system

Abstract

Provide a system. A means for collecting real estate transaction data, contract data, and sales promotion data; means for analyzing and structuring said data; A means for sellers to enter property information; A means for buyers to input their desired conditions; A means for collating and matching the property information with the desired conditions; A means for proposing properties based on the matching results; How to schedule a tour, A means for automatically generating a sales contract; A system including a means for collecting fees.

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] High brokerage fees and complicated administrative procedures in real estate transactions place a heavy burden on both sellers and buyers. The traditional method of using a real estate brokerage company involves high labor costs, and the commission often reaches approximately 3% of the property price. The objective of this invention is to solve these problems and provide a system that enables efficient and inexpensive real estate transactions. [Means for solving the problem]

[0005] According to the present invention, the above problems are solved by using the following means: A means for collecting real estate transaction data, contract data, and sales promotion data is provided. A means for analyzing and structuring the collected data is used. A means for sellers to input property information and a means for buyers to input desired conditions are provided. Furthermore, a means for comparing and matching property information with desired conditions and a means for proposing properties based on the matching results are included. By also providing a means for arranging viewing dates, a means for automatically generating sales contracts, and a means for collecting fees, it is possible to automate the entire real estate transaction process and reduce fees.

[0006] "Real estate transaction data" refers to past transaction information and statistical data relating to the sale, purchase, and rental of real estate.

[0007] "Contract data" refers to data on legally binding contracts relating to the sale, purchase, or rental of properties.

[0008] "Promotional Data" means advertising and marketing materials and data used to promote the sale or rental of a Property.

[0009] "Means" refers to a method, device, or software function for achieving a specific purpose.

[0010] "Analysis" is the process of breaking down data and extracting patterns and regularities.

[0011] "Structuring" refers to organizing data and converting it into a certain format or form.

[0012] "Property information" refers to detailed information about real estate, such as the property's location, price, area, and facilities.

[0013] "Desired conditions" refer to the conditions and requirements (budget, area, size, facilities, etc.) that the buyer desires regarding the ideal property.

[0014] "Matching" is the process of comparing two or more data sets to identify similarities and differences.

[0015] "Matching" is the process of finding the best pair based on the seller's property information and the buyer's desired conditions.

[0016] "Suggestion" means presenting the optimal option to the user based on the selected information.

[0017] "Viewing schedule coordination" is the process of setting a date and time for a property viewing, taking into consideration the schedules of the seller and buyer.

[0018] A "sales contract" is a legally binding document relating to the sale and purchase of real estate, detailing the contents of the contract.

[0019] "Automatic generation" refers to the use of programs or algorithms to create specific documents or data without human intervention.

[0020] "Fee collection" is the process of collecting a set fee from a user for a service provided. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention is a system for automating real estate brokerage business. This system operates by interoperating with a server, a terminal, and a user.

[0043] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. The server preprocesses the collected data, converts it into an appropriate format, and centralizes it. The server then analyzes this data using machine learning algorithms and stores it in a structured database.

[0044] Next, the user (seller) enters information about their property through the terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and the terminal sends this data to the server. The server stores the received property information in a database and indexes the seller's property information in a searchable format.

[0045] Meanwhile, the user (buyer) inputs the conditions of the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, and the server stores the received conditions.

[0046] The server compares the stored property information with the buyer's desired conditions, runs the corresponding matching algorithm, and finds properties that match the buyer's desired conditions. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The buyer can then review the proposed property list through the terminal and view the details of the properties that interest them.

[0047] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and arranges the viewing date. The server then notifies both the seller and the buyer of the viewing date, helping to ensure the viewing goes smoothly.

[0048] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server uses generation AI to automatically create a sales contract. The contract is sent to both devices, and the users (seller and buyer) review and sign the contract. The server saves the signed contract and converts it into a legally valid format.

[0049] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0050] As described above, the present invention provides a system that fully automates real estate brokerage operations, resulting in efficient and cost-effective transactions for both parties.

[0051] Examples:

[0052] An individual (seller) looking to sell a property in Tokyo accesses a real estate brokerage system and registers property information. Let's say the seller is selling a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. The system stores this information in a database and makes it searchable by other users. Similarly, a buyer looking for a property in Tokyo enters their desired conditions into the system. If the desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system automatically extracts the seller's properties and proposes them to the buyer. The buyer then requests a viewing, and the system arranges a viewing date. After the viewing, if the buyer indicates their intention to purchase, a sales contract is automatically generated, and the signature and commission payment are completed through the system. This entire process is fully automated, making real estate transactions smooth and low-cost.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it converts the collected data into a unified format and manages it centrally.

[0056] Step 2:

[0057] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category, using natural language processing technology.

[0058] Step 3:

[0059] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0060] Step 4:

[0061] The server then verifies the property information received, stores it in a database in the appropriate format, and indexes this information in a searchable format.

[0062] Step 5:

[0063] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal. The desired conditions are immediately sent to the server.

[0064] Step 6:

[0065] The server stores the buyer's requirements and matches them with the property information, using a matching algorithm to identify the property that best meets the requirements.

[0066] Step 7:

[0067] The server generates a list of properties that match the buyer's desired conditions and sends the list to the terminal. The user (buyer) can check the list and view detailed information.

[0068] Step 8:

[0069] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0070] Step 9:

[0071] The server checks the seller's schedule and automatically adjusts the tour date, and notifies the seller and buyer of the adjusted tour date via their terminals.

[0072] Step 10:

[0073] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generation AI.

[0074] Step 11:

[0075] The created sales contract is sent to the seller and buyer via the terminal, where both parties confirm the contents of the contract and sign it on the terminal.

[0076] Step 12:

[0077] The server converts the signed contract into a legally valid format and stores it in a database.

[0078] Step 13:

[0079] The server calculates a commission of 1% of the property price and charges it to the seller and buyer. The commission is paid via the terminal, and after confirming the payment, the completion of the transaction is recorded.

[0080] These are the detailed processing steps that take place within the system, which will efficiently automate real estate transactions and significantly reduce costs.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Traditional real estate brokerage requires a lot of manual work and time, making transactions complicated and requiring efficient and speedy processing. Furthermore, the process involves a wide range of tasks, such as matching buyers and sellers, creating contracts, and arranging viewing dates, and full automation is required. Furthermore, automating the collection of commissions can reduce transaction costs and ensure smooth real estate transactions.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes means for collecting data, means for preprocessing and structuring the data, means for sellers to input real estate property information, means for buyers to input desired property conditions, means for preprocessing and saving the property information and the desired conditions, means for matching the property information with the desired conditions, means for proposing properties based on the matching results, means for arranging viewing dates, means for automatically generating a sales contract, and means for automatically collecting fees. This makes it possible to automate all real estate transaction operations efficiently and quickly, thereby reducing transaction costs.

[0086] "Means of collecting data" refers to a means of centrally collecting data related to real estate transactions, contract data, and sales promotion data.

[0087] The "means for preprocessing and structuring the data" refers to a means for converting the collected data into an appropriate format, and preparing it for centralized management and analysis using machine learning algorithms.

[0088] "Means for sellers to input information about real estate properties" refers to an interface for sellers to input detailed information about their properties (e.g., location, price, area, facilities), and is a means for transmitting information to a server via a terminal.

[0089] "Means for buyers to input the conditions for the property they desire" refers to an interface for buyers to input the conditions for the property they desire (e.g., budget, area, size, facilities), and is a means for transmitting information to the server via a terminal.

[0090] The "means for preprocessing and storing the property information and desired conditions" is a means for preprocessing the input property information and desired conditions and storing them in a database.

[0091] The "means for matching the property information with the desired conditions" refers to a means for executing an algorithm that matches the stored property information with the desired conditions and identifies a property that matches the buyer's desires.

[0092] The "means for proposing properties based on the results of the matching" refers to a means for generating a list of suitable properties based on the results of the matching algorithm and presenting the list to the buyer.

[0093] The "means of arranging a viewing date" refers to a means of matching the buyer's desired viewing date with the seller's schedule and arranging a viewing date that is convenient for both parties.

[0094] "Means for automatically generating a sales contract" refers to a means for automatically generating a contract using a generative AI model and sending the contract to both users.

[0095] A "means for automatically collecting fees" is a means for calculating fees based on the property price and automatically collecting fees from sellers and buyers.

[0096] The present invention is a system for fully automating real estate brokerage business, which operates in cooperation with a server, terminals, and users.

[0097] Hardware and software used

[0098] Server: Database management systems (e.g., MySQL (registered trademark), PostgreSQL), machine learning algorithms (e.g., scikit-learn, TENSORFLOW (registered trademark)), generative AI models (e.g., GPT-4 (registered trademark))

[0099] Devices: PC, smartphone, web application, mobile app

[0100] Data format: JSON, CSV

[0101] Database: Structured database (e.g., MySQL, PostgreSQL), indexing system (e.g., ElasticSearch (registered trademark))

[0102] Prompt input example: Text format

[0103] System Operation

[0104] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server collects data through various APIs and database connections and performs preprocessing. Preprocessing involves converting the data into an appropriate format (e.g., JSON) and removing noise and missing values ​​to prepare it for centralized management. The server also structures the data for analysis and analyzes it using machine learning algorithms. The analysis results are stored in a structured database (e.g., MySQL).

[0105] Next, the user (seller) enters property information. Detailed information such as the property's location, price, area, and facilities is entered via a web application or mobile app displayed on the device (PC or smartphone). The device then sends the entered information to the server. The server stores the received information in a database and makes it searchable using an indexing system (e.g., Elasticsearch).

[0106] Similarly, the user (buyer) inputs their desired conditions, such as budget, area, size, and facilities, through a terminal. The terminal sends the information to the server, which then stores it in a database.

[0107] The server compares the stored property information with the buyer's desired conditions. It then runs a matching algorithm (e.g., collaborative filtering, content-based filtering) to identify suitable properties. The server then generates a property list based on the results and sends it to the terminal. The user (buyer) can then view the proposed property list through the terminal.

[0108] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the terminal. The server uses this information to check the seller's schedule and arranges the viewing date. The viewing date is notified to both the seller and the buyer.

[0109] After viewing the property, if the user (buyer) indicates their intention to purchase the property, the server automatically generates a sales contract using a generative AI model (e.g., GPT-4). At this time, the server inputs the following prompt sentence into the generative AI to create the contract:

[0110] "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo."

[0111] The generated contract is sent to both terminals, where the users (seller and buyer) confirm the contents and digitally sign them. The server stores the signed contract and converts it into a legally valid format.

[0112] Finally, the server automatically collects a 1% commission on the property price. Users (sellers and buyers) complete the commission payment on the system, and the server records the completion of the transaction once it has confirmed the payment.

[0113] In this way, the system of the present invention can automate each stage of a real estate transaction efficiently and quickly, thereby reducing transaction costs.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1: Data collection and preprocessing

[0116] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server uses APIs and SQL queries to extract data and convert it into formats (e.g., JSON, CSV). Preprocessing includes filling in missing values ​​and removing noise data. The input data is the raw data from various databases, and the output data is preprocessed data in a standardized format.

[0117] Step 2: Enter property information

[0118] The user (seller) uses a terminal to enter property information (location, price, area, facilities, etc.). The terminal provides a form-based interface, verifies the entered data, and then sends it to the server. The input data is the property information entered by the seller, and the output data is the property data in JSON format that is sent to the server.

[0119] Step 3: Enter your desired conditions

[0120] The user (buyer) uses a terminal to input desired conditions (budget, area, size, facilities, etc.). The terminal also provides a form-based interface and sends the input information to the server. The input data is the buyer's desired conditions, and the output data is the desired conditions data in JSON format that is sent to the server.

[0121] Step 4: Storing and indexing data

[0122] The server stores the received property information and desired conditions in a database. The stored data is indexed and made searchable (e.g., Elasticsearch). The input data is JSON data of the property information and desired conditions, and the output data is in an indexed database state.

[0123] Step 5: Match property information with desired conditions

[0124] The server matches the stored property information with the buyer's desired criteria. It uses specific algorithms (e.g., collaborative filtering, content-based filtering) to identify properties that match the buyer's desired criteria. The input data is the indexed property information and desired criteria, and the output data is the matching property list.

[0125] Step 6: Property proposal

[0126] The server generates a list of properties to be proposed based on the matching results and sends the list to the terminal. The user (buyer) checks the proposed property list through the terminal. The input data is the property list of the matching results, and the output data is the property list displayed on the terminal.

[0127] Step 7: Arrange a tour date

[0128] The user (buyer) inputs the desired tour date into the terminal. The server checks it against the seller's schedule and arranges an appropriate tour date. The server notifies the seller and buyer of the tour date. The input data is the desired tour date, and the output data is a notification of the adjusted tour date.

[0129] Step 8: Auto-generate a sales contract

[0130] When a user (buyer) indicates their intention to purchase, the device sends that information to the server. The server then uses a generative AI model (e.g., GPT-4) to automatically generate a sales contract. An example of a prompt is "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo." The generated contract is sent to both devices, and the users (seller and buyer) confirm the contents and sign electronically. The input data is the information indicating their intention to purchase, and the output data is the generated contract.

[0131] Step 9: Fee Collection

[0132] The server automatically collects a commission of 1% of the property price from the seller and buyer. Users (sellers and buyers) complete the commission payment on the system. The server confirms the payment and records the completion of the transaction. The input data is the property price and commission rate, and the output data is a record of the commission collected.

[0133] (Application example 1)

[0134] 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."

[0135] In real estate transactions, efficient matching between sellers and buyers and quick contract procedures are required. Furthermore, scheduling property viewings and contracts is complicated, making it difficult for both parties to communicate smoothly. This issue is also common to service provision and reservation systems in brick-and-mortar stores, and there is a particular need for efficient and smooth service provision between store owners and users. This project aims to solve these issues.

[0136] 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.

[0137] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for sellers to input property information or store information, means for buyers to input desired conditions, means for collating and matching the property information or store information with the desired conditions, means for proposing properties or stores based on the collation results, means for arranging viewing dates or available reservation dates and times, means for automatically generating contracts, and means for collecting fees. This enables efficient and smooth matching, schedule adjustment, contract conclusion, and automatic fee collection in real estate transactions and brick-and-mortar store services.

[0138] "Real estate transaction data" refers to data that includes information regarding the sale, purchase, and rental of properties.

[0139] "Contract data" refers to data on documents relating to sales or rental contracts.

[0140] "Promotional Data" means data that includes marketing information for the purpose of promoting sales, purchases, or rentals.

[0141] "Seller" is the person or entity selling or renting the property or store.

[0142] "Property information" is data that includes detailed information about the property, such as its location, price, area, and facilities.

[0143] "Store information" is data including detailed information such as the store's location, business hours, services offered, and price range.

[0144] "Buyer" means a person or legal entity seeking to purchase or occupy a property or store.

[0145] "Desired conditions" are the conditions the buyer desires regarding the property or store.

[0146] "Matching" means comparing the seller's property or store information with the buyer's desired conditions to find a suitable match.

[0147] A "proposal" is the introduction of a property or store to a buyer based on the matching results.

[0148] "Viewing dates" and "reservation dates" are schedules for sellers and buyers to inspect properties and stores.

[0149] "Automatic contract generation" means that the system automatically creates the contents of a sales or usage contract.

[0150] "Fee collection" means automatically collecting fees from sellers and buyers for using the system.

[0151] This invention is a system that efficiently and automatically matches property and store information and speeds up contract procedures. It is equipped with means for collecting, analyzing, and structuring real estate transaction data, contract data, and sales promotion data. It also includes a function that allows sellers and buyers to input their respective information, performs matching, and proposes the most suitable property or store.

[0152] 1. System Configuration

[0153] The server runs in a cloud environment such as AWS (registered trademark) (Amazon Web Services) and collects, analyzes, stores, and structures data. React Native (for smartphones) and React (for the web) are used for the front end, and an interface with the devices (smartphones and computers) where users input information is built. Node.js and Express are used for the back end, and are responsible for data processing and API provision. SQL databases (MySQL) and NoSQL databases (MongoDB) are used. Furthermore, the scikit-learn library is used for machine learning to implement a matching algorithm.

[0154] 2. Data collection and analysis

[0155] The server collects real estate transaction data, contract data, and sales promotion data from various databases, analyzes and structures it, and uses machine learning algorithms to convert the collected data into an appropriate format for centralized management.

[0156] 3. Enter seller and buyer information

[0157] Sellers input their property or store information through a terminal. The input information includes location, price, area, facilities, business hours, etc. Buyers also input the conditions for the property or store they are looking for through a terminal. The input conditions include budget, area, size, specific facilities and services, etc.

[0158] 4. Matching and Proposal

[0159] The server uses machine learning to match the seller's property or store information with the buyer's desired conditions and generates the optimal matching results. Based on these results, the optimal property or store is proposed and provided to the buyer.

[0160] 5. Arrangement of tour dates or available reservation dates

[0161] The system automatically coordinates viewing dates and available reservation dates for properties and stores by checking the schedules of both the seller and buyer. The system suggests the optimal date and time based on the schedules of both parties, helping to ensure that viewings and reservations go smoothly.

[0162] 6. Automatically generate and sign contracts

[0163] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract. The contract is created using a generative AI model and sent to both devices. The user can then review the contract and sign it via their device.

[0164] 7. Collection of Fees

[0165] Finally, fees for using the property or store are automatically collected from the seller and buyer via the system, and the transaction is completed.

[0166] Specific examples

[0167] For example, a user searching for a cafe in Tokyo enters the following prompt on their smartphone:

[0168] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[0169] The system matches cafes that meet the criteria and presents available dates and times for reservations. The user selects the desired date and time and confirms the reservation through the system. Finally, a usage agreement with the cafe is automatically generated, which is signed and confirmed by both the user and the cafe. This series of processes is carried out efficiently and smoothly, bringing benefits to both the user and the cafe owner.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Because the collected data is inconsistent in format and content, it is preprocessed to convert it into a unified format. Specifically, it parses the JSON and XML formatted data, extracts the necessary fields, and stores them in a structured database. This process is expected to use AWS's data lake service.

[0173] Step 2:

[0174] Through the terminal, sellers input property or store information, including the property or store's location, price, area, facilities, and opening hours. The terminal then sends the input information to the server, which stores the received data in a database and indexes it for searchability.

[0175] Step 3:

[0176] Through the terminal, buyers input their desired property or store conditions, such as budget, area, size, specific facilities and services, etc. The terminal then transmits the desired conditions to the server, which stores the information in a database.

[0177] Step 4:

[0178] The server uses a machine learning algorithm to match the seller's property or store information with the buyer's desired conditions. The algorithm used in this process is implemented using the scikit-learn library. Specifically, the input data is treated as features, and matching is performed by calculating the similarity. The matching results obtained in this way are stored in a database.

[0179] Step 5:

[0180] The server then proposes the most suitable property or store to the buyer based on the matching results. The proposed list is sent to the buyer's terminal and can be viewed by the buyer. The proposed list includes detailed information about the property or store.

[0181] Step 6:

[0182] When a buyer selects a tour date or an available reservation date and time, that information is sent to the server. The server checks the seller's schedule and automatically adjusts the optimal tour date or reservation date and time. The adjusted results are notified to the seller's and buyer's terminals.

[0183] Step 7:

[0184] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract using a generative AI model. This contract is then sent to both devices, where the user can review the contents and electronically sign.

[0185] Step 8:

[0186] Once the contract procedure is completed, the server automatically collects the fee. To collect the fee, an electronic payment service is used. Once payment is confirmed, the transaction is completed and a record is saved in the database.

[0187] The data processing and calculations performed at each step are as follows:

[0188] In step 1, various data is collected, converted into an appropriate format, and centrally managed.

[0189] In steps 2 and 3, the data entered by the user is formatted, sent to the server, and saved.

[0190] In step 4, machine learning algorithms are used to collate the data and generate matching results.

[0191] In step 5, properties and stores are proposed based on the matching results.

[0192] Step 6 automates tours and reservations through schedule adjustments.

[0193] In step 7, a generative AI model is used to automatically generate a contract and assist with electronic signatures.

[0194] In step 8, fees are automatically collected using an electronic payment service.

[0195] For example, here's a prompt that a user searching for a cafe in Tokyo might enter:

[0196] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[0197] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0198] This invention is a system for automating real estate brokerage business, and further combines an emotion engine that recognizes user emotions and provides optimal services. The system operates in cooperation with a server, terminals, and users.

[0199] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it preprocesses it, converts it into a unified format, and centrally manages it. Then, the server analyzes the data using machine learning algorithms and stores it in a structured database by category.

[0200] The user (seller) enters information about their property through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format.

[0201] The user (buyer) inputs the conditions for the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, which then stores the received conditions. Furthermore, the emotion engine recognizes the emotion of the user when entering the information and records it in a database.

[0202] The server compares property information with the buyer's desired conditions. At this time, an emotion engine analyzes the user's emotional state and reflects this in the property suggestions. The matching algorithm identifies properties that meet the desired conditions and then takes the user's emotions into consideration to suggest the most suitable property. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The user (buyer) can review this list and view detailed information.

[0203] When a user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and adjusts the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and proposes the optimal date. The server then notifies both the seller and the buyer of the viewing date.

[0204] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server automatically creates a sales contract using generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts.

[0205] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then verifies the payment and records the completion of the transaction.

[0206] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment located in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, another user looking for a property in Tokyo enters their desired conditions into the system. If this user's desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract the seller's properties, and the emotion engine will make suggestions while checking the user's emotional state. Intentions to view properties and the emotional state at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[0207] The above is a specific embodiment of the system that combines the emotion engine, which enables efficient and emotion-conscious real estate transactions.

[0208] The processing flow will be explained below.

[0209] Step 1:

[0210] The server collects real estate transaction data, contract data, and sales promotion data from various databases, converts the collected data into an appropriate format, and manages it centrally.

[0211] Step 2:

[0212] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category. It also uses natural language processing technology to analyze the meaning of the data and create an index.

[0213] Step 3:

[0214] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0215] Step 4:

[0216] The server stores the received property information in a database, automatically verifies that the data is accurate and complete, and indexes the stored property information in a searchable format.

[0217] Step 5:

[0218] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal, and the desired conditions are immediately sent to the server.

[0219] Step 6:

[0220] The server stores the desired conditions received from the buyer. Furthermore, when the user inputs the conditions, the terminal uses an emotion engine to analyze the user's emotional state (e.g., satisfaction, anxiety, expectation) and records it in a database.

[0221] Step 7:

[0222] The server compares the stored property information with the buyer's desired conditions and executes a matching algorithm, during which an emotion engine analyzes the user's emotional state and reflects it in the property proposals.

[0223] Step 8:

[0224] The server generates a property list based on the matching results and sends it to the user's (buyer's) terminal in a format that is easy for the user to view. The emotion engine monitors the user's reaction when making a proposal and provides necessary support.

[0225] Step 9:

[0226] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0227] Step 10:

[0228] The server checks the seller's schedule and automatically adjusts the tour date. At this time, the emotion engine analyzes the user's emotions and suggests the optimal tour date and time. The adjusted tour date is notified to the seller and buyer via their terminals.

[0229] Step 11:

[0230] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generative AI. During this process, the emotion engine also records the user's emotional state.

[0231] Step 12:

[0232] The created sales contract is sent to the seller and buyer via the terminal. The users (seller and buyer) check the contents of the contract and sign it on the terminal. At this time, the emotion engine detects the user's anxieties and concerns at the time of signing and provides appropriate support.

[0233] Step 13:

[0234] The server converts the signed contract into a legally valid format and stores it in a database.

[0235] Step 14:

[0236] The server calculates the commission of 1% of the property price for both the seller and the buyer, issues an invoice, and records the completion of the transaction after the commission is paid via the terminal.

[0237] The above are the detailed processing steps of this system that combines an emotion engine. As a concrete example, consider the case where a user wants to sell a property in Tokyo. This user registers property information in the system, and the property is proposed to another user as a property that matches their desired conditions. The emotion engine analyzes the user's emotional state at the time of proposal, viewing, and contract signing, and supports the user so that they can proceed with the transaction with peace of mind. This system realizes efficient and user-friendly real estate transactions.

[0238] Example 2

[0239] 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."

[0240] In traditional real estate brokerage, many processes, such as data collection, analysis, property matching, scheduling tours, creating contracts, and collecting fees, were performed manually, resulting in time-consuming, labor-intensive, and inefficient processes. Furthermore, the process often ignored the user's emotional state, causing anxiety and doubt during the transaction. There is a need to solve these problems and realize efficient real estate transactions that take the user's emotions into consideration.

[0241] 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.

[0242] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for preprocessing the data, converting it into a unified format, and centrally managing it, means for analyzing the data using a machine learning algorithm and saving it in a structured database, means for sellers to input property information, means for indexing the input property information in a searchable format, means for buyers to input desired conditions, means for recognizing the buyer's emotions at the time of input and recording them in a database, means for comparing and matching the property information with the desired conditions and the buyer's emotional state, means for proposing optimal properties based on the matching results, means for arranging a viewing schedule, means for comparing the schedules of the buyer and seller and proposing a viewing schedule taking into account the buyer's emotional state, means for automatically generating a sales contract based on a generative AI model, means for recording the user's emotions at the time of signing and providing support for any concerns or doubts, means for automatically collecting fees, and means for confirming payment and recording the completion of the transaction, thereby enabling efficient real estate transactions that are considerate of the user's emotions.

[0243] "Real estate transaction data" refers to all information related to the sale, purchase, rental, and contract of real estate, and specifically includes data such as the property price, location, area, facilities, and contract terms.

[0244] "Contract data" refers to the information contained in contracts used in real estate transactions, including legal clauses, information about the parties, terms of the transaction, signatures, and the like.

[0245] "Promotional Data" refers to marketing information used to promote real estate transactions, including advertising campaigns, customer interest and behavior data, and promotional information.

[0246] "Preprocessing" refers to the processing performed before analyzing data, and includes operations such as cleaning the data, filling in missing values, and standardizing the format.

[0247] A "unified format" refers to converting data of different formats into a consistent format, making it easier to centrally manage and analyze data obtained from various sources.

[0248] A "machine learning algorithm" is a computational technique for analyzing data and finding patterns, and the results are used to make predictions and optimizations.

[0249] A "structured database" is a database system for systematically organizing and storing data, storing data in a table format to enable efficient searching and manipulation.

[0250] "Property information" refers to detailed information about real estate provided by the seller, specifically data including location, price, area, number of rooms, facilities, etc.

[0251] "Indexing to a searchable state" refers to the process of organizing and registering data so that it can be searched efficiently, allowing data to be quickly retrieved based on keywords or conditions.

[0252] "Desired conditions" refer to the characteristics and conditions of the property desired by the buyer, and include specific requests such as budget, area, size, and facilities.

[0253] "Recognizing emotions and recording them in a database" refers to the operation of analyzing the user's emotional state and storing the results in a database, making it possible to use data that takes into account the user's psychological state.

[0254] "Verifying and matching" refers to the process of comparing and considering the seller's property information with the buyer's desired conditions and emotional state, and identifying and proposing properties that meet the matching conditions.

[0255] "Proposing the best property" means selecting and recommending the property that is most suitable for the buyer based on the analysis results and the user's emotional state.

[0256] "Adjusting viewing dates" refers to the operation of confirming and adjusting the schedules of the seller and buyer to decide on a date to view the property.

[0257] A "generative AI model" refers to an artificial intelligence method for automatically generating new information and documents based on large amounts of data, and is a technology that performs natural language processing and document generation.

[0258] "Recording emotions during signing and providing support for anxiety and doubts" refers to the operation of recording the user's emotional state when signing a contract and providing support and assistance as needed.

[0259] "Automatically collecting fees" refers to the operation of automatically calculating and collecting transaction fees by the system.

[0260] "Recording the completion of a transaction" refers to the operation of registering and saving the final status of the transaction in the system and recording that the transaction has officially ended.

[0261] The present invention provides a system for improving the efficiency of real estate brokerage services and providing services that take user emotions into consideration. This system operates in cooperation with a server, a terminal, and a user. Specific embodiments are described below.

[0262] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, it efficiently collects large amounts of data using Apache Hadoop, preprocesses the data using Python's pandas library, converts it into a unified format, and centrally manages it. This centrally managed data is then stored in a relational database such as MySQL or PostgreSQL. The server then analyzes the data using machine learning algorithms such as Scikit-learn and TensorFlow, and stores the analysis results in a structured database.

[0263] Users (sellers) enter their property information from a device (PC or smartphone app). Specifically, they enter detailed information such as the property's location, price, area, and facilities into a form, and this data is sent from the device to the server. The server indexes the received property information into a search engine such as Elasticsearch, making it searchable.

[0264] The user (buyer) inputs the conditions for the property they are looking for on their device. This information includes desired conditions such as budget, area, size, and facilities. These desired conditions are sent from the device to the server and stored. Furthermore, an emotion engine (e.g., Amazon Rekognition or Microsoft® Azure® Face API) analyzes the face and text entered by the user to recognize emotions and record the results in a database.

[0265] The server compares property information with the buyer's desired conditions and emotional state to suggest the most suitable property. Specifically, it compares property information using Elasticsearch and runs a matching algorithm using a recommendation system library (e.g., Surprise or LightFM). As a result, a list of the most suitable properties is generated and sent to the user's (buyer's) device.

[0266] When a user (buyer) wishes to visit a property, they input their desired dates into the system. The server checks the schedules of the seller and buyer, and then uses an emotion engine to suggest the optimal date for the visit. Once the date for the visit has been decided, the server notifies both the seller and buyer.

[0267] If a user (buyer) wishes to purchase a property, they express their intention through their device. The server automatically creates a sales contract using a generative AI model (e.g., OpenAI (registered trademark) GPT) and sends this contract to both users. The user signs the contract on their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[0268] The server automatically collects a 1% commission from the seller and buyer of the property. This process uses online payment services such as Stripe or PayPal API. Once the payment is confirmed, the server records the transaction as completed.

[0269] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, if another user looking for a property enters their desired conditions, setting "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract matching properties, and the emotion engine will make the optimal proposal while checking the user's emotions. Intentions to view properties and emotions at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[0270] An example prompt is:

[0271] "Please register information about a 3LDK apartment for sale for 70 million yen in the system."

[0272] or

[0273] "I'm looking for a 3LDK apartment in Tokyo. My budget is 80 million yen."

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] The server collects real estate transaction data, contract data, and sales promotion data from various databases. The input is a dataset provided by multiple databases, and the output is data in a unified format. The specific operations for data collection involve acquiring the data using Apache Hadoop, preprocessing the data using Python's pandas library, completing missing values, and unifying the format.

[0277] Step 2:

[0278] The server analyzes the preprocessed data and generates analytical results using machine learning algorithms. The input is the preprocessed data, and the output is the analytical results. Specifically, it uses libraries such as Scikit-learn and TensorFlow to train models for estimating property prices and predicting buyer behavior. The analytical results are stored in a structured database.

[0279] Step 3:

[0280] The user (seller) enters their property information from a terminal. The input is detailed property information (location, price, area, facilities, etc.), and the output is indexed property information. Specifically, the user enters detailed property information using an input form, and the data is sent to the server using an HTTP request. The server indexes the received data in the Elasticsearch search engine.

[0281] Step 4:

[0282] The user (buyer) inputs the desired property conditions from a terminal. The input is the desired conditions (budget, area, size, facilities, etc.), and the output is the saved desired condition data. In concrete terms, the desired conditions are entered using an input form, and the information is sent to the server via an HTTP request. The emotion engine is used to analyze the user's emotions at the time of input, and the results are recorded in a database.

[0283] Step 5:

[0284] The server compares property information with the buyer's desired conditions and emotional state to generate the optimal property list. The input is property information, desired conditions, and emotional data, and the output is the optimal property list. Specifically, it uses Elasticsearch to search for properties that match the conditions and executes a matching algorithm using the Recommendation System library. The generated property list is sent to the terminal.

[0285] Step 6:

[0286] The user (buyer) inputs the tour schedule. The input is the desired tour schedule, and the output is the adjusted tour schedule. Specifically, the desired tour schedule is entered from the terminal, and the information is sent to the server via an HTTP request. The server compares it with the seller's schedule and proposes the optimal tour schedule taking into account the buyer's emotional state. This schedule is notified to both the seller and the buyer.

[0287] Step 7:

[0288] When a user (buyer) expresses their intention to purchase, the server automatically generates a sales contract using a generative AI model. The input is information about the sales contract, and the output is an automatically generated contract. Specifically, a contract is created using a generative AI model such as OpenAI GPT, and the contract is sent to the user. The user signs the contract through their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[0289] Step 8:

[0290] The server automatically collects the fee and completes the transaction. The input is the purchase amount and fee calculation information, and the output is a record of the transaction completion. Specifically, it automates the collection of fees using Stripe or PayPal API, and once payment is confirmed, records the completion of the transaction in the database.

[0291] (Application example 2)

[0292] 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."

[0293] Current real estate brokerage systems have difficulty accurately matching the needs of buyers and sellers, and rarely consider the user's emotional state when making proposals. This often leaves users feeling frustrated and stressed when searching for a property. Furthermore, efficient advertisement generation and delivery is lacking, reducing the opportunities for users to receive the most appropriate information.

[0294] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for recognizing the user's emotions and making optimal property proposals based on the emotional state, and means for generating and providing real estate advertisements based on the emotional state. This makes it possible to make appropriate property proposals and advertisements based on the user's emotional state.

[0295] "Real estate transaction data" refers to information relating to the sale, purchase, or rental of real estate, and includes details such as the property's location, price, area, floor plan, and age.

[0296] "Contract data" refers to document data that describes the contract details related to real estate transactions, and is electronic data such as sales contracts and rental contracts.

[0297] "Promotional Data" means data relating to marketing and sales promotions, including information about advertising campaigns, promotional materials, and consumer responses.

[0298] "Means for recognizing emotions" refers to technology that analyzes a user's input and behavior to identify their emotional state, and is a method that uses natural language processing and machine learning algorithms.

[0299] "Means for making optimal property proposals" refers to technology that selects and proposes the most suitable property based on the user's desired conditions and emotional state.

[0300] "Means for generating and providing real estate advertisements" refers to a technology that uses a generative AI model to create advertising copy about real estate and provides it at a time that corresponds to the user's emotional state.

[0301] The "emotional state of a user" refers to the emotions that a user has in a particular situation, and is a general term for emotions such as satisfaction, stress, joy, and sadness.

[0302] The present invention is a system that automates real estate brokerage operations and provides optimal services by recognizing user emotions. This system operates in cooperation with a server, terminals, and users.

[0303] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collection, this data is preprocessed and converted into a unified format for centralized management. Next, the server analyzes the data using machine learning algorithms and stores it in a database structured by category. The specific software used is Pandas and SQLite.

[0304] The user (seller) enters their property information through a terminal. This information includes details such as the property's location, price, area, and facilities, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format. The user (buyer) also enters the property conditions they desire through the terminal. These conditions are also sent from the terminal to the server, and the server stores the received conditions.

[0305] The emotion engine recognizes the emotion of the user's input and records it in a database. This emotion engine uses the Google® Cloud Natural Language API.

[0306] The server compares the entered property information with the buyer's desired conditions and performs matching. At this time, an emotion engine analyzes the user's emotional state and reflects it in the property suggestions. The matching algorithm is implemented using Scikit-learn, identifies properties that meet the desired conditions, and suggests the most suitable property taking the user's emotions into consideration. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal.

[0307] The user (buyer) can check this list and view detailed information. If they wish to view a property they are interested in, they input their desired dates into the system. The server checks this against the seller's schedule and arranges the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and suggests the most appropriate date. The viewing date is then notified to both the seller and the buyer.

[0308] After viewing the property, if the user (buyer) wishes to purchase it, they express their intention to do so via their device. The server automatically creates a sales contract using the generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts. OpenAI's GPT model is used for the generation AI.

[0309] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0310] For example, if a user inputs "I'm tired of searching for a property lately," the system will analyze this input and generate and provide a positive ad copy that takes into account the user's emotional state. This ad copy will be provided in the form of "Tired of searching for a property? We have a great suggestion to help you relax. Please take a look."

[0311] This system will enable efficient and emotionally sensitive real estate transactions and advertising.

[0312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0313] Step 1:

[0314] The server collects real estate transaction data, contract data, and sales promotion data from various databases and performs preprocessing. During this process, the Pandas library is used to convert the data into a unified format such as CSV and save it in an SQLite database. Data input is performed via API from external databases, and output is data saved in a unified format.

[0315] Step 2:

[0316] The user (seller) enters property information through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered into an input form, and this data is sent from the terminal to the server. The input data is sent to the server in a standardized format such as JSON, and the server stores it in a database and indexes it so that it can be searched.

[0317] Step 3:

[0318] The user (buyer) inputs the desired property conditions through a terminal. Desired conditions include budget, area, size, facilities, etc. These desired conditions are sent from the terminal to the server, which then stores the received conditions in a database. The input data is sent to the server in a standardized format such as JSON and stored in the database.

[0319] Step 4:

[0320] The emotion engine recognizes the emotion expressed by the user when they input text and records it in a database. Sentiment analysis uses the Google Cloud Natural Language API to analyze the user's input text and calculate an emotion score. The input is the user's text data, and the output is the emotion score and its classification result (satisfaction, stress, etc.).

[0321] Step 5:

[0322] The server compares the entered property information with the buyer's desired conditions and performs matching. It uses Scikit-learn to apply a machine learning matching algorithm. At this time, the emotional state of the buyer is also reflected in the analysis results using an emotion engine. The input is the seller's property information, the buyer's desired conditions, and an emotion score, and the output is a list of optimal property proposals.

[0323] Step 6:

[0324] Users (buyers) can check the proposed property listings on their devices and view detailed information. The user interface is implemented as a web page or mobile app, and the information provided is obtained in real time from the server.

[0325] Step 7:

[0326] When a user (buyer) wishes to tour the property, they enter the desired tour dates into the system. The server checks the seller's schedule and automatically adjusts the tour dates. The Google Calendar API is used to adjust the tour dates. The input is the user's desired tour dates, and the output is the adjusted tour dates.

[0327] Step 8:

[0328] The server automatically generates a sales contract using a generative AI model. It uses OpenAI's GPT model to create a contract template and sends it to users (sellers and buyers). The input is basic contract information and sentiment scores, and the output is an automatically generated contract.

[0329] Step 9:

[0330] Users (seller and buyer) review the contract and sign it electronically through their devices. This process uses an electronic signature platform (e.g., DocuSign). The input is the generated contract, and the output is the signed contract.

[0331] Step 10:

[0332] The server automatically collects a 1% commission from the seller and buyer of the property price. This process uses an electronic payment service (e.g., Stripe). The input is the property price and commission information, and the output is confirmation of the commission collected.

[0333] Example prompt sentence:

[0334] "I'm tired of searching for properties lately."

[0335] 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.

[0336] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0337] 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.

[0338] [Second embodiment]

[0339] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0340] 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.

[0341] 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).

[0342] 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.

[0343] 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.

[0344] 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).

[0345] 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.

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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.

[0350] 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."

[0351] The present invention is a system for automating real estate brokerage business. This system operates by interoperating with a server, a terminal, and a user.

[0352] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. The server preprocesses the collected data, converts it into an appropriate format, and centralizes it. The server then analyzes this data using machine learning algorithms and stores it in a structured database.

[0353] Next, the user (seller) enters information about their property through the terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and the terminal sends this data to the server. The server stores the received property information in a database and indexes the seller's property information in a searchable format.

[0354] Meanwhile, the user (buyer) inputs the conditions of the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, and the server stores the received conditions.

[0355] The server compares the stored property information with the buyer's desired conditions, runs the corresponding matching algorithm, and finds properties that match the buyer's desired conditions. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The buyer can then review the proposed property list through the terminal and view the details of the properties that interest them.

[0356] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and arranges the viewing date. The server then notifies both the seller and the buyer of the viewing date, helping to ensure the viewing goes smoothly.

[0357] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server uses generation AI to automatically create a sales contract. The contract is sent to both devices, and the users (seller and buyer) review and sign the contract. The server saves the signed contract and converts it into a legally valid format.

[0358] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0359] As described above, the present invention provides a system that fully automates real estate brokerage operations, resulting in efficient and cost-effective transactions for both parties.

[0360] Examples:

[0361] An individual (seller) looking to sell a property in Tokyo accesses a real estate brokerage system and registers property information. Let's say the seller is selling a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. The system stores this information in a database and makes it searchable by other users. Similarly, a buyer looking for a property in Tokyo enters their desired conditions into the system. If the desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system automatically extracts the seller's properties and proposes them to the buyer. The buyer then requests a viewing, and the system arranges a viewing date. After the viewing, if the buyer indicates their intention to purchase, a sales contract is automatically generated, and the signature and commission payment are completed through the system. This entire process is fully automated, making real estate transactions smooth and low-cost.

[0362] The processing flow will be explained below.

[0363] Step 1:

[0364] The server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it converts the collected data into a unified format and manages it centrally.

[0365] Step 2:

[0366] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category, using natural language processing technology.

[0367] Step 3:

[0368] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0369] Step 4:

[0370] The server then verifies the property information received, stores it in a database in the appropriate format, and indexes this information in a searchable format.

[0371] Step 5:

[0372] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal. The desired conditions are immediately sent to the server.

[0373] Step 6:

[0374] The server stores the buyer's requirements and matches them with the property information, using a matching algorithm to identify the property that best meets the requirements.

[0375] Step 7:

[0376] The server generates a list of properties that match the buyer's desired conditions and sends the list to the terminal. The user (buyer) can check the list and view detailed information.

[0377] Step 8:

[0378] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0379] Step 9:

[0380] The server checks the seller's schedule and automatically adjusts the tour date, and notifies the seller and buyer of the adjusted tour date via their terminals.

[0381] Step 10:

[0382] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generation AI.

[0383] Step 11:

[0384] The created sales contract is sent to the seller and buyer via the terminal, where both parties confirm the contents of the contract and sign it on the terminal.

[0385] Step 12:

[0386] The server converts the signed contract into a legally valid format and stores it in a database.

[0387] Step 13:

[0388] The server calculates a commission of 1% of the property price and charges it to the seller and buyer. The commission is paid via the terminal, and after confirming the payment, the completion of the transaction is recorded.

[0389] These are the detailed processing steps that take place within the system, which will efficiently automate real estate transactions and significantly reduce costs.

[0390] Example 1

[0391] 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."

[0392] Traditional real estate brokerage requires a lot of manual work and time, making transactions complicated and requiring efficient and speedy processing. Furthermore, the process involves a wide range of tasks, such as matching buyers and sellers, creating contracts, and arranging viewing dates, and full automation is required. Furthermore, automating the collection of commissions can reduce transaction costs and ensure smooth real estate transactions.

[0393] 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.

[0394] In this invention, the server includes means for collecting data, means for preprocessing and structuring the data, means for sellers to input real estate property information, means for buyers to input desired property conditions, means for preprocessing and saving the property information and the desired conditions, means for matching the property information with the desired conditions, means for proposing properties based on the matching results, means for arranging viewing dates, means for automatically generating a sales contract, and means for automatically collecting fees. This makes it possible to automate all real estate transaction operations efficiently and quickly, thereby reducing transaction costs.

[0395] "Means of collecting data" refers to a means of centrally collecting data related to real estate transactions, contract data, and sales promotion data.

[0396] The "means for preprocessing and structuring the data" refers to a means for converting the collected data into an appropriate format, and preparing it for centralized management and analysis using machine learning algorithms.

[0397] "Means for sellers to input information about real estate properties" refers to an interface for sellers to input detailed information about their properties (e.g., location, price, area, facilities), and is a means for transmitting information to a server via a terminal.

[0398] "Means for buyers to input the conditions for the property they desire" refers to an interface for buyers to input the conditions for the property they desire (e.g., budget, area, size, facilities), and is a means for transmitting information to the server via a terminal.

[0399] The "means for preprocessing and storing the property information and desired conditions" is a means for preprocessing the input property information and desired conditions and storing them in a database.

[0400] The "means for matching the property information with the desired conditions" refers to a means for executing an algorithm that matches the stored property information with the desired conditions and identifies a property that matches the buyer's desires.

[0401] The "means for proposing properties based on the results of the matching" refers to a means for generating a list of suitable properties based on the results of the matching algorithm and presenting the list to the buyer.

[0402] The "means of arranging a viewing date" refers to a means of matching the buyer's desired viewing date with the seller's schedule and arranging a viewing date that is convenient for both parties.

[0403] "Means for automatically generating a sales contract" refers to a means for automatically generating a contract using a generative AI model and sending the contract to both users.

[0404] A "means for automatically collecting fees" is a means for calculating fees based on the property price and automatically collecting fees from sellers and buyers.

[0405] The present invention is a system for fully automating real estate brokerage business, which operates in cooperation with a server, terminals, and users.

[0406] Hardware and software used

[0407] Server: Database management systems (e.g., MySQL, PostgreSQL), machine learning algorithms (e.g., scikit-learn, TensorFlow), generative AI models (e.g., GPT-4)

[0408] Devices: PC, smartphone, web application, mobile app

[0409] Data format: JSON, CSV

[0410] Database: Structured database (e.g. MySQL, PostgreSQL), indexing system (e.g. Elasticsearch)

[0411] Prompt input example: Text format

[0412] System Operation

[0413] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server collects data through various APIs and database connections and performs preprocessing. Preprocessing involves converting the data into an appropriate format (e.g., JSON) and removing noise and missing values ​​to prepare it for centralized management. The server also structures the data for analysis and analyzes it using machine learning algorithms. The analysis results are stored in a structured database (e.g., MySQL).

[0414] Next, the user (seller) enters property information. Detailed information such as the property's location, price, area, and facilities is entered via a web application or mobile app displayed on the device (PC or smartphone). The device then sends the entered information to the server. The server stores the received information in a database and makes it searchable using an indexing system (e.g., Elasticsearch).

[0415] Similarly, the user (buyer) inputs their desired conditions, such as budget, area, size, and facilities, through a terminal. The terminal sends the information to the server, which then stores it in a database.

[0416] The server compares the stored property information with the buyer's desired conditions. It then runs a matching algorithm (e.g., collaborative filtering, content-based filtering) to identify suitable properties. The server then generates a property list based on the results and sends it to the terminal. The user (buyer) can then view the proposed property list through the terminal.

[0417] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the terminal. The server uses this information to check the seller's schedule and arranges the viewing date. The viewing date is notified to both the seller and the buyer.

[0418] After viewing the property, if the user (buyer) indicates their intention to purchase the property, the server automatically generates a sales contract using a generative AI model (e.g., GPT-4). At this time, the server inputs the following prompt sentence into the generative AI to create the contract:

[0419] "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo."

[0420] The generated contract is sent to both terminals, where the users (seller and buyer) confirm the contents and digitally sign them. The server stores the signed contract and converts it into a legally valid format.

[0421] Finally, the server automatically collects a 1% commission on the property price. Users (sellers and buyers) complete the commission payment on the system, and the server records the completion of the transaction once it has confirmed the payment.

[0422] In this way, the system of the present invention can automate each stage of a real estate transaction efficiently and quickly, thereby reducing transaction costs.

[0423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0424] Step 1: Data collection and preprocessing

[0425] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server uses APIs and SQL queries to extract data and convert it into formats (e.g., JSON, CSV). Preprocessing includes filling in missing values ​​and removing noise data. The input data is the raw data from various databases, and the output data is preprocessed data in a standardized format.

[0426] Step 2: Enter property information

[0427] The user (seller) uses a terminal to enter property information (location, price, area, facilities, etc.). The terminal provides a form-based interface, verifies the entered data, and then sends it to the server. The input data is the property information entered by the seller, and the output data is the property data in JSON format that is sent to the server.

[0428] Step 3: Enter your desired conditions

[0429] The user (buyer) uses a terminal to input desired conditions (budget, area, size, facilities, etc.). The terminal also provides a form-based interface and sends the input information to the server. The input data is the buyer's desired conditions, and the output data is the desired conditions data in JSON format that is sent to the server.

[0430] Step 4: Storing and indexing data

[0431] The server stores the received property information and desired conditions in a database. The stored data is indexed and made searchable (e.g., Elasticsearch). The input data is JSON data of the property information and desired conditions, and the output data is in an indexed database state.

[0432] Step 5: Match property information with desired conditions

[0433] The server matches the stored property information with the buyer's desired criteria. It uses specific algorithms (e.g., collaborative filtering, content-based filtering) to identify properties that match the buyer's desired criteria. The input data is the indexed property information and desired criteria, and the output data is the matching property list.

[0434] Step 6: Property proposal

[0435] The server generates a list of properties to be proposed based on the matching results and sends the list to the terminal. The user (buyer) checks the proposed property list through the terminal. The input data is the property list of the matching results, and the output data is the property list displayed on the terminal.

[0436] Step 7: Arrange a tour date

[0437] The user (buyer) inputs the desired tour date into the terminal. The server checks it against the seller's schedule and arranges an appropriate tour date. The server notifies the seller and buyer of the tour date. The input data is the desired tour date, and the output data is a notification of the adjusted tour date.

[0438] Step 8: Auto-generate a sales contract

[0439] When a user (buyer) indicates their intention to purchase, the device sends that information to the server. The server then uses a generative AI model (e.g., GPT-4) to automatically generate a sales contract. An example of a prompt is "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo." The generated contract is sent to both devices, and the users (seller and buyer) confirm the contents and sign electronically. The input data is the information indicating their intention to purchase, and the output data is the generated contract.

[0440] Step 9: Fee Collection

[0441] The server automatically collects a commission of 1% of the property price from the seller and buyer. Users (sellers and buyers) complete the commission payment on the system. The server confirms the payment and records the completion of the transaction. The input data is the property price and commission rate, and the output data is a record of the commission collected.

[0442] (Application example 1)

[0443] 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."

[0444] In real estate transactions, efficient matching between sellers and buyers and quick contract procedures are required. Furthermore, scheduling property viewings and contracts is complicated, making it difficult for both parties to communicate smoothly. This issue is also common to service provision and reservation systems in brick-and-mortar stores, and there is a particular need for efficient and smooth service provision between store owners and users. This project aims to solve these issues.

[0445] 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.

[0446] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for sellers to input property information or store information, means for buyers to input desired conditions, means for collating and matching the property information or store information with the desired conditions, means for proposing properties or stores based on the collation results, means for arranging viewing dates or available reservation dates and times, means for automatically generating contracts, and means for collecting fees. This enables efficient and smooth matching, schedule adjustment, contract conclusion, and automatic fee collection in real estate transactions and brick-and-mortar store services.

[0447] "Real estate transaction data" refers to data that includes information regarding the sale, purchase, and rental of properties.

[0448] "Contract data" refers to data on documents relating to sales or rental contracts.

[0449] "Promotional Data" means data that includes marketing information for the purpose of promoting sales, purchases, or rentals.

[0450] "Seller" is the person or entity selling or renting the property or store.

[0451] "Property information" is data that includes detailed information about the property, such as its location, price, area, and facilities.

[0452] "Store information" is data including detailed information such as the store's location, business hours, services offered, and price range.

[0453] "Buyer" means a person or legal entity seeking to purchase or occupy a property or store.

[0454] "Desired conditions" are the conditions the buyer desires regarding the property or store.

[0455] "Matching" means comparing the seller's property or store information with the buyer's desired conditions to find a suitable match.

[0456] A "proposal" is the introduction of a property or store to a buyer based on the matching results.

[0457] "Viewing dates" and "reservation dates" are schedules for sellers and buyers to inspect properties and stores.

[0458] "Automatic contract generation" means that the system automatically creates the contents of a sales or usage contract.

[0459] "Fee collection" means automatically collecting fees from sellers and buyers for using the system.

[0460] This invention is a system that efficiently and automatically matches property and store information and speeds up contract procedures. It is equipped with means for collecting, analyzing, and structuring real estate transaction data, contract data, and sales promotion data. It also includes a function that allows sellers and buyers to input their respective information, performs matching, and proposes the most suitable property or store.

[0461] 1. System Configuration

[0462] The server runs in a cloud environment such as AWS (Amazon Web Services) and collects, analyzes, stores, and structures data. React Native (for smartphones) and React (for the web) are used for the front end, building an interface with the devices (smartphones and computers) where users input information. Node.js and Express are used for the back end, handling data processing and API provision. SQL databases (MySQL) and NoSQL databases (MongoDB) are used. Additionally, the scikit-learn library is used for machine learning to implement a matching algorithm.

[0463] 2. Data collection and analysis

[0464] The server collects real estate transaction data, contract data, and sales promotion data from various databases, analyzes and structures it, and uses machine learning algorithms to convert the collected data into an appropriate format for centralized management.

[0465] 3. Enter seller and buyer information

[0466] Sellers input their property or store information through a terminal. The input information includes location, price, area, facilities, business hours, etc. Buyers also input the conditions for the property or store they are looking for through a terminal. The input conditions include budget, area, size, specific facilities and services, etc.

[0467] 4. Matching and Proposal

[0468] The server uses machine learning to match the seller's property or store information with the buyer's desired conditions and generates the optimal matching results. Based on these results, the optimal property or store is proposed and provided to the buyer.

[0469] 5. Arrangement of tour dates or available reservation dates

[0470] The system automatically coordinates viewing dates and available reservation dates for properties and stores by checking the schedules of both the seller and buyer. The system suggests the optimal date and time based on the schedules of both parties, helping to ensure that viewings and reservations go smoothly.

[0471] 6. Automatically generate and sign contracts

[0472] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract. The contract is created using a generative AI model and sent to both devices. The user can then review the contract and sign it via their device.

[0473] 7. Collection of Fees

[0474] Finally, fees for using the property or store are automatically collected from the seller and buyer via the system, and the transaction is completed.

[0475] Specific examples

[0476] For example, a user searching for a cafe in Tokyo enters the following prompt on their smartphone:

[0477] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[0478] The system matches cafes that meet the criteria and presents available dates and times for reservations. The user selects the desired date and time and confirms the reservation through the system. Finally, a usage agreement with the cafe is automatically generated, which is signed and confirmed by both the user and the cafe. This series of processes is carried out efficiently and smoothly, bringing benefits to both the user and the cafe owner.

[0479] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0480] Step 1:

[0481] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Because the collected data is inconsistent in format and content, it is preprocessed to convert it into a unified format. Specifically, it parses the JSON and XML formatted data, extracts the necessary fields, and stores them in a structured database. This process is expected to use AWS's data lake service.

[0482] Step 2:

[0483] Through the terminal, sellers input property or store information, including the property or store's location, price, area, facilities, and opening hours. The terminal then sends the input information to the server, which stores the received data in a database and indexes it for searchability.

[0484] Step 3:

[0485] Through the terminal, buyers input their desired property or store conditions, such as budget, area, size, specific facilities and services, etc. The terminal then transmits the desired conditions to the server, which stores the information in a database.

[0486] Step 4:

[0487] The server uses a machine learning algorithm to match the seller's property or store information with the buyer's desired conditions. The algorithm used in this process is implemented using the scikit-learn library. Specifically, the input data is treated as features, and matching is performed by calculating the similarity. The matching results obtained in this way are stored in a database.

[0488] Step 5:

[0489] The server then proposes the most suitable property or store to the buyer based on the matching results. The proposed list is sent to the buyer's terminal and can be viewed by the buyer. The proposed list includes detailed information about the property or store.

[0490] Step 6:

[0491] When a buyer selects a tour date or an available reservation date and time, that information is sent to the server. The server checks the seller's schedule and automatically adjusts the optimal tour date or reservation date and time. The adjusted results are notified to the seller's and buyer's terminals.

[0492] Step 7:

[0493] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract using a generative AI model. This contract is then sent to both devices, where the user can review the contents and electronically sign.

[0494] Step 8:

[0495] Once the contract procedure is completed, the server automatically collects the fee. To collect the fee, an electronic payment service is used. Once payment is confirmed, the transaction is completed and a record is saved in the database.

[0496] The data processing and calculations performed at each step are as follows:

[0497] In step 1, various data is collected, converted into an appropriate format, and centrally managed.

[0498] In steps 2 and 3, the data entered by the user is formatted, sent to the server, and saved.

[0499] In step 4, machine learning algorithms are used to collate the data and generate matching results.

[0500] In step 5, properties and stores are proposed based on the matching results.

[0501] Step 6 automates tours and reservations through schedule adjustments.

[0502] In step 7, a generative AI model is used to automatically generate a contract and assist with electronic signatures.

[0503] In step 8, fees are automatically collected using an electronic payment service.

[0504] For example, here's a prompt that a user searching for a cafe in Tokyo might enter:

[0505] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[0506] 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.

[0507] This invention is a system for automating real estate brokerage business, and further combines an emotion engine that recognizes user emotions and provides optimal services. The system operates in cooperation with a server, terminals, and users.

[0508] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it preprocesses it, converts it into a unified format, and centrally manages it. Then, the server analyzes the data using machine learning algorithms and stores it in a structured database by category.

[0509] The user (seller) enters information about their property through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format.

[0510] The user (buyer) inputs the conditions for the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, which then stores the received conditions. Furthermore, the emotion engine recognizes the emotion of the user when entering the information and records it in a database.

[0511] The server compares property information with the buyer's desired conditions. At this time, an emotion engine analyzes the user's emotional state and reflects this in the property suggestions. The matching algorithm identifies properties that meet the desired conditions and then takes the user's emotions into consideration to suggest the most suitable property. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The user (buyer) can review this list and view detailed information.

[0512] When a user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and adjusts the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and proposes the optimal date. The server then notifies both the seller and the buyer of the viewing date.

[0513] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server automatically creates a sales contract using generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts.

[0514] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then verifies the payment and records the completion of the transaction.

[0515] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment located in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, another user looking for a property in Tokyo enters their desired conditions into the system. If this user's desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract the seller's properties, and the emotion engine will make suggestions while checking the user's emotional state. Intentions to view properties and the emotional state at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[0516] The above is a specific embodiment of the system that combines the emotion engine, which enables efficient and emotion-conscious real estate transactions.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] The server collects real estate transaction data, contract data, and sales promotion data from various databases, converts the collected data into an appropriate format, and manages it centrally.

[0520] Step 2:

[0521] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category. It also uses natural language processing technology to analyze the meaning of the data and create an index.

[0522] Step 3:

[0523] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0524] Step 4:

[0525] The server stores the received property information in a database, automatically verifies that the data is accurate and complete, and indexes the stored property information in a searchable format.

[0526] Step 5:

[0527] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal, and the desired conditions are immediately sent to the server.

[0528] Step 6:

[0529] The server stores the desired conditions received from the buyer. Furthermore, when the user inputs the conditions, the terminal uses an emotion engine to analyze the user's emotional state (e.g., satisfaction, anxiety, expectation) and records it in a database.

[0530] Step 7:

[0531] The server compares the stored property information with the buyer's desired conditions and executes a matching algorithm, during which an emotion engine analyzes the user's emotional state and reflects it in the property proposals.

[0532] Step 8:

[0533] The server generates a property list based on the matching results and sends it to the user's (buyer's) terminal in a format that is easy for the user to view. The emotion engine monitors the user's reaction when making a proposal and provides necessary support.

[0534] Step 9:

[0535] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0536] Step 10:

[0537] The server checks the seller's schedule and automatically adjusts the tour date. At this time, the emotion engine analyzes the user's emotions and suggests the optimal tour date and time. The adjusted tour date is notified to the seller and buyer via their terminals.

[0538] Step 11:

[0539] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generative AI. During this process, the emotion engine also records the user's emotional state.

[0540] Step 12:

[0541] The created sales contract is sent to the seller and buyer via the terminal. The users (seller and buyer) check the contents of the contract and sign it on the terminal. At this time, the emotion engine detects the user's anxieties and concerns at the time of signing and provides appropriate support.

[0542] Step 13:

[0543] The server converts the signed contract into a legally valid format and stores it in a database.

[0544] Step 14:

[0545] The server calculates the commission of 1% of the property price for both the seller and the buyer, issues an invoice, and records the completion of the transaction after the commission is paid via the terminal.

[0546] The above are the detailed processing steps of this system that combines an emotion engine. As a concrete example, consider the case where a user wants to sell a property in Tokyo. This user registers property information in the system, and the property is proposed to another user as a property that matches their desired conditions. The emotion engine analyzes the user's emotional state at the time of proposal, viewing, and contract signing, and supports the user so that they can proceed with the transaction with peace of mind. This system realizes efficient and user-friendly real estate transactions.

[0547] Example 2

[0548] 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."

[0549] In traditional real estate brokerage, many processes, such as data collection, analysis, property matching, scheduling tours, creating contracts, and collecting fees, were performed manually, resulting in time-consuming, labor-intensive, and inefficient processes. Furthermore, the process often ignored the user's emotional state, causing anxiety and doubt during the transaction. There is a need to solve these problems and realize efficient real estate transactions that take the user's emotions into consideration.

[0550] 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.

[0551] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for preprocessing the data, converting it into a unified format, and centrally managing it, means for analyzing the data using a machine learning algorithm and saving it in a structured database, means for sellers to input property information, means for indexing the input property information in a searchable format, means for buyers to input desired conditions, means for recognizing the buyer's emotions at the time of input and recording them in a database, means for comparing and matching the property information with the desired conditions and the buyer's emotional state, means for proposing optimal properties based on the matching results, means for arranging a viewing schedule, means for comparing the schedules of the buyer and seller and proposing a viewing schedule taking into account the buyer's emotional state, means for automatically generating a sales contract based on a generative AI model, means for recording the user's emotions at the time of signing and providing support for any concerns or doubts, means for automatically collecting fees, and means for confirming payment and recording the completion of the transaction, thereby enabling efficient real estate transactions that are considerate of the user's emotions.

[0552] "Real estate transaction data" refers to all information related to the sale, purchase, rental, and contract of real estate, and specifically includes data such as the property price, location, area, facilities, and contract terms.

[0553] "Contract data" refers to the information contained in contracts used in real estate transactions, including legal clauses, information about the parties, terms of the transaction, signatures, and the like.

[0554] "Promotional Data" refers to marketing information used to promote real estate transactions, including advertising campaigns, customer interest and behavior data, and promotional information.

[0555] "Preprocessing" refers to the processing performed before analyzing data, and includes operations such as cleaning the data, filling in missing values, and standardizing the format.

[0556] A "unified format" refers to converting data of different formats into a consistent format, making it easier to centrally manage and analyze data obtained from various sources.

[0557] A "machine learning algorithm" is a computational technique for analyzing data and finding patterns, and the results are used to make predictions and optimizations.

[0558] A "structured database" is a database system for systematically organizing and storing data, storing data in a table format to enable efficient searching and manipulation.

[0559] "Property information" refers to detailed information about real estate provided by the seller, specifically data including location, price, area, number of rooms, facilities, etc.

[0560] "Indexing to a searchable state" refers to the process of organizing and registering data so that it can be searched efficiently, allowing data to be quickly retrieved based on keywords or conditions.

[0561] "Desired conditions" refer to the characteristics and conditions of the property desired by the buyer, and include specific requests such as budget, area, size, and facilities.

[0562] "Recognizing emotions and recording them in a database" refers to the operation of analyzing the user's emotional state and storing the results in a database, making it possible to use data that takes into account the user's psychological state.

[0563] "Verifying and matching" refers to the process of comparing and considering the seller's property information with the buyer's desired conditions and emotional state, and identifying and proposing properties that meet the matching conditions.

[0564] "Proposing the best property" means selecting and recommending the property that is most suitable for the buyer based on the analysis results and the user's emotional state.

[0565] "Adjusting viewing dates" refers to the operation of confirming and adjusting the schedules of the seller and buyer to decide on a date to view the property.

[0566] A "generative AI model" refers to an artificial intelligence method for automatically generating new information and documents based on large amounts of data, and is a technology that performs natural language processing and document generation.

[0567] "Recording emotions during signing and providing support for anxiety and doubts" refers to the operation of recording the user's emotional state when signing a contract and providing support and assistance as needed.

[0568] "Automatically collecting fees" refers to the operation of automatically calculating and collecting transaction fees by the system.

[0569] "Recording the completion of a transaction" refers to the operation of registering and saving the final status of the transaction in the system and recording that the transaction has officially ended.

[0570] The present invention provides a system for improving the efficiency of real estate brokerage services and providing services that take user emotions into consideration. This system operates in cooperation with a server, a terminal, and a user. Specific embodiments are described below.

[0571] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, it uses Apache Hadoop to efficiently collect large amounts of data, preprocesses the data using Python's pandas library, converts it into a unified format, and centralizes it. This centralized data is stored in a relational database such as MySQL or PostgreSQL. The server then analyzes the data using machine learning algorithms such as Scikit-learn and TensorFlow, and stores the analysis results in a structured database.

[0572] Users (sellers) enter their property information from a device (PC or smartphone app). Specifically, they enter detailed information such as the property's location, price, area, and facilities into a form, and this data is sent from the device to the server. The server indexes the received property information into a search engine such as Elasticsearch, making it searchable.

[0573] The user (buyer) inputs the conditions for the property they are looking for on their device. This information includes desired conditions such as budget, area, size, and facilities. These conditions are sent from the device to the server and stored. An emotion engine (e.g., Amazon Rekognition or Microsoft Azure Face API) then analyzes the face and text entered by the user to recognize their emotions and records the results in a database.

[0574] The server compares property information with the buyer's desired conditions and emotional state to suggest the most suitable property. Specifically, it compares property information using Elasticsearch and runs a matching algorithm using a recommendation system library (e.g., Surprise or LightFM). As a result, a list of the most suitable properties is generated and sent to the user's (buyer's) device.

[0575] When a user (buyer) wishes to visit a property, they input their desired dates into the system. The server checks the schedules of the seller and buyer, and then uses an emotion engine to suggest the optimal date for the visit. Once the date for the visit has been decided, the server notifies both the seller and buyer.

[0576] If a user (buyer) wishes to purchase a property, they express their intention through their device. The server automatically creates a sales contract using a generative AI model (e.g., OpenAI GPT) and sends this contract to both users. The user signs the contract on their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[0577] The server automatically collects a 1% commission from the seller and buyer of the property. This process uses online payment services such as Stripe or PayPal API. Once the payment is confirmed, the server records the transaction as completed.

[0578] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, if another user looking for a property enters their desired conditions, setting "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract matching properties, and the emotion engine will make the optimal proposal while checking the user's emotions. Intentions to view properties and emotions at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[0579] An example prompt is:

[0580] "Please register information about a 3LDK apartment for sale for 70 million yen in the system."

[0581] or

[0582] "I'm looking for a 3LDK apartment in Tokyo. My budget is 80 million yen."

[0583] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0584] Step 1:

[0585] The server collects real estate transaction data, contract data, and sales promotion data from various databases. The input is a dataset provided by multiple databases, and the output is data in a unified format. The specific operations for data collection involve acquiring the data using Apache Hadoop, preprocessing the data using Python's pandas library, completing missing values, and unifying the format.

[0586] Step 2:

[0587] The server analyzes the preprocessed data and generates analytical results using machine learning algorithms. The input is the preprocessed data, and the output is the analytical results. Specifically, it uses libraries such as Scikit-learn and TensorFlow to train models for estimating property prices and predicting buyer behavior. The analytical results are stored in a structured database.

[0588] Step 3:

[0589] The user (seller) enters their property information from a terminal. The input is detailed property information (location, price, area, facilities, etc.), and the output is indexed property information. Specifically, the user enters detailed property information using an input form, and the data is sent to the server using an HTTP request. The server indexes the received data in the Elasticsearch search engine.

[0590] Step 4:

[0591] The user (buyer) inputs the desired property conditions from a terminal. The input is the desired conditions (budget, area, size, facilities, etc.), and the output is the saved desired condition data. In concrete terms, the desired conditions are entered using an input form, and the information is sent to the server via an HTTP request. The emotion engine is used to analyze the user's emotions at the time of input, and the results are recorded in a database.

[0592] Step 5:

[0593] The server compares property information with the buyer's desired conditions and emotional state to generate the optimal property list. The input is property information, desired conditions, and emotional data, and the output is the optimal property list. Specifically, it uses Elasticsearch to search for properties that match the conditions and executes a matching algorithm using the Recommendation System library. The generated property list is sent to the terminal.

[0594] Step 6:

[0595] The user (buyer) inputs the tour schedule. The input is the desired tour schedule, and the output is the adjusted tour schedule. Specifically, the desired tour schedule is entered from the terminal, and the information is sent to the server via an HTTP request. The server compares it with the seller's schedule and proposes the optimal tour schedule taking into account the buyer's emotional state. This schedule is notified to both the seller and the buyer.

[0596] Step 7:

[0597] When a user (buyer) expresses their intention to purchase, the server automatically generates a sales contract using a generative AI model. The input is information about the sales contract, and the output is an automatically generated contract. Specifically, a contract is created using a generative AI model such as OpenAI GPT, and the contract is sent to the user. The user signs the contract through their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[0598] Step 8:

[0599] The server automatically collects the fee and completes the transaction. The input is the purchase amount and fee calculation information, and the output is a record of the transaction completion. Specifically, it automates the collection of fees using Stripe or PayPal API, and once payment is confirmed, records the completion of the transaction in the database.

[0600] (Application example 2)

[0601] 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."

[0602] Current real estate brokerage systems have difficulty accurately matching the needs of buyers and sellers, and rarely consider the user's emotional state when making proposals. This often leaves users feeling frustrated and stressed when searching for a property. Furthermore, efficient advertisement generation and delivery is lacking, reducing the opportunities for users to receive the most appropriate information.

[0603] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for recognizing the user's emotions and making optimal property proposals based on the emotional state, and means for generating and providing real estate advertisements based on the emotional state. This makes it possible to make appropriate property proposals and advertisements based on the user's emotional state.

[0604] "Real estate transaction data" refers to information relating to the sale, purchase, or rental of real estate, and includes details such as the property's location, price, area, floor plan, and age.

[0605] "Contract data" refers to document data that describes the contract details related to real estate transactions, and is electronic data such as sales contracts and rental contracts.

[0606] "Promotional Data" means data relating to marketing and sales promotions, including information about advertising campaigns, promotional materials, and consumer responses.

[0607] "Means for recognizing emotions" refers to technology that analyzes a user's input and behavior to identify their emotional state, and is a method that uses natural language processing and machine learning algorithms.

[0608] "Means for making optimal property proposals" refers to technology that selects and proposes the most suitable property based on the user's desired conditions and emotional state.

[0609] "Means for generating and providing real estate advertisements" refers to a technology that uses a generative AI model to create advertising copy about real estate and provides it at a time that corresponds to the user's emotional state.

[0610] The "emotional state of a user" refers to the emotions that a user has in a particular situation, and is a general term for emotions such as satisfaction, stress, joy, and sadness.

[0611] The present invention is a system that automates real estate brokerage operations and provides optimal services by recognizing user emotions. This system operates in cooperation with a server, terminals, and users.

[0612] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collection, this data is preprocessed and converted into a unified format for centralized management. Next, the server analyzes the data using machine learning algorithms and stores it in a database structured by category. The specific software used is Pandas and SQLite.

[0613] The user (seller) enters their property information through a terminal. This information includes details such as the property's location, price, area, and facilities, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format. The user (buyer) also enters the property conditions they desire through the terminal. These conditions are also sent from the terminal to the server, and the server stores the received conditions.

[0614] The emotion engine recognizes the emotion of the user's input and records it in a database. This emotion engine uses the Google Cloud Natural Language API.

[0615] The server compares the entered property information with the buyer's desired conditions and performs matching. At this time, an emotion engine analyzes the user's emotional state and reflects it in the property suggestions. The matching algorithm is implemented using Scikit-learn, identifies properties that meet the desired conditions, and suggests the most suitable property taking the user's emotions into consideration. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal.

[0616] The user (buyer) can check this list and view detailed information. If they wish to view a property they are interested in, they input their desired dates into the system. The server checks this against the seller's schedule and arranges the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and suggests the most appropriate date. The viewing date is then notified to both the seller and the buyer.

[0617] After viewing the property, if the user (buyer) wishes to purchase it, they express their intention to do so via their device. The server automatically creates a sales contract using the generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts. OpenAI's GPT model is used for the generation AI.

[0618] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0619] For example, if a user inputs "I'm tired of searching for a property lately," the system will analyze this input and generate and provide a positive ad copy that takes into account the user's emotional state. This ad copy will be provided in the form of "Tired of searching for a property? We have a great suggestion to help you relax. Please take a look."

[0620] This system will enable efficient and emotionally sensitive real estate transactions and advertising.

[0621] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0622] Step 1:

[0623] The server collects real estate transaction data, contract data, and sales promotion data from various databases and performs preprocessing. During this process, the Pandas library is used to convert the data into a unified format such as CSV and save it in an SQLite database. Data input is performed via API from external databases, and output is data saved in a unified format.

[0624] Step 2:

[0625] The user (seller) enters property information through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered into an input form, and this data is sent from the terminal to the server. The input data is sent to the server in a standardized format such as JSON, and the server stores it in a database and indexes it so that it can be searched.

[0626] Step 3:

[0627] The user (buyer) inputs the desired property conditions through a terminal. Desired conditions include budget, area, size, facilities, etc. These desired conditions are sent from the terminal to the server, which then stores the received conditions in a database. The input data is sent to the server in a standardized format such as JSON and stored in the database.

[0628] Step 4:

[0629] The emotion engine recognizes the emotion expressed by the user when they input text and records it in a database. Sentiment analysis uses the Google Cloud Natural Language API to analyze the user's input text and calculate an emotion score. The input is the user's text data, and the output is the emotion score and its classification result (satisfaction, stress, etc.).

[0630] Step 5:

[0631] The server compares the entered property information with the buyer's desired conditions and performs matching. It uses Scikit-learn to apply a machine learning matching algorithm. At this time, the emotional state of the buyer is also reflected in the analysis results using an emotion engine. The input is the seller's property information, the buyer's desired conditions, and an emotion score, and the output is a list of optimal property proposals.

[0632] Step 6:

[0633] Users (buyers) can check the proposed property listings on their devices and view detailed information. The user interface is implemented as a web page or mobile app, and the information provided is obtained in real time from the server.

[0634] Step 7:

[0635] When a user (buyer) wishes to tour the property, they enter the desired tour dates into the system. The server checks the seller's schedule and automatically adjusts the tour dates. The Google Calendar API is used to adjust the tour dates. The input is the user's desired tour dates, and the output is the adjusted tour dates.

[0636] Step 8:

[0637] The server automatically generates a sales contract using a generative AI model. It uses OpenAI's GPT model to create a contract template and sends it to users (sellers and buyers). The input is basic contract information and sentiment scores, and the output is an automatically generated contract.

[0638] Step 9:

[0639] Users (seller and buyer) review the contract and sign it electronically through their devices. This process uses an electronic signature platform (e.g., DocuSign). The input is the generated contract, and the output is the signed contract.

[0640] Step 10:

[0641] The server automatically collects a 1% commission from the seller and buyer of the property price. This process uses an electronic payment service (e.g., Stripe). The input is the property price and commission information, and the output is confirmation of the commission collected.

[0642] Example prompt sentence:

[0643] "I'm tired of searching for properties lately."

[0644] 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.

[0645] 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.

[0646] 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.

[0647] [Third embodiment]

[0648] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0649] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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."

[0660] The present invention is a system for automating real estate brokerage business. This system operates by interoperating with a server, a terminal, and a user.

[0661] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. The server preprocesses the collected data, converts it into an appropriate format, and centralizes it. The server then analyzes this data using machine learning algorithms and stores it in a structured database.

[0662] Next, the user (seller) enters information about their property through the terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and the terminal sends this data to the server. The server stores the received property information in a database and indexes the seller's property information in a searchable format.

[0663] Meanwhile, the user (buyer) inputs the conditions of the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, and the server stores the received conditions.

[0664] The server compares the stored property information with the buyer's desired conditions, runs the corresponding matching algorithm, and finds properties that match the buyer's desired conditions. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The buyer can then review the proposed property list through the terminal and view the details of the properties that interest them.

[0665] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and arranges the viewing date. The server then notifies both the seller and the buyer of the viewing date, helping to ensure the viewing goes smoothly.

[0666] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server uses generation AI to automatically create a sales contract. The contract is sent to both devices, and the users (seller and buyer) review and sign the contract. The server saves the signed contract and converts it into a legally valid format.

[0667] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0668] As described above, the present invention provides a system that fully automates real estate brokerage operations, resulting in efficient and cost-effective transactions for both parties.

[0669] Examples:

[0670] An individual (seller) looking to sell a property in Tokyo accesses a real estate brokerage system and registers property information. Let's say the seller is selling a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. The system stores this information in a database and makes it searchable by other users. Similarly, a buyer looking for a property in Tokyo enters their desired conditions into the system. If the desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system automatically extracts the seller's properties and proposes them to the buyer. The buyer then requests a viewing, and the system arranges a viewing date. After the viewing, if the buyer indicates their intention to purchase, a sales contract is automatically generated, and the signature and commission payment are completed through the system. This entire process is fully automated, making real estate transactions smooth and low-cost.

[0671] The processing flow will be explained below.

[0672] Step 1:

[0673] The server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it converts the collected data into a unified format and manages it centrally.

[0674] Step 2:

[0675] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category, using natural language processing technology.

[0676] Step 3:

[0677] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0678] Step 4:

[0679] The server then verifies the property information received, stores it in a database in the appropriate format, and indexes this information in a searchable format.

[0680] Step 5:

[0681] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal. The desired conditions are immediately sent to the server.

[0682] Step 6:

[0683] The server stores the buyer's requirements and matches them with the property information, using a matching algorithm to identify the property that best meets the requirements.

[0684] Step 7:

[0685] The server generates a list of properties that match the buyer's desired conditions and sends the list to the terminal. The user (buyer) can check the list and view detailed information.

[0686] Step 8:

[0687] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0688] Step 9:

[0689] The server checks the seller's schedule and automatically adjusts the tour date, and notifies the seller and buyer of the adjusted tour date via their terminals.

[0690] Step 10:

[0691] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generation AI.

[0692] Step 11:

[0693] The created sales contract is sent to the seller and buyer via the terminal, where both parties confirm the contents of the contract and sign it on the terminal.

[0694] Step 12:

[0695] The server converts the signed contract into a legally valid format and stores it in a database.

[0696] Step 13:

[0697] The server calculates a commission of 1% of the property price and charges it to the seller and buyer. The commission is paid via the terminal, and after confirming the payment, the completion of the transaction is recorded.

[0698] These are the detailed processing steps that take place within the system, which will efficiently automate real estate transactions and significantly reduce costs.

[0699] Example 1

[0700] 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."

[0701] Traditional real estate brokerage requires a lot of manual work and time, making transactions complicated and requiring efficient and speedy processing. Furthermore, the process involves a wide range of tasks, such as matching buyers and sellers, creating contracts, and arranging viewing dates, and full automation is required. Furthermore, automating the collection of commissions can reduce transaction costs and ensure smooth real estate transactions.

[0702] 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.

[0703] In this invention, the server includes means for collecting data, means for preprocessing and structuring the data, means for sellers to input real estate property information, means for buyers to input desired property conditions, means for preprocessing and saving the property information and the desired conditions, means for matching the property information with the desired conditions, means for proposing properties based on the matching results, means for arranging viewing dates, means for automatically generating a sales contract, and means for automatically collecting fees. This makes it possible to automate all real estate transaction operations efficiently and quickly, thereby reducing transaction costs.

[0704] "Means of collecting data" refers to a means of centrally collecting data related to real estate transactions, contract data, and sales promotion data.

[0705] The "means for preprocessing and structuring the data" refers to a means for converting the collected data into an appropriate format, and preparing it for centralized management and analysis using machine learning algorithms.

[0706] "Means for sellers to input information about real estate properties" refers to an interface for sellers to input detailed information about their properties (e.g., location, price, area, facilities), and is a means for transmitting information to a server via a terminal.

[0707] "Means for buyers to input the conditions for the property they desire" refers to an interface for buyers to input the conditions for the property they desire (e.g., budget, area, size, facilities), and is a means for transmitting information to the server via a terminal.

[0708] The "means for preprocessing and storing the property information and desired conditions" is a means for preprocessing the input property information and desired conditions and storing them in a database.

[0709] The "means for matching the property information with the desired conditions" refers to a means for executing an algorithm that matches the stored property information with the desired conditions and identifies a property that matches the buyer's desires.

[0710] The "means for proposing properties based on the results of the matching" refers to a means for generating a list of suitable properties based on the results of the matching algorithm and presenting the list to the buyer.

[0711] The "means of arranging a viewing date" refers to a means of matching the buyer's desired viewing date with the seller's schedule and arranging a viewing date that is convenient for both parties.

[0712] "Means for automatically generating a sales contract" refers to a means for automatically generating a contract using a generative AI model and sending the contract to both users.

[0713] A "means for automatically collecting fees" is a means for calculating fees based on the property price and automatically collecting fees from sellers and buyers.

[0714] The present invention is a system for fully automating real estate brokerage business, which operates in cooperation with a server, terminals, and users.

[0715] Hardware and software used

[0716] Server: Database management systems (e.g., MySQL, PostgreSQL), machine learning algorithms (e.g., scikit-learn, TensorFlow), generative AI models (e.g., GPT-4)

[0717] Devices: PC, smartphone, web application, mobile app

[0718] Data format: JSON, CSV

[0719] Database: Structured database (e.g. MySQL, PostgreSQL), indexing system (e.g. Elasticsearch)

[0720] Prompt input example: Text format

[0721] System Operation

[0722] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server collects data through various APIs and database connections and performs preprocessing. Preprocessing involves converting the data into an appropriate format (e.g., JSON) and removing noise and missing values ​​to prepare it for centralized management. The server also structures the data for analysis and analyzes it using machine learning algorithms. The analysis results are stored in a structured database (e.g., MySQL).

[0723] Next, the user (seller) enters property information. Detailed information such as the property's location, price, area, and facilities is entered via a web application or mobile app displayed on the device (PC or smartphone). The device then sends the entered information to the server. The server stores the received information in a database and makes it searchable using an indexing system (e.g., Elasticsearch).

[0724] Similarly, the user (buyer) inputs their desired conditions, such as budget, area, size, and facilities, through a terminal. The terminal sends the information to the server, which then stores it in a database.

[0725] The server compares the stored property information with the buyer's desired conditions. It then runs a matching algorithm (e.g., collaborative filtering, content-based filtering) to identify suitable properties. The server then generates a property list based on the results and sends it to the terminal. The user (buyer) can then view the proposed property list through the terminal.

[0726] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the terminal. The server uses this information to check the seller's schedule and arranges the viewing date. The viewing date is notified to both the seller and the buyer.

[0727] After viewing the property, if the user (buyer) indicates their intention to purchase the property, the server automatically generates a sales contract using a generative AI model (e.g., GPT-4). At this time, the server inputs the following prompt sentence into the generative AI to create the contract:

[0728] "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo."

[0729] The generated contract is sent to both terminals, where the users (seller and buyer) confirm the contents and digitally sign them. The server stores the signed contract and converts it into a legally valid format.

[0730] Finally, the server automatically collects a 1% commission on the property price. Users (sellers and buyers) complete the commission payment on the system, and the server records the completion of the transaction once it has confirmed the payment.

[0731] In this way, the system of the present invention can automate each stage of a real estate transaction efficiently and quickly, thereby reducing transaction costs.

[0732] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0733] Step 1: Data collection and preprocessing

[0734] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server uses APIs and SQL queries to extract data and convert it into formats (e.g., JSON, CSV). Preprocessing includes filling in missing values ​​and removing noise data. The input data is the raw data from various databases, and the output data is preprocessed data in a standardized format.

[0735] Step 2: Enter property information

[0736] The user (seller) uses a terminal to enter property information (location, price, area, facilities, etc.). The terminal provides a form-based interface, verifies the entered data, and then sends it to the server. The input data is the property information entered by the seller, and the output data is the property data in JSON format that is sent to the server.

[0737] Step 3: Enter your desired conditions

[0738] The user (buyer) uses a terminal to input desired conditions (budget, area, size, facilities, etc.). The terminal also provides a form-based interface and sends the input information to the server. The input data is the buyer's desired conditions, and the output data is the desired conditions data in JSON format that is sent to the server.

[0739] Step 4: Storing and indexing data

[0740] The server stores the received property information and desired conditions in a database. The stored data is indexed and made searchable (e.g., Elasticsearch). The input data is JSON data of the property information and desired conditions, and the output data is in an indexed database state.

[0741] Step 5: Match property information with desired conditions

[0742] The server matches the stored property information with the buyer's desired criteria. It uses specific algorithms (e.g., collaborative filtering, content-based filtering) to identify properties that match the buyer's desired criteria. The input data is the indexed property information and desired criteria, and the output data is the matching property list.

[0743] Step 6: Property proposal

[0744] The server generates a list of properties to be proposed based on the matching results and sends the list to the terminal. The user (buyer) checks the proposed property list through the terminal. The input data is the property list of the matching results, and the output data is the property list displayed on the terminal.

[0745] Step 7: Arrange a tour date

[0746] The user (buyer) inputs the desired tour date into the terminal. The server checks it against the seller's schedule and arranges an appropriate tour date. The server notifies the seller and buyer of the tour date. The input data is the desired tour date, and the output data is a notification of the adjusted tour date.

[0747] Step 8: Auto-generate a sales contract

[0748] When a user (buyer) indicates their intention to purchase, the device sends that information to the server. The server then uses a generative AI model (e.g., GPT-4) to automatically generate a sales contract. An example of a prompt is "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo." The generated contract is sent to both devices, and the users (seller and buyer) confirm the contents and sign electronically. The input data is the information indicating their intention to purchase, and the output data is the generated contract.

[0749] Step 9: Fee Collection

[0750] The server automatically collects a commission of 1% of the property price from the seller and buyer. Users (sellers and buyers) complete the commission payment on the system. The server confirms the payment and records the completion of the transaction. The input data is the property price and commission rate, and the output data is a record of the commission collected.

[0751] (Application example 1)

[0752] 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."

[0753] In real estate transactions, efficient matching between sellers and buyers and quick contract procedures are required. Furthermore, scheduling property viewings and contracts is complicated, making it difficult for both parties to communicate smoothly. This issue is also common to service provision and reservation systems in brick-and-mortar stores, and there is a particular need for efficient and smooth service provision between store owners and users. This project aims to solve these issues.

[0754] 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.

[0755] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for sellers to input property information or store information, means for buyers to input desired conditions, means for collating and matching the property information or store information with the desired conditions, means for proposing properties or stores based on the collation results, means for arranging viewing dates or available reservation dates and times, means for automatically generating contracts, and means for collecting fees. This enables efficient and smooth matching, schedule adjustment, contract conclusion, and automatic fee collection in real estate transactions and brick-and-mortar store services.

[0756] "Real estate transaction data" refers to data that includes information regarding the sale, purchase, and rental of properties.

[0757] "Contract data" refers to data on documents relating to sales or rental contracts.

[0758] "Promotional Data" means data that includes marketing information for the purpose of promoting sales, purchases, or rentals.

[0759] "Seller" is the person or entity selling or renting the property or store.

[0760] "Property information" is data that includes detailed information about the property, such as its location, price, area, and facilities.

[0761] "Store information" is data including detailed information such as the store's location, business hours, services offered, and price range.

[0762] "Buyer" means a person or legal entity seeking to purchase or occupy a property or store.

[0763] "Desired conditions" are the conditions the buyer desires regarding the property or store.

[0764] "Matching" means comparing the seller's property or store information with the buyer's desired conditions to find a suitable match.

[0765] A "proposal" is the introduction of a property or store to a buyer based on the matching results.

[0766] "Viewing dates" and "reservation dates" are schedules for sellers and buyers to inspect properties and stores.

[0767] "Automatic contract generation" means that the system automatically creates the contents of a sales or usage contract.

[0768] "Fee collection" means automatically collecting fees from sellers and buyers for using the system.

[0769] This invention is a system that efficiently and automatically matches property and store information and speeds up contract procedures. It is equipped with means for collecting, analyzing, and structuring real estate transaction data, contract data, and sales promotion data. It also includes a function that allows sellers and buyers to input their respective information, performs matching, and proposes the most suitable property or store.

[0770] 1. System Configuration

[0771] The server runs in a cloud environment such as AWS (Amazon Web Services) and collects, analyzes, stores, and structures data. React Native (for smartphones) and React (for the web) are used for the front end, building an interface with the devices (smartphones and computers) where users input information. Node.js and Express are used for the back end, handling data processing and API provision. SQL databases (MySQL) and NoSQL databases (MongoDB) are used. Additionally, the scikit-learn library is used for machine learning to implement a matching algorithm.

[0772] 2. Data collection and analysis

[0773] The server collects real estate transaction data, contract data, and sales promotion data from various databases, analyzes and structures it, and uses machine learning algorithms to convert the collected data into an appropriate format for centralized management.

[0774] 3. Enter seller and buyer information

[0775] Sellers input their property or store information through a terminal. The input information includes location, price, area, facilities, business hours, etc. Buyers also input the conditions for the property or store they are looking for through a terminal. The input conditions include budget, area, size, specific facilities and services, etc.

[0776] 4. Matching and Proposal

[0777] The server uses machine learning to match the seller's property or store information with the buyer's desired conditions and generates the optimal matching results. Based on these results, the optimal property or store is proposed and provided to the buyer.

[0778] 5. Arrangement of tour dates or available reservation dates

[0779] The system automatically coordinates viewing dates and available reservation dates for properties and stores by checking the schedules of both the seller and buyer. The system suggests the optimal date and time based on the schedules of both parties, helping to ensure that viewings and reservations go smoothly.

[0780] 6. Automatically generate and sign contracts

[0781] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract. The contract is created using a generative AI model and sent to both devices. The user can then review the contract and sign it via their device.

[0782] 7. Collection of Fees

[0783] Finally, fees for using the property or store are automatically collected from the seller and buyer via the system, and the transaction is completed.

[0784] Specific examples

[0785] For example, a user searching for a cafe in Tokyo enters the following prompt on their smartphone:

[0786] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[0787] The system matches cafes that meet the criteria and presents available dates and times for reservations. The user selects the desired date and time and confirms the reservation through the system. Finally, a usage agreement with the cafe is automatically generated, which is signed and confirmed by both the user and the cafe. This series of processes is carried out efficiently and smoothly, bringing benefits to both the user and the cafe owner.

[0788] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0789] Step 1:

[0790] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Because the collected data is inconsistent in format and content, it is preprocessed to convert it into a unified format. Specifically, it parses the JSON and XML formatted data, extracts the necessary fields, and stores them in a structured database. This process is expected to use AWS's data lake service.

[0791] Step 2:

[0792] Through the terminal, sellers input property or store information, including the property or store's location, price, area, facilities, and opening hours. The terminal then sends the input information to the server, which stores the received data in a database and indexes it for searchability.

[0793] Step 3:

[0794] Through the terminal, buyers input their desired property or store conditions, such as budget, area, size, specific facilities and services, etc. The terminal then transmits the desired conditions to the server, which stores the information in a database.

[0795] Step 4:

[0796] The server uses a machine learning algorithm to match the seller's property or store information with the buyer's desired conditions. The algorithm used in this process is implemented using the scikit-learn library. Specifically, the input data is treated as features, and matching is performed by calculating the similarity. The matching results obtained in this way are stored in a database.

[0797] Step 5:

[0798] The server then proposes the most suitable property or store to the buyer based on the matching results. The proposed list is sent to the buyer's terminal and can be viewed by the buyer. The proposed list includes detailed information about the property or store.

[0799] Step 6:

[0800] When a buyer selects a tour date or an available reservation date and time, that information is sent to the server. The server checks the seller's schedule and automatically adjusts the optimal tour date or reservation date and time. The adjusted results are notified to the seller's and buyer's terminals.

[0801] Step 7:

[0802] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract using a generative AI model. This contract is then sent to both devices, where the user can review the contents and electronically sign.

[0803] Step 8:

[0804] Once the contract procedure is completed, the server automatically collects the fee. To collect the fee, an electronic payment service is used. Once payment is confirmed, the transaction is completed and a record is saved in the database.

[0805] The data processing and calculations performed at each step are as follows:

[0806] In step 1, various data is collected, converted into an appropriate format, and centrally managed.

[0807] In steps 2 and 3, the data entered by the user is formatted, sent to the server, and saved.

[0808] In step 4, machine learning algorithms are used to collate the data and generate matching results.

[0809] In step 5, properties and stores are proposed based on the matching results.

[0810] Step 6 automates tours and reservations through schedule adjustments.

[0811] In step 7, a generative AI model is used to automatically generate a contract and assist with electronic signatures.

[0812] In step 8, fees are automatically collected using an electronic payment service.

[0813] For example, here's a prompt that a user searching for a cafe in Tokyo might enter:

[0814] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[0815] 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.

[0816] This invention is a system for automating real estate brokerage business, and further combines an emotion engine that recognizes user emotions and provides optimal services. The system operates in cooperation with a server, terminals, and users.

[0817] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it preprocesses it, converts it into a unified format, and centrally manages it. Then, the server analyzes the data using machine learning algorithms and stores it in a structured database by category.

[0818] The user (seller) enters information about their property through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format.

[0819] The user (buyer) inputs the conditions for the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, which then stores the received conditions. Furthermore, the emotion engine recognizes the emotion of the user when entering the information and records it in a database.

[0820] The server compares property information with the buyer's desired conditions. At this time, an emotion engine analyzes the user's emotional state and reflects this in the property suggestions. The matching algorithm identifies properties that meet the desired conditions and then takes the user's emotions into consideration to suggest the most suitable property. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The user (buyer) can review this list and view detailed information.

[0821] When a user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and adjusts the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and proposes the optimal date. The server then notifies both the seller and the buyer of the viewing date.

[0822] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server automatically creates a sales contract using generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts.

[0823] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then verifies the payment and records the completion of the transaction.

[0824] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment located in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, another user looking for a property in Tokyo enters their desired conditions into the system. If this user's desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract the seller's properties, and the emotion engine will make suggestions while checking the user's emotional state. Intentions to view properties and the emotional state at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[0825] The above is a specific embodiment of the system that combines the emotion engine, which enables efficient and emotion-conscious real estate transactions.

[0826] The processing flow will be explained below.

[0827] Step 1:

[0828] The server collects real estate transaction data, contract data, and sales promotion data from various databases, converts the collected data into an appropriate format, and manages it centrally.

[0829] Step 2:

[0830] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category. It also uses natural language processing technology to analyze the meaning of the data and create an index.

[0831] Step 3:

[0832] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0833] Step 4:

[0834] The server stores the received property information in a database, automatically verifies that the data is accurate and complete, and indexes the stored property information in a searchable format.

[0835] Step 5:

[0836] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal, and the desired conditions are immediately sent to the server.

[0837] Step 6:

[0838] The server stores the desired conditions received from the buyer. Furthermore, when the user inputs the conditions, the terminal uses an emotion engine to analyze the user's emotional state (e.g., satisfaction, anxiety, expectation) and records it in a database.

[0839] Step 7:

[0840] The server compares the stored property information with the buyer's desired conditions and executes a matching algorithm, during which an emotion engine analyzes the user's emotional state and reflects it in the property proposals.

[0841] Step 8:

[0842] The server generates a property list based on the matching results and sends it to the user's (buyer's) terminal in a format that is easy for the user to view. The emotion engine monitors the user's reaction when making a proposal and provides necessary support.

[0843] Step 9:

[0844] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0845] Step 10:

[0846] The server checks the seller's schedule and automatically adjusts the tour date. At this time, the emotion engine analyzes the user's emotions and suggests the optimal tour date and time. The adjusted tour date is notified to the seller and buyer via their terminals.

[0847] Step 11:

[0848] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generative AI. During this process, the emotion engine also records the user's emotional state.

[0849] Step 12:

[0850] The created sales contract is sent to the seller and buyer via the terminal. The users (seller and buyer) check the contents of the contract and sign it on the terminal. At this time, the emotion engine detects the user's anxieties and concerns at the time of signing and provides appropriate support.

[0851] Step 13:

[0852] The server converts the signed contract into a legally valid format and stores it in a database.

[0853] Step 14:

[0854] The server calculates the commission of 1% of the property price for both the seller and the buyer, issues an invoice, and records the completion of the transaction after the commission is paid via the terminal.

[0855] The above are the detailed processing steps of this system that combines an emotion engine. As a concrete example, consider the case where a user wants to sell a property in Tokyo. This user registers property information in the system, and the property is proposed to another user as a property that matches their desired conditions. The emotion engine analyzes the user's emotional state at the time of proposal, viewing, and contract signing, and supports the user so that they can proceed with the transaction with peace of mind. This system realizes efficient and user-friendly real estate transactions.

[0856] Example 2

[0857] 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."

[0858] In traditional real estate brokerage, many processes, such as data collection, analysis, property matching, scheduling tours, creating contracts, and collecting fees, were performed manually, resulting in time-consuming, labor-intensive, and inefficient processes. Furthermore, the process often ignored the user's emotional state, causing anxiety and doubt during the transaction. There is a need to solve these problems and realize efficient real estate transactions that take the user's emotions into consideration.

[0859] 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.

[0860] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for preprocessing the data, converting it into a unified format, and centrally managing it, means for analyzing the data using a machine learning algorithm and saving it in a structured database, means for sellers to input property information, means for indexing the input property information in a searchable format, means for buyers to input desired conditions, means for recognizing the buyer's emotions at the time of input and recording them in a database, means for comparing and matching the property information with the desired conditions and the buyer's emotional state, means for proposing optimal properties based on the matching results, means for arranging a viewing schedule, means for comparing the schedules of the buyer and seller and proposing a viewing schedule taking into account the buyer's emotional state, means for automatically generating a sales contract based on a generative AI model, means for recording the user's emotions at the time of signing and providing support for any concerns or doubts, means for automatically collecting fees, and means for confirming payment and recording the completion of the transaction, thereby enabling efficient real estate transactions that are considerate of the user's emotions.

[0861] "Real estate transaction data" refers to all information related to the sale, purchase, rental, and contract of real estate, and specifically includes data such as the property price, location, area, facilities, and contract terms.

[0862] "Contract data" refers to the information contained in contracts used in real estate transactions, including legal clauses, information about the parties, terms of the transaction, signatures, and the like.

[0863] "Promotional Data" refers to marketing information used to promote real estate transactions, including advertising campaigns, customer interest and behavior data, and promotional information.

[0864] "Preprocessing" refers to the processing performed before analyzing data, and includes operations such as cleaning the data, filling in missing values, and standardizing the format.

[0865] A "unified format" refers to converting data of different formats into a consistent format, making it easier to centrally manage and analyze data obtained from various sources.

[0866] A "machine learning algorithm" is a computational technique for analyzing data and finding patterns, and the results are used to make predictions and optimizations.

[0867] A "structured database" is a database system for systematically organizing and storing data, storing data in a table format to enable efficient searching and manipulation.

[0868] "Property information" refers to detailed information about real estate provided by the seller, specifically data including location, price, area, number of rooms, facilities, etc.

[0869] "Indexing to a searchable state" refers to the process of organizing and registering data so that it can be searched efficiently, allowing data to be quickly retrieved based on keywords or conditions.

[0870] "Desired conditions" refer to the characteristics and conditions of the property desired by the buyer, and include specific requests such as budget, area, size, and facilities.

[0871] "Recognizing emotions and recording them in a database" refers to the operation of analyzing the user's emotional state and storing the results in a database, making it possible to use data that takes into account the user's psychological state.

[0872] "Verifying and matching" refers to the process of comparing and considering the seller's property information with the buyer's desired conditions and emotional state, and identifying and proposing properties that meet the matching conditions.

[0873] "Proposing the best property" means selecting and recommending the property that is most suitable for the buyer based on the analysis results and the user's emotional state.

[0874] "Adjusting viewing dates" refers to the operation of confirming and adjusting the schedules of the seller and buyer to decide on a date to view the property.

[0875] A "generative AI model" refers to an artificial intelligence method for automatically generating new information and documents based on large amounts of data, and is a technology that performs natural language processing and document generation.

[0876] "Recording emotions during signing and providing support for anxiety and doubts" refers to the operation of recording the user's emotional state when signing a contract and providing support and assistance as needed.

[0877] "Automatically collecting fees" refers to the operation of automatically calculating and collecting transaction fees by the system.

[0878] "Recording the completion of a transaction" refers to the operation of registering and saving the final status of the transaction in the system and recording that the transaction has officially ended.

[0879] The present invention provides a system for improving the efficiency of real estate brokerage services and providing services that take user emotions into consideration. This system operates in cooperation with a server, a terminal, and a user. Specific embodiments are described below.

[0880] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, it uses Apache Hadoop to efficiently collect large amounts of data, preprocesses the data using Python's pandas library, converts it into a unified format, and centralizes it. This centralized data is stored in a relational database such as MySQL or PostgreSQL. The server then analyzes the data using machine learning algorithms such as Scikit-learn and TensorFlow, and stores the analysis results in a structured database.

[0881] Users (sellers) enter their property information from a device (PC or smartphone app). Specifically, they enter detailed information such as the property's location, price, area, and facilities into a form, and this data is sent from the device to the server. The server indexes the received property information into a search engine such as Elasticsearch, making it searchable.

[0882] The user (buyer) inputs the conditions for the property they are looking for on their device. This information includes desired conditions such as budget, area, size, and facilities. These conditions are sent from the device to the server and stored. An emotion engine (e.g., Amazon Rekognition or Microsoft Azure Face API) then analyzes the face and text entered by the user to recognize their emotions and records the results in a database.

[0883] The server compares property information with the buyer's desired conditions and emotional state to suggest the most suitable property. Specifically, it compares property information using Elasticsearch and runs a matching algorithm using a recommendation system library (e.g., Surprise or LightFM). As a result, a list of the most suitable properties is generated and sent to the user's (buyer's) device.

[0884] When a user (buyer) wishes to visit a property, they input their desired dates into the system. The server checks the schedules of the seller and buyer, and then uses an emotion engine to suggest the optimal date for the visit. Once the date for the visit has been decided, the server notifies both the seller and buyer.

[0885] If a user (buyer) wishes to purchase a property, they express their intention through their device. The server automatically creates a sales contract using a generative AI model (e.g., OpenAI GPT) and sends this contract to both users. The user signs the contract on their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[0886] The server automatically collects a 1% commission from the seller and buyer of the property. This process uses online payment services such as Stripe or PayPal API. Once the payment is confirmed, the server records the transaction as completed.

[0887] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, if another user looking for a property enters their desired conditions, setting "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract matching properties, and the emotion engine will make the optimal proposal while checking the user's emotions. Intentions to view properties and emotions at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[0888] An example prompt is:

[0889] "Please register information about a 3LDK apartment for sale for 70 million yen in the system."

[0890] or

[0891] "I'm looking for a 3LDK apartment in Tokyo. My budget is 80 million yen."

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Step 1:

[0894] The server collects real estate transaction data, contract data, and sales promotion data from various databases. The input is a dataset provided by multiple databases, and the output is data in a unified format. The specific operations for data collection involve acquiring the data using Apache Hadoop, preprocessing the data using Python's pandas library, completing missing values, and unifying the format.

[0895] Step 2:

[0896] The server analyzes the preprocessed data and generates analytical results using machine learning algorithms. The input is the preprocessed data, and the output is the analytical results. Specifically, it uses libraries such as Scikit-learn and TensorFlow to train models for estimating property prices and predicting buyer behavior. The analytical results are stored in a structured database.

[0897] Step 3:

[0898] The user (seller) enters their property information from a terminal. The input is detailed property information (location, price, area, facilities, etc.), and the output is indexed property information. Specifically, the user enters detailed property information using an input form, and the data is sent to the server using an HTTP request. The server indexes the received data in the Elasticsearch search engine.

[0899] Step 4:

[0900] The user (buyer) inputs the desired property conditions from a terminal. The input is the desired conditions (budget, area, size, facilities, etc.), and the output is the saved desired condition data. In concrete terms, the desired conditions are entered using an input form, and the information is sent to the server via an HTTP request. The emotion engine is used to analyze the user's emotions at the time of input, and the results are recorded in a database.

[0901] Step 5:

[0902] The server compares property information with the buyer's desired conditions and emotional state to generate the optimal property list. The input is property information, desired conditions, and emotional data, and the output is the optimal property list. Specifically, it uses Elasticsearch to search for properties that match the conditions and executes a matching algorithm using the Recommendation System library. The generated property list is sent to the terminal.

[0903] Step 6:

[0904] The user (buyer) inputs the tour schedule. The input is the desired tour schedule, and the output is the adjusted tour schedule. Specifically, the desired tour schedule is entered from the terminal, and the information is sent to the server via an HTTP request. The server compares it with the seller's schedule and proposes the optimal tour schedule taking into account the buyer's emotional state. This schedule is notified to both the seller and the buyer.

[0905] Step 7:

[0906] When a user (buyer) expresses their intention to purchase, the server automatically generates a sales contract using a generative AI model. The input is information about the sales contract, and the output is an automatically generated contract. Specifically, a contract is created using a generative AI model such as OpenAI GPT, and the contract is sent to the user. The user signs the contract through their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[0907] Step 8:

[0908] The server automatically collects the fee and completes the transaction. The input is the purchase amount and fee calculation information, and the output is a record of the transaction completion. Specifically, it automates the collection of fees using Stripe or PayPal API, and once payment is confirmed, records the completion of the transaction in the database.

[0909] (Application example 2)

[0910] 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."

[0911] Current real estate brokerage systems have difficulty accurately matching the needs of buyers and sellers, and rarely consider the user's emotional state when making proposals. This often leaves users feeling frustrated and stressed when searching for a property. Furthermore, efficient advertisement generation and delivery is lacking, reducing the opportunities for users to receive the most appropriate information.

[0912] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for recognizing the user's emotions and making optimal property proposals based on the emotional state, and means for generating and providing real estate advertisements based on the emotional state. This makes it possible to make appropriate property proposals and advertisements based on the user's emotional state.

[0913] "Real estate transaction data" refers to information relating to the sale, purchase, or rental of real estate, and includes details such as the property's location, price, area, floor plan, and age.

[0914] "Contract data" refers to document data that describes the contract details related to real estate transactions, and is electronic data such as sales contracts and rental contracts.

[0915] "Promotional Data" means data relating to marketing and sales promotions, including information about advertising campaigns, promotional materials, and consumer responses.

[0916] "Means for recognizing emotions" refers to technology that analyzes a user's input and behavior to identify their emotional state, and is a method that uses natural language processing and machine learning algorithms.

[0917] "Means for making optimal property proposals" refers to technology that selects and proposes the most suitable property based on the user's desired conditions and emotional state.

[0918] "Means for generating and providing real estate advertisements" refers to a technology that uses a generative AI model to create advertising copy about real estate and provides it at a time that corresponds to the user's emotional state.

[0919] The "emotional state of a user" refers to the emotions that a user has in a particular situation, and is a general term for emotions such as satisfaction, stress, joy, and sadness.

[0920] The present invention is a system that automates real estate brokerage operations and provides optimal services by recognizing user emotions. This system operates in cooperation with a server, terminals, and users.

[0921] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collection, this data is preprocessed and converted into a unified format for centralized management. Next, the server analyzes the data using machine learning algorithms and stores it in a database structured by category. The specific software used is Pandas and SQLite.

[0922] The user (seller) enters their property information through a terminal. This information includes details such as the property's location, price, area, and facilities, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format. The user (buyer) also enters the property conditions they desire through the terminal. These conditions are also sent from the terminal to the server, and the server stores the received conditions.

[0923] The emotion engine recognizes the emotion of the user's input and records it in a database. This emotion engine uses the Google Cloud Natural Language API.

[0924] The server compares the entered property information with the buyer's desired conditions and performs matching. At this time, an emotion engine analyzes the user's emotional state and reflects it in the property suggestions. The matching algorithm is implemented using Scikit-learn, identifies properties that meet the desired conditions, and suggests the most suitable property taking the user's emotions into consideration. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal.

[0925] The user (buyer) can check this list and view detailed information. If they wish to view a property they are interested in, they input their desired dates into the system. The server checks this against the seller's schedule and arranges the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and suggests the most appropriate date. The viewing date is then notified to both the seller and the buyer.

[0926] After viewing the property, if the user (buyer) wishes to purchase it, they express their intention to do so via their device. The server automatically creates a sales contract using the generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts. OpenAI's GPT model is used for the generation AI.

[0927] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0928] For example, if a user inputs "I'm tired of searching for a property lately," the system will analyze this input and generate and provide a positive ad copy that takes into account the user's emotional state. This ad copy will be provided in the form of "Tired of searching for a property? We have a great suggestion to help you relax. Please take a look."

[0929] This system will enable efficient and emotionally sensitive real estate transactions and advertising.

[0930] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0931] Step 1:

[0932] The server collects real estate transaction data, contract data, and sales promotion data from various databases and performs preprocessing. During this process, the Pandas library is used to convert the data into a unified format such as CSV and save it in an SQLite database. Data input is performed via API from external databases, and output is data saved in a unified format.

[0933] Step 2:

[0934] The user (seller) enters property information through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered into an input form, and this data is sent from the terminal to the server. The input data is sent to the server in a standardized format such as JSON, and the server stores it in a database and indexes it so that it can be searched.

[0935] Step 3:

[0936] The user (buyer) inputs the desired property conditions through a terminal. Desired conditions include budget, area, size, facilities, etc. These desired conditions are sent from the terminal to the server, which then stores the received conditions in a database. The input data is sent to the server in a standardized format such as JSON and stored in the database.

[0937] Step 4:

[0938] The emotion engine recognizes the emotion expressed by the user when they input text and records it in a database. Sentiment analysis uses the Google Cloud Natural Language API to analyze the user's input text and calculate an emotion score. The input is the user's text data, and the output is the emotion score and its classification result (satisfaction, stress, etc.).

[0939] Step 5:

[0940] The server compares the entered property information with the buyer's desired conditions and performs matching. It uses Scikit-learn to apply a machine learning matching algorithm. At this time, the emotional state of the buyer is also reflected in the analysis results using an emotion engine. The input is the seller's property information, the buyer's desired conditions, and an emotion score, and the output is a list of optimal property proposals.

[0941] Step 6:

[0942] Users (buyers) can check the proposed property listings on their devices and view detailed information. The user interface is implemented as a web page or mobile app, and the information provided is obtained in real time from the server.

[0943] Step 7:

[0944] When a user (buyer) wishes to tour the property, they enter the desired tour dates into the system. The server checks the seller's schedule and automatically adjusts the tour dates. The Google Calendar API is used to adjust the tour dates. The input is the user's desired tour dates, and the output is the adjusted tour dates.

[0945] Step 8:

[0946] The server automatically generates a sales contract using a generative AI model. It uses OpenAI's GPT model to create a contract template and sends it to users (sellers and buyers). The input is basic contract information and sentiment scores, and the output is an automatically generated contract.

[0947] Step 9:

[0948] Users (seller and buyer) review the contract and sign it electronically through their devices. This process uses an electronic signature platform (e.g., DocuSign). The input is the generated contract, and the output is the signed contract.

[0949] Step 10:

[0950] The server automatically collects a 1% commission from the seller and buyer of the property price. This process uses an electronic payment service (e.g., Stripe). The input is the property price and commission information, and the output is confirmation of the commission collected.

[0951] Example prompt sentence:

[0952] "I'm tired of searching for properties lately."

[0953] 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.

[0954] 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.

[0955] 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.

[0956] [Fourth embodiment]

[0957] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0958] 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.

[0959] 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).

[0960] 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.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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."

[0970] The present invention is a system for automating real estate brokerage business. This system operates by interoperating with a server, a terminal, and a user.

[0971] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. The server preprocesses the collected data, converts it into an appropriate format, and centralizes it. The server then analyzes this data using machine learning algorithms and stores it in a structured database.

[0972] Next, the user (seller) enters information about their property through the terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and the terminal sends this data to the server. The server stores the received property information in a database and indexes the seller's property information in a searchable format.

[0973] Meanwhile, the user (buyer) inputs the conditions of the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, and the server stores the received conditions.

[0974] The server compares the stored property information with the buyer's desired conditions, runs the corresponding matching algorithm, and finds properties that match the buyer's desired conditions. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The buyer can then review the proposed property list through the terminal and view the details of the properties that interest them.

[0975] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and arranges the viewing date. The server then notifies both the seller and the buyer of the viewing date, helping to ensure the viewing goes smoothly.

[0976] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server uses generation AI to automatically create a sales contract. The contract is sent to both devices, and the users (seller and buyer) review and sign the contract. The server saves the signed contract and converts it into a legally valid format.

[0977] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[0978] As described above, the present invention provides a system that fully automates real estate brokerage operations, resulting in efficient and cost-effective transactions for both parties.

[0979] Examples:

[0980] An individual (seller) looking to sell a property in Tokyo accesses a real estate brokerage system and registers property information. Let's say the seller is selling a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. The system stores this information in a database and makes it searchable by other users. Similarly, a buyer looking for a property in Tokyo enters their desired conditions into the system. If the desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system automatically extracts the seller's properties and proposes them to the buyer. The buyer then requests a viewing, and the system arranges a viewing date. After the viewing, if the buyer indicates their intention to purchase, a sales contract is automatically generated, and the signature and commission payment are completed through the system. This entire process is fully automated, making real estate transactions smooth and low-cost.

[0981] The processing flow will be explained below.

[0982] Step 1:

[0983] The server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it converts the collected data into a unified format and manages it centrally.

[0984] Step 2:

[0985] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category, using natural language processing technology.

[0986] Step 3:

[0987] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[0988] Step 4:

[0989] The server then verifies the property information received, stores it in a database in the appropriate format, and indexes this information in a searchable format.

[0990] Step 5:

[0991] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal. The desired conditions are immediately sent to the server.

[0992] Step 6:

[0993] The server stores the buyer's requirements and matches them with the property information, using a matching algorithm to identify the property that best meets the requirements.

[0994] Step 7:

[0995] The server generates a list of properties that match the buyer's desired conditions and sends the list to the terminal. The user (buyer) can check the list and view detailed information.

[0996] Step 8:

[0997] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[0998] Step 9:

[0999] The server checks the seller's schedule and automatically adjusts the tour date, and notifies the seller and buyer of the adjusted tour date via their terminals.

[1000] Step 10:

[1001] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generation AI.

[1002] Step 11:

[1003] The created sales contract is sent to the seller and buyer via the terminal, where both parties confirm the contents of the contract and sign it on the terminal.

[1004] Step 12:

[1005] The server converts the signed contract into a legally valid format and stores it in a database.

[1006] Step 13:

[1007] The server calculates a commission of 1% of the property price and charges it to the seller and buyer. The commission is paid via the terminal, and after confirming the payment, the completion of the transaction is recorded.

[1008] These are the detailed processing steps that take place within the system, which will efficiently automate real estate transactions and significantly reduce costs.

[1009] Example 1

[1010] 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."

[1011] Traditional real estate brokerage requires a lot of manual work and time, making transactions complicated and requiring efficient and speedy processing. Furthermore, the process involves a wide range of tasks, such as matching buyers and sellers, creating contracts, and arranging viewing dates, and full automation is required. Furthermore, automating the collection of commissions can reduce transaction costs and ensure smooth real estate transactions.

[1012] 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.

[1013] In this invention, the server includes means for collecting data, means for preprocessing and structuring the data, means for sellers to input real estate property information, means for buyers to input desired property conditions, means for preprocessing and saving the property information and the desired conditions, means for matching the property information with the desired conditions, means for proposing properties based on the matching results, means for arranging viewing dates, means for automatically generating a sales contract, and means for automatically collecting fees. This makes it possible to automate all real estate transaction operations efficiently and quickly, thereby reducing transaction costs.

[1014] "Means of collecting data" refers to a means of centrally collecting data related to real estate transactions, contract data, and sales promotion data.

[1015] The "means for preprocessing and structuring the data" refers to a means for converting the collected data into an appropriate format, and preparing it for centralized management and analysis using machine learning algorithms.

[1016] "Means for sellers to input information about real estate properties" refers to an interface for sellers to input detailed information about their properties (e.g., location, price, area, facilities), and is a means for transmitting information to a server via a terminal.

[1017] "Means for buyers to input the conditions for the property they desire" refers to an interface for buyers to input the conditions for the property they desire (e.g., budget, area, size, facilities), and is a means for transmitting information to the server via a terminal.

[1018] The "means for preprocessing and storing the property information and desired conditions" is a means for preprocessing the input property information and desired conditions and storing them in a database.

[1019] The "means for matching the property information with the desired conditions" refers to a means for executing an algorithm that matches the stored property information with the desired conditions and identifies a property that matches the buyer's desires.

[1020] The "means for proposing properties based on the results of the matching" refers to a means for generating a list of suitable properties based on the results of the matching algorithm and presenting the list to the buyer.

[1021] The "means of arranging a viewing date" refers to a means of matching the buyer's desired viewing date with the seller's schedule and arranging a viewing date that is convenient for both parties.

[1022] "Means for automatically generating a sales contract" refers to a means for automatically generating a contract using a generative AI model and sending the contract to both users.

[1023] A "means for automatically collecting fees" is a means for calculating fees based on the property price and automatically collecting fees from sellers and buyers.

[1024] The present invention is a system for fully automating real estate brokerage business, which operates in cooperation with a server, terminals, and users.

[1025] Hardware and software used

[1026] Server: Database management systems (e.g., MySQL, PostgreSQL), machine learning algorithms (e.g., scikit-learn, TensorFlow), generative AI models (e.g., GPT-4)

[1027] Devices: PC, smartphone, web application, mobile app

[1028] Data format: JSON, CSV

[1029] Database: Structured database (e.g. MySQL, PostgreSQL), indexing system (e.g. Elasticsearch)

[1030] Prompt input example: Text format

[1031] System Operation

[1032] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server collects data through various APIs and database connections and performs preprocessing. Preprocessing involves converting the data into an appropriate format (e.g., JSON) and removing noise and missing values ​​to prepare it for centralized management. The server also structures the data for analysis and analyzes it using machine learning algorithms. The analysis results are stored in a structured database (e.g., MySQL).

[1033] Next, the user (seller) enters property information. Detailed information such as the property's location, price, area, and facilities is entered via a web application or mobile app displayed on the device (PC or smartphone). The device then sends the entered information to the server. The server stores the received information in a database and makes it searchable using an indexing system (e.g., Elasticsearch).

[1034] Similarly, the user (buyer) inputs their desired conditions, such as budget, area, size, and facilities, through a terminal. The terminal sends the information to the server, which then stores it in a database.

[1035] The server compares the stored property information with the buyer's desired conditions. It then runs a matching algorithm (e.g., collaborative filtering, content-based filtering) to identify suitable properties. The server then generates a property list based on the results and sends it to the terminal. The user (buyer) can then view the proposed property list through the terminal.

[1036] Next, if the user (buyer) wishes to view a property they are interested in, they input their desired dates into the terminal. The server uses this information to check the seller's schedule and arranges the viewing date. The viewing date is notified to both the seller and the buyer.

[1037] After viewing the property, if the user (buyer) indicates their intention to purchase the property, the server automatically generates a sales contract using a generative AI model (e.g., GPT-4). At this time, the server inputs the following prompt sentence into the generative AI to create the contract:

[1038] "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo."

[1039] The generated contract is sent to both terminals, where the users (seller and buyer) confirm the contents and digitally sign them. The server stores the signed contract and converts it into a legally valid format.

[1040] Finally, the server automatically collects a 1% commission on the property price. Users (sellers and buyers) complete the commission payment on the system, and the server records the completion of the transaction once it has confirmed the payment.

[1041] In this way, the system of the present invention can automate each stage of a real estate transaction efficiently and quickly, thereby reducing transaction costs.

[1042] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1043] Step 1: Data collection and preprocessing

[1044] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, the server uses APIs and SQL queries to extract data and convert it into formats (e.g., JSON, CSV). Preprocessing includes filling in missing values ​​and removing noise data. The input data is the raw data from various databases, and the output data is preprocessed data in a standardized format.

[1045] Step 2: Enter property information

[1046] The user (seller) uses a terminal to enter property information (location, price, area, facilities, etc.). The terminal provides a form-based interface, verifies the entered data, and then sends it to the server. The input data is the property information entered by the seller, and the output data is the property data in JSON format that is sent to the server.

[1047] Step 3: Enter your desired conditions

[1048] The user (buyer) uses a terminal to input desired conditions (budget, area, size, facilities, etc.). The terminal also provides a form-based interface and sends the input information to the server. The input data is the buyer's desired conditions, and the output data is the desired conditions data in JSON format that is sent to the server.

[1049] Step 4: Storing and indexing data

[1050] The server stores the received property information and desired conditions in a database. The stored data is indexed and made searchable (e.g., Elasticsearch). The input data is JSON data of the property information and desired conditions, and the output data is in an indexed database state.

[1051] Step 5: Match property information with desired conditions

[1052] The server matches the stored property information with the buyer's desired criteria. It uses specific algorithms (e.g., collaborative filtering, content-based filtering) to identify properties that match the buyer's desired criteria. The input data is the indexed property information and desired criteria, and the output data is the matching property list.

[1053] Step 6: Property proposal

[1054] The server generates a list of properties to be proposed based on the matching results and sends the list to the terminal. The user (buyer) checks the proposed property list through the terminal. The input data is the property list of the matching results, and the output data is the property list displayed on the terminal.

[1055] Step 7: Arrange a tour date

[1056] The user (buyer) inputs the desired tour date into the terminal. The server checks it against the seller's schedule and arranges an appropriate tour date. The server notifies the seller and buyer of the tour date. The input data is the desired tour date, and the output data is a notification of the adjusted tour date.

[1057] Step 8: Auto-generate a sales contract

[1058] When a user (buyer) indicates their intention to purchase, the device sends that information to the server. The server then uses a generative AI model (e.g., GPT-4) to automatically generate a sales contract. An example of a prompt is "Please generate a contract for a 3LDK apartment in Shibuya Ward, Tokyo." The generated contract is sent to both devices, and the users (seller and buyer) confirm the contents and sign electronically. The input data is the information indicating their intention to purchase, and the output data is the generated contract.

[1059] Step 9: Fee Collection

[1060] The server automatically collects a commission of 1% of the property price from the seller and buyer. Users (sellers and buyers) complete the commission payment on the system. The server confirms the payment and records the completion of the transaction. The input data is the property price and commission rate, and the output data is a record of the commission collected.

[1061] (Application example 1)

[1062] 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."

[1063] In real estate transactions, efficient matching between sellers and buyers and quick contract procedures are required. Furthermore, scheduling property viewings and contracts is complicated, making it difficult for both parties to communicate smoothly. This issue is also common to service provision and reservation systems in brick-and-mortar stores, and there is a particular need for efficient and smooth service provision between store owners and users. This project aims to solve these issues.

[1064] 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.

[1065] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for sellers to input property information or store information, means for buyers to input desired conditions, means for collating and matching the property information or store information with the desired conditions, means for proposing properties or stores based on the collation results, means for arranging viewing dates or available reservation dates and times, means for automatically generating contracts, and means for collecting fees. This enables efficient and smooth matching, schedule adjustment, contract conclusion, and automatic fee collection in real estate transactions and brick-and-mortar store services.

[1066] "Real estate transaction data" refers to data that includes information regarding the sale, purchase, and rental of properties.

[1067] "Contract data" refers to data on documents relating to sales or rental contracts.

[1068] "Promotional Data" means data that includes marketing information for the purpose of promoting sales, purchases, or rentals.

[1069] "Seller" is the person or entity selling or renting the property or store.

[1070] "Property information" is data that includes detailed information about the property, such as its location, price, area, and facilities.

[1071] "Store information" is data including detailed information such as the store's location, business hours, services offered, and price range.

[1072] "Buyer" means a person or legal entity seeking to purchase or occupy a property or store.

[1073] "Desired conditions" are the conditions the buyer desires regarding the property or store.

[1074] "Matching" means comparing the seller's property or store information with the buyer's desired conditions to find a suitable match.

[1075] A "proposal" is the introduction of a property or store to a buyer based on the matching results.

[1076] "Viewing dates" and "reservation dates" are schedules for sellers and buyers to inspect properties and stores.

[1077] "Automatic contract generation" means that the system automatically creates the contents of a sales or usage contract.

[1078] "Fee collection" means automatically collecting fees from sellers and buyers for using the system.

[1079] This invention is a system that efficiently and automatically matches property and store information and speeds up contract procedures. It is equipped with means for collecting, analyzing, and structuring real estate transaction data, contract data, and sales promotion data. It also includes a function that allows sellers and buyers to input their respective information, performs matching, and proposes the most suitable property or store.

[1080] 1. System Configuration

[1081] The server runs in a cloud environment such as AWS (Amazon Web Services) and collects, analyzes, stores, and structures data. React Native (for smartphones) and React (for the web) are used for the front end, building an interface with the devices (smartphones and computers) where users input information. Node.js and Express are used for the back end, handling data processing and API provision. SQL databases (MySQL) and NoSQL databases (MongoDB) are used. Additionally, the scikit-learn library is used for machine learning to implement a matching algorithm.

[1082] 2. Data collection and analysis

[1083] The server collects real estate transaction data, contract data, and sales promotion data from various databases, analyzes and structures it, and uses machine learning algorithms to convert the collected data into an appropriate format for centralized management.

[1084] 3. Enter seller and buyer information

[1085] Sellers input their property or store information through a terminal. The input information includes location, price, area, facilities, business hours, etc. Buyers also input the conditions for the property or store they are looking for through a terminal. The input conditions include budget, area, size, specific facilities and services, etc.

[1086] 4. Matching and Proposal

[1087] The server uses machine learning to match the seller's property or store information with the buyer's desired conditions and generates the optimal matching results. Based on these results, the optimal property or store is proposed and provided to the buyer.

[1088] 5. Arrangement of tour dates or available reservation dates

[1089] The system automatically coordinates viewing dates and available reservation dates for properties and stores by checking the schedules of both the seller and buyer. The system suggests the optimal date and time based on the schedules of both parties, helping to ensure that viewings and reservations go smoothly.

[1090] 6. Automatically generate and sign contracts

[1091] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract. The contract is created using a generative AI model and sent to both devices. The user can then review the contract and sign it via their device.

[1092] 7. Collection of Fees

[1093] Finally, fees for using the property or store are automatically collected from the seller and buyer via the system, and the transaction is completed.

[1094] Specific examples

[1095] For example, a user searching for a cafe in Tokyo enters the following prompt on their smartphone:

[1096] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[1097] The system matches cafes that meet the criteria and presents available dates and times for reservations. The user selects the desired date and time and confirms the reservation through the system. Finally, a usage agreement with the cafe is automatically generated, which is signed and confirmed by both the user and the cafe. This series of processes is carried out efficiently and smoothly, bringing benefits to both the user and the cafe owner.

[1098] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1099] Step 1:

[1100] The server collects real estate transaction data, contract data, and sales promotion data from various databases. Because the collected data is inconsistent in format and content, it is preprocessed to convert it into a unified format. Specifically, it parses the JSON and XML formatted data, extracts the necessary fields, and stores them in a structured database. This process is expected to use AWS's data lake service.

[1101] Step 2:

[1102] Through the terminal, sellers input property or store information, including the property or store's location, price, area, facilities, and opening hours. The terminal then sends the input information to the server, which stores the received data in a database and indexes it for searchability.

[1103] Step 3:

[1104] Through the terminal, buyers input their desired property or store conditions, such as budget, area, size, specific facilities and services, etc. The terminal then transmits the desired conditions to the server, which stores the information in a database.

[1105] Step 4:

[1106] The server uses a machine learning algorithm to match the seller's property or store information with the buyer's desired conditions. The algorithm used in this process is implemented using the scikit-learn library. Specifically, the input data is treated as features, and matching is performed by calculating the similarity. The matching results obtained in this way are stored in a database.

[1107] Step 5:

[1108] The server then proposes the most suitable property or store to the buyer based on the matching results. The proposed list is sent to the buyer's terminal and can be viewed by the buyer. The proposed list includes detailed information about the property or store.

[1109] Step 6:

[1110] When a buyer selects a tour date or an available reservation date and time, that information is sent to the server. The server checks the seller's schedule and automatically adjusts the optimal tour date or reservation date and time. The adjusted results are notified to the seller's and buyer's terminals.

[1111] Step 7:

[1112] When a buyer wishes to purchase or use a property or store, the server automatically generates a contract using a generative AI model. This contract is then sent to both devices, where the user can review the contents and electronically sign.

[1113] Step 8:

[1114] Once the contract procedure is completed, the server automatically collects the fee. To collect the fee, an electronic payment service is used. Once payment is confirmed, the transaction is completed and a record is saved in the database.

[1115] The data processing and calculations performed at each step are as follows:

[1116] In step 1, various data is collected, converted into an appropriate format, and centrally managed.

[1117] In steps 2 and 3, the data entered by the user is formatted, sent to the server, and saved.

[1118] In step 4, machine learning algorithms are used to collate the data and generate matching results.

[1119] In step 5, properties and stores are proposed based on the matching results.

[1120] Step 6 automates tours and reservations through schedule adjustments.

[1121] In step 7, a generative AI model is used to automatically generate a contract and assist with electronic signatures.

[1122] In step 8, fees are automatically collected using an electronic payment service.

[1123] For example, here's a prompt that a user searching for a cafe in Tokyo might enter:

[1124] "I'm looking for a cafe in Tokyo that has Wi-Fi and power outlets. My budget is under 1,000 yen."

[1125] 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.

[1126] This invention is a system for automating real estate brokerage business, and further combines an emotion engine that recognizes user emotions and provides optimal services. The system operates in cooperation with a server, terminals, and users.

[1127] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collecting the data, it preprocesses it, converts it into a unified format, and centrally manages it. Then, the server analyzes the data using machine learning algorithms and stores it in a structured database by category.

[1128] The user (seller) enters information about their property through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format.

[1129] The user (buyer) inputs the conditions for the property they desire through a terminal. The information input by the buyer includes conditions such as budget, area, size, and facilities. These desired conditions are sent from the terminal to the server, which then stores the received conditions. Furthermore, the emotion engine recognizes the emotion of the user when entering the information and records it in a database.

[1130] The server compares property information with the buyer's desired conditions. At this time, an emotion engine analyzes the user's emotional state and reflects this in the property suggestions. The matching algorithm identifies properties that meet the desired conditions and then takes the user's emotions into consideration to suggest the most suitable property. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal. The user (buyer) can review this list and view detailed information.

[1131] When a user (buyer) wishes to view a property they are interested in, they input their desired dates into the system. The server checks the seller's schedule and adjusts the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and proposes the optimal date. The server then notifies both the seller and the buyer of the viewing date.

[1132] After viewing the property, if the user (buyer) wishes to purchase the property, they express their intention to do so via their device. The server automatically creates a sales contract using generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts.

[1133] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then verifies the payment and records the completion of the transaction.

[1134] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment located in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, another user looking for a property in Tokyo enters their desired conditions into the system. If this user's desired conditions are "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract the seller's properties, and the emotion engine will make suggestions while checking the user's emotional state. Intentions to view properties and the emotional state at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[1135] The above is a specific embodiment of the system that combines the emotion engine, which enables efficient and emotion-conscious real estate transactions.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] The server collects real estate transaction data, contract data, and sales promotion data from various databases, converts the collected data into an appropriate format, and manages it centrally.

[1139] Step 2:

[1140] The server analyzes the collected data using machine learning algorithms and stores it in a structured database by category. It also uses natural language processing technology to analyze the meaning of the data and create an index.

[1141] Step 3:

[1142] Users (sellers) enter information about their property (location, price, area, facilities, etc.) through a terminal. The entered information is sent to the server in real time.

[1143] Step 4:

[1144] The server stores the received property information in a database, automatically verifies that the data is accurate and complete, and indexes the stored property information in a searchable format.

[1145] Step 5:

[1146] The user (buyer) inputs the desired property conditions (budget, area, size, facilities, etc.) through a terminal, and the desired conditions are immediately sent to the server.

[1147] Step 6:

[1148] The server stores the desired conditions received from the buyer. Furthermore, when the user inputs the conditions, the terminal uses an emotion engine to analyze the user's emotional state (e.g., satisfaction, anxiety, expectation) and records it in a database.

[1149] Step 7:

[1150] The server compares the stored property information with the buyer's desired conditions and executes a matching algorithm, during which an emotion engine analyzes the user's emotional state and reflects it in the property proposals.

[1151] Step 8:

[1152] The server generates a property list based on the matching results and sends it to the user's (buyer's) terminal in a format that is easy for the user to view. The emotion engine monitors the user's reaction when making a proposal and provides necessary support.

[1153] Step 9:

[1154] The user (buyer) inputs the desired date and time to view the property that he / she is interested in from the property list through the terminal. The desired date and time is sent to the server.

[1155] Step 10:

[1156] The server checks the seller's schedule and automatically adjusts the tour date. At this time, the emotion engine analyzes the user's emotions and suggests the optimal tour date and time. The adjusted tour date is notified to the seller and buyer via their terminals.

[1157] Step 11:

[1158] After the viewing, the user (buyer) expresses their intention to purchase the property on their device. The server receives this information and automatically creates a sales contract using generative AI. During this process, the emotion engine also records the user's emotional state.

[1159] Step 12:

[1160] The created sales contract is sent to the seller and buyer via the terminal. The users (seller and buyer) check the contents of the contract and sign it on the terminal. At this time, the emotion engine detects the user's anxieties and concerns at the time of signing and provides appropriate support.

[1161] Step 13:

[1162] The server converts the signed contract into a legally valid format and stores it in a database.

[1163] Step 14:

[1164] The server calculates the commission of 1% of the property price for both the seller and the buyer, issues an invoice, and records the completion of the transaction after the commission is paid via the terminal.

[1165] The above are the detailed processing steps of this system that combines an emotion engine. As a concrete example, consider the case where a user wants to sell a property in Tokyo. This user registers property information in the system, and the property is proposed to another user as a property that matches their desired conditions. The emotion engine analyzes the user's emotional state at the time of proposal, viewing, and contract signing, and supports the user so that they can proceed with the transaction with peace of mind. This system realizes efficient and user-friendly real estate transactions.

[1166] Example 2

[1167] 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."

[1168] In traditional real estate brokerage, many processes, such as data collection, analysis, property matching, scheduling tours, creating contracts, and collecting fees, were performed manually, resulting in time-consuming, labor-intensive, and inefficient processes. Furthermore, the process often ignored the user's emotional state, causing anxiety and doubt during the transaction. There is a need to solve these problems and realize efficient real estate transactions that take the user's emotions into consideration.

[1169] 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.

[1170] In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for preprocessing the data, converting it into a unified format, and centrally managing it, means for analyzing the data using a machine learning algorithm and saving it in a structured database, means for sellers to input property information, means for indexing the input property information in a searchable format, means for buyers to input desired conditions, means for recognizing the buyer's emotions at the time of input and recording them in a database, means for comparing and matching the property information with the desired conditions and the buyer's emotional state, means for proposing optimal properties based on the matching results, means for arranging a viewing schedule, means for comparing the schedules of the buyer and seller and proposing a viewing schedule taking into account the buyer's emotional state, means for automatically generating a sales contract based on a generative AI model, means for recording the user's emotions at the time of signing and providing support for any concerns or doubts, means for automatically collecting fees, and means for confirming payment and recording the completion of the transaction, thereby enabling efficient real estate transactions that are considerate of the user's emotions.

[1171] "Real estate transaction data" refers to all information related to the sale, purchase, rental, and contract of real estate, and specifically includes data such as the property price, location, area, facilities, and contract terms.

[1172] "Contract data" refers to the information contained in contracts used in real estate transactions, including legal clauses, information about the parties, terms of the transaction, signatures, and the like.

[1173] "Promotional Data" refers to marketing information used to promote real estate transactions, including advertising campaigns, customer interest and behavior data, and promotional information.

[1174] "Preprocessing" refers to the processing performed before analyzing data, and includes operations such as cleaning the data, filling in missing values, and standardizing the format.

[1175] A "unified format" refers to converting data of different formats into a consistent format, making it easier to centrally manage and analyze data obtained from various sources.

[1176] A "machine learning algorithm" is a computational technique for analyzing data and finding patterns, and the results are used to make predictions and optimizations.

[1177] A "structured database" is a database system for systematically organizing and storing data, storing data in a table format to enable efficient searching and manipulation.

[1178] "Property information" refers to detailed information about real estate provided by the seller, specifically data including location, price, area, number of rooms, facilities, etc.

[1179] "Indexing to a searchable state" refers to the process of organizing and registering data so that it can be searched efficiently, allowing data to be quickly retrieved based on keywords or conditions.

[1180] "Desired conditions" refer to the characteristics and conditions of the property desired by the buyer, and include specific requests such as budget, area, size, and facilities.

[1181] "Recognizing emotions and recording them in a database" refers to the operation of analyzing the user's emotional state and storing the results in a database, making it possible to use data that takes into account the user's psychological state.

[1182] "Verifying and matching" refers to the process of comparing and considering the seller's property information with the buyer's desired conditions and emotional state, and identifying and proposing properties that meet the matching conditions.

[1183] "Proposing the best property" means selecting and recommending the property that is most suitable for the buyer based on the analysis results and the user's emotional state.

[1184] "Adjusting viewing dates" refers to the operation of confirming and adjusting the schedules of the seller and buyer to decide on a date to view the property.

[1185] A "generative AI model" refers to an artificial intelligence method for automatically generating new information and documents based on large amounts of data, and is a technology that performs natural language processing and document generation.

[1186] "Recording emotions during signing and providing support for anxiety and doubts" refers to the operation of recording the user's emotional state when signing a contract and providing support and assistance as needed.

[1187] "Automatically collecting fees" refers to the operation of automatically calculating and collecting transaction fees by the system.

[1188] "Recording the completion of a transaction" refers to the operation of registering and saving the final status of the transaction in the system and recording that the transaction has officially ended.

[1189] The present invention provides a system for improving the efficiency of real estate brokerage services and providing services that take user emotions into consideration. This system operates in cooperation with a server, a terminal, and a user. Specific embodiments are described below.

[1190] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. Specifically, it uses Apache Hadoop to efficiently collect large amounts of data, preprocesses the data using Python's pandas library, converts it into a unified format, and centralizes it. This centralized data is stored in a relational database such as MySQL or PostgreSQL. The server then analyzes the data using machine learning algorithms such as Scikit-learn and TensorFlow, and stores the analysis results in a structured database.

[1191] Users (sellers) enter their property information from a device (PC or smartphone app). Specifically, they enter detailed information such as the property's location, price, area, and facilities into a form, and this data is sent from the device to the server. The server indexes the received property information into a search engine such as Elasticsearch, making it searchable.

[1192] The user (buyer) inputs the conditions for the property they are looking for on their device. This information includes desired conditions such as budget, area, size, and facilities. These conditions are sent from the device to the server and stored. An emotion engine (e.g., Amazon Rekognition or Microsoft Azure Face API) then analyzes the face and text entered by the user to recognize their emotions and records the results in a database.

[1193] The server compares property information with the buyer's desired conditions and emotional state to suggest the most suitable property. Specifically, it compares property information using Elasticsearch and runs a matching algorithm using a recommendation system library (e.g., Surprise or LightFM). As a result, a list of the most suitable properties is generated and sent to the user's (buyer's) device.

[1194] When a user (buyer) wishes to visit a property, they input their desired dates into the system. The server checks the schedules of the seller and buyer, and then uses an emotion engine to suggest the optimal date for the visit. Once the date for the visit has been decided, the server notifies both the seller and buyer.

[1195] If a user (buyer) wishes to purchase a property, they express their intention through their device. The server automatically creates a sales contract using a generative AI model (e.g., OpenAI GPT) and sends this contract to both users. The user signs the contract on their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[1196] The server automatically collects a 1% commission from the seller and buyer of the property. This process uses online payment services such as Stripe or PayPal API. Once the payment is confirmed, the server records the transaction as completed.

[1197] As a concrete example, an individual who wants to sell a property in Tokyo accesses the system and registers property information. This individual wants to sell a 3LDK apartment in Shibuya Ward, Tokyo, for 70 million yen. Meanwhile, if another user looking for a property enters their desired conditions, setting "Tokyo, apartment, 3LDK, budget within 80 million yen," the system will automatically extract matching properties, and the emotion engine will make the optimal proposal while checking the user's emotions. Intentions to view properties and emotions at the time of contract are also managed, allowing the transaction to proceed with peace of mind.

[1198] An example prompt is:

[1199] "Please register information about a 3LDK apartment for sale for 70 million yen in the system."

[1200] or

[1201] "I'm looking for a 3LDK apartment in Tokyo. My budget is 80 million yen."

[1202] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1203] Step 1:

[1204] The server collects real estate transaction data, contract data, and sales promotion data from various databases. The input is a dataset provided by multiple databases, and the output is data in a unified format. The specific operations for data collection involve acquiring the data using Apache Hadoop, preprocessing the data using Python's pandas library, completing missing values, and unifying the format.

[1205] Step 2:

[1206] The server analyzes the preprocessed data and generates analytical results using machine learning algorithms. The input is the preprocessed data, and the output is the analytical results. Specifically, it uses libraries such as Scikit-learn and TensorFlow to train models for estimating property prices and predicting buyer behavior. The analytical results are stored in a structured database.

[1207] Step 3:

[1208] The user (seller) enters their property information from a terminal. The input is detailed property information (location, price, area, facilities, etc.), and the output is indexed property information. Specifically, the user enters detailed property information using an input form, and the data is sent to the server using an HTTP request. The server indexes the received data in the Elasticsearch search engine.

[1209] Step 4:

[1210] The user (buyer) inputs the desired property conditions from a terminal. The input is the desired conditions (budget, area, size, facilities, etc.), and the output is the saved desired condition data. In concrete terms, the desired conditions are entered using an input form, and the information is sent to the server via an HTTP request. The emotion engine is used to analyze the user's emotions at the time of input, and the results are recorded in a database.

[1211] Step 5:

[1212] The server compares property information with the buyer's desired conditions and emotional state to generate the optimal property list. The input is property information, desired conditions, and emotional data, and the output is the optimal property list. Specifically, it uses Elasticsearch to search for properties that match the conditions and executes a matching algorithm using the Recommendation System library. The generated property list is sent to the terminal.

[1213] Step 6:

[1214] The user (buyer) inputs the tour schedule. The input is the desired tour schedule, and the output is the adjusted tour schedule. Specifically, the desired tour schedule is entered from the terminal, and the information is sent to the server via an HTTP request. The server compares it with the seller's schedule and proposes the optimal tour schedule taking into account the buyer's emotional state. This schedule is notified to both the seller and the buyer.

[1215] Step 7:

[1216] When a user (buyer) expresses their intention to purchase, the server automatically generates a sales contract using a generative AI model. The input is information about the sales contract, and the output is an automatically generated contract. Specifically, a contract is created using a generative AI model such as OpenAI GPT, and the contract is sent to the user. The user signs the contract through their device, and the emotion engine records their emotions at the time of signing and provides support as needed.

[1217] Step 8:

[1218] The server automatically collects the fee and completes the transaction. The input is the purchase amount and fee calculation information, and the output is a record of the transaction completion. Specifically, it automates the collection of fees using Stripe or PayPal API, and once payment is confirmed, records the completion of the transaction in the database.

[1219] (Application example 2)

[1220] 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."

[1221] Current real estate brokerage systems have difficulty accurately matching the needs of buyers and sellers, and rarely consider the user's emotional state when making proposals. This often leaves users feeling frustrated and stressed when searching for a property. Furthermore, efficient advertisement generation and delivery is lacking, reducing the opportunities for users to receive the most appropriate information.

[1222] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting real estate transaction data, contract data, and sales promotion data, means for analyzing and structuring the data, means for recognizing the user's emotions and making optimal property proposals based on the emotional state, and means for generating and providing real estate advertisements based on the emotional state. This makes it possible to make appropriate property proposals and advertisements based on the user's emotional state.

[1223] "Real estate transaction data" refers to information relating to the sale, purchase, or rental of real estate, and includes details such as the property's location, price, area, floor plan, and age.

[1224] "Contract data" refers to document data that describes the contract details related to real estate transactions, and is electronic data such as sales contracts and rental contracts.

[1225] "Promotional Data" means data relating to marketing and sales promotions, including information about advertising campaigns, promotional materials, and consumer responses.

[1226] "Means for recognizing emotions" refers to technology that analyzes a user's input and behavior to identify their emotional state, and is a method that uses natural language processing and machine learning algorithms.

[1227] "Means for making optimal property proposals" refers to technology that selects and proposes the most suitable property based on the user's desired conditions and emotional state.

[1228] "Means for generating and providing real estate advertisements" refers to a technology that uses a generative AI model to create advertising copy about real estate and provides it at a time that corresponds to the user's emotional state.

[1229] The "emotional state of a user" refers to the emotions that a user has in a particular situation, and is a general term for emotions such as satisfaction, stress, joy, and sadness.

[1230] The present invention is a system that automates real estate brokerage operations and provides optimal services by recognizing user emotions. This system operates in cooperation with a server, terminals, and users.

[1231] First, the server collects real estate transaction data, contract data, and sales promotion data from various databases. After collection, this data is preprocessed and converted into a unified format for centralized management. Next, the server analyzes the data using machine learning algorithms and stores it in a database structured by category. The specific software used is Pandas and SQLite.

[1232] The user (seller) enters their property information through a terminal. This information includes details such as the property's location, price, area, and facilities, and this data is sent from the terminal to the server. The server stores the received property information in a database and indexes it in a searchable format. The user (buyer) also enters the property conditions they desire through the terminal. These conditions are also sent from the terminal to the server, and the server stores the received conditions.

[1233] The emotion engine recognizes the emotion of the user's input and records it in a database. This emotion engine uses the Google Cloud Natural Language API.

[1234] The server compares the entered property information with the buyer's desired conditions and performs matching. At this time, an emotion engine analyzes the user's emotional state and reflects it in the property suggestions. The matching algorithm is implemented using Scikit-learn, identifies properties that meet the desired conditions, and suggests the most suitable property taking the user's emotions into consideration. Based on the results of this comparison, the server generates a list of properties suitable for the buyer and sends it to the terminal.

[1235] The user (buyer) can check this list and view detailed information. If they wish to view a property they are interested in, they input their desired dates into the system. The server checks this against the seller's schedule and arranges the viewing date. At this time, the emotion engine takes the user's emotional state into consideration and suggests the most appropriate date. The viewing date is then notified to both the seller and the buyer.

[1236] After viewing the property, if the user (buyer) wishes to purchase it, they express their intention to do so via their device. The server automatically creates a sales contract using the generation AI, which is then sent to both users. The users (seller and buyer) check the contents and sign on their devices. The emotion engine also records the user's emotions when creating and signing the contract, and provides support if they have any concerns or doubts. OpenAI's GPT model is used for the generation AI.

[1237] Finally, the server collects a 1% commission from the seller and buyer of the property. This commission collection process is also automated, and users can complete payments on the system. The server then confirms the payment and records the completion of the transaction.

[1238] For example, if a user inputs "I'm tired of searching for a property lately," the system will analyze this input and generate and provide a positive ad copy that takes into account the user's emotional state. This ad copy will be provided in the form of "Tired of searching for a property? We have a great suggestion to help you relax. Please take a look."

[1239] This system will enable efficient and emotionally sensitive real estate transactions and advertising.

[1240] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1241] Step 1:

[1242] The server collects real estate transaction data, contract data, and sales promotion data from various databases and performs preprocessing. During this process, the Pandas library is used to convert the data into a unified format such as CSV and save it in an SQLite database. Data input is performed via API from external databases, and output is data saved in a unified format.

[1243] Step 2:

[1244] The user (seller) enters property information through a terminal. Specifically, detailed information such as the property's location, price, area, and facilities is entered into an input form, and this data is sent from the terminal to the server. The input data is sent to the server in a standardized format such as JSON, and the server stores it in a database and indexes it so that it can be searched.

[1245] Step 3:

[1246] The user (buyer) inputs the desired property conditions through a terminal. Desired conditions include budget, area, size, facilities, etc. These desired conditions are sent from the terminal to the server, which then stores the received conditions in a database. The input data is sent to the server in a standardized format such as JSON and stored in the database.

[1247] Step 4:

[1248] The emotion engine recognizes the emotion expressed by the user when they input text and records it in a database. Sentiment analysis uses the Google Cloud Natural Language API to analyze the user's input text and calculate an emotion score. The input is the user's text data, and the output is the emotion score and its classification result (satisfaction, stress, etc.).

[1249] Step 5:

[1250] The server compares the entered property information with the buyer's desired conditions and performs matching. It uses Scikit-learn to apply a machine learning matching algorithm. At this time, the emotional state of the buyer is also reflected in the analysis results using an emotion engine. The input is the seller's property information, the buyer's desired conditions, and an emotion score, and the output is a list of optimal property proposals.

[1251] Step 6:

[1252] Users (buyers) can check the proposed property listings on their devices and view detailed information. The user interface is implemented as a web page or mobile app, and the information provided is obtained in real time from the server.

[1253] Step 7:

[1254] When a user (buyer) wishes to tour the property, they enter the desired tour dates into the system. The server checks the seller's schedule and automatically adjusts the tour dates. The Google Calendar API is used to adjust the tour dates. The input is the user's desired tour dates, and the output is the adjusted tour dates.

[1255] Step 8:

[1256] The server automatically generates a sales contract using a generative AI model. It uses OpenAI's GPT model to create a contract template and sends it to users (sellers and buyers). The input is basic contract information and sentiment scores, and the output is an automatically generated contract.

[1257] Step 9:

[1258] Users (seller and buyer) review the contract and sign it electronically through their devices. This process uses an electronic signature platform (e.g., DocuSign). The input is the generated contract, and the output is the signed contract.

[1259] Step 10:

[1260] The server automatically collects a 1% commission from the seller and buyer of the property price. This process uses an electronic payment service (e.g., Stripe). The input is the property price and commission information, and the output is confirmation of the commission collected.

[1261] Example prompt sentence:

[1262] "I'm tired of searching for properties lately."

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] 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).

[1270] 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.

[1271] 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."

[1272] 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.

[1273] 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).

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] The following is further disclosed regarding the above embodiment.

[1285] (Claim 1)

[1286] a means for collecting real estate transaction data, contract data, and sales promotion data;

[1287] means for analyzing and structuring said data;

[1288] A means for sellers to enter property information;

[1289] A means for buyers to input their desired conditions;

[1290] A means for collating and matching the property information with the desired conditions;

[1291] A means for proposing properties based on the matching results;

[1292] How to schedule a tour,

[1293] A means for automatically generating a sales contract;

[1294] A system including a means for collecting fees.

[1295] (Claim 2)

[1296] The system according to claim 1, which matches the schedules of the seller and the buyer and automatically arranges the viewing date.

[1297] (Claim 3)

[1298] 2. The system of claim 1, which automatically generates a sales contract and assists both parties in signing it.

[1299] "Example 1"

[1300] (Claim 1)

[1301] a means of collecting data;

[1302] means for pre-processing and structuring said data;

[1303] A means for sellers to enter information about real estate properties;

[1304] A means for buyers to input the conditions of the property they desire,

[1305] means for preprocessing and storing the property information and the desired conditions;

[1306] A means for matching the property information with the desired conditions;

[1307] A means for proposing properties based on the matching results;

[1308] How to schedule a tour,

[1309] A means for automatically generating a sales contract;

[1310] A system that includes a means for automatically collecting fees.

[1311] (Claim 2)

[1312] The system according to claim 1, which automatically matches the schedules of the seller and the buyer and arranges the viewing date.

[1313] (Claim 3)

[1314] The system of claim 1 automatically generates a sales contract based on a generative AI model and assists both parties in signing it.

[1315] "Application Example 1"

[1316] (Claim 1)

[1317] a means for collecting real estate transaction data, contract data, and sales promotion data;

[1318] means for analyzing and structuring said data;

[1319] A means for sellers to input property or store information;

[1320] A means for buyers to input their desired conditions;

[1321] a means for collating and matching the property information or store information with the desired conditions;

[1322] A means for proposing properties or stores based on the collation results;

[1323] A means to schedule a tour or available appointment;

[1324] A means for automatically generating contracts;

[1325] A system including a means for collecting fees.

[1326] (Claim 2)

[1327] The system according to claim 1, which checks the schedules of the seller and buyer and automatically adjusts the viewing date or reservation date and time.

[1328] (Claim 3)

[1329] 2. The system of claim 1, which automatically generates a contract and assists both parties in signing it.

[1330] "Example 2: Combining Emotion Engines"

[1331] (Claim 1)

[1332] a means for collecting real estate transaction data, contract data, and promotional data;

[1333] means for preprocessing the data, converting it into a unified format, and managing it in a unified manner;

[1334] means for analyzing the data using a machine learning algorithm and storing the data in a structured database;

[1335] A means for sellers to enter property information;

[1336] A means for indexing the entered property information in a searchable form;

[1337] A means for buyers to input their desired conditions;

[1338] a means for recognizing and recording in a database the buyer's input emotions;

[1339] a means for collating and matching the property information with the desired conditions and the emotional state of the buyer;

[1340] A means for proposing the most suitable property based on the collation results;

[1341] How to schedule a tour,

[1342] A means of matching buyer and seller schedules and proposing viewing dates taking into account emotional states;

[1343] A means for automatically generating sales contracts based on an AI model;

[1344] ...

Claims

1. a means for collecting real estate transaction data, contract data, and sales promotion data; means for analyzing and structuring said data; A means for sellers to enter property information; A means for buyers to input their desired conditions; A means for collating and matching the property information with the desired conditions; A means for proposing properties based on the matching results; How to schedule a tour, A means for automatically generating a sales contract; A system including a means for collecting fees.

2. The system according to claim 1, wherein the schedules of the seller and the buyer are collated and the viewing dates are automatically arranged.

3. The system according to claim 1, wherein the system automatically generates a sales contract and assists both parties in signing it.

Images