guide for proceeding with the negotiation.

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1:

[1314] User: Access the system login page using a web browser, enter your user ID and password, and click the login button.

[1315] Input: User ID, Password

[1316] Output: Session ID

[1317] Specific operation: The server authenticates the user ID and password in the database, and if authentication is successful, generates a session ID and returns it to the user.

[1318] Step 2:

[1319] User: After logging in, the user is taken to a form page where they can enter their requests and conditions. They enter their budget, location, desired property type, construction period, etc. into the form and click the submit button.

[1320] Input: Budget, Location, Property Type, Construction Period

[1321] Output: Structured data, sentiment data

[1322] Specific operation: The server receives the input data and analyzes it using a natural language processing (NLP) module. At the same time, the emotion processing engine analyzes the user's facial expressions and tone of voice to generate emotion data. The server then stores the analyzed requests, conditions, and emotion data in a database.

[1323] Step 3:

[1324] Server: Based on user input information, it generates surrogate artificial intelligence (AI) for the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1325] Input: Structured data, sentiment data

[1326] Output: An instance of each surrogate AI

[1327] Specific operation: The server separately generates a landowner AI, a construction company AI, a building materials manufacturer AI, a developer AI, a real estate agent AI, and a financial institution AI, and loads the user's requests, conditions, and emotional data into each of them.

[1328] Step 4:

[1329] Each surrogate AI: Initiates communication with other surrogate AIs, shares their requests and conditions, and advances negotiations.

[1330] Input: User requests and conditions, emotional data

[1331] Output: Negotiation result data

[1332] Specific operation: Each agent AI uses its internal algorithm to formulate a strategy based on the requested requests and conditions, and negotiates with other agent AIs. For example, the landowner AI adjusts the price conditions for the land, and the building materials manufacturer AI estimates the cost of building materials.

[1333] Step 5:

[1334] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1335] Inputs: Market data, historical negotiation data

[1336] Output: Market analysis results

[1337] How it works: The server uses Hugging Face's Transformers library to collect and analyze the latest market trends and important trading information, and provides the results to each agent AI. The agent AI then uses this information to optimize its negotiation strategy.

[1338] Step 6:

[1339] Server: When each proxy AI negotiation is completed, it compiles all the results and notifies the user.

[1340] Input: Negotiation result data

[1341] Output: Final negotiation results, satisfaction data

[1342] Specific operation: The server generates a detailed report of the negotiation results and displays it on the user's dashboard. At the same time, the emotion processing engine analyzes the user's emotions regarding the negotiation results and generates satisfaction data. These data are stored in a database.

[1343] Step 7:

[1344] Server: Accumulates negotiation data, sentiment data, and market trend data, and updates the self-learning dataset.

[1345] Inputs: Negotiation data, sentiment data, market data

[1346] Output: Updated AI model

[1347] How it works: The server stores historical data and uses machine learning algorithms to train the surrogate AI. It monitors the learning process and updates the AI ​​model as needed, for example by training a new model if performance degradation is detected.

[1348] (Application example 2)

[1349] 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."

[1350] Conventional product transactions and procurement negotiations in brick-and-mortar stores are typically conducted manually, resulting in a complex and time-consuming negotiation process that is inefficient. Furthermore, the lack of a means to properly manage emotional influences during negotiations can lead to lower user satisfaction. The present invention aims to solve these problems and provide a new system for achieving efficient and fair transactions.

[1351] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1352] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, means for Retrieval Augment Generation to analyze market trends and past negotiation data, means for providing the generated transaction information to the user, means for analyzing the user's emotions and generating emotion data, and means for accumulating negotiation data, emotion data, and market trend data and performing self-learning. This enables efficient and emotion-conscious transactions in physical stores.

[1353] "Conversational AI" is an AI system that listens to and understands players' requests and conditions in natural language.

[1354] "Proxy AI" is an AI system that automatically negotiates based on the player's requests and conditions.

[1355] "Retrieval Augment Generation Method" refers to a method for analyzing market trends and past negotiation data to acquire and generate relevant information.

[1356] "Emotion data" is the analysis and conversion of a user's emotional information into data.

[1357] "Self-learning" is the process by which the system independently learns and improves its performance based on negotiation data, sentiment data, and market trend data.

[1358] "User" refers to a person who uses the system to negotiate.

[1359] The system for implementing this invention is composed of the following main components. It is realized by the cooperation of a server, a terminal, and a user. Specifically, the server includes a conversational artificial intelligence, a proxy artificial intelligence, a Retrieval Augment Generation (RAG) means, a sentiment analysis engine, and a self-learning function. The terminal receives user input using a smartphone, smart glasses, or the like.

[1360] The server uses conversational AI to listen to the user's requests and conditions and analyzes them using natural language processing. Furthermore, the server generates user emotional data using an emotion analysis engine and provides a surrogate AI that negotiates based on that data. This allows the surrogate AI to negotiate with other surrogate AIs based on the requests and conditions entered by the user, and achieves efficient negotiations by analyzing market trends and past negotiation data using the RAG method.

[1361] The hardware used includes smartphones, smart glasses, and servers, and the software used includes sentiment analysis libraries (e.g., the sentiment analysis module from Transformers) and GPT-2 models (e.g., GPT-2 from the Transformers library).

[1362] As a concrete example, suppose a user uses a smartphone to enter the following prompt sentence:

[1363] "I visited a store in Tokyo to choose a kimono, but I would like it to be offered at a reasonable price."

[1364] First, the server receives the prompt, the conversational AI analyzes the requests and conditions, and the emotion analysis engine analyzes the user's emotions. A surrogate AI is then generated and begins negotiations based on the requests and emotion data. The surrogate AI communicates with other surrogate AIs, analyzes market trends and past data using the RAG method, and proposes optimal trading terms to the user.

[1365] This system will enable efficient and emotionally sensitive transactions in brick-and-mortar stores. For example, when purchasing an expensive wine, customers can input their desired price range using their smartphone, and the AI ​​will automatically facilitate the optimal transaction and suggest discounts and special offers based on emotional analysis.

[1366] Example prompt sentence:

[1367] "The user has made the following request: Request: Offer a new product at a special price. Emotion: Joy. Based on this request, the surrogate AI will suggest an appropriate price."

[1368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1369] Step 1:

[1370] The user inputs their requests and requirements using a smartphone or smart glasses. For example, if they input a prompt such as "I'm visiting a store in Tokyo to choose a kimono, and I'd like it to be offered at a reasonable price," the input data is sent to the server.

[1371] Step 2:

[1372] The server uses conversational AI to listen to the user's requests and requirements. The input data is passed to a natural language analysis module, which analyzes the requests and requirements and converts them into structured data. The results of this analysis are stored on the server.

[1373] Step 3:

[1374] The server's emotion analysis engine generates emotion data based on the user's input. For example, it detects emotions such as joy or anger from the user's input text and stores the emotion data together with the analysis results.

[1375] Step 4:

[1376] The server generates a substitute AI based on the request and emotion data. This substitute AI has data including the user's request and conditions and prepares to communicate with other substitute AIs.

[1377] Step 5:

[1378] The agent AI initiates communication with other agent AIs to strategically advance negotiations. During communication, each agent AI shares data on conditions and market trends with each other and formulates an appropriate negotiation strategy.

[1379] Step 6:

[1380] The server obtains the latest market information using Retrieval Augment Generation, which analyzes market trends and past negotiation data. For example, it obtains market prices and demand trends for expensive products and uses them in negotiations. This information is provided to the agent AI.

[1381] Step 7:

[1382] The generated transaction information is provided to the user through a proxy AI. The transaction information includes negotiated terms, discount information, and special offers. Users can view this information on their smartphones or smart glasses.

[1383] Step 8:

[1384] The server accumulates negotiation and sentiment data and uses a self-learning algorithm to improve the model, enabling more efficient and fairer transactions in the next negotiation.

[1385] Through these steps, the system can enable efficient and emotionally sensitive negotiations, improving the quality of transactions in physical stores.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] [Fourth embodiment]

[1390] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1391] 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.

[1392] 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).

[1393] 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.

[1394] 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.

[1395] 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).

[1396] 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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."

[1403] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate dealers, financial institutions, and consumers), and then each player's proxy AI automatically negotiates based on those conditions. Below are details of the program's processing and a specific example.

[1404] Program processing details:

[1405] The system of the present invention operates as follows.

[1406] 1. A user accesses the server

[1407] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[1408] Server: Verifies the user's credentials and starts the session.

[1409] 2. Listen to users' requests and requirements

[1410] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[1411] Server: Receives the input data, analyzes the information using a natural language processing (NLP) module, and stores it in a database.

[1412] 3. Creating a proxy AI and starting negotiations

[1413] Server: Based on the user's input information, it generates artificial intelligence representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1414] Server: Loads the user's requests and conditions into each proxy AI and initiates negotiations.

[1415] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[1416] 4. Market trend analysis and information provision using the RAG method

[1417] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1418] Server: Provides the acquired important transaction information to the user and the surrogate AI. The surrogate AI utilizes this information to optimize negotiation strategies.

[1419] 5. Review and feedback on negotiation results

[1420] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[1421] User: Review the negotiation results and provide feedback if necessary.

[1422] Server: Stores user feedback in a database.

[1423] 6. Data accumulation and self-learning

[1424] Server: Stores data on negotiations and market trends, updating the dataset for self-learning by the surrogate AI.

[1425] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[1426] Server: Monitors the learning process and updates the AI ​​model as needed.

[1427] Examples:

[1428] Step 1: Enter your request

[1429] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[1430] Server: "The data entered by the user has been parsed and saved to the database."

[1431] Step 2: Negotiation begins with surrogate AI

[1432] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[1433] Proxy AI: "I will begin negotiations with other Proxy AIs."

[1434] Step 3: Market trend analysis and information provision

[1435] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[1436] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[1437] Step 4: Review and feedback on negotiation results

[1438] Server: "Negotiation completed. User notified of outcome."

[1439] User: "Review the results and provide feedback."

[1440] Step 5: Data accumulation and learning

[1441] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[1442] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[1443] The processing flow will be explained below.

[1444] Step 1:

[1445] User: Access the server and log in.

[1446] Server: Validates the user's credentials and initiates a session.

[1447] Step 2:

[1448] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[1449] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[1450] Server: Stores the analyzed requests and conditions in a database.

[1451] Step 3:

[1452] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1453] Server: Loads each surrogate AI with the relevant player's information, wishes and conditions.

[1454] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[1455] Proxy AI: Builds a negotiation strategy using an internal algorithm based on the received conditions.

[1456] Step 4:

[1457] Proxy AI: Proceeds negotiations based on each player's conditions (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[1458] Server: Records the progress of negotiations in a database in real time.

[1459] Step 5:

[1460] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1461] Server: Provides acquired important transaction information to the proxy AI.

[1462] Proxy AI: Optimizes negotiation tactics based on the information provided and continues negotiations.

[1463] Step 6:

[1464] Server: Once the negotiation is complete, aggregate all results and notify the user.

[1465] User: Review the negotiation results and provide feedback if necessary.

[1466] Server: Stores user feedback in a database.

[1467] Step 7:

[1468] Server: Stores negotiation data and market trend data in a proprietary database.

[1469] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[1470] Server: Monitors the learning process and updates the AI ​​model as needed.

[1471] Proxy AI: Reflects learning results in the next negotiation.

[1472] Example 1

[1473] 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."

[1474] In conventional real estate transactions, negotiations between each player (landowner, construction company, building materials manufacturer, developer, real estate dealer, financial institution, and consumer) often do not proceed efficiently due to their complexity and time-consuming efforts. Furthermore, the progress and success rate of negotiations depend on the subjective judgment of each player, making it difficult to achieve a fair transaction. Furthermore, conventional systems using artificial intelligence have the problem of not being able to adequately analyze information or optimize strategies, resulting in poor transaction outcomes. The present invention aims to solve these problems and realize efficient and fair real estate transactions.

[1475] 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.

[1476] In this invention, the server includes means for using a conversational AI to hear the user's requests and conditions, means for generating a proxy AI and negotiating based on the user's requests and conditions, means for acquiring and expanding information for analyzing market trends and past negotiation data, means for providing the generated transaction information to the user, means for accumulating negotiation data and market trend data and for self-learning, means for the user to access and log in to the system using a web browser or application, means for analyzing the requests and conditions entered by the user using natural language processing and storing them in a database, means for the proxy AI to communicate with other proxy AIs to strategically advance negotiations, means for extracting important transaction information and providing it to the proxy AI and the user, and means for notifying the user of the negotiation results and receiving feedback, thereby enabling fast and efficient negotiations and fair transactions.

[1477] "Conversational artificial intelligence" is a system that uses artificial intelligence technology to converse with users in natural language and gather their requests and requirements.

[1478] "Proxy AI" is a program or system that uses AI technology to negotiate on behalf of each player.

[1479] "Information retrieval augmentation generation means" is a means of collecting and analyzing market trends and past negotiation data using the Retrieval Augment Generation (RAG) method.

[1480] "Transaction Information" refers to data relating to the results of player negotiations and market trends, and is information provided to users.

[1481] "Self-learning" is the process by which artificial intelligence uses machine learning algorithms to learn and improve its performance based on past negotiation data and market trend data.

[1482] A "web browser" is software for viewing web pages on the Internet.

[1483] An "application" is a software program designed to accomplish a particular purpose.

[1484] "Natural language processing" is a technology that processes human language using a computer to perform semantic analysis and information extraction.

[1485] A "database" is an information collection system that systematically stores data and enables it to be searched and managed.

[1486] "Feedback" refers to the results of negotiations and opinions and evaluations from users regarding their use of the system, and is information that can be used to help with future improvements and adjustments.

[1487] This invention is a system in which a conversational AI listens to the requests and conditions of each player in a real estate transaction (land owner, construction company, building material manufacturer, developer, real estate dealer, financial institution, consumer), and then a proxy AI for each player automatically negotiates based on those conditions. This system operates as follows.

[1488] 1. Hardware and software used

[1489] Hardware: Servers, devices (devices that run the web browsers and specialized applications used by users), and network infrastructure.

[1490] Software: Conversational artificial intelligence (natural language processing), surrogate artificial intelligence (machine learning algorithms), database management systems (SQL databases, NoSQL databases), web browsers (Google Chrome, Mozilla Firefox), dedicated applications.

[1491] 2. Data processing and calculation

[1492] server

[1493] Credential validation: The credentials entered by the user at login are checked against a database to verify their validity.

[1494] Natural language processing: The requests and conditions entered by the user are analyzed using a natural language processing module (e.g., spaCy or NLTK), converted into structured data, and stored in the database.

[1495] Generate surrogate AI: Based on user input data, generate surrogate AI for the relevant player using machine learning libraries such as TensorFlow or PyTorch.

[1496] RAG information analysis: We use the Retrieval Augmented Generation (RAG) method to analyze market trends and past negotiation data. Specifically, we use external data collected using scraping techniques to analyze current market trends in real time.

[1497] Notification of important information: Important transaction information obtained as a result of analysis is compiled and provided to the agent AI and users in real time.

[1498] proxy AI

[1499] Communication and negotiation: Communicate with other agent AIs via RESTful APIs, share their requests and conditions, and proceed with negotiations. Use internal algorithms to find the optimal solution for the negotiation.

[1500] Self-learning: Negotiation data and market trend data are self-learned using machine learning algorithms, and reflected in the next negotiation.

[1501] Terminal

[1502] Providing a user interface: Providing an interface for users to access the system and input their requests and requirements. Specifically, this includes form entry, button operations, etc.

[1503] Display notifications: Display the negotiation results and important information sent from the server to the user.

[1504] 3. Specific Examples

[1505] Input of user requests

[1506] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[1507] Server: "The data entered by the user has been parsed and saved to the database."

[1508] Negotiations begin with proxy AI

[1509] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests..."

[1510] Proxy AI: "I will begin negotiations with other Proxy AIs."

[1511] Market trend analysis and information provision

[1512] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[1513] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[1514] Confirmation and feedback of negotiation results

[1515] Server: "Negotiation completed. User notified of outcome."

[1516] User: "Review the results and provide feedback."

[1517] The system of the present invention is an innovative means for significantly improving the efficiency of negotiations in real estate transactions and realizing fair transactions.

[1518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1519] Processing Steps

[1520] Step 1: User Access and Login

[1521] input:

[1522] The user accesses the system's URL through a web browser or application and enters their user ID and password on the login screen.

[1523] Specific behavior:

[1524] Terminal: Launch a web browser or application and access the system URL. The login screen will appear.

[1525] User: Enter your user ID and password on the login screen and click the "Login" button.

[1526] Server: Receives the entered user ID and password and checks the authentication information against the database. If authentication is successful, the session starts and the home screen is displayed.

[1527] output:

[1528] The home screen appears, allowing the user to access the system's features.

[1529] Step 2: Enter your requirements and requirements

[1530] input:

[1531] The user enters their requests and conditions (budget, location, desired property type, construction period, etc.) into the input form on the home screen and clicks the submit button.

[1532] Specific behavior:

[1533] User: Enter requirements such as "Budget: within 200 million yen," "Location: Tokyo," and "Construction period: 1 year" into the input form on the home screen, and click the submit button.

[1534] Terminal: Sends the input form data to the server.

[1535] Server: Analyzes the received data using a natural language processing (NLP) module (e.g., spaCy or NLTK) and stores the analyzed structured data in a database.

[1536] output:

[1537] The structured data is saved in a database, which triggers the next processing step.

[1538] Step 3: Create and configure a surrogate AI

[1539] input:

[1540] Data on user requests and requirements stored on the server.

[1541] Specific behavior:

[1542] Server: Based on the user's input data, it generates surrogate AI for the relevant players (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.) using machine learning libraries such as TensorFlow and PyTorch.

[1543] Server: Loads the user's requests and conditions into the generated surrogate AI.

[1544] output:

[1545] Multiple proxy AIs are generated and loaded with the user's requests and conditions.

[1546] Step 4: Negotiation begins with surrogate AI

[1547] input:

[1548] User requests and conditions loaded into each surrogate AI.

[1549] Specific behavior:

[1550] Delegate AI: Communicates with other Delegate AIs via RESTful APIs, shares their requests and conditions, and uses internal algorithms to advance negotiations.

[1551] For example, a land owner AI might propose the condition "can be sold for 150 million yen" to another proxy AI, and the construction company AI might respond "can be constructed within the budget."

[1552] output:

[1553] Negotiations continue to progress and optimal terms are found.

[1554] Step 5: Analyze market trends and provide information

[1555] input:

[1556] Market trend information and past negotiation data collected by the server.

[1557] Specific behavior:

[1558] Server: Analyzes market trends and historical negotiation data using Retrieval Augmented Generation (RAG) techniques, specifically scraping data from external data sources and performing real-time analysis.

[1559] Server: Extracts important transaction information obtained as a result of the analysis and provides it to the proxy AI and the user.

[1560] For example, information such as "land prices in Tokyo have increased 10% compared to the previous year" is collected as a current market trend, and this information is notified to the proxy AI.

[1561] output:

[1562] Key transaction information is obtained, and the surrogate AI optimizes the negotiation strategy based on it.

[1563] Step 6: Review and feedback on negotiation results

[1564] input:

[1565] Negotiation result data and user feedback information.

[1566] Specific behavior:

[1567] Server: Once the negotiation is complete, the server consolidates all the results and notifies the user via email or in-app notification.

[1568] User: After receiving the notification, log back into the system to check the negotiation results and provide feedback if necessary.

[1569] For example, the user may input, "The negotiation process went smoothly, but I'm dissatisfied because it was over budget."

[1570] output:

[1571] The negotiation results and feedback information confirmed by the user are stored in a database.

[1572] Step 7: Data accumulation and self-learning

[1573] input:

[1574] Negotiation data and feedback information.

[1575] Specific behavior:

[1576] Server: Records negotiation data and feedback information in a database and prepares for the next negotiation.

[1577] Surrogate AI: Acquires new data and uses machine learning algorithms (e.g., reinforcement learning) to self-learn and improve negotiation tactics.

[1578] Server: Monitors the learning progress and adjusts the algorithm parameters as needed.

[1579] output:

[1580] Deputy AI with improved negotiation skills and updated systems.

[1581] (Application example 1)

[1582] 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."

[1583] Existing negotiation systems in the real estate industry have faced challenges such as the difficulty of reconciling the diverse requests and conditions between each player and the complexity of efficiently conducting optimal transactions. Furthermore, supply chain management and appropriate price negotiations are important for procuring materials within a factory, but doing this manually takes time and effort. This leads to problems such as a lack of negotiating power and an increased risk of human error.

[1584] 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.

[1585] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, Retrieval Augment Generation means for analyzing market trends and past negotiation data, means for allowing a user to input material requirements and automatically negotiate with suppliers in the procurement of materials within a factory, and means for selecting the most suitable supplier based on the material requirements and optimizing prices. This enables efficient and optimal transactions in line with the player's requests, making material procurement more efficient and reducing costs.

[1586] "Conversational AI" is AI that can have natural conversations with users via voice and text.

[1587] A "surrogate AI" is an AI generated to negotiate with other surrogate AIs based on the user's requests and conditions.

[1588] "Retrieval Augment Generation Method" is a method for automatically generating transaction information by analyzing past negotiation data and market trends.

[1589] "In-factory material procurement" is the process of properly securing materials and parts necessary for factory production activities.

[1590] "Material requirements" are the specific conditions and specifications for the materials to be procured, such as quantity, quality, and delivery date.

[1591] "Supplier" means a supplier that supplies materials and parts to the factory.

[1592] "Market trends" refers to information that refers to general trends such as the current market state and price fluctuations.

[1593] "Price optimization" is the process of procuring materials of the required quality and quantity at the optimal price while keeping costs down.

[1594] This invention is a system for in-factory material procurement and supply chain management that uses conversational AI to hear the requests and conditions of players (factory personnel, suppliers) and then uses proxy AI to efficiently automate negotiations. An embodiment of this system is shown below.

[1595] System Overview

[1596] The server is configured using the following hardware and software.

[1597] Hardware: High-performance servers, IoT devices in factories

[1598] software:

[1599] Natural Language Processing (NLP) modules (e.g., spaCy, NLTK)

[1600] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1601] Database (e.g. MySQL, MongoDB)

[1602] Libraries suitable for implementing Retrieval Augment Generation (RAG) techniques (e.g., Transformers)

[1603] Processing flow

[1604] User Input and Data Analysis

[1605] Using a terminal, factory personnel input material requirements (e.g., quantity, quality, delivery date). The server analyzes this information using a natural language processing (NLP) module and stores it in a database, allowing the input requirements to be treated as concrete data.

[1606] Creation of a surrogate AI and the start of negotiations

[1607] Based on the analyzed data, the server generates surrogate AIs for the relevant suppliers. Each surrogate AI loads the user's requirements and initiates automatic negotiations with the suppliers.

[1608] Market trend analysis

[1609] The server uses the RAG methodology to collect and analyze market trends and past negotiation data, thereby understanding current market prices and trends and providing information that can be used in negotiations.

[1610] Notification and optimization of negotiation results

[1611] After the negotiation is completed, the server notifies the user of the results in real time. The user can then review the results and enter feedback as needed. This allows the user to obtain quotes and delivery terms from the most suitable suppliers.

[1612] Specific examples

[1613] For example, a factory worker enters the following prompt:

[1614] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[1615] Based on this prompt, the server analyzes the information and generates a suitable supplier's surrogate AI. The surrogate AI then negotiates with other surrogate AIs, grasps market trends using the RAG method, and proposes the optimal price and delivery date. Finally, the negotiation results are notified to the factory staff in real time for confirmation and feedback.

[1616] This invention significantly improves the efficiency of material procurement within factories, reducing costs and strengthening supply chain risk management.

[1617] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1618] Step 1:

[1619] A user uses a terminal to input material requirements, including specific conditions such as quantity, quality, and delivery date, and the input information is sent from the terminal to the server.

[1620] Input: Material requirements (e.g. quantity, quality, delivery date)

[1621] Output: Material requirements sent to the server

[1622] Specific behavior:

[1623] The factory worker enters the following as the prompt:

[1624] "We would like to procure 1,000 units of aluminum materials needed next month. The quality must be A grade or higher, and the delivery time must be within three weeks."

[1625] The server receives this information and proceeds to the next step.

[1626] Step 2:

[1627] The server uses a natural language processing (NLP) module to analyze the material requirements submitted by the user. This analysis converts the requirements into a format that can be stored in a database. Once the analysis is complete, the data is stored in the database.

[1628] Input: Material requirements submitted by the user

[1629] Output: The parsed data and how it is stored in the database

[1630] Specific behavior:

[1631] The server uses an NLP module (e.g., spaCy, NLTK) to parse the prompt sentence and break it down into the elements "aluminum materials," "1,000 units," "A grade or higher," and "within 3 weeks." The parsed data is stored in a database.

[1632] Step 3:

[1633] The server generates surrogate artificial intelligence (AI) for the relevant suppliers based on the analyzed data, and simultaneously loads the user's requirements into each surrogate AI to initiate negotiations with the suppliers.

[1634] Input: Analyzed material requirements

[1635] Output: Generated surrogate AI and data for starting negotiations

[1636] Specific behavior:

[1637] The server uses the analyzed data to generate a surrogate AI for an appropriate supplier, and loads the requirement of "procure 1,000 units of A-grade aluminum materials within three weeks" into the surrogate AI, which then begins negotiations with the supplier.

[1638] Step 4:

[1639] The server uses Retrieval Augment Generation (RAG) techniques to analyze market trends and past negotiation data, and based on this, it understands current market prices and trends and provides useful information for negotiations to the surrogate AI.

[1640] Input: Market trend data, past negotiation data

[1641] Output: Market price and trend information provided to the surrogate AI

[1642] Specific behavior:

[1643] The server uses RAG techniques (e.g., the Transformers library) to analyze market trends and extract information such as "the current market price is X yen per unit." This information is fed back to the proxy AI and used during negotiations.

[1644] Step 5:

[1645] Once the negotiation is complete, the server notifies the user of the results in real time. The user can then review the results and provide feedback if necessary. This feedback is also stored in the database and used for future negotiations.

[1646] Input: Negotiation results, user feedback

[1647] Output: Negotiation results communicated to the user and feedback stored in a database

[1648] Specific behavior:

[1649] The server receives the negotiation results from the proxy AI and notifies the user of the information that "the quote from a specific supplier is Y yen, and the delivery time is Z weeks." The user checks the results and enters feedback such as "the delivery time is too short," which is then saved in the database.

[1650] This series of steps significantly improves the efficiency of material procurement within the factory and enables transactions to be made with the most suitable supplier.

[1651] 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.

[1652] This invention is a system in which a conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and a proxy AI automatically negotiates based on that information. Furthermore, this invention combines an emotion engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. Details of the program's processing and specific examples are provided below.

[1653] Program processing details:

[1654] The system of the present invention operates as follows.

[1655] 1. A user accesses the server

[1656] User: First, access the server and log in to enter requests and conditions for real estate transactions.

[1657] Server: Verifies the user's credentials and starts the session.

[1658] 2. Listen to users' requests and requirements

[1659] User: Enters specific requests and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[1660] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[1661] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[1662] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[1663] 3. Creating a proxy AI and starting negotiations

[1664] Server: Based on user input, it generates surrogate AI for related players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1665] Server: Loads each surrogate AI with the user's requests, conditions, and emotional data, and initiates negotiations.

[1666] Proxy AI: Communicates with other Proxy AIs, shares their requests and conditions, and negotiates based on its internal algorithm.

[1667] 4. Market trend analysis and information provision using the RAG method

[1668] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1669] Server: Provides the acquired important transaction information to the user and the surrogate AI, which then uses this information to optimize negotiation strategies.

[1670] 5. Review and feedback on negotiation results

[1671] Server: Once the negotiation is complete, it summarizes all the results and notifies the user.

[1672] User: Review the negotiation results and provide feedback if necessary.

[1673] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[1674] Server: Stores user feedback and emotion data in a database.

[1675] 6. Data accumulation and self-learning

[1676] Server: Accumulates negotiation data, sentiment data, and market trend data to update the dataset for self-learning by the surrogate AI.

[1677] Surrogate AI: Uses machine learning algorithms to self-learn and improve negotiation skills.

[1678] Server: Monitors the learning process and updates the AI ​​model as needed.

[1679] Examples:

[1680] Step 1: Enter your request

[1681] User: "I'd like to purchase land in Tokyo for less than 200 million yen. I'd like construction to take one year."

[1682] Server: "The data entered by the user has been parsed and saved to the database."

[1683] Emotion Engine: "Analyzes the user's facial expressions and generates emotion data."

[1684] Step 2: Negotiation begins with surrogate AI

[1685] Server: "We've created a Land Owner AI, a Construction Contractor AI, a Building Materials Manufacturer AI, a Developer AI, a Real Estate Agent AI, and a Financial Institution AI. Loading user requests and sentiment data..."

[1686] Proxy AI: "I will begin negotiations with other Proxy AIs."

[1687] Step 3: Market trend analysis and information provision

[1688] Server: "We analyzed the latest market trends using the RAG methodology and provided the key points to the surrogate AI."

[1689] Proxy AI: "We are proceeding with negotiations based on the information you provided."

[1690] Step 4: Review and feedback on negotiation results

[1691] Server: "Negotiation completed. User notified of outcome."

[1692] User: "Review the results and provide feedback."

[1693] Emotion Engine: "We analyzed users' emotions regarding the negotiation outcome and generated satisfaction data."

[1694] Step 5: Data accumulation and learning

[1695] Server: "We have accumulated negotiation data and begun self-learning. We will reflect this in the next negotiation."

[1696] The system of the present invention is a new means for further improving the efficiency of negotiations and realizing fair transactions by using user emotional information.

[1697] The processing flow will be explained below.

[1698] Step 1:

[1699] User: Access the server and log in.

[1700] Server: Validates the user's credentials and initiates a session.

[1701] Step 2:

[1702] User: Enters their requirements and requirements into an on-screen form (e.g., budget, location, desired property type, construction period, etc.).

[1703] Server: Receives input data and analyzes the information using a natural language processing (NLP) module.

[1704] Emotion engine: Analyzes emotions from the user's facial expressions and tone of voice when data is entered, and generates emotional data.

[1705] Server: Stores the analyzed requests, conditions, and emotion data in a database.

[1706] Step 3:

[1707] Server: Based on the user's requests and conditions, it instantiates the AI ​​representatives of the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1708] Server: Loads each surrogate AI with relevant player information, desires, conditions, and emotion data.

[1709] Proxy AI: Initiate communication with other Proxy AIs and share their wishes and conditions.

[1710] Proxy AI: An internal algorithm builds a negotiation strategy based on the received conditions and emotional data.

[1711] Step 4:

[1712] Proxy AI: Proceed with negotiations based on each player's conditions and emotional data (e.g., price negotiations, delivery date adjustments, specification adjustments, etc.).

[1713] Server: Records the progress of negotiations in a database in real time.

[1714] Step 5:

[1715] Server: Analyzes market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1716] Server: Provides acquired important transaction information to the proxy AI.

[1717] Surrogate AI: Optimizes negotiation tactics based on provided information and emotional data and continues negotiations.

[1718] Step 6:

[1719] Server: Once the negotiation is complete, aggregate all results and notify the user.

[1720] User: Review the negotiation results and provide feedback if necessary.

[1721] Emotion Engine: Analyzes user emotions regarding negotiation results and generates satisfaction data.

[1722] Server: Stores user feedback and emotion data in a database.

[1723] Step 7:

[1724] Server: Stores negotiation data, market trend data, and sentiment data in a proprietary database.

[1725] Surrogate AI: Using machine learning algorithms to self-learn and improve negotiation skills based on accumulated data.

[1726] Server: Monitors the learning process and updates the AI ​​model as needed.

[1727] Proxy AI: Reflects learning results in the next negotiation.

[1728] Example 2

[1729] 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."

[1730] Conventional real estate transaction systems have difficulty in properly gathering the requests and conditions of each party and conducting negotiations efficiently. Furthermore, they are unable to take into account the user's feelings during the negotiation process, resulting in problems with fairness and inefficiency in transactions. Furthermore, conventional systems are unable to fully utilize market trends and past negotiation data, making it difficult to formulate optimal negotiation strategies.

[1731] 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.

[1732] In this invention, the server includes means for listening to the player's requests and conditions using a conversational AI, means for generating emotion data using an emotion processing engine that recognizes the user's emotions, and means for generating a proxy AI and negotiating based on the player's requests and conditions, thereby improving the efficiency of negotiations and enabling fair transactions that take into account the user's emotional information.

[1733] "Conversational AI" refers to AI that has the ability to listen to the player's requests and conditions, understand them, and respond appropriately.

[1734] An "emotion processing engine" refers to an engine that analyzes a user's facial expressions, tone of voice, etc., and generates emotional data about the user.

[1735] "Proxy AI" refers to an AI that negotiates with other proxy AIs based on the player's requests and conditions.

[1736] "Retrieval Augment Generation Means" refers to the method and means for retrieving information and generating additional information based on that information.

[1737] "Generated transaction information" refers to detailed information regarding transactions created through negotiations between proxy AIs.

[1738] "Market Trend Data" means data regarding current and historical market movements and trading trends.

[1739] "Self-learning" refers to the process by which artificial intelligence uses past and newly acquired data to improve its performance.

[1740] This invention is a system in which conversational AI listens to the requests and conditions of each player in the real estate industry (landowners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, and consumers), and then a proxy AI automatically negotiates based on that information. Furthermore, it combines an emotion processing engine that recognizes the user's emotions, and utilizes the user's emotional data in the negotiation process. This system utilizes advanced AI technology to realize efficient and fair real estate transactions.

[1741] Hardware and software used

[1742] This system uses the following hardware and software:

[1743] server:

[1744] Various AI modules are executed using servers with high-speed processing capabilities, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[1745] Device:

[1746] Users access the system using devices such as PCs, smartphones, and tablets. These devices are connected to the Internet and users log in to the system via a web browser.

[1747] Conversational Artificial Intelligence:

[1748] Google Dialogflow and IBM Watson Assistant are used as natural language processing (NLP) modules to listen to and analyze user requests and conditions.

[1749] Emotion Processing Engine:

[1750] Microsoft Azure Emotion API and Amazon Rekognition are used as engines to analyze the user's facial expressions and tone of voice.

[1751] Deputy AI:

[1752] It is developed using machine learning libraries such as TensorFlow and PyTorch, which allows automatic negotiations to be performed on behalf of each player.

[1753] Market Analysis:

[1754] It uses Retrieval Augment Generation (RAG) techniques, specifically using Hugging Face's Transformers library to analyze market trends and historical negotiation data.

[1755] Specific examples

[1756] Step 1: Enter your request

[1757] The user enters their request into an on-screen form, such as "I'd like to purchase land in Tokyo for less than 200 million yen. I would like the construction period to be one year." The server receives this information and analyzes it using a natural language processing module. At the same time, the emotion processing engine generates emotion data from the user's facial expressions and stores this data in a database.

[1758] Step 2: Negotiation begins with surrogate AI

[1759] The server generates AIs for the landowner, construction company, building materials manufacturer, developer, real estate agent, and financial institution. These AIs receive user requests and emotional data and begin negotiations with other AIs. For example, the landowner AI adjusts the price of the land, and the construction company AI proposes the construction period.

[1760] Step 3: Market trend analysis and information provision

[1761] The server analyzes the latest market trends using the RAG method and provides key points to the surrogate AI, which then uses the information to negotiate and present the optimal terms.

[1762] Step 4: Review and feedback on negotiation results

[1763] When the negotiation is over, the server compiles all the results and notifies the user. The user checks the results and enters feedback. The emotion processing engine analyzes the user's feelings about the negotiation results and generates satisfaction data. This data is stored on the server and used for the next negotiation.

[1764] Step 5: Data accumulation and learning

[1765] The server accumulates negotiation data and emotional data and updates the dataset for the surrogate AI to self-learn. The surrogate AI uses machine learning algorithms to improve its negotiation skills. The server monitors this learning process and updates the AI ​​model as needed.

[1766] Example prompt sentence:

[1767] A user wishes to purchase land in Tokyo for less than 200 million yen. The construction period is within one year. To proceed with this negotiation, please generate AIs for the land owner, construction company, building materials manufacturer, developer, real estate agent, and financial institution, and load them with the user's requests and sentiment data. Use the RAG method to collect appropriate information based on the latest market trends and provide it as a guide for proceeding with the negotiation.

[1768] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1769] Step 1:

[1770] User: Access the system login page using a web browser, enter your user ID and password, and click the login button.

[1771] Input: User ID, Password

[1772] Output: Session ID

[1773] Specific operation: The server authenticates the user ID and password in the database, and if authentication is successful, generates a session ID and returns it to the user.

[1774] Step 2:

[1775] User: After logging in, the user is taken to a form page where they can enter their requests and conditions. They enter their budget, location, desired property type, construction period, etc. into the form and click the submit button.

[1776] Input: Budget, Location, Property Type, Construction Period

[1777] Output: Structured data, sentiment data

[1778] Specific operation: The server receives the input data and analyzes it using a natural language processing (NLP) module. At the same time, the emotion processing engine analyzes the user's facial expressions and tone of voice to generate emotion data. The server then stores the analyzed requests, conditions, and emotion data in a database.

[1779] Step 3:

[1780] Server: Based on user input information, it generates surrogate artificial intelligence (AI) for the relevant players (land owners, construction companies, building material manufacturers, developers, real estate agents, financial institutions, etc.).

[1781] Input: Structured data, sentiment data

[1782] Output: An instance of each surrogate AI

[1783] Specific operation: The server separately generates a landowner AI, a construction company AI, a building materials manufacturer AI, a developer AI, a real estate agent AI, and a financial institution AI, and loads the user's requests, conditions, and emotional data into each of them.

[1784] Step 4:

[1785] Each surrogate AI: Initiates communication with other surrogate AIs, shares their requests and conditions, and advances negotiations.

[1786] Input: User requests and conditions, emotional data

[1787] Output: Negotiation result data

[1788] Specific operation: Each agent AI uses its internal algorithm to formulate a strategy based on the requested requests and conditions, and negotiates with other agent AIs. For example, the landowner AI adjusts the price conditions for the land, and the building materials manufacturer AI estimates the cost of building materials.

[1789] Step 5:

[1790] Server: Analyzes current market trends and past negotiation data using Retrieval Augment Generation (RAG) techniques.

[1791] Inputs: Market data, historical negotiation data

[1792] Output: Market analysis results

[1793] How it works: The server uses Hugging Face's Transformers library to collect and analyze the latest market trends and important trading information, and provides the results to each agent AI. The agent AI then uses this information to optimize its negotiation strategy.

[1794] Step 6:

[1795] Server: When each proxy AI negotiation is completed, it compiles all the results and notifies the user.

[1796] Input: Negotiation result data

[1797] Output: Final negotiation results, satisfaction data

[1798] Specific operation: The server generates a detailed report of the negotiation results and displays it on the user's dashboard. At the same time, the emotion processing engine analyzes the user's emotions regarding the negotiation results and generates satisfaction data. These data are stored in a database.

[1799] Step 7:

[1800] Server: Accumulates negotiation data, sentiment data, and market trend data, and updates the self-learning dataset.

[1801] Inputs: Negotiation data, sentiment data, market data

[1802] Output: Updated AI model

[1803] How it works: The server stores historical data and uses machine learning algorithms to train the surrogate AI. It monitors the learning process and updates the AI ​​model as needed, for example by training a new model if performance degradation is detected.

[1804] (Application example 2)

[1805] 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."

[1806] Conventional product transactions and procurement negotiations in brick-and-mortar stores are typically conducted manually, resulting in a complex and time-consuming negotiation process that is inefficient. Furthermore, the lack of a means to properly manage emotional influences during negotiations can lead to lower user satisfaction. The present invention aims to solve these problems and provide a new system for achieving efficient and fair transactions.

[1807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1808] In this invention, the server includes means for using conversational AI to hear the player's requests and conditions, means for generating a proxy AI and negotiating based on the player's requests and conditions, means for Retrieval Augment Generation to analyze market trends and past negotiation data, means for providing the generated transaction information to the user, means for analyzing the user's emotions and generating emotion data, and means for accumulating negotiation data, emotion data, and market trend data and performing self-learning. This enables efficient and emotion-conscious transactions in physical stores.

[1809] "Conversational AI" is an AI system that listens to and understands players' requests and conditions in natural language.

[1810] "Proxy AI" is an AI system that automatically negotiates based on the player's requests and conditions.

[1811] "Retrieval Augment Generation Method" refers to a method for analyzing market trends and past negotiation data to acquire and generate relevant information.

[1812] "Emotion data" is the analysis and conversion of a user's emotional information into data.

[1813] "Self-learning" is the process by which the system independently learns and improves its performance based on negotiation data, sentiment data, and market trend data.

[1814] "User" refers to a person who uses the system to negotiate.

[1815] The system for implementing this invention is composed of the following main components. It is realized by the cooperation of a server, a terminal, and a user. Specifically, the server includes a conversational artificial intelligence, a proxy artificial intelligence, a Retrieval Augment Generation (RAG) means, a sentiment analysis engine, and a self-learning function. The terminal receives user input using a smartphone, smart glasses, or the like.

[1816] The server uses conversational AI to listen to the user's requests and conditions and analyzes them using natural language processing. Furthermore, the server generates user emotional data using an emotion analysis engine and provides a surrogate AI that negotiates based on that data. This allows the surrogate AI to negotiate with other surrogate AIs based on the requests and conditions entered by the user, and achieves efficient negotiations by analyzing market trends and past negotiation data using the RAG method.

[1817] The hardware used includes smartphones, smart glasses, and servers, and the software used includes sentiment analysis libraries (e.g., the sentiment analysis module from Transformers) and GPT-2 models (e.g., GPT-2 from the Transformers library).

[1818] As a concrete example, suppose a user uses a smartphone to enter the following prompt sentence:

[1819] "I visited a store in Tokyo to choose a kimono, but I would like it to be offered at a reasonable price."

[1820] First, the server receives the prompt, the conversational AI analyzes the requests and conditions, and the emotion analysis engine analyzes the user's emotions. A surrogate AI is then generated and begins negotiations based on the requests and emotion data. The surrogate AI communicates with other surrogate AIs, analyzes market trends and past data using the RAG method, and proposes optimal trading terms to the user.

[1821] This system will enable efficient and emotionally sensitive transactions in brick-and-mortar stores. For example, when purchasing an expensive wine, customers can input their desired price range using their smartphone, and the AI ​​will automatically facilitate the optimal transaction and suggest discounts and special offers based on emotional analysis.

[1822] Example prompt sentence:

[1823] "The user has made the following request: Request: Offer a new product at a special price. Emotion: Joy. Based on this request, the surrogate AI will suggest an appropriate price."

[1824] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1825] Step 1:

[1826] The user inputs their requests and requirements using a smartphone or smart glasses. For example, if they input a prompt such as "I'm visiting a store in Tokyo to choose a kimono, and I'd like it to be offered at a reasonable price," the input data is sent to the server.

[1827] Step 2:

[1828] The server uses conversational AI to listen to the user's requests and requirements. The input data is passed to a natural language analysis module, which analyzes the requests and requirements and converts them into structured data. The results of this analysis are stored on the server.

[1829] Step 3:

[1830] The server's emotion analysis engine generates emotion data based on the user's input. For example, it detects emotions such as joy or anger from the user's input text and stores the emotion data together with the analysis results.

[1831] Step 4:

[1832] The server generates a substitute AI based on the request and emotion data. This substitute AI has data including the user's request and conditions and prepares to communicate with other substitute AIs.

[1833] Step 5:

[1834] The agent AI initiates communication with other agent AIs to strategically advance negotiations. During communication, each agent AI shares data on conditions and market trends with each other and formulates an appropriate negotiation strategy.

[1835] Step 6:

[1836] The server obtains the latest market information using Retrieval Augment Generation, which analyzes market trends and past negotiation data. For example, it obtains market prices and demand trends for expensive products and uses them in negotiations. This information is provided to the agent AI.

[1837] Step 7:

[1838] The generated transaction information is provided to the user through a proxy AI. The transaction information includes negotiated terms, discount information, and special offers. Users can view this information on their smartphones or smart glasses.

[1839] Step 8:

[1840] The server accumulates negotiation and sentiment data and uses a self-learning algorithm to improve the model, enabling more efficient and fairer transactions in the next negotiation.

[1841] Through these steps, the system can enable efficient and emotionally sensitive negotiations, improving the quality of transactions in physical stores.

[1842] 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.

[1843] 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.

[1844] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1845] 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.

[1846] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1847] 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.

[1848] 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).

[1849] 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.

[1850] 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."

[1851] 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.

[1852] 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).

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] 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.

[1859] 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.

[1860] 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.

[1861] 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.

[1862] 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.

[1863] The following is further disclosed regarding the above embodiment.

[1864] (Claim 1)

[1865] A means of listening to players' requests and conditions using conversational AI,

[1866] A means to generate a proxy AI and negotiate based on the player's requests and conditions;

[1867] Retrieval Augment Generation means for analyzing market trends and past negotiation data;

[1868] means for providing the generated transaction information to a user;

[1869] A means of accumulating negotiation data and market trend data and conducting self-learning;

[1870] A system including:

[1871] (Claim 2)

[1872] 2. The system according to claim 1, wherein the conversational artificial intelligence includes means for analyzing the player's requests and conditions using natural language processing and storing the results in a database.

[1873] (Claim 3)

[1874] 10. The system of claim 1, wherein the agent artificial intelligence includes means for communicating with other agent artificial intelligences and strategically negotiating with them.

[1875] "Example 1"

[1876] (Claim 1)

[1877] A means of listening to users' requests and conditions using conversational artificial intelligence,

[1878] A means for generating a proxy artificial intelligence and negotiating based on the user's requests and conditions;

[1879] an information acquisition and generation means for analyzing market trends and past negotiation data;

[1880] a means for providing the generated transaction information to a user;

[1881] A means of accumulating negotiation data and market trend data and conducting self-learning;

[1882] A means for users to access and log in to the system using a web browser or application;

[1883] A means for analyzing requests and conditions entered by users using natural language processing and storing them in a database;

[1884] A means for a proxy AI to communicate with other proxy AIs and strategically advance negotiations;

[1885] A means for extracting important transaction information and providing it to the proxy artificial intelligence and users;

[1886] a means of notifying users of the results of the negotiations and receiving feedback;

[1887] A system including:

[1888] (Claim 2)

[1889] The system according to claim 1, wherein the conversational artificial intelligence includes means for analyzing the user's requests and conditions using natural language processing and storing the results in a database.

[1890] (Claim 3)

[1891] 10. The system of claim 1, wherein the agent artificial intelligence includes means for communicating with other agent artificial intelligences and strategically negotiating with them.

[1892] "Application Example 1"

[1893] (Claim 1)

[1894] A means of listening to players' requests and conditions using conversational AI,

[1895] A means to generate a proxy AI and negotiate based on the player's requests and conditions;

[1896] Retrieval Augment Generation means for analyzing market trends and past negotiation data;

[1897] means for providing the generated transaction information to a user;

[1898] A means of accumulating negotiation data and market trend data and conducting self-learning;

[1899] A means for users to input material requirements and automatically negotiate with suppliers for in-factory material procurement;

[1900] A means to select the best supplier based on material requirements and optimize prices;

[1901] A system including:

[1902] (Claim 2)

[1903] 2. The system according to claim 1, wherein the conversational artificial intelligence includes means for analyzing the player's requests and conditions using natural language processing and storing the results in a database.

[1904] (Claim 3)

[1905] 10. The system of claim 1, wherein the agent artificial intelligence includes means for communicating with other agent artificial intelligences and strategically negotiating with them.

[1906] "Example 2: Combining Emotion Engines"

[1907] (Claim 1)

[1908] A means of listening to players' requests and conditions using conversational AI,

[1909] means for generating emotion data by an emotion processing engine that recognizes the emotion of a user;

[1910] A means to generate a proxy AI and negotiate based on the player's requests and conditions;

[1911] Retrieval Augment Generation means for analyzing market trends and past negotiation data;

[1912] means for providing the generated transaction information to a user;

[1913] A means of accumulating negotiation data and market trend data and conducting self-learning;

[1914] A system including:

[1915] (Claim 2)

[1916] 2. The system according to claim 1, wherein the conversational artificial intelligence includes means for analyzing the player's requests and conditions using natural language processing and storing the results in a database.

[1917] (Claim 3)

[1918] 10. The system of claim 1, wherein the agent artificial intelligence includes means for communicating with other agent artificial intelligences and strategically negotiating with them.

[1919] "Application example 2 when combining emotion engines"

[1920] (Claim 1)

[1921] A means of listening to players' requests and conditions using conversational AI,

[1922] A means to generate a proxy AI and negotiate based on the player's requests and conditions;

[1923] Retrieval Augment Generation means for analyzing market trends and past negotiation data;

[1924] a means for providing the generated transaction information to a user;

[1925] A means for analyzing a user's emotions and generating emotion data;

[1926] A means for accumulating negotiation data, sentiment data, and market trend data and for self-learning;

[1927] A system including:

[1928] (Claim 2)

[1929] 2. The system according to claim 1, wherein the conversational artificial intelligence includes means for analyzing the player's requests and conditions using natural language processing and storing the results in a database.

[1930] (Claim 3)

[1931] 10. The system of claim 1, wherein the agent artificial intelligence includes means for communicating with other agent artificial intelligences and strategically negotiating with them. [Explanation of symbols]

[1932] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of listening to players' requests and conditions using conversational AI, A means to generate a proxy AI and negotiate based on the player's requests and conditions; Retrieval Augment Generation means for analyzing market trends and past negotiation data; means for providing the generated transaction information to a user; A means of accumulating negotiation data and market trend data and conducting self-learning; A system including:

2. 2. The system according to claim 1, wherein the conversational artificial intelligence includes means for analyzing the player's requests and conditions by natural language processing and storing the results in a database.

3. 2. The system of claim 1, wherein the agent artificial intelligence includes means for communicating with other agent artificial intelligences and strategically conducting negotiations.

Images