System

Abstract

A system is provided.SOLUTION: A means by which the borrower uploads several property photographs and drawings and provides property information, a means by which the server automatically analyzes the uploaded property photographs and drawings using a generative artificial intelligence model and extracts detailed property information, a means by which the server registers the extracted detailed property information in a database, a means by which the borrower inputs a property search condition and transmits the search condition to the server, and a means by which the server searches the property database using the generative artificial intelligence model based on the received search condition; A system including means for extracting a property matching a condition, means for transmitting a search result to a terminal of a borrower by a server, means for uploading a property photograph captured by a broker for field investigation and transmitting the property photograph to the server, means for analyzing the transmitted photograph using a generative artificial intelligence model and calculating an original state recovery cost by the server, and means for automatically generating an instruction to a constructor based on the calculated cost by the server.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The 8.2 million vacant homes nationwide, accounting for 13.5% of all housing units, have become a social problem. The main causes of this vacant home problem are an oversupply of new homes and an imbalance in the used home market. Due to high barriers to entry into the used home market, many vacant homes remain unused. In addition, the complicated information transmission and procedures between lenders, borrowers, and real estate agents make it difficult to conduct transactions efficiently. This has led to problems such as the time and cost required for registering property information, searching, and administrative work. [Means for solving the problem]

[0005] This invention aims to solve the problem of vacant houses by proposing a system that utilizes a generative AI model to streamline property information registration, search, and administrative work. Specifically, we provide a system that includes the following means:

[0006] 1. A means for lenders to provide property information by uploading several property photos and drawings.

[0007] 2. The server will automatically analyze the uploaded property photos and drawings using a generative artificial intelligence model to extract detailed property information.

[0008] 3. The server registers the extracted property details in a database.

[0009] 4. A means for borrowers to enter property search criteria and send them to the server.

[0010] 5. The server uses a generated artificial intelligence model to search the property database based on the received search conditions and extract properties that match the conditions.

[0011] 6. The server is the means for transmitting search results to the borrower's terminal.

[0012] 7. A means for real estate agents to upload property photos taken for on-site inspections and send them to the server.

[0013] 8. The server will analyze the submitted photos using a generative artificial intelligence model and use it to calculate the cost of restoration to the original state.

[0014] 9. The server will automatically generate instructions for the construction company based on the calculated costs.

[0015] This will allow landlords to easily register properties, tenants to quickly find properties that meet their desired conditions, and real estate agents to streamline various administrative tasks, promoting the effective use of vacant houses and contributing to solving social problems.

[0016] "Property information" refers to detailed data about a property, including the property's location, room size, layout, and equipment status.

[0017] "Registration" is the act of storing collected property information in a database for future use.

[0018] "Search" is the act of examining property information in a database based on specific criteria to find a property that matches your criteria.

[0019] A "generative AI model" is an artificial intelligence system that analyzes data such as photographs and drawings and automatically extracts information.

[0020] A "lender" is an individual or legal entity that offers a property that it owns to a borrower.

[0021] A "borrower" is an individual or legal entity that wishes to rent a property from a lender.

[0022] A "broker" is an individual or legal entity that mediates property transactions between lenders and borrowers.

[0023] A "terminal" is an electronic device (e.g., a PC, smartphone, or tablet) that a user uses to exchange information with a server.

[0024] A "server" is a specialized computer system that processes, stores, and serves data over a network.

[0025] "Uploading" is the act of sending data from a terminal to a server and storing it. [Brief explanation of the drawings]

[0026] [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

[0027] 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.

[0028] First, the terms used in the following description will be explained.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] [First embodiment]

[0035] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0036] 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.

[0037] 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).

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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."

[0047] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[0048] Lender Processing

[0049] 1. Users (lenders) can easily register property information.

[0050] The lender uses the terminal to upload several property photos and drawings.

[0051] The device sends the uploaded data to the server.

[0052] The server automatically analyzes the data it receives using a generated artificial intelligence model to extract detailed information about the property.

[0053] The extracted information is immediately registered in the property database by the server, and a notification of registration completion is sent to the lender's terminal.

[0054] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[0055] Borrower Processing

[0056] 2. Users (renters) can easily search for the property they want.

[0057] The tenant enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[0058] The terminal transmits the received search conditions to the server.

[0059] Based on the conditions received by the server, the property database is searched using a generated artificial intelligence model to extract properties that meet the conditions.

[0060] The server sends the search results to the borrower's terminal, where the borrower can check the detailed information.

[0061] Example: When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts properties that most closely match those conditions and sends the results in list format.

[0062] Intermediary Processing

[0063] 3. Users (intermediaries) can streamline various administrative tasks.

[0064] The real estate agent uploads property photos taken during on-site inspections from the terminal.

[0065] The device sends the uploaded photos to the server.

[0066] The server analyzes the received photos using a generated artificial intelligence model and automatically generates an estimate of the cost of restoring the property to its original condition.

[0067] The server creates instructions for the construction company based on the generated estimate and sends them to the intermediary's terminal.

[0068] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and automatically creates and sends instructions to the appropriate contractor based on that estimate.

[0069] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they are looking for, and agents can efficiently carry out their administrative work. This will promote the effective use of vacant houses and contribute to solving social problems.

[0070] The processing flow will be explained below.

[0071] Lender Processing

[0072] Step 1:

[0073] The user (lender) uses a terminal to select and upload several property photos and drawings.

[0074] Step 2:

[0075] The terminal sends the uploaded property photos and drawings to the server.

[0076] Step 3:

[0077] The server stores the received data and runs the generative AI model.

[0078] Step 4:

[0079] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[0080] Step 5:

[0081] The server registers the extracted property details in a database.

[0082] Step 6:

[0083] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[0084] Borrower Processing

[0085] Step 1:

[0086] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[0087] Step 2:

[0088] The terminal transmits the entered search conditions to the server.

[0089] Step 3:

[0090] The server stores the received search conditions and launches the generative AI model.

[0091] Step 4:

[0092] The generative AI model searches a property database and extracts properties that match the criteria.

[0093] Step 5:

[0094] The server sends the extracted search results to the user's (borrower's) terminal.

[0095] Step 6:

[0096] The user (borrower) views the search results on their device and checks the detailed information.

[0097] Intermediary Processing

[0098] Step 1:

[0099] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[0100] Step 2:

[0101] The device sends the uploaded photos to the server.

[0102] Step 3:

[0103] The server stores the received photos and runs the generative AI model.

[0104] Step 4:

[0105] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[0106] Step 5:

[0107] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[0108] Step 6:

[0109] The server sends the generated instructions to the user's (intermediary's) terminal.

[0110] Example 1

[0111] 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."

[0112] Conventional property information registration, search, and management systems lacked functionality to meet the different needs of each user, resulting in low efficiency in information registration and search. As a result, landlords could not easily register property information, tenants could not quickly search for the property they wanted, and real estate agents often suffered from inefficient administrative work. In addition, data accuracy and search precision were low, making it difficult to effectively utilize vacant homes.

[0113] 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.

[0114] In this invention, the server includes a means for a lender to provide property information by uploading several property photos and drawings, a means for a terminal to transmit the uploaded property photos and drawings to the server, and a means for the server to automatically analyze the property photos and drawings using a generative AI model, extract property details, and register them in a database. This enables a system that allows lenders to easily register property information, borrowers to efficiently search for properties, and agents to perform administrative tasks quickly and accurately.

[0115] A "lender" is an individual or legal entity that owns or manages a property and wishes to rent the property to others.

[0116] A "borrower" is an individual or corporation who wishes to rent a property, and is a user who wants to search for properties and find one that meets their requirements.

[0117] A "broker" is an individual or corporation that acts as an intermediary between the lender and the borrower in property transactions, and is a specialist that handles administrative tasks such as property inspections and contract procedures.

[0118] "Terminal" means an electronic device used by a lender, borrower, or intermediary to input, send, and receive information. Examples include smartphones and personal computers.

[0119] A "server" is a computer system that provides services over a network and is a central device that analyzes, registers, searches, and manages property information.

[0120] A "generative AI model" is a model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing.

[0121] "Property information" refers to detailed data about a property, including photographs, drawings, room size, facilities, floor plan, and other information.

[0122] A "database" is an electronic recording medium in which property information is organized and stored, and is a system for efficiently querying, adding, and updating data.

[0123] "Search conditions" are items that indicate the characteristics and requirements of the property desired by the tenant, and examples include floor plan, location, age of the building, etc.

[0124] "Search results" are generated by the server by querying a property database based on search criteria and generating a list of properties that match the criteria.

[0125] "Restoration costs" are the costs required to return the property to its original condition, and are calculated based on information obtained by the real estate agent during an on-site inspection.

[0126] An "instruction sheet" is a document generated by the server that clearly states the details and costs of restoration to the original state and requests the contractor to carry out the work.

[0127] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[0128] Hardware and software used

[0129] Hardware:

[0130] Terminal: An electronic device used by a user to input, send, and receive information. Examples include smartphones and personal computers.

[0131] Server: A computer system that provides services over a network and is the central device that analyzes, registers, searches, and manages property information.

[0132] software:

[0133] Generative AI model: A model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing (e.g., OpenAI GPT-4).

[0134] Database: An electronic recording medium in which property information is organized and stored, and a system for efficiently querying, adding, and updating data (e.g., database software such as MySQL).

[0135] Lender Operation Flow

[0136] 1. User (lender) property information registration

[0137] The lender uploads property photos and drawings using a terminal, which then sends the uploaded data to the server, which then receives it.

[0138] 2. Data analysis and registration by the server

[0139] The server uses a generative AI model to automatically analyze the uploaded photos and drawings and extract detailed property information. This information is immediately registered in a database. The server then sends a notification to the lender that the property information has been registered.

[0140] Borrower Operation Flow

[0141] 1. User (borrower) enters property search criteria

[0142] The renter enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the terminal and sends them to the server.

[0143] 2. Conditional search by server and sending results

[0144] The server uses the generative AI model to search the property database based on the received search criteria and extracts properties that match the criteria. The search results are sent to the borrower's device, where they can view the results and check detailed information.

[0145] Intermediary operation flow

[0146] 1. User (agent) uploads property photos

[0147] The real estate agent uploads property photos taken for on-site inspections from the terminal, which then sends them to the server.

[0148] 2. Photo analysis and quotation generation by the server

[0149] The server analyzes the received photos using a generative AI model to calculate the cost of restoration to the original state, then automatically generates instructions for the contractor based on the calculated cost and sends them to the intermediary.

[0150] Examples of concrete examples and prompts

[0151] Examples of lenders include:

[0152] When a landlord uploads photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[0153] Example prompt sentence:

[0154] Upload photos and drawings of your living room, kitchen, bedroom and bathroom to extract property details and add them to our database.

[0155] Examples of borrowers:

[0156] When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts the properties that most closely match those conditions and sends the results in list format.

[0157] Example prompt sentence:

[0158] Search for properties that meet your criteria: 2LDK, 5-minute walk from the station, newly built.

[0159] Examples of intermediaries include:

[0160] When a real estate agent uploads photos from their on-site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and then automatically creates and sends instructions to the appropriate contractor based on that estimate.

[0161] Example prompt sentence:

[0162] Upload site inspection photos to generate restoration cost estimates and create instructions for contractors.

[0163] This system allows landlords to easily register property information, tenants to quickly search for the property they want, and agents to efficiently carry out their administrative work. As a result, it is expected that the effective use of vacant houses will be promoted, contributing to the solution of social issues.

[0164] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0165] Lender Processing

[0166] Step 1:

[0167] The user opens the property information registration screen

[0168] Input: Access to property information registration screen

[0169] Operation: The user operates the device to open the property information registration screen. The screen that appears contains an interface for uploading property photos and drawings.

[0170] Output: The property information registration screen will be displayed on the terminal.

[0171] Step 2:

[0172] Users select and upload property photos and drawings

[0173] Input: Selected property photos and drawings

[0174] How it works: A user uses their device to select property photos and drawings and clicks the upload button.

[0175] Output: The selected data is temporarily saved on the device.

[0176] Step 3:

[0177] The device sends the data to the server

[0178] Input: Uploaded property photos and drawing data

[0179] Operation: The device sends the selected property photos and drawing data to the server in a batch process. The progress of the transfer is displayed to the user in real time.

[0180] Output: Property photos and drawing data are sent to the server.

[0181] Step 4:

[0182] The server analyzes the data

[0183] Input: Property photos and drawing data submitted

[0184] How it works: The server launches the generative AI model and analyzes the data sent. The generative AI model extracts detailed property information (e.g., room size, facilities, and layout) from the image.

[0185] Output: Detailed property information extracted by analysis

[0186] Step 5:

[0187] The server registers the property information in the database

[0188] Input: Extracted property details

[0189] Operation: The server converts the generated property details into a standard format and records them in a database.

[0190] Output: Property details are registered in the database.

[0191] Step 6:

[0192] The server sends a notification to the user that registration is complete.

[0193] Input: Notification information for registration completion

[0194] Operation: The server creates a registration completion notification and sends it to the user's terminal.

[0195] Output: The device receives the notification and displays it to the user.

[0196] Borrower Processing

[0197] Step 1:

[0198] The user enters property search criteria

[0199] Input: Property search criteria (e.g. 2LDK, 5-minute walk from station, new construction)

[0200] Operation: The user operates the device, opens the property search screen, enters the conditions, and clicks the search button.

[0201] Output: The entered search criteria are temporarily saved on the device.

[0202] Step 2:

[0203] The device sends the search criteria to the server.

[0204] Input: Entered search criteria

[0205] Operation: The device sends search criteria to the server.

[0206] Output: The search criteria is sent to the server.

[0207] Step 3:

[0208] The server searches the property database based on the criteria

[0209] Input: Search criteria

[0210] How it works: The server uses the generated AI model to search the property database and extract properties that match the criteria.

[0211] Output: A list of properties that match the criteria

[0212] Step 4:

[0213] The server sends the search results to the user

[0214] Input: List of properties that match your criteria

[0215] How it works: The server formats the search results into a list and sends it to the user's device.

[0216] Output: The search result list is sent to the terminal and displayed to the user.

[0217] Intermediary Processing

[0218] Step 1:

[0219] Users upload field survey photos

[0220] Input: Photos taken during field survey

[0221] Action: The user operates the device, selects a property photo, and clicks the upload button.

[0222] Output: The selected photos are temporarily saved on your device.

[0223] Step 2:

[0224] The device sends the photo data to the server.

[0225] Input: Selected photo data

[0226] How it works: The device sends batches of photo data to the server. The progress of the transfer is displayed to the user in real time.

[0227] Output: The photo data is sent to the server.

[0228] Step 3:

[0229] The server analyzes the photo

[0230] Input: Submitted photo data

[0231] How it works: The server launches a generative AI model and analyzes the photo data. The generative AI model estimates the need for restoration and the cost.

[0232] Output: Estimated restoration costs

[0233] Step 4:

[0234] The server generates instructions based on the estimate.

[0235] Input: Estimated restoration costs

[0236] How it works: The server automatically generates detailed instructions for the contractor based on the estimate.

[0237] Output: Instructions are generated.

[0238] Step 5:

[0239] The server sends instructions to the user

[0240] Input: Generated instructions

[0241] How it works: The server sends instructions to the user's device, allowing for subsequent approval or modification.

[0242] Output: The terminal receives the instructions and displays them to the user.

[0243] (Application example 1)

[0244] 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."

[0245] Conventional property information registration and management systems have faced challenges such as the need for manual input and ensuring the accuracy of information. It is also difficult to efficiently register and search detailed information about vacant houses and brick-and-mortar stores, and the time and effort required for cost estimates based on on-site surveys and instructions to construction companies is particularly significant. This has hindered the effective utilization of vacant houses and brick-and-mortar stores, causing social problems.

[0246] 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.

[0247] In this invention, the server includes: a means for a lender to upload several property information photos and drawings to provide property information; a means for the server to automatically analyze the uploaded photos and drawings using a generative AI model and extract detailed property information; a means for the server to register the extracted detailed property information in a database; a means for a borrower to input property search conditions and send them to the server; a means for the server to search the database using a generative AI model based on the received search conditions and extract properties that match the conditions; a means for the server to send the search results to the borrower's terminal; a means for a real estate agent to upload photos taken for on-site inspection and send them to the server; and a means for the server to analyze the sent photos using a generative AI model and calculate restoration costs. The system includes a means for uploading store information and store search criteria to the server, a means for the server to automatically generate instructions to a construction company based on the calculated costs, a means for a store manager to provide store information by uploading store information photos and layouts, a means for a tenant to input store search criteria and send them to the server, a means for the server to search a database using a generative AI model based on the received search criteria and extract stores that match the criteria, a means for the server to send the store search results to the tenant's terminal, a means for a real estate agent to upload store photos taken for on-site inspections and send them to the server, a means for the server to analyze the sent photos using a generative AI model and calculate the cost of restoring the store to its original condition, and a means for the server to automatically generate instructions to a construction company based on the calculated costs. This enables efficient and accurate registration, search, and management of property and store information, as well as rapid estimation of restoration costs.

[0248] A "lender" is the person or entity that owns the property or store and provides the information.

[0249] "Property information" is data showing details of a property, such as photos and drawings of the property.

[0250] A "server" is a computer system that stores and manages data.

[0251] A "generative AI model" is an artificial intelligence model trained based on large amounts of data, and is a technology that analyzes and generates data.

[0252] "Property details" refers to information extracted using a generative AI model, including detailed attributes and features of the property.

[0253] A "database" is a collection of organized data, a place where property information and store information are stored.

[0254] A "lessee" is a person or entity wishing to use the property or business.

[0255] "Property search conditions" are information that specifies the characteristics and conditions of the property or store desired by the borrower.

[0256] An "intermediary" is a person or organization that acts as an intermediary between a lender and a borrower for the sale of a property or store.

[0257] A "site inspection" is an investigation carried out to check the actual condition of a property or store.

[0258] "Restoration costs" are the costs required to return a property or store to its original condition.

[0259] A "contractor" is a person or organization that carries out construction or repairs on a property or business.

[0260] "Store information" is data that shows details of the store, such as photos and layout of the physical store.

[0261] A "tenant" is a person or organization that rents a store or property for use.

[0262] This system was developed to support lenders, borrowers, real estate agents, and store managers in efficiently registering, searching, and managing property and store information, estimating restoration costs, and generating instructions for construction companies. A specific embodiment is shown below.

[0263] Lender and brick-and-mortar store manager operations

[0264] Lenders or store managers upload several property information photos and drawings, or store information photos and layouts, from their smartphones, PCs, or other devices. The uploaded data is sent to a server, which automatically analyzes the data using a generative AI model. From this analysis, detailed information about the property or store is extracted and registered in a property information database.

[0265] Borrower and Tenant Operations

[0266] Renters and tenants enter search criteria for the desired property or store on their device and send them to the server. The server uses a generative AI model to search the property information database based on the received search criteria and extracts properties or stores that match the criteria. The server then sends the search results to the renter or tenant's device, where they can check detailed information.

[0267] Intermediary manipulation

[0268] The real estate agent uploads photos of the property or store taken for on-site inspections from their device. The uploaded photos are sent to a server, which analyzes them using a generative AI model and calculates the cost of restoration to the original state. The server then automatically generates instructions for the contractor based on the calculated costs and sends the instructions to the real estate agent's device as needed.

[0269] Hardware and software used

[0270] The hardware used includes smartphones, PCs, and servers. The smartphones and PCs are used by landlords, borrowers, brokers, brick-and-mortar store managers, and tenants to upload data and enter search criteria. The servers are responsible for analyzing and storing the data, and automatically analyze the input data using generative AI models.

[0271] The software used is the openai library for implementing the generative AI model, and PIL (Python Imaging Library) for image processing.

[0272] Examples of concrete examples and prompts

[0273] Examples of lenders and brick-and-mortar managers

[0274] When renters submit photos of their living rooms, kitchens, bedrooms, and bathrooms, the server automatically analyzes them and registers the room sizes and facilities in the database. Similarly, physical store managers submit photos and layouts of their stores, and store details are registered in the database.

[0275] Example prompt: "This is a photo of the living area of ​​a store. Can you give me more information about this store?"

[0276] Examples of intermediaries

[0277] When the agent uploads photos from the on-site inspection, the server analyzes the photos, calculates the cost of restoring the property to its original condition, and automatically creates and sends instructions to the contractor.

[0278] Sample prompt: "These are photos of a store for a site inspection. Please estimate the cost of restoring it to its original condition."

[0279] This enables efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[0280] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0281] Step 1:

[0282] The lender or the manager of the brick-and-mortar store uploads several property information photos and drawings, or store information photos and layout, from a smartphone or PC. The entered photos and drawings are sent to the server via the data upload function, which provides the server with basic information about the property or store.

[0283] Step 2:

[0284] The server automatically analyzes the uploaded property information photos and drawings, or store information photos and layouts, using a generative AI model. The AI ​​model analyzes the images using an image processing library (e.g., PIL) and extracts detailed information such as room size, facilities, and layout information. The extracted information is converted into structured data. The input for this step is the uploaded image data, and the output is the extracted property and store details.

[0285] Step 3:

[0286] The server registers the extracted property and store details in a property information database. Using the database registration function, the structured data is efficiently stored in the database, making it easier to store the information and to search and view it later.

[0287] Step 4:

[0288] The borrower or tenant enters search criteria for the desired property or store on a terminal and sends them to the server. The entered search criteria are transmitted to the server via the database query function, and the information search is then ready.

[0289] Step 5:

[0290] The server uses the generative AI model to search the property information database based on the received search criteria. It uses the AI ​​model and database query function to extract properties and stores that match the search criteria. The input for this step is the search criteria, and the output is a list of properties and stores that match the criteria.

[0291] Step 6:

[0292] The server sends the search results to the borrower's or tenant's terminal. The server uses the search result sending function to provide detailed information on properties or stores that match the criteria to the user's terminal. This allows the user to check the selected search results.

[0293] Step 7:

[0294] The real estate agent uploads property or store photos taken for on-site inspections from their device and sends them to the server, which provides the data from the on-site inspection to the server for subsequent analysis.

[0295] Step 8:

[0296] The server analyzes the submitted on-site inspection photos using a generation AI model to calculate the cost of restoration to the original state. The AI ​​model uses an image processing library to determine the level of damage in the photos and the need for repairs, and generates the calculated cost as data.

[0297] Step 9:

[0298] The server automatically generates instructions for the contractor based on the calculated restoration costs. Using the instruction generation function, the server creates instructions including the necessary work areas and cost estimates and sends them to the contractor.

[0299] These processing steps enable efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[0300] 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.

[0301] This invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage vacant property information. This system provides functions that meet the needs of three parties: landlords, tenants, and agents, and further analyzes the user's emotional state to optimize the system's response.

[0302] Lender Processing

[0303] 1. Users (lenders) can easily register property information.

[0304] The lender uses the terminal to select and upload several property photos and drawings.

[0305] The terminal sends the uploaded property photos and drawings to the server.

[0306] The server stores the received data and runs the generative AI model.

[0307] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[0308] The server registers the extracted property details in a database.

[0309] The emotional engine analyzes the emotional state of the lender and adjusts the registration priority or content of the property information based on the emotional state.

[0310] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[0311] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[0312] Borrower Processing

[0313] 2. Users (renters) can easily search for the property they want.

[0314] Renters enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[0315] The terminal transmits the entered search conditions to the server.

[0316] The server stores the received search conditions and launches the generative AI model.

[0317] The generative AI model searches a property database and extracts properties that match the criteria.

[0318] The server sends the extracted search results to the user's (borrower's) terminal.

[0319] An emotional engine analyzes the borrower's emotional state and adjusts how search results are displayed or ordered.

[0320] The user (borrower) views the search results on their device and checks detailed information.

[0321] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[0322] Intermediary Processing

[0323] 3. Users (intermediaries) can streamline various administrative tasks.

[0324] The real estate agent uploads property photos taken for on-site inspections from the terminal.

[0325] The device sends the uploaded photos to the server.

[0326] The server stores the received photos and runs the generative AI model.

[0327] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[0328] An emotion engine analyzes the emotional state of the intermediary and adjusts the presentation or content of the calculated fees.

[0329] Based on the estimate generated by the server, instructions are automatically generated for the contractor.

[0330] The server sends the generated instructions to the user's (intermediary's) terminal.

[0331] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoration, and if the emotion engine determines that the real estate agent is under high stress, the results are displayed in a more concise and clear format.

[0332] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they want, and agents can efficiently carry out their administrative work. Furthermore, by taking into account the user's emotional state, it is possible to respond optimally to individual needs, improving the overall user experience. This will promote the effective use of vacant houses and contribute to solving social problems.

[0333] The processing flow will be explained below.

[0334] Lender Processing

[0335] Step 1:

[0336] The user (lender) uses the terminal to select and upload property photos and drawings.

[0337] Step 2:

[0338] The terminal sends the uploaded property photos and drawings to the server.

[0339] Step 3:

[0340] The server receives the transmitted data and activates the generative AI model.

[0341] Step 4:

[0342] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[0343] Step 5:

[0344] The server registers the extracted property details in a database.

[0345] Step 6:

[0346] The server runs an emotion engine to analyze the emotional state of the lender.

[0347] Step 7:

[0348] An emotion engine adjusts the listing priority or content of property information based on the emotional state of the lender.

[0349] Step 8:

[0350] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[0351] Borrower Processing

[0352] Step 1:

[0353] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[0354] Step 2:

[0355] The terminal transmits the entered search conditions to the server.

[0356] Step 3:

[0357] The server stores the received search conditions and launches the generative AI model.

[0358] Step 4:

[0359] The generative AI model searches a property database and extracts properties that match the criteria.

[0360] Step 5:

[0361] The server sends the extracted search results to the user's (borrower's) terminal.

[0362] Step 6:

[0363] The server activates an emotion engine to analyze the borrower's emotional state.

[0364] Step 7:

[0365] An emotional engine adjusts the display or order of search results based on the borrower's emotional state.

[0366] Step 8:

[0367] The user (borrower) views the search results on their device and checks the detailed information.

[0368] Intermediary Processing

[0369] Step 1:

[0370] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[0371] Step 2:

[0372] The device sends the uploaded photos to the server.

[0373] Step 3:

[0374] The server stores the received photos and runs the generative AI model.

[0375] Step 4:

[0376] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[0377] Step 5:

[0378] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[0379] Step 6:

[0380] The server sends the generated quote to the user's (intermediary's) terminal.

[0381] Step 7:

[0382] The server activates an emotion engine to analyze the emotional state of the agent.

[0383] Step 8:

[0384] An emotion engine adjusts the presentation or content of the calculation results based on the emotional state of the intermediary.

[0385] Step 9:

[0386] The server sends the generated instructions to the construction company's terminal.

[0387] This allows the emotion engine to be used to optimally respond to the user's emotional state, improving the overall user experience.

[0388] Example 2

[0389] 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."

[0390] The problem is that the registration, search, and management of vacant house property information is complicated, time-consuming, and labor-intensive. Furthermore, the system response is not optimized to take into account the user's emotional state, making it difficult to improve the user experience. It is necessary to solve these issues and promote the effective utilization of vacant houses.

[0391] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically analyzing property images and blueprints uploaded by a lender using a generative AI model to extract property detailed information, means for searching a property data storage device using the generative AI model based on received search conditions to extract properties that match the conditions, and emotion engine means for analyzing the user's emotional state and adjusting the registration priority or content based on the emotional state. This enables efficient registration, search, and management of property information and optimal responses according to the user's emotional state, thereby improving the overall user experience.

[0392] A "lender" is a person who owns real estate property or who acts on behalf of the owner and who intends to rent out the property.

[0393] A "borrower" is a person who wishes to rent a real estate property, searches for information about the property, and wishes to enter into a contract.

[0394] An "intermediary" is a person who acts as an intermediary between a lender and a borrower, introducing properties and facilitating the contract procedures.

[0395] "Property images" are photographs or drawings showing the exterior and interior of a real estate property, and are visual information for understanding the details of the property.

[0396] A "blueprint" is a drawing that shows the floor plan and layout of a real estate property, and specifically represents the structure and dimensions of the property.

[0397] A "generative AI model" is a model that uses artificial intelligence technology to analyze and predict data, and is trained using machine learning algorithms.

[0398] A "server" is a computer system that processes, stores, and analyzes data and provides services to other devices over a network.

[0399] A "data storage device" is a device for storing information physically or electronically, such as a database or file storage device.

[0400] An "emotion engine" is a software component that analyzes the user's emotional state from their voice or text and adjusts the system's behavior.

[0401] "Registration priority" is an index that indicates the priority of property information registration work, and is a criterion for the system to perform registration work efficiently.

[0402] "Property details" refers to information that indicates specific attributes such as the size, layout, and facilities of the property, and is data necessary to understand the characteristics of the property.

[0403] "Search conditions" are conditions that specify the attributes of the property desired by the borrower, and include specific requirements such as the type of property, size, and location.

[0404] "Restoration costs" are the costs necessary to return the property to its original condition after the tenant moves out, including repairs, cleaning, etc.

[0405] A "construction contractor" is a professional contractor that repairs, renovates, cleans, etc. real estate properties and carries out restoration work to their original condition.

[0406] An "instruction sheet" is a document that instructs a specific task and indicates the specific work content and costs to the contractor.

[0407] The present invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage property information for vacant homes. Specific embodiments of this system are described below.

[0408] The system is used by three parties: lenders, borrowers, and intermediaries, and provides functions tailored to the needs of each user. The system's main hardware includes servers, terminals, and data storage devices. The system's main software includes generative AI models, emotion engines, and user interfaces.

[0409] Lender Processing

[0410] Lenders register property information via their devices. They upload photos and blueprints of the property, which are then received by the server. Specific photos and blueprints are selected via a smartphone app or web app, and the server then clicks the upload button. The server then sends this data to the generative AI model, which automatically extracts detailed property information. During this process, the generative AI model uses image processing algorithms to identify detailed information such as the property's size, layout, and amenities.

[0411] For example, when a lender uploads photos of their living room, kitchen, bedroom, and bathroom, the server passes them to the generative AI model, and records the size and characteristics of each room in a data storage device. During this process, the emotion engine analyzes the lender's emotional state, and if it determines that the lender is tense, it will respond by quickly sending a registration completion notification.

[0412] Example prompt sentence:

[0413] "Analyze photos of the living room, kitchen, bedroom, and bathroom."

[0414] Borrower Processing

[0415] The borrower conducts a property search through their device. They enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) and click the search button. The device sends the search conditions to the server, which then activates the generative AI model and searches for information in the property data storage device. The search results are sent from the server to the borrower's device, where they can be viewed. The emotion engine adjusts the way the search results are displayed, and in some cases, highlights them.

[0416] For example, if a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria, generates a list, and sends it to the terminal. If the emotion engine determines that the borrower is increasingly interested, it highlights the search results and displays them.

[0417] Example prompt sentence:

[0418] "Search for a newly built property with a 2LDK, 5-minute walk from the station."

[0419] Intermediary Processing

[0420] Real estate agents can upload property images for on-site inspections to streamline their administrative work. When photos of inspected properties are uploaded from a device, the server receives them and performs image analysis using a generative AI model. As a result of the analysis, the cost of restoration to the original state is calculated, and instructions to the construction company are automatically generated based on that cost. The emotion engine analyzes the emotional state of the agent and adjusts the display of the results as necessary.

[0421] For example, if a real estate agent uploads photos of damage to a property, the server analyzes them and calculates the cost of repairs. If the emotion engine analyzes the agent's emotional state and determines that they are stressed, it displays the results in a concise and clear format.

[0422] Example prompt sentence:

[0423] Please estimate the cost of restoration from this photo.

[0424] These processes will enable landlords to easily register property information, tenants to quickly search for the property they desire, and real estate agents to efficiently perform their administrative tasks. It will also enable responses that take into account the user's emotional state, improving the overall user experience. This will promote the effective use of vacant homes and contribute to solving social problems.

[0425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0426] Lender property information registration processing

[0427] Step 1:

[0428] The user selects property photos and blueprints using the terminal and clicks the upload button. The input is the property photos and blueprints, and the output is that these files are sent from the terminal to the server.

[0429] Step 2:

[0430] The terminal sends the uploaded file to the server. Specifically, the terminal sends an HTTP POST request to the server, with the input being the selected property photo and blueprint, and the output being the file being saved on the server.

[0431] Step 3:

[0432] The server saves the received file in storage and launches the generative AI model. The input is the uploaded file, and the output is the invocation of the generative AI model's interface. Specifically, the server saves the file in cloud storage (e.g., AWS S3) and triggers the execution of the generative AI model (e.g., TensorFlow).

[0433] Step 4:

[0434] The generative AI model analyzes property photos and blueprints to automatically extract property details such as size, layout, and equipment status. The input is the saved property photos and blueprints, and the output is the extracted property details. Specifically, the generative AI model identifies information and extracts data through image processing algorithms.

[0435] Step 5:

[0436] The server registers the extracted property details in a database. The input is the property details, and the output is to register them in a database. Specifically, the server executes an SQL query to insert the information into a database (e.g. MySQL).

[0437] Step 6:

[0438] The emotion engine analyzes the emotional state of the lender and adjusts the registration priority or content based on the emotional state. The input is the lender's emotional information, and the output is the adjusted registration priority or content. Specifically, it uses NLP technology (e.g., BERT) to analyze the user's emotional state.

[0439] Step 7:

[0440] The server sends a notification to the user's device that the property information has been registered. The input is the registration completion notification, and the output is the notification sent to the user's device. Specifically, the server sends the notification using a communication API (e.g., Firebase Cloud Messaging).

[0441] Borrower property search processing

[0442] Step 1:

[0443] The user inputs the desired property search criteria from the terminal and clicks the search button. The input is the property search criteria, and the output is the transmission of these criteria to the server.

[0444] Step 2:

[0445] The terminal sends the entered search criteria to the server. Specifically, the terminal sends an HTTP GET or POST request. The input is the search criteria, and the output is the server receiving the criteria.

[0446] Step 3:

[0447] The server stores the received search conditions and launches the generative AI model. The input is the search conditions, and the output is the invocation of the interface of the generative AI model. Specifically, the server calls the API to execute the AI ​​model based on the saved conditions.

[0448] Step 4:

[0449] The generative AI model searches a property database and extracts properties that match the criteria. The input is the search criteria and the property database, and the output is a list of properties that match the criteria. Specifically, the AI ​​model generates a database query and searches the database (e.g., PostgreSQL).

[0450] Step 5:

[0451] The server sends the extracted search results to the user's device. The input is the search results, and the output is the results sent to the user's device. Specifically, the server formats the results in JSON format and returns them as an HTTP response.

[0452] Step 6:

[0453] The emotion engine analyzes the borrower's emotional state and adjusts the display method or order of search results. The input is the borrower's emotional information, and the output is the adjusted search result display. Specifically, the emotion engine analyzes the user's click speed and mouse movement.

[0454] Step 7:

[0455] The user views the search results on the device and checks the detailed information. The input is the search results, and the output is the display of detailed information. Specifically, the user clicks on a property from the list of search results to move to the details page.

[0456] Streamlining of administrative work for intermediaries

[0457] Step 1:

[0458] Users upload property images taken for on-site inspections from their terminals. The input is inspection photos, and the output is that these photos are sent to the server.

[0459] Step 2:

[0460] The device sends the uploaded photo to the server. Specifically, the device sends an HTTP POST request, where the input is the uploaded photo and the output is the photo to be saved on the server.

[0461] Step 3:

[0462] The server saves the received photos in storage and launches the generative AI model. The input is the saved photo, and the output is the invocation of the interface of the generative AI model. Specifically, the server saves the photo in cloud storage (e.g., Google Cloud Storage) and triggers the execution of the generative AI model.

[0463] Step 4:

[0464] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs. The input is the stored photos, and the output is the cost estimate. Specifically, the AI ​​model uses an image processing algorithm to identify damaged areas and generate an estimate.

[0465] Step 5:

[0466] The emotion engine analyzes the broker's emotional state and adjusts the presentation method or content of the calculated cost. The input is the broker's emotional information, and the output is the adjusted quote display. Specifically, the emotion engine performs text and voice analysis to adjust the screen layout and messages.

[0467] Step 6:

[0468] The server automatically generates instructions for the contractor based on the generated estimate. The input is the estimate result, and the output is the automatically generated instructions. Specifically, the program inserts the estimate data into a template and generates the instructions.

[0469] Step 7:

[0470] The server sends the generated instructions to the user's device. The input is the automatically generated instructions, and the output is the instructions sent to the user's device. Specifically, the server generates the instructions as a PDF file and sends an email or a download link.

[0471] This allows the entire system to operate efficiently and improves the user experience.

[0472] (Application example 2)

[0473] 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."

[0474] Currently, systems for efficiently registering, searching, and managing vacant property information struggle to meet the needs of lenders, borrowers, and agents. Furthermore, they provide uniform responses and operations without considering the user's emotional state, resulting in an unoptimized user experience. Furthermore, in-store property information management lacks an intuitive and efficient interface, making registering and searching property information cumbersome.

[0475] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0476] In this invention, the server includes: a means for a lender to upload several property photos and drawings to provide property information; a means for automatically analyzing the uploaded property photos and drawings using a generative artificial intelligence model to extract property details; and a means for registering the extracted property details in a database. This enables efficient registration of property information. Additionally, the server includes: a means for a borrower to input property search criteria and transmit them to the server; a means for searching the property database using a generative artificial intelligence model based on the received search criteria to extract properties that match the criteria; and a means for transmitting the search results to the borrower's terminal. This allows borrowers to quickly find their desired property. Furthermore, the server includes: a means for a real estate agent to upload property photos taken for on-site inspections, a means for analyzing the transmitted photos using a generative artificial intelligence model to calculate restoration costs, a means for automatically generating instructions for a contractor based on the calculated costs, a means for detecting a user's emotional state using an emotional state analysis engine to optimize system response, and a means for providing an interface using a smart device when registering and searching for property information at a physical store. This will streamline the intermediary's administrative work and also enable optimal responses that take into account the user's emotional state, improving the overall user experience.

[0477] A "lender" is a person or entity that owns the property and intends to rent it out.

[0478] "Lessee" means an individual or entity that intends to rent the property.

[0479] An "intermediary" is an individual or organization that acts as an intermediary between lenders and borrowers to facilitate transactions.

[0480] A "server" is a computer system for processing and managing data over a network.

[0481] A "generative AI model" is an artificial intelligence algorithm that has the ability to generate information from given data.

[0482] An "emotional state analysis engine" is an algorithm or device for analyzing a user's emotions and detecting their state.

[0483] A "smartphone" is a mobile device that has mobile communication capabilities and can run multifunctional applications.

[0484] A "head-mounted display" is a device worn on the head that displays information within the field of vision.

[0485] "Property photos" are images taken of the interior and exterior of a property.

[0486] A "drawing" is a blueprint that illustrates the layout and structure of a property.

[0487] "Property detailed information" is information that includes specific characteristics of the property, such as the size, layout, and facilities.

[0488] A "property database" is a database for systematically managing detailed information about properties.

[0489] The "registration completion notice" is a notice to inform the user that the property information has been successfully registered.

[0490] "Search criteria" refers to the conditions of the property desired by the borrower (e.g., number of rooms, location, age of building, etc.).

[0491] An "instruction document" is a document that instructs a specific task or procedure.

[0492] A "site inspection" is an investigation carried out by actually visiting a property to check its condition.

[0493] "Restoration costs" are the costs required to return the property to its original condition.

[0494] This invention provides a system that efficiently registers, searches, and manages property information by combining a generative AI model and an emotional state analysis engine. The following hardware and software are used to implement the invention.

[0495] Hardware used

[0496] server

[0497] Smartphone (e.g. iPhone, Android)

[0498] Head-mounted displays (e.g., Oculus Quest 2)

[0499] Software used

[0500] Generative AI model: OpenAI GPT-4

[0501] Emotional state analysis engine: Affectiva SDK

[0502] Database: Firebase, MySQL

[0503] Image analysis: Google Cloud Vision API

[0504] Specific Embodiments of the System

[0505] Lender manipulation

[0506] 1. The user (lender) uses their smartphone to take several photos and drawings of the property and upload them through the application.

[0507] 2. The terminal sends the uploaded property photos and drawings to the server.

[0508] 3. The server stores the received data and activates the generative AI model to automatically extract detailed property information (room size, layout, equipment status, etc.).

[0509] 4. The server registers the extracted property details in a database and analyzes the lender's emotional state using an emotional state analysis engine.

[0510] 5. Adjust the priority or content of property listings based on emotional state and notify lenders that property listings have been completed.

[0511] Example: When a lender sends photos and drawings of the living room, kitchen, bedroom, and bathroom via smartphone, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[0512] Borrower operations

[0513] 1. The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the application via a smartphone or head-mounted display.

[0514] 2. The device sends the search criteria to the server.

[0515] 3. Based on the search criteria received by the server, the generative AI model is activated to search the property database and extract properties that match the criteria.

[0516] 4. The server sends the extracted search results to the borrower's device, and the emotional state analysis engine analyzes the borrower's emotional state.

[0517] 5. Adjust the way search results are displayed or ordered based on emotional state, making them more intuitive for users.

[0518] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[0519] Intermediary manipulation

[0520] 1. The real estate agent uploads property photos taken for on-site inspections using their smartphone.

[0521] 2. The device sends the uploaded photos to the server.

[0522] 3. The server stores the received photos, launches a generative AI model to analyze the images, and automatically calculates the cost of restoration to the original state.

[0523] 4. The server automatically generates instructions for the construction company based on the calculated costs and analyzes the agent's emotional state using an emotional state analysis engine.

[0524] 5. Adjust the presentation of the calculation results based on the emotional state, generate instructions, and send them to the intermediary's terminal.

[0525] Example: When a broker uploads photos from a site inspection, the server analyzes the photos and calculates the cost of restoration. If the emotion engine determines that the broker is stressed, the results are displayed in a more concise and clear format.

[0526] Prompt Sentence Examples

[0527] "Please analyze photos and drawings of the property, automatically extract the room size, layout, and equipment status, and present detailed information. Also, please analyze the user's emotional state and provide an appropriate interface."

[0528] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0529] Step 1:

[0530] Lenders upload property photos and drawings

[0531] The user (lender) takes several photos and drawings of the property using their smartphone and uploads them through the application. The input data are the property photos and drawings, and the output data is sent to the server.

[0532] Step 2:

[0533] Submit property photos and drawings

[0534] The terminal sends the uploaded property photos and drawings to the server. The input data are the uploaded photos and drawings, and the purpose of the operation is to send them to the server.

[0535] Step 3:

[0536] The server receives and stores the data

[0537] The server stores the received property photos and drawings. The input is the photos and drawings sent from the terminal, and the output is that they are stored in the server.

[0538] Step 4:

[0539] Launch the generative AI model to extract property details

[0540] The server launches the generative AI model and analyzes the stored property photos and drawings. The input data are the photos and drawings stored on the server, and the property's size, layout, and equipment status are automatically extracted through data processing and calculation. The output is the extracted property details.

[0541] Step 5:

[0542] Register property details in the database

[0543] The server registers the extracted property details in a database. The input data is the property details from the generative AI model, and the output is the property information registered in the database.

[0544] Step 6:

[0545] Analyzing the emotional state of lenders with an emotion engine

[0546] The server uses an emotional state analysis engine to analyze the emotional state of the lender. The input is data indicating the emotional state of the lender, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[0547] Step 7:

[0548] Adjustment of property information registration priority or content

[0549] The server adjusts the registration priority or content of the property information based on the analyzed emotional state. The input is the analyzed emotional state and property detail information, and the adjusted property information is the output.

[0550] Step 8:

[0551] Send a notification that property information has been registered

[0552] The server notifies the lender that the property registration is complete. The input is the adjusted property information, and the output is a notification sent to the lender's terminal.

[0553] Step 9:

[0554] The borrower enters property search criteria

[0555] The user (renter) inputs the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) into the application via a smartphone or head-mounted display. The input data represents the renter's desired conditions, and the device then sends this to the server.

[0556] Step 10:

[0557] Send search criteria to the server

[0558] The terminal transmits the search criteria entered by the borrower to the server. The input data is the borrower's search criteria, and the data transmitted to the server is the output.

[0559] Step 11:

[0560] Generate property database and search with AI model

[0561] The server launches a generative AI model based on the received search criteria and searches the property database. The input data are the search criteria and the property database, and the output is a list of properties that match the criteria.

[0562] Step 12:

[0563] Send search results to the borrower's device

[0564] The server sends the search results to the borrower's terminal. The input data is a list of properties that match the conditions, and the output is the search results sent to the borrower's terminal.

[0565] Step 13:

[0566] Analyze the borrower's emotional state with an emotional state analysis engine

[0567] The server uses an emotional state analysis engine to analyze the emotional state of the borrower. The input data is data indicating the emotional state of the borrower, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[0568] Step 14:

[0569] Adjust how search results are displayed or ordered

[0570] The server adjusts the display method or order of the search results based on the analyzed emotional state, with the analyzed emotional state and the search results being the input and the adjusted display results being the output.

[0571] Step 15:

[0572] Agents upload property photos

[0573] The real estate agent uploads property photos taken for on-site inspections using a smartphone. The input data is the inspection photos, and the device sends them to the server.

[0574] Step 16:

[0575] Submit property photos

[0576] The terminal sends the uploaded property photos to the server. The input data is the uploaded survey photos, and the transmission to the server is the output.

[0577] Step 17:

[0578] Retention and analysis of submitted photos

[0579] The server launches the generative AI model, stores and analyzes the property photos sent to it. The input data are the uploaded survey photos, and the restoration costs are automatically calculated from the photos through data processing and calculation. The output is the calculated restoration costs.

[0580] Step 18:

[0581] Automatically generate instructions based on calculations of restoration costs

[0582] The server automatically generates instructions for the contractor based on the calculated restoration costs. The input data is the calculated restoration costs, and the output is the automatically generated instructions.

[0583] Step 19:

[0584] Analyzing the emotional state of intermediaries with an emotion engine

[0585] The server uses an emotional state analysis engine to analyze the emotional state of the intermediary. The input data is data indicating the emotional state of the intermediary, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[0586] Step 20:

[0587] Adjust the way the calculation results are presented and send instructions

[0588] The server adjusts the presentation method of the calculation result based on the analyzed emotional state and sends instructions to the intermediary terminal. The input is the analyzed emotional state and the generated instructions, and the adjusted instructions are sent to the intermediary terminal.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] [Second embodiment]

[0593] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] 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.

[0604] 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."

[0605] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[0606] Lender Processing

[0607] 1. Users (lenders) can easily register property information.

[0608] The lender uses the terminal to upload several property photos and drawings.

[0609] The device sends the uploaded data to the server.

[0610] The server automatically analyzes the data it receives using a generated artificial intelligence model to extract detailed information about the property.

[0611] The extracted information is immediately registered in the property database by the server, and a notification of registration completion is sent to the lender's terminal.

[0612] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[0613] Borrower Processing

[0614] 2. Users (renters) can easily search for the property they want.

[0615] The tenant enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[0616] The terminal transmits the received search conditions to the server.

[0617] Based on the conditions received by the server, the property database is searched using a generated artificial intelligence model to extract properties that meet the conditions.

[0618] The server sends the search results to the borrower's terminal, where the borrower can check the detailed information.

[0619] Example: When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts properties that most closely match those conditions and sends the results in list format.

[0620] Intermediary Processing

[0621] 3. Users (intermediaries) can streamline various administrative tasks.

[0622] The real estate agent uploads property photos taken during on-site inspections from the terminal.

[0623] The device sends the uploaded photos to the server.

[0624] The server analyzes the received photos using a generated artificial intelligence model and automatically generates an estimate of the cost of restoring the property to its original condition.

[0625] The server creates instructions for the construction company based on the generated estimate and sends them to the intermediary's terminal.

[0626] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and automatically creates and sends instructions to the appropriate contractor based on that estimate.

[0627] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they are looking for, and agents can efficiently carry out their administrative work. This will promote the effective use of vacant houses and contribute to solving social problems.

[0628] The processing flow will be explained below.

[0629] Lender Processing

[0630] Step 1:

[0631] The user (lender) uses a terminal to select and upload several property photos and drawings.

[0632] Step 2:

[0633] The terminal sends the uploaded property photos and drawings to the server.

[0634] Step 3:

[0635] The server stores the received data and runs the generative AI model.

[0636] Step 4:

[0637] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[0638] Step 5:

[0639] The server registers the extracted property details in a database.

[0640] Step 6:

[0641] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[0642] Borrower Processing

[0643] Step 1:

[0644] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[0645] Step 2:

[0646] The terminal transmits the entered search conditions to the server.

[0647] Step 3:

[0648] The server stores the received search conditions and launches the generative AI model.

[0649] Step 4:

[0650] The generative AI model searches a property database and extracts properties that match the criteria.

[0651] Step 5:

[0652] The server sends the extracted search results to the user's (borrower's) terminal.

[0653] Step 6:

[0654] The user (borrower) views the search results on their device and checks the detailed information.

[0655] Intermediary Processing

[0656] Step 1:

[0657] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[0658] Step 2:

[0659] The device sends the uploaded photos to the server.

[0660] Step 3:

[0661] The server stores the received photos and runs the generative AI model.

[0662] Step 4:

[0663] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[0664] Step 5:

[0665] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[0666] Step 6:

[0667] The server sends the generated instructions to the user's (intermediary's) terminal.

[0668] Example 1

[0669] 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."

[0670] Conventional property information registration, search, and management systems lacked functionality to meet the different needs of each user, resulting in low efficiency in information registration and search. As a result, landlords could not easily register property information, tenants could not quickly search for the property they wanted, and real estate agents often suffered from inefficient administrative work. In addition, data accuracy and search precision were low, making it difficult to effectively utilize vacant homes.

[0671] 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.

[0672] In this invention, the server includes a means for a lender to provide property information by uploading several property photos and drawings, a means for a terminal to transmit the uploaded property photos and drawings to the server, and a means for the server to automatically analyze the property photos and drawings using a generative AI model, extract property details, and register them in a database. This enables a system that allows lenders to easily register property information, borrowers to efficiently search for properties, and agents to perform administrative tasks quickly and accurately.

[0673] A "lender" is an individual or legal entity that owns or manages a property and wishes to rent the property to others.

[0674] A "borrower" is an individual or corporation who wishes to rent a property, and is a user who wants to search for properties and find one that meets their requirements.

[0675] A "broker" is an individual or corporation that acts as an intermediary between the lender and the borrower in property transactions, and is a specialist that handles administrative tasks such as property inspections and contract procedures.

[0676] "Terminal" means an electronic device used by a lender, borrower, or intermediary to input, send, and receive information. Examples include smartphones and personal computers.

[0677] A "server" is a computer system that provides services over a network and is a central device that analyzes, registers, searches, and manages property information.

[0678] A "generative AI model" is a model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing.

[0679] "Property information" refers to detailed data about a property, including photographs, drawings, room size, facilities, floor plan, and other information.

[0680] A "database" is an electronic recording medium in which property information is organized and stored, and is a system for efficiently querying, adding, and updating data.

[0681] "Search conditions" are items that indicate the characteristics and requirements of the property desired by the tenant, and examples include floor plan, location, age of the building, etc.

[0682] "Search results" are generated by the server by querying a property database based on search criteria and generating a list of properties that match the criteria.

[0683] "Restoration costs" are the costs required to return the property to its original condition, and are calculated based on information obtained by the real estate agent during an on-site inspection.

[0684] An "instruction sheet" is a document generated by the server that clearly states the details and costs of restoration to the original state and requests the contractor to carry out the work.

[0685] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[0686] Hardware and software used

[0687] Hardware:

[0688] Terminal: An electronic device used by a user to input, send, and receive information. Examples include smartphones and personal computers.

[0689] Server: A computer system that provides services over a network and is the central device that analyzes, registers, searches, and manages property information.

[0690] software:

[0691] Generative AI model: A model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing (e.g., OpenAI GPT-4).

[0692] Database: An electronic recording medium in which property information is organized and stored, and a system for efficiently querying, adding, and updating data (e.g., database software such as MySQL).

[0693] Lender Operation Flow

[0694] 1. User (lender) property information registration

[0695] The lender uploads property photos and drawings using a terminal, which then sends the uploaded data to the server, which then receives it.

[0696] 2. Data analysis and registration by the server

[0697] The server uses a generative AI model to automatically analyze the uploaded photos and drawings and extract detailed property information. This information is immediately registered in a database. The server then sends a notification to the lender that the property information has been registered.

[0698] Borrower Operation Flow

[0699] 1. User (borrower) enters property search criteria

[0700] The renter enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the terminal and sends them to the server.

[0701] 2. Conditional search by server and sending results

[0702] The server uses the generative AI model to search the property database based on the received search criteria and extracts properties that match the criteria. The search results are sent to the borrower's device, where they can view the results and check detailed information.

[0703] Intermediary operation flow

[0704] 1. User (agent) uploads property photos

[0705] The real estate agent uploads property photos taken for on-site inspections from the terminal, which then sends them to the server.

[0706] 2. Photo analysis and quotation generation by the server

[0707] The server analyzes the received photos using a generative AI model to calculate the cost of restoration to the original state, then automatically generates instructions for the contractor based on the calculated cost and sends them to the intermediary.

[0708] Examples of concrete examples and prompts

[0709] Examples of lenders include:

[0710] When a landlord uploads photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[0711] Example prompt sentence:

[0712] Upload photos and drawings of your living room, kitchen, bedroom and bathroom to extract property details and add them to our database.

[0713] Examples of borrowers:

[0714] When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts the properties that most closely match those conditions and sends the results in list format.

[0715] Example prompt sentence:

[0716] Search for properties that meet your criteria: 2LDK, 5-minute walk from the station, newly built.

[0717] Examples of intermediaries include:

[0718] When a real estate agent uploads photos from their on-site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and then automatically creates and sends instructions to the appropriate contractor based on that estimate.

[0719] Example prompt sentence:

[0720] Upload site inspection photos to generate restoration cost estimates and create instructions for contractors.

[0721] This system allows landlords to easily register property information, tenants to quickly search for the property they want, and agents to efficiently carry out their administrative work. As a result, it is expected that the effective use of vacant houses will be promoted, contributing to the solution of social issues.

[0722] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0723] Lender Processing

[0724] Step 1:

[0725] The user opens the property information registration screen

[0726] Input: Access to property information registration screen

[0727] Operation: The user operates the device to open the property information registration screen. The screen that appears contains an interface for uploading property photos and drawings.

[0728] Output: The property information registration screen will be displayed on the terminal.

[0729] Step 2:

[0730] Users select and upload property photos and drawings

[0731] Input: Selected property photos and drawings

[0732] How it works: A user uses their device to select property photos and drawings and clicks the upload button.

[0733] Output: The selected data is temporarily saved on the device.

[0734] Step 3:

[0735] The device sends the data to the server

[0736] Input: Uploaded property photos and drawing data

[0737] Operation: The device sends the selected property photos and drawing data to the server in a batch process. The progress of the transfer is displayed to the user in real time.

[0738] Output: Property photos and drawing data are sent to the server.

[0739] Step 4:

[0740] The server analyzes the data

[0741] Input: Property photos and drawing data submitted

[0742] How it works: The server launches the generative AI model and analyzes the data sent. The generative AI model extracts detailed property information (e.g., room size, facilities, and layout) from the image.

[0743] Output: Detailed property information extracted by analysis

[0744] Step 5:

[0745] The server registers the property information in the database

[0746] Input: Extracted property details

[0747] Operation: The server converts the generated property details into a standard format and records them in a database.

[0748] Output: Property details are registered in the database.

[0749] Step 6:

[0750] The server sends a notification to the user that registration is complete.

[0751] Input: Notification information for registration completion

[0752] Operation: The server creates a registration completion notification and sends it to the user's terminal.

[0753] Output: The device receives the notification and displays it to the user.

[0754] Borrower Processing

[0755] Step 1:

[0756] The user enters property search criteria

[0757] Input: Property search criteria (e.g. 2LDK, 5-minute walk from station, new construction)

[0758] Operation: The user operates the device, opens the property search screen, enters the conditions, and clicks the search button.

[0759] Output: The entered search criteria are temporarily saved on the device.

[0760] Step 2:

[0761] The device sends the search criteria to the server.

[0762] Input: Entered search criteria

[0763] Operation: The device sends search criteria to the server.

[0764] Output: The search criteria is sent to the server.

[0765] Step 3:

[0766] The server searches the property database based on the criteria

[0767] Input: Search criteria

[0768] How it works: The server uses the generated AI model to search the property database and extract properties that match the criteria.

[0769] Output: A list of properties that match the criteria

[0770] Step 4:

[0771] The server sends the search results to the user

[0772] Input: List of properties that match your criteria

[0773] How it works: The server formats the search results into a list and sends it to the user's device.

[0774] Output: The search result list is sent to the terminal and displayed to the user.

[0775] Intermediary Processing

[0776] Step 1:

[0777] Users upload field survey photos

[0778] Input: Photos taken during field survey

[0779] Action: The user operates the device, selects a property photo, and clicks the upload button.

[0780] Output: The selected photos are temporarily saved on your device.

[0781] Step 2:

[0782] The device sends the photo data to the server.

[0783] Input: Selected photo data

[0784] How it works: The device sends batches of photo data to the server. The progress of the transfer is displayed to the user in real time.

[0785] Output: The photo data is sent to the server.

[0786] Step 3:

[0787] The server analyzes the photo

[0788] Input: Submitted photo data

[0789] How it works: The server launches a generative AI model and analyzes the photo data. The generative AI model estimates the need for restoration and the cost.

[0790] Output: Estimated restoration costs

[0791] Step 4:

[0792] The server generates instructions based on the estimate.

[0793] Input: Estimated restoration costs

[0794] How it works: The server automatically generates detailed instructions for the contractor based on the estimate.

[0795] Output: Instructions are generated.

[0796] Step 5:

[0797] The server sends instructions to the user

[0798] Input: Generated instructions

[0799] How it works: The server sends instructions to the user's device, allowing for subsequent approval or modification.

[0800] Output: The terminal receives the instructions and displays them to the user.

[0801] (Application example 1)

[0802] 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."

[0803] Conventional property information registration and management systems have faced challenges such as the need for manual input and ensuring the accuracy of information. It is also difficult to efficiently register and search detailed information about vacant houses and brick-and-mortar stores, and the time and effort required for cost estimates based on on-site surveys and instructions to construction companies is particularly significant. This has hindered the effective utilization of vacant houses and brick-and-mortar stores, causing social problems.

[0804] 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.

[0805] In this invention, the server includes: a means for a lender to upload several property information photos and drawings to provide property information; a means for the server to automatically analyze the uploaded photos and drawings using a generative AI model and extract detailed property information; a means for the server to register the extracted detailed property information in a database; a means for a borrower to input property search conditions and send them to the server; a means for the server to search the database using a generative AI model based on the received search conditions and extract properties that match the conditions; a means for the server to send the search results to the borrower's terminal; a means for a real estate agent to upload photos taken for on-site inspection and send them to the server; and a means for the server to analyze the sent photos using a generative AI model and calculate restoration costs. The system includes a means for uploading store information and store search criteria to the server, a means for the server to automatically generate instructions to a construction company based on the calculated costs, a means for a store manager to provide store information by uploading store information photos and layouts, a means for a tenant to input store search criteria and send them to the server, a means for the server to search a database using a generative AI model based on the received search criteria and extract stores that match the criteria, a means for the server to send the store search results to the tenant's terminal, a means for a real estate agent to upload store photos taken for on-site inspections and send them to the server, a means for the server to analyze the sent photos using a generative AI model and calculate the cost of restoring the store to its original condition, and a means for the server to automatically generate instructions to a construction company based on the calculated costs. This enables efficient and accurate registration, search, and management of property and store information, as well as rapid estimation of restoration costs.

[0806] A "lender" is the person or entity that owns the property or store and provides the information.

[0807] "Property information" is data showing details of a property, such as photos and drawings of the property.

[0808] A "server" is a computer system that stores and manages data.

[0809] A "generative AI model" is an artificial intelligence model trained based on large amounts of data, and is a technology that analyzes and generates data.

[0810] "Property details" refers to information extracted using a generative AI model, including detailed attributes and features of the property.

[0811] A "database" is a collection of organized data, a place where property information and store information are stored.

[0812] A "lessee" is a person or entity wishing to use the property or business.

[0813] "Property search conditions" are information that specifies the characteristics and conditions of the property or store desired by the borrower.

[0814] An "intermediary" is a person or organization that acts as an intermediary between a lender and a borrower for the sale of a property or store.

[0815] A "site inspection" is an investigation carried out to check the actual condition of a property or store.

[0816] "Restoration costs" are the costs required to return a property or store to its original condition.

[0817] A "contractor" is a person or organization that carries out construction or repairs on a property or business.

[0818] "Store information" is data that shows details of the store, such as photos and layout of the physical store.

[0819] A "tenant" is a person or organization that rents a store or property for use.

[0820] This system was developed to support lenders, borrowers, real estate agents, and store managers in efficiently registering, searching, and managing property and store information, estimating restoration costs, and generating instructions for construction companies. A specific embodiment is shown below.

[0821] Lender and brick-and-mortar store manager operations

[0822] Lenders or store managers upload several property information photos and drawings, or store information photos and layouts, from their smartphones, PCs, or other devices. The uploaded data is sent to a server, which automatically analyzes the data using a generative AI model. From this analysis, detailed information about the property or store is extracted and registered in a property information database.

[0823] Borrower and Tenant Operations

[0824] Renters and tenants enter search criteria for the desired property or store on their device and send them to the server. The server uses a generative AI model to search the property information database based on the received search criteria and extracts properties or stores that match the criteria. The server then sends the search results to the renter or tenant's device, where they can check detailed information.

[0825] Intermediary manipulation

[0826] The real estate agent uploads photos of the property or store taken for on-site inspections from their device. The uploaded photos are sent to a server, which analyzes them using a generative AI model and calculates the cost of restoration to the original state. The server then automatically generates instructions for the contractor based on the calculated costs and sends the instructions to the real estate agent's device as needed.

[0827] Hardware and software used

[0828] The hardware used includes smartphones, PCs, and servers. The smartphones and PCs are used by landlords, borrowers, brokers, brick-and-mortar store managers, and tenants to upload data and enter search criteria. The servers are responsible for analyzing and storing the data, and automatically analyze the input data using generative AI models.

[0829] The software used is the openai library for implementing the generative AI model, and PIL (Python Imaging Library) for image processing.

[0830] Examples of concrete examples and prompts

[0831] Examples of lenders and brick-and-mortar managers

[0832] When renters submit photos of their living rooms, kitchens, bedrooms, and bathrooms, the server automatically analyzes them and registers the room sizes and facilities in the database. Similarly, physical store managers submit photos and layouts of their stores, and store details are registered in the database.

[0833] Example prompt: "This is a photo of the living area of ​​a store. Can you give me more information about this store?"

[0834] Examples of intermediaries

[0835] When the agent uploads photos from the on-site inspection, the server analyzes the photos, calculates the cost of restoring the property to its original condition, and automatically creates and sends instructions to the contractor.

[0836] Sample prompt: "These are photos of a store for a site inspection. Please estimate the cost of restoring it to its original condition."

[0837] This enables efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[0838] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0839] Step 1:

[0840] The lender or the manager of the brick-and-mortar store uploads several property information photos and drawings, or store information photos and layout, from a smartphone or PC. The entered photos and drawings are sent to the server via the data upload function, which provides the server with basic information about the property or store.

[0841] Step 2:

[0842] The server automatically analyzes the uploaded property information photos and drawings, or store information photos and layouts, using a generative AI model. The AI ​​model analyzes the images using an image processing library (e.g., PIL) and extracts detailed information such as room size, facilities, and layout information. The extracted information is converted into structured data. The input for this step is the uploaded image data, and the output is the extracted property and store details.

[0843] Step 3:

[0844] The server registers the extracted property and store details in a property information database. Using the database registration function, the structured data is efficiently stored in the database, making it easier to store the information and to search and view it later.

[0845] Step 4:

[0846] The borrower or tenant enters search criteria for the desired property or store on a terminal and sends them to the server. The entered search criteria are transmitted to the server via the database query function, and the information search is then ready.

[0847] Step 5:

[0848] The server uses the generative AI model to search the property information database based on the received search criteria. It uses the AI ​​model and database query function to extract properties and stores that match the search criteria. The input for this step is the search criteria, and the output is a list of properties and stores that match the criteria.

[0849] Step 6:

[0850] The server sends the search results to the borrower's or tenant's terminal. The server uses the search result sending function to provide detailed information on properties or stores that match the criteria to the user's terminal. This allows the user to check the selected search results.

[0851] Step 7:

[0852] The real estate agent uploads property or store photos taken for on-site inspections from their device and sends them to the server, which provides the data from the on-site inspection to the server for subsequent analysis.

[0853] Step 8:

[0854] The server analyzes the submitted on-site inspection photos using a generation AI model to calculate the cost of restoration to the original state. The AI ​​model uses an image processing library to determine the level of damage in the photos and the need for repairs, and generates the calculated cost as data.

[0855] Step 9:

[0856] The server automatically generates instructions for the contractor based on the calculated restoration costs. Using the instruction generation function, the server creates instructions including the necessary work areas and cost estimates and sends them to the contractor.

[0857] These processing steps enable efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[0858] 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.

[0859] This invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage vacant property information. This system provides functions that meet the needs of three parties: landlords, tenants, and agents, and further analyzes the user's emotional state to optimize the system's response.

[0860] Lender Processing

[0861] 1. Users (lenders) can easily register property information.

[0862] The lender uses the terminal to select and upload several property photos and drawings.

[0863] The terminal sends the uploaded property photos and drawings to the server.

[0864] The server stores the received data and runs the generative AI model.

[0865] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[0866] The server registers the extracted property details in a database.

[0867] The emotional engine analyzes the emotional state of the lender and adjusts the registration priority or content of the property information based on the emotional state.

[0868] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[0869] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[0870] Borrower Processing

[0871] 2. Users (renters) can easily search for the property they want.

[0872] Renters enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[0873] The terminal transmits the entered search conditions to the server.

[0874] The server stores the received search conditions and launches the generative AI model.

[0875] The generative AI model searches a property database and extracts properties that match the criteria.

[0876] The server sends the extracted search results to the user's (borrower's) terminal.

[0877] An emotional engine analyzes the borrower's emotional state and adjusts how search results are displayed or ordered.

[0878] The user (borrower) views the search results on their device and checks detailed information.

[0879] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[0880] Intermediary Processing

[0881] 3. Users (intermediaries) can streamline various administrative tasks.

[0882] The real estate agent uploads property photos taken for on-site inspections from the terminal.

[0883] The device sends the uploaded photos to the server.

[0884] The server stores the received photos and runs the generative AI model.

[0885] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[0886] An emotion engine analyzes the emotional state of the intermediary and adjusts the presentation or content of the calculated fees.

[0887] Based on the estimate generated by the server, instructions are automatically generated for the contractor.

[0888] The server sends the generated instructions to the user's (intermediary's) terminal.

[0889] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoration, and if the emotion engine determines that the real estate agent is under high stress, the results are displayed in a more concise and clear format.

[0890] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they want, and agents can efficiently carry out their administrative work. Furthermore, by taking into account the user's emotional state, it is possible to respond optimally to individual needs, improving the overall user experience. This will promote the effective use of vacant houses and contribute to solving social problems.

[0891] The processing flow will be explained below.

[0892] Lender Processing

[0893] Step 1:

[0894] The user (lender) uses the terminal to select and upload property photos and drawings.

[0895] Step 2:

[0896] The terminal sends the uploaded property photos and drawings to the server.

[0897] Step 3:

[0898] The server receives the transmitted data and activates the generative AI model.

[0899] Step 4:

[0900] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[0901] Step 5:

[0902] The server registers the extracted property details in a database.

[0903] Step 6:

[0904] The server runs an emotion engine to analyze the emotional state of the lender.

[0905] Step 7:

[0906] An emotion engine adjusts the listing priority or content of property information based on the emotional state of the lender.

[0907] Step 8:

[0908] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[0909] Borrower Processing

[0910] Step 1:

[0911] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[0912] Step 2:

[0913] The terminal transmits the entered search conditions to the server.

[0914] Step 3:

[0915] The server stores the received search conditions and launches the generative AI model.

[0916] Step 4:

[0917] The generative AI model searches a property database and extracts properties that match the criteria.

[0918] Step 5:

[0919] The server sends the extracted search results to the user's (borrower's) terminal.

[0920] Step 6:

[0921] The server activates an emotion engine to analyze the borrower's emotional state.

[0922] Step 7:

[0923] An emotional engine adjusts the display or order of search results based on the borrower's emotional state.

[0924] Step 8:

[0925] The user (borrower) views the search results on their device and checks the detailed information.

[0926] Intermediary Processing

[0927] Step 1:

[0928] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[0929] Step 2:

[0930] The device sends the uploaded photos to the server.

[0931] Step 3:

[0932] The server stores the received photos and runs the generative AI model.

[0933] Step 4:

[0934] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[0935] Step 5:

[0936] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[0937] Step 6:

[0938] The server sends the generated quote to the user's (intermediary's) terminal.

[0939] Step 7:

[0940] The server activates an emotion engine to analyze the emotional state of the agent.

[0941] Step 8:

[0942] An emotion engine adjusts the presentation or content of the calculation results based on the emotional state of the intermediary.

[0943] Step 9:

[0944] The server sends the generated instructions to the construction company's terminal.

[0945] This allows the emotion engine to be used to optimally respond to the user's emotional state, improving the overall user experience.

[0946] Example 2

[0947] 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."

[0948] The problem is that the registration, search, and management of vacant house property information is complicated, time-consuming, and labor-intensive. Furthermore, the system response is not optimized to take into account the user's emotional state, making it difficult to improve the user experience. It is necessary to solve these issues and promote the effective utilization of vacant houses.

[0949] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically analyzing property images and blueprints uploaded by a lender using a generative AI model to extract property detailed information, means for searching a property data storage device using the generative AI model based on received search conditions to extract properties that match the conditions, and emotion engine means for analyzing the user's emotional state and adjusting the registration priority or content based on the emotional state. This enables efficient registration, search, and management of property information and optimal responses according to the user's emotional state, thereby improving the overall user experience.

[0950] A "lender" is a person who owns real estate property or who acts on behalf of the owner and who intends to rent out the property.

[0951] A "borrower" is a person who wishes to rent a real estate property, searches for information about the property, and wishes to enter into a contract.

[0952] An "intermediary" is a person who acts as an intermediary between a lender and a borrower, introducing properties and facilitating the contract procedures.

[0953] "Property images" are photographs or drawings showing the exterior and interior of a real estate property, and are visual information for understanding the details of the property.

[0954] A "blueprint" is a drawing that shows the floor plan and layout of a real estate property, and specifically represents the structure and dimensions of the property.

[0955] A "generative AI model" is a model that uses artificial intelligence technology to analyze and predict data, and is trained using machine learning algorithms.

[0956] A "server" is a computer system that processes, stores, and analyzes data and provides services to other devices over a network.

[0957] A "data storage device" is a device for storing information physically or electronically, such as a database or file storage device.

[0958] An "emotion engine" is a software component that analyzes the user's emotional state from their voice or text and adjusts the system's behavior.

[0959] "Registration priority" is an index that indicates the priority of property information registration work, and is a criterion for the system to perform registration work efficiently.

[0960] "Property details" refers to information that indicates specific attributes such as the size, layout, and facilities of the property, and is data necessary to understand the characteristics of the property.

[0961] "Search conditions" are conditions that specify the attributes of the property desired by the borrower, and include specific requirements such as the type of property, size, and location.

[0962] "Restoration costs" are the costs necessary to return the property to its original condition after the tenant moves out, including repairs, cleaning, etc.

[0963] A "construction contractor" is a professional contractor that repairs, renovates, cleans, etc. real estate properties and carries out restoration work to their original condition.

[0964] An "instruction sheet" is a document that instructs a specific task and indicates the specific work content and costs to the contractor.

[0965] The present invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage property information for vacant homes. Specific embodiments of this system are described below.

[0966] The system is used by three parties: lenders, borrowers, and intermediaries, and provides functions tailored to the needs of each user. The system's main hardware includes servers, terminals, and data storage devices. The system's main software includes generative AI models, emotion engines, and user interfaces.

[0967] Lender Processing

[0968] Lenders register property information via their devices. They upload photos and blueprints of the property, which are then received by the server. Specific photos and blueprints are selected via a smartphone app or web app, and the server then clicks the upload button. The server then sends this data to the generative AI model, which automatically extracts detailed property information. During this process, the generative AI model uses image processing algorithms to identify detailed information such as the property's size, layout, and amenities.

[0969] For example, when a lender uploads photos of their living room, kitchen, bedroom, and bathroom, the server passes them to the generative AI model, and records the size and characteristics of each room in a data storage device. During this process, the emotion engine analyzes the lender's emotional state, and if it determines that the lender is tense, it will respond by quickly sending a registration completion notification.

[0970] Example prompt sentence:

[0971] "Analyze photos of the living room, kitchen, bedroom, and bathroom."

[0972] Borrower Processing

[0973] The borrower conducts a property search through their device. They enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) and click the search button. The device sends the search conditions to the server, which then activates the generative AI model and searches for information in the property data storage device. The search results are sent from the server to the borrower's device, where they can be viewed. The emotion engine adjusts the way the search results are displayed, and in some cases, highlights them.

[0974] For example, if a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria, generates a list, and sends it to the terminal. If the emotion engine determines that the borrower is increasingly interested, it highlights the search results and displays them.

[0975] Example prompt sentence:

[0976] "Search for a newly built property with a 2LDK, 5-minute walk from the station."

[0977] Intermediary Processing

[0978] Real estate agents can upload property images for on-site inspections to streamline their administrative work. When photos of inspected properties are uploaded from a device, the server receives them and performs image analysis using a generative AI model. As a result of the analysis, the cost of restoration to the original state is calculated, and instructions to the construction company are automatically generated based on that cost. The emotion engine analyzes the emotional state of the agent and adjusts the display of the results as necessary.

[0979] For example, if a real estate agent uploads photos of damage to a property, the server analyzes them and calculates the cost of repairs. If the emotion engine analyzes the agent's emotional state and determines that they are stressed, it displays the results in a concise and clear format.

[0980] Example prompt sentence:

[0981] Please estimate the cost of restoration from this photo.

[0982] These processes will enable landlords to easily register property information, tenants to quickly search for the property they desire, and real estate agents to efficiently perform their administrative tasks. It will also enable responses that take into account the user's emotional state, improving the overall user experience. This will promote the effective use of vacant homes and contribute to solving social problems.

[0983] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0984] Lender property information registration processing

[0985] Step 1:

[0986] The user selects property photos and blueprints using the terminal and clicks the upload button. The input is the property photos and blueprints, and the output is that these files are sent from the terminal to the server.

[0987] Step 2:

[0988] The terminal sends the uploaded file to the server. Specifically, the terminal sends an HTTP POST request to the server, with the input being the selected property photo and blueprint, and the output being the file being saved on the server.

[0989] Step 3:

[0990] The server saves the received file in storage and launches the generative AI model. The input is the uploaded file, and the output is the invocation of the generative AI model's interface. Specifically, the server saves the file in cloud storage (e.g., AWS S3) and triggers the execution of the generative AI model (e.g., TensorFlow).

[0991] Step 4:

[0992] The generative AI model analyzes property photos and blueprints to automatically extract property details such as size, layout, and equipment status. The input is the saved property photos and blueprints, and the output is the extracted property details. Specifically, the generative AI model identifies information and extracts data through image processing algorithms.

[0993] Step 5:

[0994] The server registers the extracted property details in a database. The input is the property details, and the output is to register them in a database. Specifically, the server executes an SQL query to insert the information into a database (e.g. MySQL).

[0995] Step 6:

[0996] The emotion engine analyzes the emotional state of the lender and adjusts the registration priority or content based on the emotional state. The input is the lender's emotional information, and the output is the adjusted registration priority or content. Specifically, it uses NLP technology (e.g., BERT) to analyze the user's emotional state.

[0997] Step 7:

[0998] The server sends a notification to the user's device that the property information has been registered. The input is the registration completion notification, and the output is the notification sent to the user's device. Specifically, the server sends the notification using a communication API (e.g., Firebase Cloud Messaging).

[0999] Borrower property search processing

[1000] Step 1:

[1001] The user inputs the desired property search criteria from the terminal and clicks the search button. The input is the property search criteria, and the output is the transmission of these criteria to the server.

[1002] Step 2:

[1003] The terminal sends the entered search criteria to the server. Specifically, the terminal sends an HTTP GET or POST request. The input is the search criteria, and the output is the server receiving the criteria.

[1004] Step 3:

[1005] The server stores the received search conditions and launches the generative AI model. The input is the search conditions, and the output is the invocation of the interface of the generative AI model. Specifically, the server calls the API to execute the AI ​​model based on the saved conditions.

[1006] Step 4:

[1007] The generative AI model searches a property database and extracts properties that match the criteria. The input is the search criteria and the property database, and the output is a list of properties that match the criteria. Specifically, the AI ​​model generates a database query and searches the database (e.g., PostgreSQL).

[1008] Step 5:

[1009] The server sends the extracted search results to the user's device. The input is the search results, and the output is the results sent to the user's device. Specifically, the server formats the results in JSON format and returns them as an HTTP response.

[1010] Step 6:

[1011] The emotion engine analyzes the borrower's emotional state and adjusts the display method or order of search results. The input is the borrower's emotional information, and the output is the adjusted search result display. Specifically, the emotion engine analyzes the user's click speed and mouse movement.

[1012] Step 7:

[1013] The user views the search results on the device and checks the detailed information. The input is the search results, and the output is the display of detailed information. Specifically, the user clicks on a property from the list of search results to move to the details page.

[1014] Streamlining of administrative work for intermediaries

[1015] Step 1:

[1016] Users upload property images taken for on-site inspections from their terminals. The input is inspection photos, and the output is that these photos are sent to the server.

[1017] Step 2:

[1018] The device sends the uploaded photo to the server. Specifically, the device sends an HTTP POST request, where the input is the uploaded photo and the output is the photo to be saved on the server.

[1019] Step 3:

[1020] The server saves the received photos in storage and launches the generative AI model. The input is the saved photo, and the output is the invocation of the interface of the generative AI model. Specifically, the server saves the photo in cloud storage (e.g., Google Cloud Storage) and triggers the execution of the generative AI model.

[1021] Step 4:

[1022] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs. The input is the stored photos, and the output is the cost estimate. Specifically, the AI ​​model uses an image processing algorithm to identify damaged areas and generate an estimate.

[1023] Step 5:

[1024] The emotion engine analyzes the broker's emotional state and adjusts the presentation method or content of the calculated cost. The input is the broker's emotional information, and the output is the adjusted quote display. Specifically, the emotion engine performs text and voice analysis to adjust the screen layout and messages.

[1025] Step 6:

[1026] The server automatically generates instructions for the contractor based on the generated estimate. The input is the estimate result, and the output is the automatically generated instructions. Specifically, the program inserts the estimate data into a template and generates the instructions.

[1027] Step 7:

[1028] The server sends the generated instructions to the user's device. The input is the automatically generated instructions, and the output is the instructions sent to the user's device. Specifically, the server generates the instructions as a PDF file and sends an email or a download link.

[1029] This allows the entire system to operate efficiently and improves the user experience.

[1030] (Application example 2)

[1031] 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."

[1032] Currently, systems for efficiently registering, searching, and managing vacant property information struggle to meet the needs of lenders, borrowers, and agents. Furthermore, they provide uniform responses and operations without considering the user's emotional state, resulting in an unoptimized user experience. Furthermore, in-store property information management lacks an intuitive and efficient interface, making registering and searching property information cumbersome.

[1033] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1034] In this invention, the server includes: a means for a lender to upload several property photos and drawings to provide property information; a means for automatically analyzing the uploaded property photos and drawings using a generative artificial intelligence model to extract property details; and a means for registering the extracted property details in a database. This enables efficient registration of property information. Additionally, the server includes: a means for a borrower to input property search criteria and transmit them to the server; a means for searching the property database using a generative artificial intelligence model based on the received search criteria to extract properties that match the criteria; and a means for transmitting the search results to the borrower's terminal. This allows borrowers to quickly find their desired property. Furthermore, the server includes: a means for a real estate agent to upload property photos taken for on-site inspections, a means for analyzing the transmitted photos using a generative artificial intelligence model to calculate restoration costs, a means for automatically generating instructions for a contractor based on the calculated costs, a means for detecting a user's emotional state using an emotional state analysis engine to optimize system response, and a means for providing an interface using a smart device when registering and searching for property information at a physical store. This will streamline the intermediary's administrative work and also enable optimal responses that take into account the user's emotional state, improving the overall user experience.

[1035] A "lender" is a person or entity that owns the property and intends to rent it out.

[1036] "Lessee" means an individual or entity that intends to rent the property.

[1037] An "intermediary" is an individual or organization that acts as an intermediary between lenders and borrowers to facilitate transactions.

[1038] A "server" is a computer system for processing and managing data over a network.

[1039] A "generative AI model" is an artificial intelligence algorithm that has the ability to generate information from given data.

[1040] An "emotional state analysis engine" is an algorithm or device for analyzing a user's emotions and detecting their state.

[1041] A "smartphone" is a mobile device that has mobile communication capabilities and can run multifunctional applications.

[1042] A "head-mounted display" is a device worn on the head that displays information within the field of vision.

[1043] "Property photos" are images taken of the interior and exterior of a property.

[1044] A "drawing" is a blueprint that illustrates the layout and structure of a property.

[1045] "Property detailed information" is information that includes specific characteristics of the property, such as the size, layout, and facilities.

[1046] A "property database" is a database for systematically managing detailed information about properties.

[1047] The "registration completion notice" is a notice to inform the user that the property information has been successfully registered.

[1048] "Search criteria" refers to the conditions of the property desired by the borrower (e.g., number of rooms, location, age of building, etc.).

[1049] An "instruction document" is a document that instructs a specific task or procedure.

[1050] A "site inspection" is an investigation carried out by actually visiting a property to check its condition.

[1051] "Restoration costs" are the costs required to return the property to its original condition.

[1052] This invention provides a system that efficiently registers, searches, and manages property information by combining a generative AI model and an emotional state analysis engine. The following hardware and software are used to implement the invention.

[1053] Hardware used

[1054] server

[1055] Smartphone (e.g. iPhone, Android)

[1056] Head-mounted displays (e.g., Oculus Quest 2)

[1057] Software used

[1058] Generative AI model: OpenAI GPT-4

[1059] Emotional state analysis engine: Affectiva SDK

[1060] Database: Firebase, MySQL

[1061] Image analysis: Google Cloud Vision API

[1062] Specific Embodiments of the System

[1063] Lender manipulation

[1064] 1. The user (lender) uses their smartphone to take several photos and drawings of the property and upload them through the application.

[1065] 2. The terminal sends the uploaded property photos and drawings to the server.

[1066] 3. The server stores the received data and activates the generative AI model to automatically extract detailed property information (room size, layout, equipment status, etc.).

[1067] 4. The server registers the extracted property details in a database and analyzes the lender's emotional state using an emotional state analysis engine.

[1068] 5. Adjust the priority or content of property listings based on emotional state and notify lenders that property listings have been completed.

[1069] Example: When a lender sends photos and drawings of the living room, kitchen, bedroom, and bathroom via smartphone, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[1070] Borrower operations

[1071] 1. The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the application via a smartphone or head-mounted display.

[1072] 2. The device sends the search criteria to the server.

[1073] 3. Based on the search criteria received by the server, the generative AI model is activated to search the property database and extract properties that match the criteria.

[1074] 4. The server sends the extracted search results to the borrower's device, and the emotional state analysis engine analyzes the borrower's emotional state.

[1075] 5. Adjust the way search results are displayed or ordered based on emotional state, making them more intuitive for users.

[1076] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[1077] Intermediary manipulation

[1078] 1. The real estate agent uploads property photos taken for on-site inspections using their smartphone.

[1079] 2. The device sends the uploaded photos to the server.

[1080] 3. The server stores the received photos, launches a generative AI model to analyze the images, and automatically calculates the cost of restoration to the original state.

[1081] 4. The server automatically generates instructions for the construction company based on the calculated costs and analyzes the agent's emotional state using an emotional state analysis engine.

[1082] 5. Adjust the presentation of the calculation results based on the emotional state, generate instructions, and send them to the intermediary's terminal.

[1083] Example: When a broker uploads photos from a site inspection, the server analyzes the photos and calculates the cost of restoration. If the emotion engine determines that the broker is stressed, the results are displayed in a more concise and clear format.

[1084] Prompt Sentence Examples

[1085] "Please analyze photos and drawings of the property, automatically extract the room size, layout, and equipment status, and present detailed information. Also, please analyze the user's emotional state and provide an appropriate interface."

[1086] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1087] Step 1:

[1088] Lenders upload property photos and drawings

[1089] The user (lender) takes several photos and drawings of the property using their smartphone and uploads them through the application. The input data are the property photos and drawings, and the output data is sent to the server.

[1090] Step 2:

[1091] Submit property photos and drawings

[1092] The terminal sends the uploaded property photos and drawings to the server. The input data are the uploaded photos and drawings, and the purpose of the operation is to send them to the server.

[1093] Step 3:

[1094] The server receives and stores the data

[1095] The server stores the received property photos and drawings. The input is the photos and drawings sent from the terminal, and the output is that they are stored in the server.

[1096] Step 4:

[1097] Launch the generative AI model to extract property details

[1098] The server launches the generative AI model and analyzes the stored property photos and drawings. The input data are the photos and drawings stored on the server, and the property's size, layout, and equipment status are automatically extracted through data processing and calculation. The output is the extracted property details.

[1099] Step 5:

[1100] Register property details in the database

[1101] The server registers the extracted property details in a database. The input data is the property details from the generative AI model, and the output is the property information registered in the database.

[1102] Step 6:

[1103] Analyzing the emotional state of lenders with an emotion engine

[1104] The server uses an emotional state analysis engine to analyze the emotional state of the lender. The input is data indicating the emotional state of the lender, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[1105] Step 7:

[1106] Adjustment of property information registration priority or content

[1107] The server adjusts the registration priority or content of the property information based on the analyzed emotional state. The input is the analyzed emotional state and property detail information, and the adjusted property information is the output.

[1108] Step 8:

[1109] Send a notification that property information has been registered

[1110] The server notifies the lender that the property registration is complete. The input is the adjusted property information, and the output is a notification sent to the lender's terminal.

[1111] Step 9:

[1112] The borrower enters property search criteria

[1113] The user (renter) inputs the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) into the application via a smartphone or head-mounted display. The input data represents the renter's desired conditions, and the device then sends this to the server.

[1114] Step 10:

[1115] Send search criteria to the server

[1116] The terminal transmits the search criteria entered by the borrower to the server. The input data is the borrower's search criteria, and the data transmitted to the server is the output.

[1117] Step 11:

[1118] Generate property database and search with AI model

[1119] The server launches a generative AI model based on the received search criteria and searches the property database. The input data are the search criteria and the property database, and the output is a list of properties that match the criteria.

[1120] Step 12:

[1121] Send search results to the borrower's device

[1122] The server sends the search results to the borrower's terminal. The input data is a list of properties that match the conditions, and the output is the search results sent to the borrower's terminal.

[1123] Step 13:

[1124] Analyze the borrower's emotional state with an emotional state analysis engine

[1125] The server uses an emotional state analysis engine to analyze the emotional state of the borrower. The input data is data indicating the emotional state of the borrower, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[1126] Step 14:

[1127] Adjust how search results are displayed or ordered

[1128] The server adjusts the display method or order of the search results based on the analyzed emotional state, with the analyzed emotional state and the search results being the input and the adjusted display results being the output.

[1129] Step 15:

[1130] Agents upload property photos

[1131] The real estate agent uploads property photos taken for on-site inspections using a smartphone. The input data is the inspection photos, and the device sends them to the server.

[1132] Step 16:

[1133] Submit property photos

[1134] The terminal sends the uploaded property photos to the server. The input data is the uploaded survey photos, and the transmission to the server is the output.

[1135] Step 17:

[1136] Retention and analysis of submitted photos

[1137] The server launches the generative AI model, stores and analyzes the property photos sent to it. The input data are the uploaded survey photos, and the restoration costs are automatically calculated from the photos through data processing and calculation. The output is the calculated restoration costs.

[1138] Step 18:

[1139] Automatically generate instructions based on calculations of restoration costs

[1140] The server automatically generates instructions for the contractor based on the calculated restoration costs. The input data is the calculated restoration costs, and the output is the automatically generated instructions.

[1141] Step 19:

[1142] Analyzing the emotional state of intermediaries with an emotion engine

[1143] The server uses an emotional state analysis engine to analyze the emotional state of the intermediary. The input data is data indicating the emotional state of the intermediary, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[1144] Step 20:

[1145] Adjust the way the calculation results are presented and send instructions

[1146] The server adjusts the presentation method of the calculation result based on the analyzed emotional state and sends instructions to the intermediary terminal. The input is the analyzed emotional state and the generated instructions, and the adjusted instructions are sent to the intermediary terminal.

[1147] 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.

[1148] 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.

[1149] 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.

[1150] [Third embodiment]

[1151] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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).

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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."

[1163] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[1164] Lender Processing

[1165] 1. Users (lenders) can easily register property information.

[1166] The lender uses the terminal to upload several property photos and drawings.

[1167] The device sends the uploaded data to the server.

[1168] The server automatically analyzes the data it receives using a generated artificial intelligence model to extract detailed information about the property.

[1169] The extracted information is immediately registered in the property database by the server, and a notification of registration completion is sent to the lender's terminal.

[1170] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[1171] Borrower Processing

[1172] 2. Users (renters) can easily search for the property they want.

[1173] The tenant enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[1174] The terminal transmits the received search conditions to the server.

[1175] Based on the conditions received by the server, the property database is searched using a generated artificial intelligence model to extract properties that meet the conditions.

[1176] The server sends the search results to the borrower's terminal, where the borrower can check the detailed information.

[1177] Example: When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts properties that most closely match those conditions and sends the results in list format.

[1178] Intermediary Processing

[1179] 3. Users (intermediaries) can streamline various administrative tasks.

[1180] The real estate agent uploads property photos taken during on-site inspections from the terminal.

[1181] The device sends the uploaded photos to the server.

[1182] The server analyzes the received photos using a generated artificial intelligence model and automatically generates an estimate of the cost of restoring the property to its original condition.

[1183] The server creates instructions for the construction company based on the generated estimate and sends them to the intermediary's terminal.

[1184] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and automatically creates and sends instructions to the appropriate contractor based on that estimate.

[1185] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they are looking for, and agents can efficiently carry out their administrative work. This will promote the effective use of vacant houses and contribute to solving social problems.

[1186] The processing flow will be explained below.

[1187] Lender Processing

[1188] Step 1:

[1189] The user (lender) uses a terminal to select and upload several property photos and drawings.

[1190] Step 2:

[1191] The terminal sends the uploaded property photos and drawings to the server.

[1192] Step 3:

[1193] The server stores the received data and runs the generative AI model.

[1194] Step 4:

[1195] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[1196] Step 5:

[1197] The server registers the extracted property details in a database.

[1198] Step 6:

[1199] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[1200] Borrower Processing

[1201] Step 1:

[1202] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[1203] Step 2:

[1204] The terminal transmits the entered search conditions to the server.

[1205] Step 3:

[1206] The server stores the received search conditions and launches the generative AI model.

[1207] Step 4:

[1208] The generative AI model searches a property database and extracts properties that match the criteria.

[1209] Step 5:

[1210] The server sends the extracted search results to the user's (borrower's) terminal.

[1211] Step 6:

[1212] The user (borrower) views the search results on their device and checks the detailed information.

[1213] Intermediary Processing

[1214] Step 1:

[1215] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[1216] Step 2:

[1217] The device sends the uploaded photos to the server.

[1218] Step 3:

[1219] The server stores the received photos and runs the generative AI model.

[1220] Step 4:

[1221] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[1222] Step 5:

[1223] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[1224] Step 6:

[1225] The server sends the generated instructions to the user's (intermediary's) terminal.

[1226] Example 1

[1227] 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."

[1228] Conventional property information registration, search, and management systems lacked functionality to meet the different needs of each user, resulting in low efficiency in information registration and search. As a result, landlords could not easily register property information, tenants could not quickly search for the property they wanted, and real estate agents often suffered from inefficient administrative work. In addition, data accuracy and search precision were low, making it difficult to effectively utilize vacant homes.

[1229] 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.

[1230] In this invention, the server includes a means for a lender to provide property information by uploading several property photos and drawings, a means for a terminal to transmit the uploaded property photos and drawings to the server, and a means for the server to automatically analyze the property photos and drawings using a generative AI model, extract property details, and register them in a database. This enables a system that allows lenders to easily register property information, borrowers to efficiently search for properties, and agents to perform administrative tasks quickly and accurately.

[1231] A "lender" is an individual or legal entity that owns or manages a property and wishes to rent the property to others.

[1232] A "borrower" is an individual or corporation who wishes to rent a property, and is a user who wants to search for properties and find one that meets their requirements.

[1233] A "broker" is an individual or corporation that acts as an intermediary between the lender and the borrower in property transactions, and is a specialist that handles administrative tasks such as property inspections and contract procedures.

[1234] "Terminal" means an electronic device used by a lender, borrower, or intermediary to input, send, and receive information. Examples include smartphones and personal computers.

[1235] A "server" is a computer system that provides services over a network and is a central device that analyzes, registers, searches, and manages property information.

[1236] A "generative AI model" is a model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing.

[1237] "Property information" refers to detailed data about a property, including photographs, drawings, room size, facilities, floor plan, and other information.

[1238] A "database" is an electronic recording medium in which property information is organized and stored, and is a system for efficiently querying, adding, and updating data.

[1239] "Search conditions" are items that indicate the characteristics and requirements of the property desired by the tenant, and examples include floor plan, location, age of the building, etc.

[1240] "Search results" are generated by the server by querying a property database based on search criteria and generating a list of properties that match the criteria.

[1241] "Restoration costs" are the costs required to return the property to its original condition, and are calculated based on information obtained by the real estate agent during an on-site inspection.

[1242] An "instruction sheet" is a document generated by the server that clearly states the details and costs of restoration to the original state and requests the contractor to carry out the work.

[1243] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[1244] Hardware and software used

[1245] Hardware:

[1246] Terminal: An electronic device used by a user to input, send, and receive information. Examples include smartphones and personal computers.

[1247] Server: A computer system that provides services over a network and is the central device that analyzes, registers, searches, and manages property information.

[1248] software:

[1249] Generative AI model: A model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing (e.g., OpenAI GPT-4).

[1250] Database: An electronic recording medium in which property information is organized and stored, and a system for efficiently querying, adding, and updating data (e.g., database software such as MySQL).

[1251] Lender Operation Flow

[1252] 1. User (lender) property information registration

[1253] The lender uploads property photos and drawings using a terminal, which then sends the uploaded data to the server, which then receives it.

[1254] 2. Data analysis and registration by the server

[1255] The server uses a generative AI model to automatically analyze the uploaded photos and drawings and extract detailed property information. This information is immediately registered in a database. The server then sends a notification to the lender that the property information has been registered.

[1256] Borrower Operation Flow

[1257] 1. User (borrower) enters property search criteria

[1258] The renter enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the terminal and sends them to the server.

[1259] 2. Conditional search by server and sending results

[1260] The server uses the generative AI model to search the property database based on the received search criteria and extracts properties that match the criteria. The search results are sent to the borrower's device, where they can view the results and check detailed information.

[1261] Intermediary operation flow

[1262] 1. User (agent) uploads property photos

[1263] The real estate agent uploads property photos taken for on-site inspections from the terminal, which then sends them to the server.

[1264] 2. Photo analysis and quotation generation by the server

[1265] The server analyzes the received photos using a generative AI model to calculate the cost of restoration to the original state, then automatically generates instructions for the contractor based on the calculated cost and sends them to the intermediary.

[1266] Examples of concrete examples and prompts

[1267] Examples of lenders include:

[1268] When a landlord uploads photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[1269] Example prompt sentence:

[1270] Upload photos and drawings of your living room, kitchen, bedroom and bathroom to extract property details and add them to our database.

[1271] Examples of borrowers:

[1272] When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts the properties that most closely match those conditions and sends the results in list format.

[1273] Example prompt sentence:

[1274] Search for properties that meet your criteria: 2LDK, 5-minute walk from the station, newly built.

[1275] Examples of intermediaries include:

[1276] When a real estate agent uploads photos from their on-site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and then automatically creates and sends instructions to the appropriate contractor based on that estimate.

[1277] Example prompt sentence:

[1278] Upload site inspection photos to generate restoration cost estimates and create instructions for contractors.

[1279] This system allows landlords to easily register property information, tenants to quickly search for the property they want, and agents to efficiently carry out their administrative work. As a result, it is expected that the effective use of vacant houses will be promoted, contributing to the solution of social issues.

[1280] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1281] Lender Processing

[1282] Step 1:

[1283] The user opens the property information registration screen

[1284] Input: Access to property information registration screen

[1285] Operation: The user operates the device to open the property information registration screen. The screen that appears contains an interface for uploading property photos and drawings.

[1286] Output: The property information registration screen will be displayed on the terminal.

[1287] Step 2:

[1288] Users select and upload property photos and drawings

[1289] Input: Selected property photos and drawings

[1290] How it works: A user uses their device to select property photos and drawings and clicks the upload button.

[1291] Output: The selected data is temporarily saved on the device.

[1292] Step 3:

[1293] The device sends the data to the server

[1294] Input: Uploaded property photos and drawing data

[1295] Operation: The device sends the selected property photos and drawing data to the server in a batch process. The progress of the transfer is displayed to the user in real time.

[1296] Output: Property photos and drawing data are sent to the server.

[1297] Step 4:

[1298] The server analyzes the data

[1299] Input: Property photos and drawing data submitted

[1300] How it works: The server launches the generative AI model and analyzes the data sent. The generative AI model extracts detailed property information (e.g., room size, facilities, and layout) from the image.

[1301] Output: Detailed property information extracted by analysis

[1302] Step 5:

[1303] The server registers the property information in the database

[1304] Input: Extracted property details

[1305] Operation: The server converts the generated property details into a standard format and records them in a database.

[1306] Output: Property details are registered in the database.

[1307] Step 6:

[1308] The server sends a notification to the user that registration is complete.

[1309] Input: Notification information for registration completion

[1310] Operation: The server creates a registration completion notification and sends it to the user's terminal.

[1311] Output: The device receives the notification and displays it to the user.

[1312] Borrower Processing

[1313] Step 1:

[1314] The user enters property search criteria

[1315] Input: Property search criteria (e.g. 2LDK, 5-minute walk from station, new construction)

[1316] Operation: The user operates the device, opens the property search screen, enters the conditions, and clicks the search button.

[1317] Output: The entered search criteria are temporarily saved on the device.

[1318] Step 2:

[1319] The device sends the search criteria to the server.

[1320] Input: Entered search criteria

[1321] Operation: The device sends search criteria to the server.

[1322] Output: The search criteria is sent to the server.

[1323] Step 3:

[1324] The server searches the property database based on the criteria

[1325] Input: Search criteria

[1326] How it works: The server uses the generated AI model to search the property database and extract properties that match the criteria.

[1327] Output: A list of properties that match the criteria

[1328] Step 4:

[1329] The server sends the search results to the user

[1330] Input: List of properties that match your criteria

[1331] How it works: The server formats the search results into a list and sends it to the user's device.

[1332] Output: The search result list is sent to the terminal and displayed to the user.

[1333] Intermediary Processing

[1334] Step 1:

[1335] Users upload field survey photos

[1336] Input: Photos taken during field survey

[1337] Action: The user operates the device, selects a property photo, and clicks the upload button.

[1338] Output: The selected photos are temporarily saved on your device.

[1339] Step 2:

[1340] The device sends the photo data to the server.

[1341] Input: Selected photo data

[1342] How it works: The device sends batches of photo data to the server. The progress of the transfer is displayed to the user in real time.

[1343] Output: The photo data is sent to the server.

[1344] Step 3:

[1345] The server analyzes the photo

[1346] Input: Submitted photo data

[1347] How it works: The server launches a generative AI model and analyzes the photo data. The generative AI model estimates the need for restoration and the cost.

[1348] Output: Estimated restoration costs

[1349] Step 4:

[1350] The server generates instructions based on the estimate.

[1351] Input: Estimated restoration costs

[1352] How it works: The server automatically generates detailed instructions for the contractor based on the estimate.

[1353] Output: Instructions are generated.

[1354] Step 5:

[1355] The server sends instructions to the user

[1356] Input: Generated instructions

[1357] How it works: The server sends instructions to the user's device, allowing for subsequent approval or modification.

[1358] Output: The terminal receives the instructions and displays them to the user.

[1359] (Application example 1)

[1360] 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."

[1361] Conventional property information registration and management systems have faced challenges such as the need for manual input and ensuring the accuracy of information. It is also difficult to efficiently register and search detailed information about vacant houses and brick-and-mortar stores, and the time and effort required for cost estimates based on on-site surveys and instructions to construction companies is particularly significant. This has hindered the effective utilization of vacant houses and brick-and-mortar stores, causing social problems.

[1362] 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.

[1363] In this invention, the server includes: a means for a lender to upload several property information photos and drawings to provide property information; a means for the server to automatically analyze the uploaded photos and drawings using a generative AI model and extract detailed property information; a means for the server to register the extracted detailed property information in a database; a means for a borrower to input property search conditions and send them to the server; a means for the server to search the database using a generative AI model based on the received search conditions and extract properties that match the conditions; a means for the server to send the search results to the borrower's terminal; a means for a real estate agent to upload photos taken for on-site inspection and send them to the server; and a means for the server to analyze the sent photos using a generative AI model and calculate restoration costs. The system includes a means for uploading store information and store search criteria to the server, a means for the server to automatically generate instructions to a construction company based on the calculated costs, a means for a store manager to provide store information by uploading store information photos and layouts, a means for a tenant to input store search criteria and send them to the server, a means for the server to search a database using a generative AI model based on the received search criteria and extract stores that match the criteria, a means for the server to send the store search results to the tenant's terminal, a means for a real estate agent to upload store photos taken for on-site inspections and send them to the server, a means for the server to analyze the sent photos using a generative AI model and calculate the cost of restoring the store to its original condition, and a means for the server to automatically generate instructions to a construction company based on the calculated costs. This enables efficient and accurate registration, search, and management of property and store information, as well as rapid estimation of restoration costs.

[1364] A "lender" is the person or entity that owns the property or store and provides the information.

[1365] "Property information" is data showing details of a property, such as photos and drawings of the property.

[1366] A "server" is a computer system that stores and manages data.

[1367] A "generative AI model" is an artificial intelligence model trained based on large amounts of data, and is a technology that analyzes and generates data.

[1368] "Property details" refers to information extracted using a generative AI model, including detailed attributes and features of the property.

[1369] A "database" is a collection of organized data, a place where property information and store information are stored.

[1370] A "lessee" is a person or entity wishing to use the property or business.

[1371] "Property search conditions" are information that specifies the characteristics and conditions of the property or store desired by the borrower.

[1372] An "intermediary" is a person or organization that acts as an intermediary between a lender and a borrower for the sale of a property or store.

[1373] A "site inspection" is an investigation carried out to check the actual condition of a property or store.

[1374] "Restoration costs" are the costs required to return a property or store to its original condition.

[1375] A "contractor" is a person or organization that carries out construction or repairs on a property or business.

[1376] "Store information" is data that shows details of the store, such as photos and layout of the physical store.

[1377] A "tenant" is a person or organization that rents a store or property for use.

[1378] This system was developed to support lenders, borrowers, real estate agents, and store managers in efficiently registering, searching, and managing property and store information, estimating restoration costs, and generating instructions for construction companies. A specific embodiment is shown below.

[1379] Lender and brick-and-mortar store manager operations

[1380] Lenders or store managers upload several property information photos and drawings, or store information photos and layouts, from their smartphones, PCs, or other devices. The uploaded data is sent to a server, which automatically analyzes the data using a generative AI model. From this analysis, detailed information about the property or store is extracted and registered in a property information database.

[1381] Borrower and Tenant Operations

[1382] Renters and tenants enter search criteria for the desired property or store on their device and send them to the server. The server uses a generative AI model to search the property information database based on the received search criteria and extracts properties or stores that match the criteria. The server then sends the search results to the renter or tenant's device, where they can check detailed information.

[1383] Intermediary manipulation

[1384] The real estate agent uploads photos of the property or store taken for on-site inspections from their device. The uploaded photos are sent to a server, which analyzes them using a generative AI model and calculates the cost of restoration to the original state. The server then automatically generates instructions for the contractor based on the calculated costs and sends the instructions to the real estate agent's device as needed.

[1385] Hardware and software used

[1386] The hardware used includes smartphones, PCs, and servers. The smartphones and PCs are used by landlords, borrowers, brokers, brick-and-mortar store managers, and tenants to upload data and enter search criteria. The servers are responsible for analyzing and storing the data, and automatically analyze the input data using generative AI models.

[1387] The software used is the openai library for implementing the generative AI model, and PIL (Python Imaging Library) for image processing.

[1388] Examples of concrete examples and prompts

[1389] Examples of lenders and brick-and-mortar managers

[1390] When renters submit photos of their living rooms, kitchens, bedrooms, and bathrooms, the server automatically analyzes them and registers the room sizes and facilities in the database. Similarly, physical store managers submit photos and layouts of their stores, and store details are registered in the database.

[1391] Example prompt: "This is a photo of the living area of ​​a store. Can you give me more information about this store?"

[1392] Examples of intermediaries

[1393] When the agent uploads photos from the on-site inspection, the server analyzes the photos, calculates the cost of restoring the property to its original condition, and automatically creates and sends instructions to the contractor.

[1394] Sample prompt: "These are photos of a store for a site inspection. Please estimate the cost of restoring it to its original condition."

[1395] This enables efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[1396] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1397] Step 1:

[1398] The lender or the manager of the brick-and-mortar store uploads several property information photos and drawings, or store information photos and layout, from a smartphone or PC. The entered photos and drawings are sent to the server via the data upload function, which provides the server with basic information about the property or store.

[1399] Step 2:

[1400] The server automatically analyzes the uploaded property information photos and drawings, or store information photos and layouts, using a generative AI model. The AI ​​model analyzes the images using an image processing library (e.g., PIL) and extracts detailed information such as room size, facilities, and layout information. The extracted information is converted into structured data. The input for this step is the uploaded image data, and the output is the extracted property and store details.

[1401] Step 3:

[1402] The server registers the extracted property and store details in a property information database. Using the database registration function, the structured data is efficiently stored in the database, making it easier to store the information and to search and view it later.

[1403] Step 4:

[1404] The borrower or tenant enters search criteria for the desired property or store on a terminal and sends them to the server. The entered search criteria are transmitted to the server via the database query function, and the information search is then ready.

[1405] Step 5:

[1406] The server uses the generative AI model to search the property information database based on the received search criteria. It uses the AI ​​model and database query function to extract properties and stores that match the search criteria. The input for this step is the search criteria, and the output is a list of properties and stores that match the criteria.

[1407] Step 6:

[1408] The server sends the search results to the borrower's or tenant's terminal. The server uses the search result sending function to provide detailed information on properties or stores that match the criteria to the user's terminal. This allows the user to check the selected search results.

[1409] Step 7:

[1410] The real estate agent uploads property or store photos taken for on-site inspections from their device and sends them to the server, which provides the data from the on-site inspection to the server for subsequent analysis.

[1411] Step 8:

[1412] The server analyzes the submitted on-site inspection photos using a generation AI model to calculate the cost of restoration to the original state. The AI ​​model uses an image processing library to determine the level of damage in the photos and the need for repairs, and generates the calculated cost as data.

[1413] Step 9:

[1414] The server automatically generates instructions for the contractor based on the calculated restoration costs. Using the instruction generation function, the server creates instructions including the necessary work areas and cost estimates and sends them to the contractor.

[1415] These processing steps enable efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[1416] 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.

[1417] This invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage vacant property information. This system provides functions that meet the needs of three parties: landlords, tenants, and agents, and further analyzes the user's emotional state to optimize the system's response.

[1418] Lender Processing

[1419] 1. Users (lenders) can easily register property information.

[1420] The lender uses the terminal to select and upload several property photos and drawings.

[1421] The terminal sends the uploaded property photos and drawings to the server.

[1422] The server stores the received data and runs the generative AI model.

[1423] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[1424] The server registers the extracted property details in a database.

[1425] The emotional engine analyzes the emotional state of the lender and adjusts the registration priority or content of the property information based on the emotional state.

[1426] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[1427] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[1428] Borrower Processing

[1429] 2. Users (renters) can easily search for the property they want.

[1430] Renters enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[1431] The terminal transmits the entered search conditions to the server.

[1432] The server stores the received search conditions and launches the generative AI model.

[1433] The generative AI model searches a property database and extracts properties that match the criteria.

[1434] The server sends the extracted search results to the user's (borrower's) terminal.

[1435] An emotional engine analyzes the borrower's emotional state and adjusts how search results are displayed or ordered.

[1436] The user (borrower) views the search results on their device and checks detailed information.

[1437] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[1438] Intermediary Processing

[1439] 3. Users (intermediaries) can streamline various administrative tasks.

[1440] The real estate agent uploads property photos taken for on-site inspections from the terminal.

[1441] The device sends the uploaded photos to the server.

[1442] The server stores the received photos and runs the generative AI model.

[1443] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[1444] An emotion engine analyzes the emotional state of the intermediary and adjusts the presentation or content of the calculated fees.

[1445] Based on the estimate generated by the server, instructions are automatically generated for the contractor.

[1446] The server sends the generated instructions to the user's (intermediary's) terminal.

[1447] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoration, and if the emotion engine determines that the real estate agent is under high stress, the results are displayed in a more concise and clear format.

[1448] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they want, and agents can efficiently carry out their administrative work. Furthermore, by taking into account the user's emotional state, it is possible to respond optimally to individual needs, improving the overall user experience. This will promote the effective use of vacant houses and contribute to solving social problems.

[1449] The processing flow will be explained below.

[1450] Lender Processing

[1451] Step 1:

[1452] The user (lender) uses the terminal to select and upload property photos and drawings.

[1453] Step 2:

[1454] The terminal sends the uploaded property photos and drawings to the server.

[1455] Step 3:

[1456] The server receives the transmitted data and activates the generative AI model.

[1457] Step 4:

[1458] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[1459] Step 5:

[1460] The server registers the extracted property details in a database.

[1461] Step 6:

[1462] The server runs an emotion engine to analyze the emotional state of the lender.

[1463] Step 7:

[1464] An emotion engine adjusts the listing priority or content of property information based on the emotional state of the lender.

[1465] Step 8:

[1466] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[1467] Borrower Processing

[1468] Step 1:

[1469] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[1470] Step 2:

[1471] The terminal transmits the entered search conditions to the server.

[1472] Step 3:

[1473] The server stores the received search conditions and launches the generative AI model.

[1474] Step 4:

[1475] The generative AI model searches a property database and extracts properties that match the criteria.

[1476] Step 5:

[1477] The server sends the extracted search results to the user's (borrower's) terminal.

[1478] Step 6:

[1479] The server activates an emotion engine to analyze the borrower's emotional state.

[1480] Step 7:

[1481] An emotional engine adjusts the display or order of search results based on the borrower's emotional state.

[1482] Step 8:

[1483] The user (borrower) views the search results on their device and checks the detailed information.

[1484] Intermediary Processing

[1485] Step 1:

[1486] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[1487] Step 2:

[1488] The device sends the uploaded photos to the server.

[1489] Step 3:

[1490] The server stores the received photos and runs the generative AI model.

[1491] Step 4:

[1492] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[1493] Step 5:

[1494] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[1495] Step 6:

[1496] The server sends the generated quote to the user's (intermediary's) terminal.

[1497] Step 7:

[1498] The server activates an emotion engine to analyze the emotional state of the agent.

[1499] Step 8:

[1500] An emotion engine adjusts the presentation or content of the calculation results based on the emotional state of the intermediary.

[1501] Step 9:

[1502] The server sends the generated instructions to the construction company's terminal.

[1503] This allows the emotion engine to be used to optimally respond to the user's emotional state, improving the overall user experience.

[1504] Example 2

[1505] 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."

[1506] The problem is that the registration, search, and management of vacant house property information is complicated, time-consuming, and labor-intensive. Furthermore, the system response is not optimized to take into account the user's emotional state, making it difficult to improve the user experience. It is necessary to solve these issues and promote the effective utilization of vacant houses.

[1507] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically analyzing property images and blueprints uploaded by a lender using a generative AI model to extract property detailed information, means for searching a property data storage device using the generative AI model based on received search conditions to extract properties that match the conditions, and emotion engine means for analyzing the user's emotional state and adjusting the registration priority or content based on the emotional state. This enables efficient registration, search, and management of property information and optimal responses according to the user's emotional state, thereby improving the overall user experience.

[1508] A "lender" is a person who owns real estate property or who acts on behalf of the owner and who intends to rent out the property.

[1509] A "borrower" is a person who wishes to rent a real estate property, searches for information about the property, and wishes to enter into a contract.

[1510] An "intermediary" is a person who acts as an intermediary between a lender and a borrower, introducing properties and facilitating the contract procedures.

[1511] "Property images" are photographs or drawings showing the exterior and interior of a real estate property, and are visual information for understanding the details of the property.

[1512] A "blueprint" is a drawing that shows the floor plan and layout of a real estate property, and specifically represents the structure and dimensions of the property.

[1513] A "generative AI model" is a model that uses artificial intelligence technology to analyze and predict data, and is trained using machine learning algorithms.

[1514] A "server" is a computer system that processes, stores, and analyzes data and provides services to other devices over a network.

[1515] A "data storage device" is a device for storing information physically or electronically, such as a database or file storage device.

[1516] An "emotion engine" is a software component that analyzes the user's emotional state from their voice or text and adjusts the system's behavior.

[1517] "Registration priority" is an index that indicates the priority of property information registration work, and is a criterion for the system to perform registration work efficiently.

[1518] "Property details" refers to information that indicates specific attributes such as the size, layout, and facilities of the property, and is data necessary to understand the characteristics of the property.

[1519] "Search conditions" are conditions that specify the attributes of the property desired by the borrower, and include specific requirements such as the type of property, size, and location.

[1520] "Restoration costs" are the costs necessary to return the property to its original condition after the tenant moves out, including repairs, cleaning, etc.

[1521] A "construction contractor" is a professional contractor that repairs, renovates, cleans, etc. real estate properties and carries out restoration work to their original condition.

[1522] An "instruction sheet" is a document that instructs a specific task and indicates the specific work content and costs to the contractor.

[1523] The present invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage property information for vacant homes. Specific embodiments of this system are described below.

[1524] The system is used by three parties: lenders, borrowers, and intermediaries, and provides functions tailored to the needs of each user. The system's main hardware includes servers, terminals, and data storage devices. The system's main software includes generative AI models, emotion engines, and user interfaces.

[1525] Lender Processing

[1526] Lenders register property information via their devices. They upload photos and blueprints of the property, which are then received by the server. Specific photos and blueprints are selected via a smartphone app or web app, and the server then clicks the upload button. The server then sends this data to the generative AI model, which automatically extracts detailed property information. During this process, the generative AI model uses image processing algorithms to identify detailed information such as the property's size, layout, and amenities.

[1527] For example, when a lender uploads photos of their living room, kitchen, bedroom, and bathroom, the server passes them to the generative AI model, and records the size and characteristics of each room in a data storage device. During this process, the emotion engine analyzes the lender's emotional state, and if it determines that the lender is tense, it will respond by quickly sending a registration completion notification.

[1528] Example prompt sentence:

[1529] "Analyze photos of the living room, kitchen, bedroom, and bathroom."

[1530] Borrower Processing

[1531] The borrower conducts a property search through their device. They enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) and click the search button. The device sends the search conditions to the server, which then activates the generative AI model and searches for information in the property data storage device. The search results are sent from the server to the borrower's device, where they can be viewed. The emotion engine adjusts the way the search results are displayed, and in some cases, highlights them.

[1532] For example, if a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria, generates a list, and sends it to the terminal. If the emotion engine determines that the borrower is increasingly interested, it highlights the search results and displays them.

[1533] Example prompt sentence:

[1534] "Search for a newly built property with a 2LDK, 5-minute walk from the station."

[1535] Intermediary Processing

[1536] Real estate agents can upload property images for on-site inspections to streamline their administrative work. When photos of inspected properties are uploaded from a device, the server receives them and performs image analysis using a generative AI model. As a result of the analysis, the cost of restoration to the original state is calculated, and instructions to the construction company are automatically generated based on that cost. The emotion engine analyzes the emotional state of the agent and adjusts the display of the results as necessary.

[1537] For example, if a real estate agent uploads photos of damage to a property, the server analyzes them and calculates the cost of repairs. If the emotion engine analyzes the agent's emotional state and determines that they are stressed, it displays the results in a concise and clear format.

[1538] Example prompt sentence:

[1539] Please estimate the cost of restoration from this photo.

[1540] These processes will enable landlords to easily register property information, tenants to quickly search for the property they desire, and real estate agents to efficiently perform their administrative tasks. It will also enable responses that take into account the user's emotional state, improving the overall user experience. This will promote the effective use of vacant homes and contribute to solving social problems.

[1541] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1542] Lender property information registration processing

[1543] Step 1:

[1544] The user selects property photos and blueprints using the terminal and clicks the upload button. The input is the property photos and blueprints, and the output is that these files are sent from the terminal to the server.

[1545] Step 2:

[1546] The terminal sends the uploaded file to the server. Specifically, the terminal sends an HTTP POST request to the server, with the input being the selected property photo and blueprint, and the output being the file being saved on the server.

[1547] Step 3:

[1548] The server saves the received file in storage and launches the generative AI model. The input is the uploaded file, and the output is the invocation of the generative AI model's interface. Specifically, the server saves the file in cloud storage (e.g., AWS S3) and triggers the execution of the generative AI model (e.g., TensorFlow).

[1549] Step 4:

[1550] The generative AI model analyzes property photos and blueprints to automatically extract property details such as size, layout, and equipment status. The input is the saved property photos and blueprints, and the output is the extracted property details. Specifically, the generative AI model identifies information and extracts data through image processing algorithms.

[1551] Step 5:

[1552] The server registers the extracted property details in a database. The input is the property details, and the output is to register them in a database. Specifically, the server executes an SQL query to insert the information into a database (e.g. MySQL).

[1553] Step 6:

[1554] The emotion engine analyzes the emotional state of the lender and adjusts the registration priority or content based on the emotional state. The input is the lender's emotional information, and the output is the adjusted registration priority or content. Specifically, it uses NLP technology (e.g., BERT) to analyze the user's emotional state.

[1555] Step 7:

[1556] The server sends a notification to the user's device that the property information has been registered. The input is the registration completion notification, and the output is the notification sent to the user's device. Specifically, the server sends the notification using a communication API (e.g., Firebase Cloud Messaging).

[1557] Borrower property search processing

[1558] Step 1:

[1559] The user inputs the desired property search criteria from the terminal and clicks the search button. The input is the property search criteria, and the output is the transmission of these criteria to the server.

[1560] Step 2:

[1561] The terminal sends the entered search criteria to the server. Specifically, the terminal sends an HTTP GET or POST request. The input is the search criteria, and the output is the server receiving the criteria.

[1562] Step 3:

[1563] The server stores the received search conditions and launches the generative AI model. The input is the search conditions, and the output is the invocation of the interface of the generative AI model. Specifically, the server calls the API to execute the AI ​​model based on the saved conditions.

[1564] Step 4:

[1565] The generative AI model searches a property database and extracts properties that match the criteria. The input is the search criteria and the property database, and the output is a list of properties that match the criteria. Specifically, the AI ​​model generates a database query and searches the database (e.g., PostgreSQL).

[1566] Step 5:

[1567] The server sends the extracted search results to the user's device. The input is the search results, and the output is the results sent to the user's device. Specifically, the server formats the results in JSON format and returns them as an HTTP response.

[1568] Step 6:

[1569] The emotion engine analyzes the borrower's emotional state and adjusts the display method or order of search results. The input is the borrower's emotional information, and the output is the adjusted search result display. Specifically, the emotion engine analyzes the user's click speed and mouse movement.

[1570] Step 7:

[1571] The user views the search results on the device and checks the detailed information. The input is the search results, and the output is the display of detailed information. Specifically, the user clicks on a property from the list of search results to move to the details page.

[1572] Streamlining of administrative work for intermediaries

[1573] Step 1:

[1574] Users upload property images taken for on-site inspections from their terminals. The input is inspection photos, and the output is that these photos are sent to the server.

[1575] Step 2:

[1576] The device sends the uploaded photo to the server. Specifically, the device sends an HTTP POST request, where the input is the uploaded photo and the output is the photo to be saved on the server.

[1577] Step 3:

[1578] The server saves the received photos in storage and launches the generative AI model. The input is the saved photo, and the output is the invocation of the interface of the generative AI model. Specifically, the server saves the photo in cloud storage (e.g., Google Cloud Storage) and triggers the execution of the generative AI model.

[1579] Step 4:

[1580] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs. The input is the stored photos, and the output is the cost estimate. Specifically, the AI ​​model uses an image processing algorithm to identify damaged areas and generate an estimate.

[1581] Step 5:

[1582] The emotion engine analyzes the broker's emotional state and adjusts the presentation method or content of the calculated cost. The input is the broker's emotional information, and the output is the adjusted quote display. Specifically, the emotion engine performs text and voice analysis to adjust the screen layout and messages.

[1583] Step 6:

[1584] The server automatically generates instructions for the contractor based on the generated estimate. The input is the estimate result, and the output is the automatically generated instructions. Specifically, the program inserts the estimate data into a template and generates the instructions.

[1585] Step 7:

[1586] The server sends the generated instructions to the user's device. The input is the automatically generated instructions, and the output is the instructions sent to the user's device. Specifically, the server generates the instructions as a PDF file and sends an email or a download link.

[1587] This allows the entire system to operate efficiently and improves the user experience.

[1588] (Application example 2)

[1589] 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."

[1590] Currently, systems for efficiently registering, searching, and managing vacant property information struggle to meet the needs of lenders, borrowers, and agents. Furthermore, they provide uniform responses and operations without considering the user's emotional state, resulting in an unoptimized user experience. Furthermore, in-store property information management lacks an intuitive and efficient interface, making registering and searching property information cumbersome.

[1591] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1592] In this invention, the server includes: a means for a lender to upload several property photos and drawings to provide property information; a means for automatically analyzing the uploaded property photos and drawings using a generative artificial intelligence model to extract property details; and a means for registering the extracted property details in a database. This enables efficient registration of property information. Additionally, the server includes: a means for a borrower to input property search criteria and transmit them to the server; a means for searching the property database using a generative artificial intelligence model based on the received search criteria to extract properties that match the criteria; and a means for transmitting the search results to the borrower's terminal. This allows borrowers to quickly find their desired property. Furthermore, the server includes: a means for a real estate agent to upload property photos taken for on-site inspections, a means for analyzing the transmitted photos using a generative artificial intelligence model to calculate restoration costs, a means for automatically generating instructions for a contractor based on the calculated costs, a means for detecting a user's emotional state using an emotional state analysis engine to optimize system response, and a means for providing an interface using a smart device when registering and searching for property information at a physical store. This will streamline the intermediary's administrative work and also enable optimal responses that take into account the user's emotional state, improving the overall user experience.

[1593] A "lender" is a person or entity that owns the property and intends to rent it out.

[1594] "Lessee" means an individual or entity that intends to rent the property.

[1595] An "intermediary" is an individual or organization that acts as an intermediary between lenders and borrowers to facilitate transactions.

[1596] A "server" is a computer system for processing and managing data over a network.

[1597] A "generative AI model" is an artificial intelligence algorithm that has the ability to generate information from given data.

[1598] An "emotional state analysis engine" is an algorithm or device for analyzing a user's emotions and detecting their state.

[1599] A "smartphone" is a mobile device that has mobile communication capabilities and can run multifunctional applications.

[1600] A "head-mounted display" is a device worn on the head that displays information within the field of vision.

[1601] "Property photos" are images taken of the interior and exterior of a property.

[1602] A "drawing" is a blueprint that illustrates the layout and structure of a property.

[1603] "Property detailed information" is information that includes specific characteristics of the property, such as the size, layout, and facilities.

[1604] A "property database" is a database for systematically managing detailed information about properties.

[1605] The "registration completion notice" is a notice to inform the user that the property information has been successfully registered.

[1606] "Search criteria" refers to the conditions of the property desired by the borrower (e.g., number of rooms, location, age of building, etc.).

[1607] An "instruction document" is a document that instructs a specific task or procedure.

[1608] A "site inspection" is an investigation carried out by actually visiting a property to check its condition.

[1609] "Restoration costs" are the costs required to return the property to its original condition.

[1610] This invention provides a system that efficiently registers, searches, and manages property information by combining a generative AI model and an emotional state analysis engine. The following hardware and software are used to implement the invention.

[1611] Hardware used

[1612] server

[1613] Smartphone (e.g. iPhone, Android)

[1614] Head-mounted displays (e.g., Oculus Quest 2)

[1615] Software used

[1616] Generative AI model: OpenAI GPT-4

[1617] Emotional state analysis engine: Affectiva SDK

[1618] Database: Firebase, MySQL

[1619] Image analysis: Google Cloud Vision API

[1620] Specific Embodiments of the System

[1621] Lender manipulation

[1622] 1. The user (lender) uses their smartphone to take several photos and drawings of the property and upload them through the application.

[1623] 2. The terminal sends the uploaded property photos and drawings to the server.

[1624] 3. The server stores the received data and activates the generative AI model to automatically extract detailed property information (room size, layout, equipment status, etc.).

[1625] 4. The server registers the extracted property details in a database and analyzes the lender's emotional state using an emotional state analysis engine.

[1626] 5. Adjust the priority or content of property listings based on emotional state and notify lenders that property listings have been completed.

[1627] Example: When a lender sends photos and drawings of the living room, kitchen, bedroom, and bathroom via smartphone, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[1628] Borrower operations

[1629] 1. The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the application via a smartphone or head-mounted display.

[1630] 2. The device sends the search criteria to the server.

[1631] 3. Based on the search criteria received by the server, the generative AI model is activated to search the property database and extract properties that match the criteria.

[1632] 4. The server sends the extracted search results to the borrower's device, and the emotional state analysis engine analyzes the borrower's emotional state.

[1633] 5. Adjust the way search results are displayed or ordered based on emotional state, making them more intuitive for users.

[1634] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[1635] Intermediary manipulation

[1636] 1. The real estate agent uploads property photos taken for on-site inspections using their smartphone.

[1637] 2. The device sends the uploaded photos to the server.

[1638] 3. The server stores the received photos, launches a generative AI model to analyze the images, and automatically calculates the cost of restoration to the original state.

[1639] 4. The server automatically generates instructions for the construction company based on the calculated costs and analyzes the agent's emotional state using an emotional state analysis engine.

[1640] 5. Adjust the presentation of the calculation results based on the emotional state, generate instructions, and send them to the intermediary's terminal.

[1641] Example: When a broker uploads photos from a site inspection, the server analyzes the photos and calculates the cost of restoration. If the emotion engine determines that the broker is stressed, the results are displayed in a more concise and clear format.

[1642] Prompt Sentence Examples

[1643] "Please analyze photos and drawings of the property, automatically extract the room size, layout, and equipment status, and present detailed information. Also, please analyze the user's emotional state and provide an appropriate interface."

[1644] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1645] Step 1:

[1646] Lenders upload property photos and drawings

[1647] The user (lender) takes several photos and drawings of the property using their smartphone and uploads them through the application. The input data are the property photos and drawings, and the output data is sent to the server.

[1648] Step 2:

[1649] Submit property photos and drawings

[1650] The terminal sends the uploaded property photos and drawings to the server. The input data are the uploaded photos and drawings, and the purpose of the operation is to send them to the server.

[1651] Step 3:

[1652] The server receives and stores the data

[1653] The server stores the received property photos and drawings. The input is the photos and drawings sent from the terminal, and the output is that they are stored in the server.

[1654] Step 4:

[1655] Launch the generative AI model to extract property details

[1656] The server launches the generative AI model and analyzes the stored property photos and drawings. The input data are the photos and drawings stored on the server, and the property's size, layout, and equipment status are automatically extracted through data processing and calculation. The output is the extracted property details.

[1657] Step 5:

[1658] Register property details in the database

[1659] The server registers the extracted property details in a database. The input data is the property details from the generative AI model, and the output is the property information registered in the database.

[1660] Step 6:

[1661] Analyzing the emotional state of lenders with an emotion engine

[1662] The server uses an emotional state analysis engine to analyze the emotional state of the lender. The input is data indicating the emotional state of the lender, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[1663] Step 7:

[1664] Adjustment of property information registration priority or content

[1665] The server adjusts the registration priority or content of the property information based on the analyzed emotional state. The input is the analyzed emotional state and property detail information, and the adjusted property information is the output.

[1666] Step 8:

[1667] Send a notification that property information has been registered

[1668] The server notifies the lender that the property registration is complete. The input is the adjusted property information, and the output is a notification sent to the lender's terminal.

[1669] Step 9:

[1670] The borrower enters property search criteria

[1671] The user (renter) inputs the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) into the application via a smartphone or head-mounted display. The input data represents the renter's desired conditions, and the device then sends this to the server.

[1672] Step 10:

[1673] Send search criteria to the server

[1674] The terminal transmits the search criteria entered by the borrower to the server. The input data is the borrower's search criteria, and the data transmitted to the server is the output.

[1675] Step 11:

[1676] Generate property database and search with AI model

[1677] The server launches a generative AI model based on the received search criteria and searches the property database. The input data are the search criteria and the property database, and the output is a list of properties that match the criteria.

[1678] Step 12:

[1679] Send search results to the borrower's device

[1680] The server sends the search results to the borrower's terminal. The input data is a list of properties that match the conditions, and the output is the search results sent to the borrower's terminal.

[1681] Step 13:

[1682] Analyze the borrower's emotional state with an emotional state analysis engine

[1683] The server uses an emotional state analysis engine to analyze the emotional state of the borrower. The input data is data indicating the emotional state of the borrower, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[1684] Step 14:

[1685] Adjust how search results are displayed or ordered

[1686] The server adjusts the display method or order of the search results based on the analyzed emotional state, with the analyzed emotional state and the search results being the input and the adjusted display results being the output.

[1687] Step 15:

[1688] Agents upload property photos

[1689] The real estate agent uploads property photos taken for on-site inspections using a smartphone. The input data is the inspection photos, and the device sends them to the server.

[1690] Step 16:

[1691] Submit property photos

[1692] The terminal sends the uploaded property photos to the server. The input data is the uploaded survey photos, and the transmission to the server is the output.

[1693] Step 17:

[1694] Retention and analysis of submitted photos

[1695] The server launches the generative AI model, stores and analyzes the property photos sent to it. The input data are the uploaded survey photos, and the restoration costs are automatically calculated from the photos through data processing and calculation. The output is the calculated restoration costs.

[1696] Step 18:

[1697] Automatically generate instructions based on calculations of restoration costs

[1698] The server automatically generates instructions for the contractor based on the calculated restoration costs. The input data is the calculated restoration costs, and the output is the automatically generated instructions.

[1699] Step 19:

[1700] Analyzing the emotional state of intermediaries with an emotion engine

[1701] The server uses an emotional state analysis engine to analyze the emotional state of the intermediary. The input data is data indicating the emotional state of the intermediary, such as operation patterns and voice data, and the emotional state is detected through data processing and data calculation. The output is the analyzed emotional state.

[1702] Step 20:

[1703] Adjust the way the calculation results are presented and send instructions

[1704] The server adjusts the presentation method of the calculation result based on the analyzed emotional state and sends instructions to the intermediary terminal. The input is the analyzed emotional state and the generated instructions, and the adjusted instructions are sent to the intermediary terminal.

[1705] 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.

[1706] 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.

[1707] 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.

[1708] [Fourth embodiment]

[1709] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1710] 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.

[1711] 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).

[1712] 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.

[1713] 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.

[1714] 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).

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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."

[1722] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[1723] Lender Processing

[1724] 1. Users (lenders) can easily register property information.

[1725] The lender uses the terminal to upload several property photos and drawings.

[1726] The device sends the uploaded data to the server.

[1727] The server automatically analyzes the data it receives using a generated artificial intelligence model to extract detailed information about the property.

[1728] The extracted information is immediately registered in the property database by the server, and a notification of registration completion is sent to the lender's terminal.

[1729] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[1730] Borrower Processing

[1731] 2. Users (renters) can easily search for the property they want.

[1732] The tenant enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[1733] The terminal transmits the received search conditions to the server.

[1734] Based on the conditions received by the server, the property database is searched using a generated artificial intelligence model to extract properties that meet the conditions.

[1735] The server sends the search results to the borrower's terminal, where the borrower can check the detailed information.

[1736] Example: When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts properties that most closely match those conditions and sends the results in list format.

[1737] Intermediary Processing

[1738] 3. Users (intermediaries) can streamline various administrative tasks.

[1739] The real estate agent uploads property photos taken during on-site inspections from the terminal.

[1740] The device sends the uploaded photos to the server.

[1741] The server analyzes the received photos using a generated artificial intelligence model and automatically generates an estimate of the cost of restoring the property to its original condition.

[1742] The server creates instructions for the construction company based on the generated estimate and sends them to the intermediary's terminal.

[1743] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and automatically creates and sends instructions to the appropriate contractor based on that estimate.

[1744] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they are looking for, and agents can efficiently carry out their administrative work. This will promote the effective use of vacant houses and contribute to solving social problems.

[1745] The processing flow will be explained below.

[1746] Lender Processing

[1747] Step 1:

[1748] The user (lender) uses a terminal to select and upload several property photos and drawings.

[1749] Step 2:

[1750] The terminal sends the uploaded property photos and drawings to the server.

[1751] Step 3:

[1752] The server stores the received data and runs the generative AI model.

[1753] Step 4:

[1754] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[1755] Step 5:

[1756] The server registers the extracted property details in a database.

[1757] Step 6:

[1758] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[1759] Borrower Processing

[1760] Step 1:

[1761] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[1762] Step 2:

[1763] The terminal transmits the entered search conditions to the server.

[1764] Step 3:

[1765] The server stores the received search conditions and launches the generative AI model.

[1766] Step 4:

[1767] The generative AI model searches a property database and extracts properties that match the criteria.

[1768] Step 5:

[1769] The server sends the extracted search results to the user's (borrower's) terminal.

[1770] Step 6:

[1771] The user (borrower) views the search results on their device and checks the detailed information.

[1772] Intermediary Processing

[1773] Step 1:

[1774] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[1775] Step 2:

[1776] The device sends the uploaded photos to the server.

[1777] Step 3:

[1778] The server stores the received photos and runs the generative AI model.

[1779] Step 4:

[1780] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[1781] Step 5:

[1782] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[1783] Step 6:

[1784] The server sends the generated instructions to the user's (intermediary's) terminal.

[1785] Example 1

[1786] 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."

[1787] Conventional property information registration, search, and management systems lacked functionality to meet the different needs of each user, resulting in low efficiency in information registration and search. As a result, landlords could not easily register property information, tenants could not quickly search for the property they wanted, and real estate agents often suffered from inefficient administrative work. In addition, data accuracy and search precision were low, making it difficult to effectively utilize vacant homes.

[1788] 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.

[1789] In this invention, the server includes a means for a lender to provide property information by uploading several property photos and drawings, a means for a terminal to transmit the uploaded property photos and drawings to the server, and a means for the server to automatically analyze the property photos and drawings using a generative AI model, extract property details, and register them in a database. This enables a system that allows lenders to easily register property information, borrowers to efficiently search for properties, and agents to perform administrative tasks quickly and accurately.

[1790] A "lender" is an individual or legal entity that owns or manages a property and wishes to rent the property to others.

[1791] A "borrower" is an individual or corporation who wishes to rent a property, and is a user who wants to search for properties and find one that meets their requirements.

[1792] A "broker" is an individual or corporation that acts as an intermediary between the lender and the borrower in property transactions, and is a specialist that handles administrative tasks such as property inspections and contract procedures.

[1793] "Terminal" means an electronic device used by a lender, borrower, or intermediary to input, send, and receive information. Examples include smartphones and personal computers.

[1794] A "server" is a computer system that provides services over a network and is a central device that analyzes, registers, searches, and manages property information.

[1795] A "generative AI model" is a model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing.

[1796] "Property information" refers to detailed data about a property, including photographs, drawings, room size, facilities, floor plan, and other information.

[1797] A "database" is an electronic recording medium in which property information is organized and stored, and is a system for efficiently querying, adding, and updating data.

[1798] "Search conditions" are items that indicate the characteristics and requirements of the property desired by the tenant, and examples include floor plan, location, age of the building, etc.

[1799] "Search results" are generated by the server by querying a property database based on search criteria and generating a list of properties that match the criteria.

[1800] "Restoration costs" are the costs required to return the property to its original condition, and are calculated based on information obtained by the real estate agent during an on-site inspection.

[1801] An "instruction sheet" is a document generated by the server that clearly states the details and costs of restoration to the original state and requests the contractor to carry out the work.

[1802] This invention is a system that utilizes generative AI models to efficiently register, search, and manage information on vacant properties. This system provides functions that meet the needs of three parties: landlords, tenants, and real estate agents.

[1803] Hardware and software used

[1804] Hardware:

[1805] Terminal: An electronic device used by a user to input, send, and receive information. Examples include smartphones and personal computers.

[1806] Server: A computer system that provides services over a network and is the central device that analyzes, registers, searches, and manages property information.

[1807] software:

[1808] Generative AI model: A model that uses artificial intelligence and is an algorithm that learns from large amounts of data to automatically process specific tasks. Specific examples include models that perform image analysis and natural language processing (e.g., OpenAI GPT-4).

[1809] Database: An electronic recording medium in which property information is organized and stored, and a system for efficiently querying, adding, and updating data (e.g., database software such as MySQL).

[1810] Lender Operation Flow

[1811] 1. User (lender) property information registration

[1812] The lender uploads property photos and drawings using a terminal, which then sends the uploaded data to the server, which then receives it.

[1813] 2. Data analysis and registration by the server

[1814] The server uses a generative AI model to automatically analyze the uploaded photos and drawings and extract detailed property information. This information is immediately registered in a database. The server then sends a notification to the lender that the property information has been registered.

[1815] Borrower Operation Flow

[1816] 1. User (borrower) enters property search criteria

[1817] The renter enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) into the terminal and sends them to the server.

[1818] 2. Conditional search by server and sending results

[1819] The server uses the generative AI model to search the property database based on the received search criteria and extracts properties that match the criteria. The search results are sent to the borrower's device, where they can view the results and check detailed information.

[1820] Intermediary operation flow

[1821] 1. User (agent) uploads property photos

[1822] The real estate agent uploads property photos taken for on-site inspections from the terminal, which then sends them to the server.

[1823] 2. Photo analysis and quotation generation by the server

[1824] The server analyzes the received photos using a generative AI model to calculate the cost of restoration to the original state, then automatically generates instructions for the contractor based on the calculated cost and sends them to the intermediary.

[1825] Examples of concrete examples and prompts

[1826] Examples of lenders include:

[1827] When a landlord uploads photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database.

[1828] Example prompt sentence:

[1829] Upload photos and drawings of your living room, kitchen, bedroom and bathroom to extract property details and add them to our database.

[1830] Examples of borrowers:

[1831] When a renter enters and submits the conditions "2LDK, 5-minute walk from the station, new building," the server extracts the properties that most closely match those conditions and sends the results in list format.

[1832] Example prompt sentence:

[1833] Search for properties that meet your criteria: 2LDK, 5-minute walk from the station, newly built.

[1834] Examples of intermediaries include:

[1835] When a real estate agent uploads photos from their on-site inspection, the server analyzes the photos to calculate the cost of restoring the property to its original condition, and then automatically creates and sends instructions to the appropriate contractor based on that estimate.

[1836] Example prompt sentence:

[1837] Upload site inspection photos to generate restoration cost estimates and create instructions for contractors.

[1838] This system allows landlords to easily register property information, tenants to quickly search for the property they want, and agents to efficiently carry out their administrative work. As a result, it is expected that the effective use of vacant houses will be promoted, contributing to the solution of social issues.

[1839] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1840] Lender Processing

[1841] Step 1:

[1842] The user opens the property information registration screen

[1843] Input: Access to property information registration screen

[1844] Operation: The user operates the device to open the property information registration screen. The screen that appears contains an interface for uploading property photos and drawings.

[1845] Output: The property information registration screen will be displayed on the terminal.

[1846] Step 2:

[1847] Users select and upload property photos and drawings

[1848] Input: Selected property photos and drawings

[1849] How it works: A user uses their device to select property photos and drawings and clicks the upload button.

[1850] Output: The selected data is temporarily saved on the device.

[1851] Step 3:

[1852] The device sends the data to the server

[1853] Input: Uploaded property photos and drawing data

[1854] Operation: The device sends the selected property photos and drawing data to the server in a batch process. The progress of the transfer is displayed to the user in real time.

[1855] Output: Property photos and drawing data are sent to the server.

[1856] Step 4:

[1857] The server analyzes the data

[1858] Input: Property photos and drawing data submitted

[1859] How it works: The server launches the generative AI model and analyzes the data sent. The generative AI model extracts detailed property information (e.g., room size, facilities, and layout) from the image.

[1860] Output: Detailed property information extracted by analysis

[1861] Step 5:

[1862] The server registers the property information in the database

[1863] Input: Extracted property details

[1864] Operation: The server converts the generated property details into a standard format and records them in a database.

[1865] Output: Property details are registered in the database.

[1866] Step 6:

[1867] The server sends a notification to the user that registration is complete.

[1868] Input: Notification information for registration completion

[1869] Operation: The server creates a registration completion notification and sends it to the user's terminal.

[1870] Output: The device receives the notification and displays it to the user.

[1871] Borrower Processing

[1872] Step 1:

[1873] The user enters property search criteria

[1874] Input: Property search criteria (e.g. 2LDK, 5-minute walk from station, new construction)

[1875] Operation: The user operates the device, opens the property search screen, enters the conditions, and clicks the search button.

[1876] Output: The entered search criteria are temporarily saved on the device.

[1877] Step 2:

[1878] The device sends the search criteria to the server.

[1879] Input: Entered search criteria

[1880] Operation: The device sends search criteria to the server.

[1881] Output: The search criteria is sent to the server.

[1882] Step 3:

[1883] The server searches the property database based on the criteria

[1884] Input: Search criteria

[1885] How it works: The server uses the generated AI model to search the property database and extract properties that match the criteria.

[1886] Output: A list of properties that match the criteria

[1887] Step 4:

[1888] The server sends the search results to the user

[1889] Input: List of properties that match your criteria

[1890] How it works: The server formats the search results into a list and sends it to the user's device.

[1891] Output: The search result list is sent to the terminal and displayed to the user.

[1892] Intermediary Processing

[1893] Step 1:

[1894] Users upload field survey photos

[1895] Input: Photos taken during field survey

[1896] Action: The user operates the device, selects a property photo, and clicks the upload button.

[1897] Output: The selected photos are temporarily saved on your device.

[1898] Step 2:

[1899] The device sends the photo data to the server.

[1900] Input: Selected photo data

[1901] How it works: The device sends batches of photo data to the server. The progress of the transfer is displayed to the user in real time.

[1902] Output: The photo data is sent to the server.

[1903] Step 3:

[1904] The server analyzes the photo

[1905] Input: Submitted photo data

[1906] How it works: The server launches a generative AI model and analyzes the photo data. The generative AI model estimates the need for restoration and the cost.

[1907] Output: Estimated restoration costs

[1908] Step 4:

[1909] The server generates instructions based on the estimate.

[1910] Input: Estimated restoration costs

[1911] How it works: The server automatically generates detailed instructions for the contractor based on the estimate.

[1912] Output: Instructions are generated.

[1913] Step 5:

[1914] The server sends instructions to the user

[1915] Input: Generated instructions

[1916] How it works: The server sends instructions to the user's device, allowing for subsequent approval or modification.

[1917] Output: The terminal receives the instructions and displays them to the user.

[1918] (Application example 1)

[1919] 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."

[1920] Conventional property information registration and management systems have faced challenges such as the need for manual input and ensuring the accuracy of information. It is also difficult to efficiently register and search detailed information about vacant houses and brick-and-mortar stores, and the time and effort required for cost estimates based on on-site surveys and instructions to construction companies is particularly significant. This has hindered the effective utilization of vacant houses and brick-and-mortar stores, causing social problems.

[1921] 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.

[1922] In this invention, the server includes: a means for a lender to upload several property information photos and drawings to provide property information; a means for the server to automatically analyze the uploaded photos and drawings using a generative AI model and extract detailed property information; a means for the server to register the extracted detailed property information in a database; a means for a borrower to input property search conditions and send them to the server; a means for the server to search the database using a generative AI model based on the received search conditions and extract properties that match the conditions; a means for the server to send the search results to the borrower's terminal; a means for a real estate agent to upload photos taken for on-site inspection and send them to the server; and a means for the server to analyze the sent photos using a generative AI model and calculate restoration costs. The system includes a means for uploading store information and store search criteria to the server, a means for the server to automatically generate instructions to a construction company based on the calculated costs, a means for a store manager to provide store information by uploading store information photos and layouts, a means for a tenant to input store search criteria and send them to the server, a means for the server to search a database using a generative AI model based on the received search criteria and extract stores that match the criteria, a means for the server to send the store search results to the tenant's terminal, a means for a real estate agent to upload store photos taken for on-site inspections and send them to the server, a means for the server to analyze the sent photos using a generative AI model and calculate the cost of restoring the store to its original condition, and a means for the server to automatically generate instructions to a construction company based on the calculated costs. This enables efficient and accurate registration, search, and management of property and store information, as well as rapid estimation of restoration costs.

[1923] A "lender" is the person or entity that owns the property or store and provides the information.

[1924] "Property information" is data showing details of a property, such as photos and drawings of the property.

[1925] A "server" is a computer system that stores and manages data.

[1926] A "generative AI model" is an artificial intelligence model trained based on large amounts of data, and is a technology that analyzes and generates data.

[1927] "Property details" refers to information extracted using a generative AI model, including detailed attributes and features of the property.

[1928] A "database" is a collection of organized data, a place where property information and store information are stored.

[1929] A "lessee" is a person or entity wishing to use the property or business.

[1930] "Property search conditions" are information that specifies the characteristics and conditions of the property or store desired by the borrower.

[1931] An "intermediary" is a person or organization that acts as an intermediary between a lender and a borrower for the sale of a property or store.

[1932] A "site inspection" is an investigation carried out to check the actual condition of a property or store.

[1933] "Restoration costs" are the costs required to return a property or store to its original condition.

[1934] A "contractor" is a person or organization that carries out construction or repairs on a property or business.

[1935] "Store information" is data that shows details of the store, such as photos and layout of the physical store.

[1936] A "tenant" is a person or organization that rents a store or property for use.

[1937] This system was developed to support lenders, borrowers, real estate agents, and store managers in efficiently registering, searching, and managing property and store information, estimating restoration costs, and generating instructions for construction companies. A specific embodiment is shown below.

[1938] Lender and brick-and-mortar store manager operations

[1939] Lenders or store managers upload several property information photos and drawings, or store information photos and layouts, from their smartphones, PCs, or other devices. The uploaded data is sent to a server, which automatically analyzes the data using a generative AI model. From this analysis, detailed information about the property or store is extracted and registered in a property information database.

[1940] Borrower and Tenant Operations

[1941] Renters and tenants enter search criteria for the desired property or store on their device and send them to the server. The server uses a generative AI model to search the property information database based on the received search criteria and extracts properties or stores that match the criteria. The server then sends the search results to the renter or tenant's device, where they can check detailed information.

[1942] Intermediary manipulation

[1943] The real estate agent uploads photos of the property or store taken for on-site inspections from their device. The uploaded photos are sent to a server, which analyzes them using a generative AI model and calculates the cost of restoration to the original state. The server then automatically generates instructions for the contractor based on the calculated costs and sends the instructions to the real estate agent's device as needed.

[1944] Hardware and software used

[1945] The hardware used includes smartphones, PCs, and servers. The smartphones and PCs are used by landlords, borrowers, brokers, brick-and-mortar store managers, and tenants to upload data and enter search criteria. The servers are responsible for analyzing and storing the data, and automatically analyze the input data using generative AI models.

[1946] The software used is the openai library for implementing the generative AI model, and PIL (Python Imaging Library) for image processing.

[1947] Examples of concrete examples and prompts

[1948] Examples of lenders and brick-and-mortar managers

[1949] When renters submit photos of their living rooms, kitchens, bedrooms, and bathrooms, the server automatically analyzes them and registers the room sizes and facilities in the database. Similarly, physical store managers submit photos and layouts of their stores, and store details are registered in the database.

[1950] Example prompt: "This is a photo of the living area of ​​a store. Can you give me more information about this store?"

[1951] Examples of intermediaries

[1952] When the agent uploads photos from the on-site inspection, the server analyzes the photos, calculates the cost of restoring the property to its original condition, and automatically creates and sends instructions to the contractor.

[1953] Sample prompt: "These are photos of a store for a site inspection. Please estimate the cost of restoring it to its original condition."

[1954] This enables efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[1955] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1956] Step 1:

[1957] The lender or the manager of the brick-and-mortar store uploads several property information photos and drawings, or store information photos and layout, from a smartphone or PC. The entered photos and drawings are sent to the server via the data upload function, which provides the server with basic information about the property or store.

[1958] Step 2:

[1959] The server automatically analyzes the uploaded property information photos and drawings, or store information photos and layouts, using a generative AI model. The AI ​​model analyzes the images using an image processing library (e.g., PIL) and extracts detailed information such as room size, facilities, and layout information. The extracted information is converted into structured data. The input for this step is the uploaded image data, and the output is the extracted property and store details.

[1960] Step 3:

[1961] The server registers the extracted property and store details in a property information database. Using the database registration function, the structured data is efficiently stored in the database, making it easier to store the information and to search and view it later.

[1962] Step 4:

[1963] The borrower or tenant enters search criteria for the desired property or store on a terminal and sends them to the server. The entered search criteria are transmitted to the server via the database query function, and the information search is then ready.

[1964] Step 5:

[1965] The server uses the generative AI model to search the property information database based on the received search criteria. It uses the AI ​​model and database query function to extract properties and stores that match the search criteria. The input for this step is the search criteria, and the output is a list of properties and stores that match the criteria.

[1966] Step 6:

[1967] The server sends the search results to the borrower's or tenant's terminal. The server uses the search result sending function to provide detailed information on properties or stores that match the criteria to the user's terminal. This allows the user to check the selected search results.

[1968] Step 7:

[1969] The real estate agent uploads property or store photos taken for on-site inspections from their device and sends them to the server, which provides the data from the on-site inspection to the server for subsequent analysis.

[1970] Step 8:

[1971] The server analyzes the submitted on-site inspection photos using a generation AI model to calculate the cost of restoration to the original state. The AI ​​model uses an image processing library to determine the level of damage in the photos and the need for repairs, and generates the calculated cost as data.

[1972] Step 9:

[1973] The server automatically generates instructions for the contractor based on the calculated restoration costs. Using the instruction generation function, the server creates instructions including the necessary work areas and cost estimates and sends them to the contractor.

[1974] These processing steps enable efficient and accurate registration, search, and management of property and store information, as well as quick estimation of restoration costs.

[1975] 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.

[1976] This invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage vacant property information. This system provides functions that meet the needs of three parties: landlords, tenants, and agents, and further analyzes the user's emotional state to optimize the system's response.

[1977] Lender Processing

[1978] 1. Users (lenders) can easily register property information.

[1979] The lender uses the terminal to select and upload several property photos and drawings.

[1980] The terminal sends the uploaded property photos and drawings to the server.

[1981] The server stores the received data and runs the generative AI model.

[1982] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[1983] The server registers the extracted property details in a database.

[1984] The emotional engine analyzes the emotional state of the lender and adjusts the registration priority or content of the property information based on the emotional state.

[1985] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[1986] Example: When a lender submits photos and drawings of the living room, kitchen, bedroom, and bathroom, the server automatically analyzes them and registers the room size and facilities in a database. If the emotion engine determines that the lender is emotionally tense, it will take action such as sending an early registration completion notification.

[1987] Borrower Processing

[1988] 2. Users (renters) can easily search for the property they want.

[1989] Renters enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new building) on ​​the terminal.

[1990] The terminal transmits the entered search conditions to the server.

[1991] The server stores the received search conditions and launches the generative AI model.

[1992] The generative AI model searches a property database and extracts properties that match the criteria.

[1993] The server sends the extracted search results to the user's (borrower's) terminal.

[1994] An emotional engine analyzes the borrower's emotional state and adjusts how search results are displayed or ordered.

[1995] The user (borrower) views the search results on their device and checks detailed information.

[1996] Example: When a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria and sends the results in list form. If the emotion engine determines that the borrower is increasingly interested, it highlights the properties.

[1997] Intermediary Processing

[1998] 3. Users (intermediaries) can streamline various administrative tasks.

[1999] The real estate agent uploads property photos taken for on-site inspections from the terminal.

[2000] The device sends the uploaded photos to the server.

[2001] The server stores the received photos and runs the generative AI model.

[2002] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[2003] An emotion engine analyzes the emotional state of the intermediary and adjusts the presentation or content of the calculated fees.

[2004] Based on the estimate generated by the server, instructions are automatically generated for the contractor.

[2005] The server sends the generated instructions to the user's (intermediary's) terminal.

[2006] Example: When a real estate agent uploads photos from a site inspection, the server analyzes the photos to calculate the cost of restoration, and if the emotion engine determines that the real estate agent is under high stress, the results are displayed in a more concise and clear format.

[2007] Through these operations, the system provides an environment in which landlords can easily register property information, tenants can quickly search for the property they want, and agents can efficiently carry out their administrative work. Furthermore, by taking into account the user's emotional state, it is possible to respond optimally to individual needs, improving the overall user experience. This will promote the effective use of vacant houses and contribute to solving social problems.

[2008] The processing flow will be explained below.

[2009] Lender Processing

[2010] Step 1:

[2011] The user (lender) uses the terminal to select and upload property photos and drawings.

[2012] Step 2:

[2013] The terminal sends the uploaded property photos and drawings to the server.

[2014] Step 3:

[2015] The server receives the transmitted data and activates the generative AI model.

[2016] Step 4:

[2017] The generative AI model analyzes property photos and drawings and automatically extracts detailed property information such as room size, layout, and equipment status.

[2018] Step 5:

[2019] The server registers the extracted property details in a database.

[2020] Step 6:

[2021] The server runs an emotion engine to analyze the emotional state of the lender.

[2022] Step 7:

[2023] An emotion engine adjusts the listing priority or content of property information based on the emotional state of the lender.

[2024] Step 8:

[2025] The server sends a notification of completion of property information registration to the user's (lender's) terminal.

[2026] Borrower Processing

[2027] Step 1:

[2028] The user (renter) enters the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) on the terminal.

[2029] Step 2:

[2030] The terminal transmits the entered search conditions to the server.

[2031] Step 3:

[2032] The server stores the received search conditions and launches the generative AI model.

[2033] Step 4:

[2034] The generative AI model searches a property database and extracts properties that match the criteria.

[2035] Step 5:

[2036] The server sends the extracted search results to the user's (borrower's) terminal.

[2037] Step 6:

[2038] The server activates an emotion engine to analyze the borrower's emotional state.

[2039] Step 7:

[2040] An emotional engine adjusts the display or order of search results based on the borrower's emotional state.

[2041] Step 8:

[2042] The user (borrower) views the search results on their device and checks the detailed information.

[2043] Intermediary Processing

[2044] Step 1:

[2045] The user (agent) uploads property photos taken for on-site inspection from the terminal.

[2046] Step 2:

[2047] The device sends the uploaded photos to the server.

[2048] Step 3:

[2049] The server stores the received photos and runs the generative AI model.

[2050] Step 4:

[2051] The generative AI model analyzes the images and automatically calculates an estimate of restoration costs.

[2052] Step 5:

[2053] Based on the calculated estimate, the server automatically generates instructions for the construction company.

[2054] Step 6:

[2055] The server sends the generated quote to the user's (intermediary's) terminal.

[2056] Step 7:

[2057] The server activates an emotion engine to analyze the emotional state of the agent.

[2058] Step 8:

[2059] An emotion engine adjusts the presentation or content of the calculation results based on the emotional state of the intermediary.

[2060] Step 9:

[2061] The server sends the generated instructions to the construction company's terminal.

[2062] This allows the emotion engine to be used to optimally respond to the user's emotional state, improving the overall user experience.

[2063] Example 2

[2064] 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."

[2065] The problem is that the registration, search, and management of vacant house property information is complicated, time-consuming, and labor-intensive. Furthermore, the system response is not optimized to take into account the user's emotional state, making it difficult to improve the user experience. It is necessary to solve these issues and promote the effective utilization of vacant houses.

[2066] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically analyzing property images and blueprints uploaded by a lender using a generative AI model to extract property detailed information, means for searching a property data storage device using the generative AI model based on received search conditions to extract properties that match the conditions, and emotion engine means for analyzing the user's emotional state and adjusting the registration priority or content based on the emotional state. This enables efficient registration, search, and management of property information and optimal responses according to the user's emotional state, thereby improving the overall user experience.

[2067] A "lender" is a person who owns real estate property or who acts on behalf of the owner and who intends to rent out the property.

[2068] A "borrower" is a person who wishes to rent a real estate property, searches for information about the property, and wishes to enter into a contract.

[2069] An "intermediary" is a person who acts as an intermediary between a lender and a borrower, introducing properties and facilitating the contract procedures.

[2070] "Property images" are photographs or drawings showing the exterior and interior of a real estate property, and are visual information for understanding the details of the property.

[2071] A "blueprint" is a drawing that shows the floor plan and layout of a real estate property, and specifically represents the structure and dimensions of the property.

[2072] A "generative AI model" is a model that uses artificial intelligence technology to analyze and predict data, and is trained using machine learning algorithms.

[2073] A "server" is a computer system that processes, stores, and analyzes data and provides services to other devices over a network.

[2074] A "data storage device" is a device for storing information physically or electronically, such as a database or file storage device.

[2075] An "emotion engine" is a software component that analyzes the user's emotional state from their voice or text and adjusts the system's behavior.

[2076] "Registration priority" is an index that indicates the priority of property information registration work, and is a criterion for the system to perform registration work efficiently.

[2077] "Property details" refers to information that indicates specific attributes such as the size, layout, and facilities of the property, and is data necessary to understand the characteristics of the property.

[2078] "Search conditions" are conditions that specify the attributes of the property desired by the borrower, and include specific requirements such as the type of property, size, and location.

[2079] "Restoration costs" are the costs necessary to return the property to its original condition after the tenant moves out, including repairs, cleaning, etc.

[2080] A "construction contractor" is a professional contractor that repairs, renovates, cleans, etc. real estate properties and carries out restoration work to their original condition.

[2081] An "instruction sheet" is a document that instructs a specific task and indicates the specific work content and costs to the contractor.

[2082] The present invention is a system that combines a generative AI model and an emotion engine to efficiently register, search, and manage property information for vacant homes. Specific embodiments of this system are described below.

[2083] The system is used by three parties: lenders, borrowers, and intermediaries, and provides functions tailored to the needs of each user. The system's main hardware includes servers, terminals, and data storage devices. The system's main software includes generative AI models, emotion engines, and user interfaces.

[2084] Lender Processing

[2085] Lenders register property information via their devices. They upload photos and blueprints of the property, which are then received by the server. Specific photos and blueprints are selected via a smartphone app or web app, and the server then clicks the upload button. The server then sends this data to the generative AI model, which automatically extracts detailed property information. During this process, the generative AI model uses image processing algorithms to identify detailed information such as the property's size, layout, and amenities.

[2086] For example, when a lender uploads photos of their living room, kitchen, bedroom, and bathroom, the server passes them to the generative AI model, and records the size and characteristics of each room in a data storage device. During this process, the emotion engine analyzes the lender's emotional state, and if it determines that the lender is tense, it will respond by quickly sending a registration completion notification.

[2087] Example prompt sentence:

[2088] "Analyze photos of the living room, kitchen, bedroom, and bathroom."

[2089] Borrower Processing

[2090] The borrower conducts a property search through their device. They enter the desired property conditions (e.g., 2LDK, 5-minute walk from the station, new construction) and click the search button. The device sends the search conditions to the server, which then activates the generative AI model and searches for information in the property data storage device. The search results are sent from the server to the borrower's device, where they can be viewed. The emotion engine adjusts the way the search results are displayed, and in some cases, highlights them.

[2091] For example, if a borrower enters and submits the criteria "2LDK, 5-minute walk from the station, new construction," the server extracts properties that most closely match those criteria, generates a list, and sends it to the terminal. If the emotion engine determines that the borrower is increasingly interested, it highlights the search results and displays them.

[2092] Example prompt sentence:

[2093] "Search for a newly built property with a 2LDK, 5-minute walk from the station."

[2094] Intermediary Processing

[2095] Real estate agents can upload property images for on-site inspections to streamline their administrative work. When photos of inspected properties are uploaded from a device, the server receives them and performs image analysis using a generative AI model. As a result of the analysis, the cost of restoration to the original state is calculated, and instructions to the construction company are automatically generated based on that cost. The emotion engine analyzes the emotional state of the agent and adjusts the display of the results as necessary.

[2096] For example, if a real estate agent uploads photos of damage to a property, the server analyzes them and calculates the cost of repairs. If the emotion engine analyzes the agent's emotional state and determines that they are stressed, it displays the results in a concise and clear format.

[2097] Example prompt sentence:

[2098] Please estimate the cost of restoration from this photo.

[2099] These processes will enable landlords to easily register property information, tenants to quickly search for the property they desire, and real estate agents to efficiently perform their administrative tasks. It will also enable responses that take into account the user's emotional state, improving the overall user experience. This will promote the effective use of vacant homes and contribute to solving social problems.

[2100] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2101] Lender property information registration processing

[2102] Step 1:

[2103] The user selects property photos and blueprints using the terminal and clicks the upload button. The input is the property photos and blueprints, and the output is that these files are sent from the terminal to the server.

[2104] Step 2:

[2105] The terminal sends the uploaded file to the server. Specifically, the terminal sends an HTTP POST request to the server, with the input being the selected property photo and blueprint, and the output being the file being saved on the server.

[2106] Step 3:

[2107] The server saves the received file in storage and launches the generative AI model. The input is the uploaded file, and the output is the invocation of the generative AI model's interface. Specifically, the server saves the file in cloud storage (e.g., AWS S3) and triggers the execution of the generative AI model (e.g., TensorFlow).

[2108] Step 4:

[2109] The generative AI model analyzes property photos and blueprints to automatically extract property details such as size, layout, and equipment status. The input is the saved property photos and blueprints, and the output is the extracted property details. Specifically, the generative AI model identifies information and extracts data through image processing algorithms.

[2110] Step 5:

[2111] The server registers the extracted property details in a database. The input is the property details, and the output is to register them in a database. Specifically, the server executes an SQL query to insert the information into a database (e.g. MySQL).

[2112] Step 6:

[2113] The emotion engine analyzes the emotional state of the lender and adjusts the registration priority or content based on the emotional state. The input is the lender's emotional information, and the output is the adjusted registration priority or content. Specifically, it uses NLP technology (e.g., BERT) to analyze the user's emotional state.

[2114] Step 7:

[2115] The server sends a notification to the user's device that the property information has bee...

Claims

1. A means for lenders to provide property information by uploading several property photos and drawings; A server automatically analyzes the uploaded property photos and drawings using a generating artificial intelligence model to extract detailed property information; A means for the server to register the extracted property detail information in a database; A means for a borrower to input property search conditions and transmit them to a server; A server searches a property database using a generated artificial intelligence model based on the received search conditions and extracts properties that match the conditions; A means for the server to transmit the search results to the borrower's terminal; A means for real estate agents to upload property photos taken for on-site inspections and send them to the server; A server analyzes the transmitted photograph using a generative artificial intelligence model and calculates the cost of restoration to the original state; A means for the server to automatically generate instructions to a construction company based on the calculated costs; A system including:

2. The system according to claim 1 , further comprising means for the lender to receive a notification that the property information has been registered.

3. 2. The system according to claim 1, further comprising means for the borrower to view search results from the server and check detailed information.

Images