system

Abstract

Provide a system. [Solution] means for automatically collecting real estate data from publicly available databases; A method to predict fair prices using collected real estate data and an AI model; a means for visually displaying the predicted fair price; A means to send push notifications of property information that matches the conditions of the desired rental area, A system including:

Description

[Technical Field]

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

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

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

[0004] In real estate transactions, individual owners and investors find it difficult to gather information to determine the appropriate price, making it particularly difficult for ordinary consumers without specialized knowledge. Furthermore, pricing of rental properties and rent revisions at the time of lease renewal often fail to adapt to market fluctuations. This creates inefficiencies in real estate transactions and hinders market revitalization. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, it includes a means for automatically collecting real estate data from a public database. This means makes it possible to efficiently obtain the latest market data. Next, it includes a means for analyzing the collected real estate data using a generative AI model and predicting fair prices. This enables highly accurate price predictions based on past trends and current market conditions. Furthermore, it includes a means for visually displaying the predicted fair prices, allowing users to intuitively check the property valuation. Finally, it provides a means for sending push notifications of property information that matches the desired rental area conditions, allowing users to receive useful information in real time. With the above means, it realizes a system that enables individual owners and investors to efficiently conduct real estate transactions and promotes market revitalization.

[0006] "Real estate data" refers to a collection of information about real estate, including detailed information such as the property's address, price, area, age, and surrounding facilities.

[0007] "Public database" means a publicly accessible database and system storing real estate-related information that is available without specific authentication.

[0008] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to analyze data, recognize patterns, and make future predictions.

[0009] "Fair price" refers to the price arrived at as a result of an objective and fair assessment of the market value of a property.

[0010] "Visually displaying" means providing information to users in a format that is easy to understand visually, such as graphs and charts, in addition to text.

[0011] "Push notification" refers to a technology that sends information directly to a user's device in real time, notifying them at the required time.

[0012] The "desired rental area" refers to the geographical range designated by the user as the desired area for rental properties. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention is a system for predicting the fair price of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following describes an embodiment of the present invention.

[0035] This system is mainly composed of three entities: a server, a terminal, and a user.

[0036] Data collection

[0037] Step 1: Collect real estate data from publicly available databases.

[0038] The server accesses databases containing publicly available real estate information (e.g., public land price data, social media trend data, property information from real estate companies, etc.) and automatically collects real estate data.

[0039] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[0040] Step 2: Cleanse the data you get.

[0041] The server filters out duplicate and inaccurate data to ensure data quality.

[0042] Data analysis

[0043] Step 3: Use a generative AI model to predict the fair price.

[0044] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[0045] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[0046] Step 4: Save the prediction results

[0047] The server stores the fair prices predicted by the generative AI model in a database.

[0048] User Interface

[0049] Step 5: Upload your property

[0050] The user uploads a property photo using a device, for example, by selecting a property photo from a smartphone or PC and clicking the upload button.

[0051] Step 6: Automatic information extraction

[0052] The server automatically extracts property information from these photos, using image analysis algorithms to extract features such as floor plan and age of the building, and stores them in a database.

[0053] Step 7: Visualize the information

[0054] The device can visually display information about the property's fair value and surrounding market prices to the user, for example by generating interactive charts and graphs and displaying them on the device's UI.

[0055] Pricing & Notifications

[0056] Step 8: Set and update rents

[0057] The server proposes appropriate rent revisions when a rental contract is renewed, and proposes rent increases or maintenance based on the desired rental area set by the user.

[0058] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[0059] Step 9: Push Notifications

[0060] Property information that matches the desired rental area conditions set by the user will be sent via push notification.

[0061] The server extracts matching property information in real time and notifies the user's terminal.

[0062] This system allows users to easily upload property information, receive highly accurate fair price assessments using generative AI models, and intuitively confirm the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications. This is expected to enable individual owners and investors to enter the real estate market more rationally and efficiently, stimulating the market.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[0066] Step 2:

[0067] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[0068] Step 3:

[0069] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[0070] Step 4:

[0071] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[0072] Step 5:

[0073] The server stores the predicted fair prices in a database.

[0074] Step 6:

[0075] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[0076] Step 7:

[0077] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[0078] Step 8:

[0079] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0080] Step 9:

[0081] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[0082] Step 10:

[0083] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0084] Example 1

[0085] 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."

[0086] The purpose of this invention is to provide efficient and accurate price predictions in real estate transactions, enabling individual owners and investors to enter the market more rationally. By accurately predicting the fair price of real estate and providing intuitive information to users, the invention also enables efficient real estate transactions by proposing appropriate rent revisions and providing real-time notifications of property information that matches the user's conditions.

[0087] 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.

[0088] In this invention, the server includes means for automatically collecting real estate data from a public database, means for performing data cleansing on the collected real estate data and filtering out duplicate and inaccurate data to ensure data quality, means for predicting a fair price using the collected real estate data with a generative AI model, means for saving the predicted fair price in a database, means for having a user upload photos of property information and automatically extracting property information from the photos using an image analysis algorithm, means for saving the extracted property information in a database, means for visually displaying the predicted fair price, means for proposing a fair rent revision when renewing a rental contract, and means for sending push notifications of property information that matches the conditions of the desired rental area. This allows users to easily upload property information, receive highly accurate price evaluations from the generative AI model, and conduct real estate transactions efficiently and intuitively.

[0089] A "publicly accessible database" is a collection of information that is made available in a publicly accessible form and that includes real estate data.

[0090] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0091] "Data cleansing" is a process for removing duplicate data and inaccurate data from collected data and ensuring the quality of the data.

[0092] A "generative AI model" is an artificial intelligence model trained using historical data to predict the fair value of a property.

[0093] A "fair price" is a price that is fair and in line with market value, calculated based on market conditions and past trends.

[0094] A "database" is an information management system for efficiently storing and managing large amounts of data.

[0095] "Image analysis algorithm" refers to a computational method for extracting specific information or features from image data.

[0096] A "visual display" is a method of presenting data or information to a user in a visual form, such as a graph or chart.

[0097] "Rent revision" is the process of reevaluating and proposing an appropriate rent when renewing a rental property contract.

[0098] "Push notification" is a mechanism that sends new information that matches certain conditions to a user's device in real time.

[0099] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system is mainly composed of three entities: a server, a terminal, and a user.

[0100] Data collection

[0101] The server automatically collects real estate data from publicly available databases. These databases include, for example, public land price data, social media trend data, and property information from real estate companies. The server automatically collects data from each database using a Python scraping library (e.g., BeautifulSoup or Scrapy). If an API is provided, the server uses the requests library to send queries to the API and retrieve data in JSON format.

[0102] Data Cleansing

[0103] The server then cleanses the collected data, a process that uses the Pandas library to filter out duplicates and inaccurate data and ensure data quality. The cleansed data is then stored in a standardized format, ready to be fed into generative AI models.

[0104] Fair price forecast

[0105] The server uses the cleansed data to predict the fair price using a generative AI model. This generative AI model is built using TENSORFLOW (registered trademark) and PyTorch and is trained based on past transaction data. This allows for highly accurate prediction of the fair price for each property. The performance of the generative AI model is evaluated using cross-validation and test data, and measures are taken to prevent overfitting.

[0106] Saving prediction results

[0107] The predicted fair prices are stored in a database by the server. This database uses a relational database such as MySQL (registered trademark) or PostgreSQL, which enables efficient storage and management of prediction results.

[0108] Property information upload and automatic information extraction

[0109] Users upload property photos using their devices (e.g., smartphones or PCs). These photos are temporarily stored in cloud storage (e.g., AWS (registered trademark) S3), and the URL is sent to the server. The server then runs image analysis algorithms using OpenCV or TensorFlow to automatically extract property information (e.g., floor plan, age) from the photos and store it in a database.

[0110] Information Visualization

[0111] The terminal uses D3.js and Chart.js to generate interactive charts and graphs, visually displaying information on the property's fair value and surrounding market price, allowing users to intuitively understand the property's value.

[0112] Rent setting and push notifications

[0113] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, by using Python's Sched library to schedule periodic rent evaluations, it can send notifications proposing new rents to users. It also detects property information that matches the conditions set by the user in real time and sends it to the device using a push notification service such as Firebase or OneSignal. This allows users to receive new property information promptly.

[0114] Examples of concrete examples and prompts

[0115] As a specific example, for a user looking for a 2LDK apartment in Shibuya Ward, Tokyo, the system works as follows:

[0116] 1. The user uploads a photo of a 2LDK apartment in Shibuya Ward from their device.

[0117] 2. The server automatically extracts information such as the floor plan and age of the building from the photo and stores it in a database.

[0118] 3. The server accesses the real estate database, cleanses the collected data, and generates a high-quality dataset.

[0119] 4. The server inputs this dataset into a generative AI model to predict the fair price.

[0120] 5. The server stores the prediction results in a database and simultaneously displays them visually on the device (as graphs or charts).

[0121] 6. When the lease is about to expire, the server sends a notification to the user suggesting a reasonable rent.

[0122] 7. The server sends push notifications of property information that matches the conditions set by the user.

[0123] Example prompt sentence:

[0124] "Please estimate the fair price of a 2LDK apartment in Shibuya Ward. The area is 70 square meters, the building is 10 years old, and the nearest station is Shibuya Station."

[0125] This system allows users to easily upload property information and receive highly accurate price valuations from a generative AI model. It also provides real-time push notifications and offers appropriate rent revisions, enabling efficient real estate transactions.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Processing flow and specific explanation

[0128] Step 1:

[0129] The server accesses public databases and automatically collects real estate data. Specifically, it uses Python scraping libraries (e.g., BeautifulSoup, Scrapy) to obtain detailed information such as property addresses, prices, area sizes, ages, and surrounding facilities from each database. It also uses the requests library to obtain data from databases that provide APIs. The input is the database URL or API endpoint, and the output is a list of collected real estate data.

[0130] Step 2:

[0131] The server performs data cleansing on the collected real estate data. This process uses the Pandas library to filter out duplicate and inaccurate data and ensure data quality. For example, it removes duplicate entries in the database and eliminates records with incorrect values. The input is the collected real estate data, and the output is a cleansed, high-quality dataset.

[0132] Step 3:

[0133] The server inputs the cleansed real estate data into a generative AI model to predict the fair price. The generative AI model, built using TensorFlow and PyTorch, predicts the price based on the property's past transaction data and market trends. As a specific example, the model is trained using past transaction data and its performance is evaluated using cross-validation. The input is the cleansed dataset, and the output is the predicted fair price.

[0134] Step 4:

[0135] The server stores the fair price predicted by the generative AI model in a database. Here, a relational database such as MySQL or PostgreSQL is used for the storage process. The input is the predicted fair price data, and the output is the predicted price information stored in the database.

[0136] Step 5:

[0137] A user uploads a property photo using a device. For example, by selecting a property photo from a smartphone or PC and clicking the upload button, the property information is sent to the server. The input is the uploaded property photo, and the output is the image URL sent to the server.

[0138] Step 6:

[0139] The server automatically extracts property information from uploaded property photos using an image analysis algorithm. Specifically, it uses image processing with OpenCV and TensorFlow to extract information such as floor plan and age of the building, and stores it in a database. The input is a property photo, and the output is the extracted property information.

[0140] Step 7:

[0141] The terminal visually displays predicted fair prices and surrounding market information to the user. Interactive charts and graphs are generated using D3.js and Chart.js and displayed in the user interface. The input is predicted fair price data and surrounding market data, and the output is an interactive display.

[0142] Step 8:

[0143] The server proposes appropriate rent revisions when a rental contract is renewed. It uses Python's Sched library to periodically schedule rental property price evaluations and notify users of proposed rent revisions. The input is rental property information and current market data, and the output is a rent revision proposal notification.

[0144] Step 9:

[0145] The server detects property information that matches the desired rental area conditions set by the user in real time and sends a push notification. Using Firebase or OneSignal, property information that matches the conditions is sent to the user's device. The input is new property information and the user's conditions, and the output is a push notification.

[0146] end

[0147] By processing in this step-by-step format, users can efficiently and intuitively perform fair value assessments, lease renewals, and receive property information.

[0148] (Application example 1)

[0149] 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."

[0150] Current real estate transaction systems require a great deal of time and effort to collect property data, predict fair prices, and visualize property information. Even when users upload property photos, the information is not accurately extracted, making it difficult to link to price predictions. Furthermore, real-time notification of property information in the most suitable rental areas hinders efficient real estate transactions.

[0151] 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.

[0152] In this invention, the server includes a means for automatically collecting real estate data from a public database, a means for using the collected real estate data to predict fair prices using a generative AI model, a means for automatically extracting property information from uploaded images, a means for visually displaying the predicted fair prices, and a means for sending push notifications of property information that matches the desired rental area. This allows users to easily upload property information, receive highly accurate fair price assessments, and intuitively confirm the value of the property. Furthermore, efficient real estate transactions are enabled through pricing of rental properties, appropriate rent proposals at the time of renewal, and real-time push notifications.

[0153] A database is a system that systematically organizes and stores information and allows it to be quickly retrieved when needed.

[0154] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0155] A "generative AI model" is an artificial intelligence model that is trained to achieve a specific purpose (e.g., price prediction) based on large amounts of data.

[0156] "Prediction" is the act of estimating future values ​​or situations based on collected data.

[0157] "Image analysis" is the process of automatically extracting useful information from image data.

[0158] A "fair price" is a fair and reasonable price calculated based on the market supply and demand situation and the characteristics of the property.

[0159] "Visualization" refers to the representation of data or information using visual means such as charts and graphs.

[0160] "Push notifications" are real-time notifications that are automatically sent from a server to a user's device.

[0161] This invention is a system for predicting the fair value of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following components and procedures are required to implement this invention.

[0162] System configuration

[0163] It mainly consists of three entities: a server, a terminal, and a user.

[0164] Data Collection and Cleansing

[0165] The server automatically collects real estate data by accessing databases containing publicly available real estate information (e.g., public databases, social media trend data, real estate agency property information, etc.). It uses programming languages ​​such as Python to send queries to the database via APIs to obtain detailed information such as the property's address, price, area, age, and surrounding facilities. The server then normalizes the data and filters out duplicate data to ensure data quality.

[0166] Fair price forecast

[0167] The server inputs the collected real estate data into a generative AI model to analyze detailed information for each property. At this stage, an AI framework such as TensorFlow is used to train a price prediction model based on past data, enabling fair and highly accurate price predictions. The generative AI model also takes into account past trends and current market conditions to predict future value fluctuations.

[0168] Upload and auto-extract property information

[0169] Users upload property photos using their devices (smartphones or PCs). For example, they select a property photo from their smartphone or PC and click the upload button. The server automatically extracts property information from this photo. Using an image analysis algorithm, it extracts features such as floor plan and age of the building and stores them in a database.

[0170] Information Visualization

[0171] The device visually displays information about the property's fair value and surrounding market prices to the user. For example, in a smartphone app developed using React Native, interactive charts and graphs are generated and displayed using D3.js, allowing users to intuitively check the property's value.

[0172] Rent setting and push notifications

[0173] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, the server monitors the expiration of the rental contract and sends a notification proposing a new rent when it's time for renewal, based on the desired rental area set by the user. Furthermore, the server sends real-time push notifications of property information that matches the desired rental area set by the user. Specifically, the server compares real estate data with the user's conditions and immediately notifies the user's device of any matching property information. This push notification function allows users to receive the latest information in a timely manner, making real estate transactions more efficient.

[0174] Examples and prompts

[0175] A specific use case might involve a user uploading a photo of a 10-year-old, 100-square-meter house in Tokyo, and predicting the appropriate price for that property. The prompt might look like this:

[0176] "This property is located in Tokyo, is a 10-year-old house with an area of ​​100 square meters. Please estimate the fair price for this property."

[0177] This system allows individual owners and investors to easily upload property information, receive highly accurate fair price assessments, and intuitively check the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications, which is expected to revitalize the real estate market.

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The server automatically collects real estate data by accessing a public database. Specifically, it uses an API to send queries to the database and obtain detailed information such as the property's address, price, area, age, surrounding facilities, etc. The input is the query to the database, and the output is the collected real estate data.

[0181] Step 2:

[0182] The server cleanses the collected data. Specifically, it removes duplicate data, filters inaccurate data, and normalizes it. The input is the collected real estate data, and the output is the cleansed real estate data. Python is used for this data cleansing.

[0183] Step 3:

[0184] The server inputs the cleansed real estate data into a generative AI model to predict fair prices. The generative AI model uses TensorFlow to train a predictive model based on historical data, taking into account past trends and current market conditions. The input is the cleansed data and a prompt for the AI ​​model, and the output is a predicted fair price.

[0185] Step 4:

[0186] The user uploads a property photo using a device. For example, they select a property photo from their smartphone or PC and click the upload button. The input is the user uploading the photo, and the output is sending the photo data to the server.

[0187] Step 5:

[0188] The server automatically extracts property information from uploaded photos. Specifically, it uses an image analysis algorithm to extract features such as floor plan and age of the building and stores them in a database. The input is the photo data, and the output is the property information extracted from the photo. This analysis uses computer vision technology.

[0189] Step 6:

[0190] The terminal visually displays information about the property's fair price and surrounding market prices to the user. Specifically, interactive charts and graphs are generated and displayed using D3.js using React Native. The input is the predicted fair price and property information, and the output is the visually displayed data.

[0191] Step 7:

[0192] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it proposes rent increases or maintenance based on the desired rental area set by the user. The input is the desired area and property data set by the user, and the output is the proposed new rent.

[0193] Step 8:

[0194] The server sends push notifications of property information that matches the user's desired rental area. The server compares real estate data with the user's conditions and notifies the user's device of matching property information in real time. The input is the user's desired conditions and the latest real estate data, and the output is a push notification.

[0195] 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.

[0196] The present invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. Furthermore, the system aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotions. The following describes an embodiment of the present invention.

[0197] Data collection

[0198] Step 1: Collect real estate data from publicly available databases.

[0199] The server accesses databases containing publicly available real estate information (e.g., public land price data, property information from real estate companies, etc.) and automatically collects real estate data.

[0200] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[0201] Step 2: Cleanse the data you get.

[0202] The server filters out duplicate and inaccurate data to ensure data quality.

[0203] Data analysis

[0204] Step 3: Use a generative AI model to predict the fair price.

[0205] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[0206] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[0207] Step 4: Save the prediction results

[0208] The server stores the fair prices predicted by the generative AI model in a database.

[0209] User Interface

[0210] Step 5: Upload your property

[0211] Users upload property photos using their device. Specifically, they select property photos from their smartphone or PC and click the upload button.

[0212] Step 6: Automatic information extraction

[0213] The server automatically extracts property information from these photos, using image analysis algorithms to analyze characteristic information such as floor plan and age of the building, and stores the information in a database.

[0214] Step 7: Visualize the information

[0215] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0216] Emotion Engine

[0217] Step 8: Recognizing User Emotions

[0218] The device recognizes the user's emotions using the user's voice input, facial expression analysis, or data from biometric sensors.

[0219] For example, a camera captures a user's facial expression while they are looking at property information, and the emotion engine analyzes the captured emotion data in real time.

[0220] Step 9: Customize the presentation of information

[0221] The emotion engine customizes the displayed information based on the user's perceived emotions.

[0222] For example, if a user is feeling stressed, provide an interface with softer colors and simpler explanations, whereas if a user is feeling positive, provide more detailed information and additional data.

[0223] Pricing & Notifications

[0224] Step 10: Set and update rents

[0225] The server proposes appropriate rent revisions when a rental contract is renewed. It proposes rent increases or maintenance based on the desired rental area set by the user.

[0226] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[0227] Step 11: Push Notifications

[0228] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0229] Specific examples

[0230] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0231] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[0232] In this way, individual owners and investors can make better decisions by making real estate transactions at fair prices and receiving appropriate information based on user emotions. The introduction of an emotion engine will improve the user experience and promote efficient and fair real estate transactions.

[0233] The processing flow will be explained below.

[0234] Step 1:

[0235] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[0236] Step 2:

[0237] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[0238] Step 3:

[0239] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[0240] Step 4:

[0241] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[0242] Step 5:

[0243] The server stores the predicted fair price in a database, making it available for subsequent processes.

[0244] Step 6:

[0245] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[0246] Step 7:

[0247] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[0248] Step 8:

[0249] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0250] Step 9:

[0251] The device can recognize the user's emotions using voice input, facial expression analysis, or data from biometric sensors. For example, a camera captures the user's facial expressions, which are then analyzed by an emotion engine.

[0252] Step 10:

[0253] The emotion engine customizes the displayed information based on the user's perceived emotions. For example, if the user is feeling stressed, the interface will be softened in color and a simple explanation will be provided.

[0254] Step 11:

[0255] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[0256] Step 12:

[0257] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0258] Example 2

[0259] 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."

[0260] The present invention aims to solve problems in real estate transactions, such as the lack of fair price evaluations, data reliability issues, and improving the user experience. It also aims to seamlessly perform automatic collection and cleansing of real estate data, fair price prediction, and information provision based on user sentiment. With conventional technology, there was no system that could perform all of these tasks in an integrated manner, making it difficult to conduct efficient and fair real estate transactions.

[0261] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0262] In this invention, the server includes: means for automatically collecting real estate data from a public database; means for cleansing the collected real estate data; means for predicting a fair price using a generative AI model based on the cleansed real estate data; means for saving the predicted fair price in a database; means for uploading property photos; means for automatically extracting information from the uploaded photos; means for visually displaying the fair price; means for recognizing a user's emotions; means for customizing information based on the recognized emotions; and means for sending push notifications of property information matching the desired rental area. This allows users to receive reliable real estate price assessments in real time and personalized information based on their emotions. It also promotes efficient and fair real estate transactions.

[0263] A "public database" is a database that collects real estate-related information that is made publicly available on the Internet by public institutions and private companies.

[0264] "Real estate data" refers to all information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0265] "Cleansing" refers to the process of removing duplicate and incorrect data from collected data to ensure data quality.

[0266] A "generative AI model" is an artificial intelligence model trained using machine learning techniques to predict the fair value of real estate.

[0267] "Fair price" refers to the fair and accurate market price of a property predicted by the generative AI model based on collected real estate data.

[0268] "Storing in a database" means storing the predicted fair price and collected real estate data in a database in an appropriate format.

[0269] "Property photos" are images uploaded by users that show the exterior and interior of a property.

[0270] "Automatic information extraction" refers to the use of image analysis algorithms to extract specific information, such as floor plan and age, from uploaded property photos.

[0271] "Visually displaying" means presenting the collected and predicted real estate data and fair prices to the user in an interactive format such as graphs and charts.

[0272] "Recognizing user emotions" means analyzing the user's emotional state through voice input, facial expression analysis, and data from biometric sensors.

[0273] "Customizing information" means adjusting the content and presentation of information based on the user's recognized emotions.

[0274] "Push notification" means notifying the user's device in real time of new real estate information that matches the conditions specified by the user.

[0275] MODE FOR CARRYING OUT THE INVENTION

[0276] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system not only collects real estate data from public databases and predicts the fair price using a generative AI model, but also improves the user experience by recognizing user emotions and customizing information.

[0277] Hardware and software used

[0278] The server uses a computer with high-performance computing resources, specifically a web server using a programming language such as Python or JavaScript (registered trademark), and a machine learning library such as Sklearn or TensorFlow.

[0279] The terminal refers to the smartphone or personal computer operated by the user, on which the web browser and dedicated applications run.

[0280] The database used is a relational database management system such as MySQL or PostgreSQL.

[0281] Processing Details

[0282] 1. Collecting real estate data from public databases

[0283] The server accesses public real estate databases (e.g., land price announcement data, property information from real estate companies) to collect the necessary data. Specifically, it sends HTTP requests using the Python requests library and saves the retrieved data in JSON format.

[0284] 2. Data Cleansing

[0285] The server uses the Pandas library to cleanse the collected data: it processes the data in data frame format, removes duplicate data with the drop_duplicates() method, and imputes missing values ​​with the fillna() method.

[0286] 3. Fair price prediction

[0287] The server inputs the cleansed data into a generative AI model to predict the appropriate price. The price prediction model is trained using TensorFlow and PyTorch, and predicts fair and accurate prices based on detailed information about each property.

[0288] 4. Saving the results

[0289] The server stores the fair prices predicted by the generative AI model in a database. It connects to the database using SQLAlchemy or Django ORM and inserts the prediction results into the appropriate tables.

[0290] 5. Upload property information

[0291] Users upload property photos from their devices, select image files and send them through their browsers, and the server receives them using web frameworks such as Flask or Django.

[0292] 6. Automatic Information Extraction

[0293] The server uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age of the building from the uploaded photos.

[0294] 7. Information Visualization

[0295] The terminal visually displays fair value and surrounding market information to the user, using D3.js and Chart.js to generate interactive graphs and charts.

[0296] 8. Emotional Recognition

[0297] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. It analyzes the user's facial expressions using OpenCV and a pre-trained model for emotion recognition.

[0298] 9. Customizing Information

[0299] The emotion engine customizes information based on the user's recognized emotions, dynamically modifying front-end CSS and JavaScript based on emotion recognition data to provide softer colors and simpler explanations for stressed users and more detailed information for more proactive users.

[0300] 10. Rent Setting and Renewal

[0301] The server proposes appropriate rent revisions when a rental property contract is renewed. It periodically checks contract expiration dates using a scheduler and sends emails and in-app notifications at the appropriate times.

[0302] 11. Push Notifications

[0303] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user. The information is sent to the user's device using a push notification service such as GOOGLE FI (registered trademark) rebase.

[0304] Specific examples

[0305] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0306] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[0307] Prompt Sentence Examples

[0308] "How can I gather real estate information from public databases and predict fair prices?"

[0309] "Please explain the algorithm that automatically extracts information from uploaded property photos."

[0310] "Tell me more about how you can recognize a user's emotions and customize the information based on them."

[0311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0312] Step 1:

[0313] The server accesses public databases to collect real estate data. Specifically, the server uses Python's requests library to send HTTP requests to obtain public land price data, property information from real estate companies, and other information. The API endpoint URL is required as input, and the output is JSON-formatted data containing detailed information such as the property's address, price, area, age, and surrounding facilities. The server temporarily stores this data in storage.

[0314] Step 2:

[0315] The server cleanses the collected data. Specifically, it processes the data in data frame format using the Pandas library. The input required is the JSON data obtained in step 1, and the output is high-quality data with duplicate data and missing values ​​filled in. The server removes duplicate data using the drop_duplicates() method and fills in missing values ​​using the fillna() method.

[0316] Step 3:

[0317] The server inputs the cleansed data into a generative AI model to predict the appropriate price. Specifically, it trains the AI ​​model using TensorFlow and PyTorch to predict prices based on detailed information about each property. High-quality cleansed data is required as input, and the output is the predicted price for each property. The server inputs the data into the trained model and uses the predict() method to make price predictions.

[0318] Step 4:

[0319] The server saves the fair price predicted by the generative AI model to a database. Specifically, it connects to the database using SQLAlchemy or Django ORM and inserts the predicted results into the appropriate table. The input is the predicted fair price, and the output is the predicted price information stored in the database. The server inserts the data using the session.add() and session.commit() methods.

[0320] Step 5:

[0321] The user uploads a property photo from their device. Specifically, they select an image file from their smartphone or PC, send it through the browser, and click the upload button. The input is a photo file of the property, and the output is the photo data stored on the server. The device sends the photo to the server using an HTTP POST request.

[0322] Step 6:

[0323] The server automatically extracts information from uploaded property photos. Specifically, it uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age from the photos. The input is the uploaded photo data, and the output is the extracted property information. The server reads the image using the cv2.imread() method and applies image analysis algorithms to extract information.

[0324] Step 7:

[0325] The terminal visually displays fair price and surrounding market information to the user. Specifically, it generates interactive graphs and charts using D3.js and Chart.js. The input required is predicted price information retrieved from a database, and the output is a graph or chart displayed in the browser. The terminal uses the JavaScript chart.draw() method to draw.

[0326] Step 8:

[0327] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. Specifically, it uses OpenCV and a pre-trained model for emotion recognition. The input requires sensor data acquired from a camera, microphone, etc., and the output is the recognized user emotion data. The device acquires video data using the cv2.VideoCapture() method and applies the emotion recognition algorithm.

[0328] Step 9:

[0329] The emotion engine customizes information based on the user's recognized emotions. Specifically, it dynamically changes CSS and JavaScript to provide softer colors and simpler explanations for stressed users and more detailed information for more active users. The input required is the emotion data output by the emotion engine, and the output is a customized user interface. The emotion engine uses if statements to change the UI depending on the conditions.

[0330] Step 10:

[0331] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it uses a scheduler to periodically check the contract expiration date and sends emails and in-app notifications at the appropriate time. The input requires the user's contract information, and the output is a notification proposing rent revisions. The server performs periodic checks using the schedule library and sends notifications using the send_email() method.

[0332] Step 11:

[0333] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user. Specifically, it uses a push notification service such as Google (registered trademark) Firebase. The input requires the user's set conditions and new property information, and the output is a notification to the user's device. The server uses the Firebase API to send a push notification every time new property data is received.

[0334] (Application example 2)

[0335] 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."

[0336] In today's real estate market, it is difficult to quickly and accurately predict fair prices. This is especially true for investors and individual owners, who find it difficult to make accurate decisions when renewing leases or purchasing new properties. Furthermore, there is a lack of systems for providing personalized information that takes user emotions into account, leaving room for improvement in the user experience.

[0337] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting real estate data from a public database, means for predicting a fair price using the collected real estate data with a generative AI model, means for visually displaying the predicted fair price, means for sending push notifications of property information that matches the desired rental area conditions, means for recognizing the user's emotions using the device's camera, and means for customizing the visual display based on the emotion recognition results. This allows users to quickly and accurately grasp fair property prices and rental conditions, and also enables the provision of personalized information according to emotions.

[0338] "Public Database" means any publicly accessible online or offline data source that contains market information or real estate-related data.

[0339] "Real estate data" refers to all information related to real estate, such as the property's address, price, area, age, and surrounding facilities.

[0340] "Fair value" refers to the reasonable and fair assessment of the value of real estate, taking into account past trends and current market conditions.

[0341] A "generative AI model" is a model built using machine learning and artificial intelligence technologies, and is an algorithm for predicting the fair price of real estate based on large amounts of data.

[0342] "Visual display means" refers to methods of presenting information to users in an easy-to-understand manner, such as using graphs, charts, or interactive maps.

[0343] "Property information that matches the conditions of the desired rental area" is information on rental properties that match the area, budget, and other requirements set by the user.

[0344] "Push notification" is a technology that notifies a device in real time of new property or rental information that matches the conditions specified by the user.

[0345] "Terminal" refers to any device that a user uses to view information, such as a smartphone, head-mounted display, or tablet.

[0346] "Means for recognizing a user's emotions using a camera" refers to technology that uses a camera or other sensors installed on the device to analyze the user's facial expressions and voice and identify their emotions.

[0347] "Means for customizing visual displays based on emotion recognition results" refers to a method for providing information optimized for individual users by adjusting the display content and interface according to the user's emotion data.

[0348] "Personalized information provision" refers to a general service that individually customizes appropriate property information and visual displays based on the user's situation and preferences.

[0349] This invention is a system that collects real estate data from public databases, uses that data to predict fair prices using a generative AI model, and also recognizes the user's emotions to provide visually customized information.

[0350] The server first accesses public databases and automatically collects real estate data. During data collection, it normalizes and filters duplicate data to ensure data quality. It then uses a generative AI model to analyze the collected real estate data and predict the appropriate price. This prediction takes into account past trends and current market conditions.

[0351] Users can visually check property information using devices such as smartphones or head-mounted displays (HMDs). The devices are equipped with cameras that capture the user's facial expressions while they are viewing the information. The facial expression data captured by the camera is analyzed in real time by an emotion recognition algorithm to identify the user's emotions (e.g., stress, excitement, etc.).

[0352] Emotional data is used to customize the format and content of the property information displayed. For example, if a user is stressed, the interface may be softened and the amount of information displayed may be simplified. On the other hand, if the user is interested, more detailed information or additional data may be provided.

[0353] For example, when a user uploads a photo of a property from their device, the server automatically extracts property information from the photo and uses a generative AI model to predict the appropriate price. The device then visually presents the appropriate price and surrounding market information to the user. Furthermore, the system analyzes the user's emotional state, and if it determines that the user is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0354] The app also has a push notification feature that sends real-time information about properties that match the area the user is looking to rent in. When the user receives the information, emotion recognition is activated, and if a positive emotion is detected, detailed property information will be provided.

[0355] An example of a prompt is as follows:

[0356] Emotion recognition prompts:

[0357] input: "Recognize emotions from images where the user is facing the camera."

[0358] output: "User emotion is stress."

[0359] Price prediction prompt:

[0360] input: "Enter price data for a specific real estate area and predict the fair value."

[0361] output: "The fair price for this property is 50 million yen."

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] The server accesses public databases and automatically collects real estate data, such as the property's address, price, area, age, and surrounding facilities. The collected data is then stored in the database.

[0365] Step 2:

[0366] The server normalizes the collected data and filters duplicate data, ensuring data quality. Data normalization involves converting data from different formats into a unified format and filtering duplicate data.

[0367] Step 3:

[0368] The server uses a generative AI model to predict the fair price based on the normalized data. The collected data is input into the generative AI model, which then obtains a predicted fair price that takes into account past trends and current market conditions.

[0369] Step 4:

[0370] The server stores the predicted fair price in a database, where it is stored along with other information for later visual presentation to the user.

[0371] Step 5:

[0372] Users upload property photos using their devices, which receive the photo data and send it to the server.

[0373] Step 6:

[0374] The server automatically extracts property information from uploaded photos, using image analysis algorithms to extract characteristic information such as floor plan and age, and adds it to a database.

[0375] Step 7:

[0376] The device visually displays the property's fair value and surrounding market information to the user, for example by generating interactive charts and graphs, in a format that allows the user to easily understand the property's value.

[0377] Step 8:

[0378] The device's camera captures the user's facial expressions and analyzes the data in real time. An emotion engine is used to recognize the user's emotions, such as stress or excitement.

[0379] Step 9:

[0380] The server customizes the visual display based on the emotion recognition results. If the user is stressed, the interface changes to softer colors and provides less information. If the user is interested, more detailed information is displayed.

[0381] Step 10:

[0382] The server pushes real-time information about properties that match the desired rental area, filters the data based on the conditions set by the user, and sends the relevant property information to the device.

[0383] Step 11:

[0384] The user checks the push notification received on their device, and their emotional data is also analyzed. If a positive emotion is detected, the server will provide additional detailed property information.

[0385] 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.

[0386] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0387] 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.

[0388] [Second embodiment]

[0389] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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).

[0395] 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. 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0400] 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."

[0401] The present invention is a system for predicting the fair price of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following describes an embodiment of the present invention.

[0402] This system is mainly composed of three entities: a server, a terminal, and a user.

[0403] Data collection

[0404] Step 1: Collect real estate data from publicly available databases.

[0405] The server accesses databases containing publicly available real estate information (e.g., public land price data, social media trend data, property information from real estate companies, etc.) and automatically collects real estate data.

[0406] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[0407] Step 2: Cleanse the data you get.

[0408] The server filters out duplicate and inaccurate data to ensure data quality.

[0409] Data analysis

[0410] Step 3: Use a generative AI model to predict the fair price.

[0411] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[0412] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[0413] Step 4: Save the prediction results

[0414] The server stores the fair prices predicted by the generative AI model in a database.

[0415] User Interface

[0416] Step 5: Upload your property

[0417] The user uploads a property photo using a device, for example, by selecting a property photo from a smartphone or PC and clicking the upload button.

[0418] Step 6: Automatic information extraction

[0419] The server automatically extracts property information from these photos, using image analysis algorithms to extract features such as floor plan and age of the building, and stores them in a database.

[0420] Step 7: Visualize the information

[0421] The device can visually display information about the property's fair value and surrounding market prices to the user, for example by generating interactive charts and graphs and displaying them on the device's UI.

[0422] Pricing & Notifications

[0423] Step 8: Set and update rents

[0424] The server proposes appropriate rent revisions when a rental contract is renewed, and proposes rent increases or maintenance based on the desired rental area set by the user.

[0425] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[0426] Step 9: Push Notifications

[0427] Property information that matches the desired rental area conditions set by the user will be sent via push notification.

[0428] The server extracts matching property information in real time and notifies the user's terminal.

[0429] This system allows users to easily upload property information, receive highly accurate fair price assessments using generative AI models, and intuitively confirm the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications. This is expected to enable individual owners and investors to enter the real estate market more rationally and efficiently, stimulating the market.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[0433] Step 2:

[0434] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[0435] Step 3:

[0436] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[0437] Step 4:

[0438] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[0439] Step 5:

[0440] The server stores the predicted fair prices in a database.

[0441] Step 6:

[0442] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[0443] Step 7:

[0444] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[0445] Step 8:

[0446] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0447] Step 9:

[0448] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[0449] Step 10:

[0450] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0451] Example 1

[0452] 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."

[0453] The purpose of this invention is to provide efficient and accurate price predictions in real estate transactions, enabling individual owners and investors to enter the market more rationally. By accurately predicting the fair price of real estate and providing intuitive information to users, the invention also enables efficient real estate transactions by proposing appropriate rent revisions and providing real-time notifications of property information that matches the user's conditions.

[0454] 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.

[0455] In this invention, the server includes means for automatically collecting real estate data from a public database, means for performing data cleansing on the collected real estate data and filtering out duplicate and inaccurate data to ensure data quality, means for predicting a fair price using the collected real estate data with a generative AI model, means for saving the predicted fair price in a database, means for having a user upload photos of property information and automatically extracting property information from the photos using an image analysis algorithm, means for saving the extracted property information in a database, means for visually displaying the predicted fair price, means for proposing a fair rent revision when renewing a rental contract, and means for sending push notifications of property information that matches the conditions of the desired rental area. This allows users to easily upload property information, receive highly accurate price evaluations from the generative AI model, and conduct real estate transactions efficiently and intuitively.

[0456] A "publicly accessible database" is a collection of information that is made available in a publicly accessible form and that includes real estate data.

[0457] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0458] "Data cleansing" is a process for removing duplicate data and inaccurate data from collected data and ensuring the quality of the data.

[0459] A "generative AI model" is an artificial intelligence model trained using historical data to predict the fair value of a property.

[0460] A "fair price" is a price that is fair and in line with market value, calculated based on market conditions and past trends.

[0461] A "database" is an information management system for efficiently storing and managing large amounts of data.

[0462] "Image analysis algorithm" refers to a computational method for extracting specific information or features from image data.

[0463] A "visual display" is a method of presenting data or information to a user in a visual form, such as a graph or chart.

[0464] "Rent revision" is the process of reevaluating and proposing an appropriate rent when renewing a rental property contract.

[0465] "Push notification" is a mechanism that sends new information that matches certain conditions to a user's device in real time.

[0466] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system is mainly composed of three entities: a server, a terminal, and a user.

[0467] Data collection

[0468] The server automatically collects real estate data from publicly available databases. These databases include, for example, public land price data, social media trend data, and property information from real estate companies. The server automatically collects data from each database using a Python scraping library (e.g., BeautifulSoup or Scrapy). If an API is provided, the server uses the requests library to send queries to the API and retrieve data in JSON format.

[0469] Data Cleansing

[0470] The server then cleanses the collected data, a process that uses the Pandas library to filter out duplicates and inaccurate data and ensure data quality. The cleansed data is then stored in a standardized format, ready to be fed into generative AI models.

[0471] Fair price forecast

[0472] The server uses the cleansed data to predict the fair price using a generative AI model. This generative AI model is built using TensorFlow and PyTorch and is trained on past transaction data. This allows for highly accurate prediction of the fair price for each property. The performance of the generative AI model is evaluated using cross-validation and test data, and measures are taken to prevent overfitting.

[0473] Saving prediction results

[0474] The predicted fair prices are stored in a database by the server. This database uses a relational database such as MySQL or PostgreSQL, which allows for efficient storage and management of prediction results.

[0475] Property information upload and automatic information extraction

[0476] Users upload photos of properties using their devices (e.g., smartphones or PCs). These photos are temporarily stored in cloud storage (e.g., AWS S3), and the URL is sent to the server. The server then runs image analysis algorithms using OpenCV or TensorFlow to automatically extract property information (e.g., floor plan, age) from the photos and store it in a database.

[0477] Information Visualization

[0478] The terminal uses D3.js and Chart.js to generate interactive charts and graphs, visually displaying information on the property's fair value and surrounding market price, allowing users to intuitively understand the property's value.

[0479] Rent setting and push notifications

[0480] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, by using Python's Sched library to schedule periodic rent evaluations, it can send notifications proposing new rents to users. It also detects property information that matches the conditions set by the user in real time and sends it to the device using a push notification service such as Firebase or OneSignal. This allows users to receive new property information promptly.

[0481] Examples of concrete examples and prompts

[0482] As a specific example, for a user looking for a 2LDK apartment in Shibuya Ward, Tokyo, the system works as follows:

[0483] 1. The user uploads a photo of a 2LDK apartment in Shibuya Ward from their device.

[0484] 2. The server automatically extracts information such as the floor plan and age of the building from the photo and stores it in a database.

[0485] 3. The server accesses the real estate database, cleanses the collected data, and generates a high-quality dataset.

[0486] 4. The server inputs this dataset into a generative AI model to predict the fair price.

[0487] 5. The server stores the prediction results in a database and simultaneously displays them visually on the device (as graphs or charts).

[0488] 6. When the lease is about to expire, the server sends a notification to the user suggesting a reasonable rent.

[0489] 7. The server sends push notifications of property information that matches the conditions set by the user.

[0490] Example prompt sentence:

[0491] "Please estimate the fair price of a 2LDK apartment in Shibuya Ward. The area is 70 square meters, the building is 10 years old, and the nearest station is Shibuya Station."

[0492] This system allows users to easily upload property information and receive highly accurate price valuations from a generative AI model. It also provides real-time push notifications and offers appropriate rent revisions, enabling efficient real estate transactions.

[0493] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0494] Processing flow and specific explanation

[0495] Step 1:

[0496] The server accesses public databases and automatically collects real estate data. Specifically, it uses Python scraping libraries (e.g., BeautifulSoup, Scrapy) to obtain detailed information such as property addresses, prices, area sizes, ages, and surrounding facilities from each database. It also uses the requests library to obtain data from databases that provide APIs. The input is the database URL or API endpoint, and the output is a list of collected real estate data.

[0497] Step 2:

[0498] The server performs data cleansing on the collected real estate data. This process uses the Pandas library to filter out duplicate and inaccurate data and ensure data quality. For example, it removes duplicate entries in the database and eliminates records with incorrect values. The input is the collected real estate data, and the output is a cleansed, high-quality dataset.

[0499] Step 3:

[0500] The server inputs the cleansed real estate data into a generative AI model to predict the fair price. The generative AI model, built using TensorFlow and PyTorch, predicts the price based on the property's past transaction data and market trends. As a specific example, the model is trained using past transaction data and its performance is evaluated using cross-validation. The input is the cleansed dataset, and the output is the predicted fair price.

[0501] Step 4:

[0502] The server stores the fair price predicted by the generative AI model in a database. Here, a relational database such as MySQL or PostgreSQL is used for the storage process. The input is the predicted fair price data, and the output is the predicted price information stored in the database.

[0503] Step 5:

[0504] A user uploads a property photo using a device. For example, by selecting a property photo from a smartphone or PC and clicking the upload button, the property information is sent to the server. The input is the uploaded property photo, and the output is the image URL sent to the server.

[0505] Step 6:

[0506] The server automatically extracts property information from uploaded property photos using an image analysis algorithm. Specifically, it uses image processing with OpenCV and TensorFlow to extract information such as floor plan and age of the building, and stores it in a database. The input is a property photo, and the output is the extracted property information.

[0507] Step 7:

[0508] The terminal visually displays predicted fair prices and surrounding market information to the user. Interactive charts and graphs are generated using D3.js and Chart.js and displayed in the user interface. The input is predicted fair price data and surrounding market data, and the output is an interactive display.

[0509] Step 8:

[0510] The server proposes appropriate rent revisions when a rental contract is renewed. It uses Python's Sched library to periodically schedule rental property price evaluations and notify users of proposed rent revisions. The input is rental property information and current market data, and the output is a rent revision proposal notification.

[0511] Step 9:

[0512] The server detects property information that matches the desired rental area conditions set by the user in real time and sends a push notification. Using Firebase or OneSignal, property information that matches the conditions is sent to the user's device. The input is new property information and the user's conditions, and the output is a push notification.

[0513] end

[0514] By processing in this step-by-step format, users can efficiently and intuitively perform fair value assessments, lease renewals, and receive property information.

[0515] (Application example 1)

[0516] 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."

[0517] Current real estate transaction systems require a great deal of time and effort to collect property data, predict fair prices, and visualize property information. Even when users upload property photos, the information is not accurately extracted, making it difficult to link to price predictions. Furthermore, real-time notification of property information in the most suitable rental areas hinders efficient real estate transactions.

[0518] 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.

[0519] In this invention, the server includes a means for automatically collecting real estate data from a public database, a means for using the collected real estate data to predict fair prices using a generative AI model, a means for automatically extracting property information from uploaded images, a means for visually displaying the predicted fair prices, and a means for sending push notifications of property information that matches the desired rental area. This allows users to easily upload property information, receive highly accurate fair price assessments, and intuitively confirm the value of the property. Furthermore, efficient real estate transactions are enabled through pricing of rental properties, appropriate rent proposals at the time of renewal, and real-time push notifications.

[0520] A database is a system that systematically organizes and stores information and allows it to be quickly retrieved when needed.

[0521] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0522] A "generative AI model" is an artificial intelligence model that is trained to achieve a specific purpose (e.g., price prediction) based on large amounts of data.

[0523] "Prediction" is the act of estimating future values ​​or situations based on collected data.

[0524] "Image analysis" is the process of automatically extracting useful information from image data.

[0525] A "fair price" is a fair and reasonable price calculated based on the market supply and demand situation and the characteristics of the property.

[0526] "Visualization" refers to the representation of data or information using visual means such as charts and graphs.

[0527] "Push notifications" are real-time notifications that are automatically sent from a server to a user's device.

[0528] This invention is a system for predicting the fair value of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following components and procedures are required to implement this invention.

[0529] System configuration

[0530] It mainly consists of three entities: a server, a terminal, and a user.

[0531] Data Collection and Cleansing

[0532] The server automatically collects real estate data by accessing databases containing publicly available real estate information (e.g., public databases, social media trend data, real estate agency property information, etc.). It uses programming languages ​​such as Python to send queries to the database via APIs to obtain detailed information such as the property's address, price, area, age, and surrounding facilities. The server then normalizes the data and filters out duplicate data to ensure data quality.

[0533] Fair price forecast

[0534] The server inputs the collected real estate data into a generative AI model to analyze detailed information for each property. At this stage, an AI framework such as TensorFlow is used to train a price prediction model based on past data, enabling fair and highly accurate price predictions. The generative AI model also takes into account past trends and current market conditions to predict future value fluctuations.

[0535] Upload and auto-extract property information

[0536] Users upload property photos using their devices (smartphones or PCs). For example, they select a property photo from their smartphone or PC and click the upload button. The server automatically extracts property information from this photo. Using an image analysis algorithm, it extracts features such as floor plan and age of the building and stores them in a database.

[0537] Information Visualization

[0538] The device visually displays information about the property's fair value and surrounding market prices to the user. For example, in a smartphone app developed using React Native, interactive charts and graphs are generated and displayed using D3.js, allowing users to intuitively check the property's value.

[0539] Rent setting and push notifications

[0540] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, the server monitors the expiration of the rental contract and sends a notification proposing a new rent when it's time for renewal, based on the desired rental area set by the user. Furthermore, the server sends real-time push notifications of property information that matches the desired rental area set by the user. Specifically, the server compares real estate data with the user's conditions and immediately notifies the user's device of any matching property information. This push notification function allows users to receive the latest information in a timely manner, making real estate transactions more efficient.

[0541] Examples and prompts

[0542] A specific use case might involve a user uploading a photo of a 10-year-old, 100-square-meter house in Tokyo, and predicting the appropriate price for that property. The prompt might look like this:

[0543] "This property is located in Tokyo, is a 10-year-old house with an area of ​​100 square meters. Please estimate the fair price for this property."

[0544] This system allows individual owners and investors to easily upload property information, receive highly accurate fair price assessments, and intuitively check the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications, which is expected to revitalize the real estate market.

[0545] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0546] Step 1:

[0547] The server automatically collects real estate data by accessing a public database. Specifically, it uses an API to send queries to the database and obtain detailed information such as the property's address, price, area, age, surrounding facilities, etc. The input is the query to the database, and the output is the collected real estate data.

[0548] Step 2:

[0549] The server cleanses the collected data. Specifically, it removes duplicate data, filters inaccurate data, and normalizes it. The input is the collected real estate data, and the output is the cleansed real estate data. Python is used for this data cleansing.

[0550] Step 3:

[0551] The server inputs the cleansed real estate data into a generative AI model to predict fair prices. The generative AI model uses TensorFlow to train a predictive model based on historical data, taking into account past trends and current market conditions. The input is the cleansed data and a prompt for the AI ​​model, and the output is a predicted fair price.

[0552] Step 4:

[0553] The user uploads a property photo using a device. For example, they select a property photo from their smartphone or PC and click the upload button. The input is the user uploading the photo, and the output is sending the photo data to the server.

[0554] Step 5:

[0555] The server automatically extracts property information from uploaded photos. Specifically, it uses an image analysis algorithm to extract features such as floor plan and age of the building and stores them in a database. The input is the photo data, and the output is the property information extracted from the photo. This analysis uses computer vision technology.

[0556] Step 6:

[0557] The terminal visually displays information about the property's fair price and surrounding market prices to the user. Specifically, interactive charts and graphs are generated and displayed using D3.js using React Native. The input is the predicted fair price and property information, and the output is the visually displayed data.

[0558] Step 7:

[0559] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it proposes rent increases or maintenance based on the desired rental area set by the user. The input is the desired area and property data set by the user, and the output is the proposed new rent.

[0560] Step 8:

[0561] The server sends push notifications of property information that matches the user's desired rental area. The server compares real estate data with the user's conditions and notifies the user's device of matching property information in real time. The input is the user's desired conditions and the latest real estate data, and the output is a push notification.

[0562] 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.

[0563] The present invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. Furthermore, the system aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotions. The following describes an embodiment of the present invention.

[0564] Data collection

[0565] Step 1: Collect real estate data from publicly available databases.

[0566] The server accesses databases containing publicly available real estate information (e.g., public land price data, property information from real estate companies, etc.) and automatically collects real estate data.

[0567] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[0568] Step 2: Cleanse the data you get.

[0569] The server filters out duplicate and inaccurate data to ensure data quality.

[0570] Data analysis

[0571] Step 3: Use a generative AI model to predict the fair price.

[0572] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[0573] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[0574] Step 4: Save the prediction results

[0575] The server stores the fair prices predicted by the generative AI model in a database.

[0576] User Interface

[0577] Step 5: Upload your property

[0578] Users upload property photos using their device. Specifically, they select property photos from their smartphone or PC and click the upload button.

[0579] Step 6: Automatic information extraction

[0580] The server automatically extracts property information from these photos, using image analysis algorithms to analyze characteristic information such as floor plan and age of the building, and stores the information in a database.

[0581] Step 7: Visualize the information

[0582] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0583] Emotion Engine

[0584] Step 8: Recognizing User Emotions

[0585] The device recognizes the user's emotions using the user's voice input, facial expression analysis, or data from biometric sensors.

[0586] For example, a camera captures a user's facial expression while they are looking at property information, and the emotion engine analyzes the captured emotion data in real time.

[0587] Step 9: Customize the presentation of information

[0588] The emotion engine customizes the displayed information based on the user's perceived emotions.

[0589] For example, if a user is feeling stressed, provide an interface with softer colors and simpler explanations, whereas if a user is feeling positive, provide more detailed information and additional data.

[0590] Pricing & Notifications

[0591] Step 10: Set and update rents

[0592] The server proposes appropriate rent revisions when a rental contract is renewed. It proposes rent increases or maintenance based on the desired rental area set by the user.

[0593] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[0594] Step 11: Push Notifications

[0595] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0596] Specific examples

[0597] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0598] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[0599] In this way, individual owners and investors can make better decisions by making real estate transactions at fair prices and receiving appropriate information based on user emotions. The introduction of an emotion engine will improve the user experience and promote efficient and fair real estate transactions.

[0600] The processing flow will be explained below.

[0601] Step 1:

[0602] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[0603] Step 2:

[0604] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[0605] Step 3:

[0606] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[0607] Step 4:

[0608] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[0609] Step 5:

[0610] The server stores the predicted fair price in a database, making it available for subsequent processes.

[0611] Step 6:

[0612] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[0613] Step 7:

[0614] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[0615] Step 8:

[0616] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0617] Step 9:

[0618] The device can recognize the user's emotions using voice input, facial expression analysis, or data from biometric sensors. For example, a camera captures the user's facial expressions, which are then analyzed by an emotion engine.

[0619] Step 10:

[0620] The emotion engine customizes the displayed information based on the user's perceived emotions. For example, if the user is feeling stressed, the interface will be softened in color and a simple explanation will be provided.

[0621] Step 11:

[0622] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[0623] Step 12:

[0624] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0625] Example 2

[0626] 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."

[0627] The present invention aims to solve problems in real estate transactions, such as the lack of fair price evaluations, data reliability issues, and improving the user experience. It also aims to seamlessly perform automatic collection and cleansing of real estate data, fair price prediction, and information provision based on user sentiment. With conventional technology, there was no system that could perform all of these tasks in an integrated manner, making it difficult to conduct efficient and fair real estate transactions.

[0628] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0629] In this invention, the server includes: means for automatically collecting real estate data from a public database; means for cleansing the collected real estate data; means for predicting a fair price using a generative AI model based on the cleansed real estate data; means for saving the predicted fair price in a database; means for uploading property photos; means for automatically extracting information from the uploaded photos; means for visually displaying the fair price; means for recognizing a user's emotions; means for customizing information based on the recognized emotions; and means for sending push notifications of property information matching the desired rental area. This allows users to receive reliable real estate price assessments in real time and personalized information based on their emotions. It also promotes efficient and fair real estate transactions.

[0630] A "public database" is a database that collects real estate-related information that is made publicly available on the Internet by public institutions and private companies.

[0631] "Real estate data" refers to all information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0632] "Cleansing" refers to the process of removing duplicate and incorrect data from collected data to ensure data quality.

[0633] A "generative AI model" is an artificial intelligence model trained using machine learning techniques to predict the fair value of real estate.

[0634] "Fair price" refers to the fair and accurate market price of a property predicted by the generative AI model based on collected real estate data.

[0635] "Storing in a database" means storing the predicted fair price and collected real estate data in a database in an appropriate format.

[0636] "Property photos" are images uploaded by users that show the exterior and interior of a property.

[0637] "Automatic information extraction" refers to the use of image analysis algorithms to extract specific information, such as floor plan and age, from uploaded property photos.

[0638] "Visually displaying" means presenting the collected and predicted real estate data and fair prices to the user in an interactive format such as graphs and charts.

[0639] "Recognizing user emotions" means analyzing the user's emotional state through voice input, facial expression analysis, and data from biometric sensors.

[0640] "Customizing information" means adjusting the content and presentation of information based on the user's recognized emotions.

[0641] "Push notification" means notifying the user's device in real time of new real estate information that matches the conditions specified by the user.

[0642] MODE FOR CARRYING OUT THE INVENTION

[0643] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system not only collects real estate data from public databases and predicts the fair price using a generative AI model, but also improves the user experience by recognizing user emotions and customizing information.

[0644] Hardware and software used

[0645] The server uses a computer with high-performance computing resources, specifically a web server using programming languages ​​such as Python or JavaScript, and machine learning libraries such as Sklearn or TensorFlow.

[0646] The terminal refers to the smartphone or personal computer operated by the user, on which the web browser and dedicated applications run.

[0647] The database used is a relational database management system such as MySQL or PostgreSQL.

[0648] Processing Details

[0649] 1. Collecting real estate data from public databases

[0650] The server accesses public real estate databases (e.g., land price announcement data, property information from real estate companies) to collect the necessary data. Specifically, it sends HTTP requests using the Python requests library and saves the retrieved data in JSON format.

[0651] 2. Data Cleansing

[0652] The server uses the Pandas library to cleanse the collected data: it processes the data in data frame format, removes duplicate data with the drop_duplicates() method, and imputes missing values ​​with the fillna() method.

[0653] 3. Fair price prediction

[0654] The server inputs the cleansed data into a generative AI model to predict the appropriate price. The price prediction model is trained using TensorFlow and PyTorch, and predicts fair and accurate prices based on detailed information about each property.

[0655] 4. Saving the results

[0656] The server stores the fair prices predicted by the generative AI model in a database. It connects to the database using SQLAlchemy or Django ORM and inserts the prediction results into the appropriate tables.

[0657] 5. Upload property information

[0658] Users upload property photos from their devices, select image files and send them through their browsers, and the server receives them using web frameworks such as Flask or Django.

[0659] 6. Automatic Information Extraction

[0660] The server uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age of the building from the uploaded photos.

[0661] 7. Information Visualization

[0662] The terminal visually displays fair value and surrounding market information to the user, using D3.js and Chart.js to generate interactive graphs and charts.

[0663] 8. Emotional Recognition

[0664] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. It analyzes the user's facial expressions using OpenCV and a pre-trained model for emotion recognition.

[0665] 9. Customizing Information

[0666] The emotion engine customizes information based on the user's recognized emotions, dynamically modifying front-end CSS and JavaScript based on emotion recognition data to provide softer colors and simpler explanations for stressed users and more detailed information for more proactive users.

[0667] 10. Rent Setting and Renewal

[0668] The server proposes appropriate rent revisions when a rental property contract is renewed. It periodically checks contract expiration dates using a scheduler and sends emails and in-app notifications at the appropriate times.

[0669] 11. Push Notifications

[0670] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user, using push notification services such as Google Firebase to send the information to the user's device.

[0671] Specific examples

[0672] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0673] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[0674] Prompt Sentence Examples

[0675] "How can I gather real estate information from public databases and predict fair prices?"

[0676] "Please explain the algorithm that automatically extracts information from uploaded property photos."

[0677] "Tell me more about how you can recognize a user's emotions and customize the information based on them."

[0678] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0679] Step 1:

[0680] The server accesses public databases to collect real estate data. Specifically, the server uses Python's requests library to send HTTP requests to obtain public land price data, property information from real estate companies, and other information. The API endpoint URL is required as input, and the output is JSON-formatted data containing detailed information such as the property's address, price, area, age, and surrounding facilities. The server temporarily stores this data in storage.

[0681] Step 2:

[0682] The server cleanses the collected data. Specifically, it processes the data in data frame format using the Pandas library. The input required is the JSON data obtained in step 1, and the output is high-quality data with duplicate data and missing values ​​filled in. The server removes duplicate data using the drop_duplicates() method and fills in missing values ​​using the fillna() method.

[0683] Step 3:

[0684] The server inputs the cleansed data into a generative AI model to predict the appropriate price. Specifically, it trains the AI ​​model using TensorFlow and PyTorch to predict prices based on detailed information about each property. High-quality cleansed data is required as input, and the output is the predicted price for each property. The server inputs the data into the trained model and uses the predict() method to make price predictions.

[0685] Step 4:

[0686] The server saves the fair price predicted by the generative AI model to a database. Specifically, it connects to the database using SQLAlchemy or Django ORM and inserts the predicted results into the appropriate table. The input is the predicted fair price, and the output is the predicted price information stored in the database. The server inserts the data using the session.add() and session.commit() methods.

[0687] Step 5:

[0688] The user uploads a property photo from their device. Specifically, they select an image file from their smartphone or PC, send it through the browser, and click the upload button. The input is a photo file of the property, and the output is the photo data stored on the server. The device sends the photo to the server using an HTTP POST request.

[0689] Step 6:

[0690] The server automatically extracts information from uploaded property photos. Specifically, it uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age from the photos. The input is the uploaded photo data, and the output is the extracted property information. The server reads the image using the cv2.imread() method and applies image analysis algorithms to extract information.

[0691] Step 7:

[0692] The terminal visually displays fair price and surrounding market information to the user. Specifically, it generates interactive graphs and charts using D3.js and Chart.js. The input required is predicted price information retrieved from a database, and the output is a graph or chart displayed in the browser. The terminal uses the JavaScript chart.draw() method to draw.

[0693] Step 8:

[0694] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. Specifically, it uses OpenCV and a pre-trained model for emotion recognition. The input requires sensor data acquired from a camera, microphone, etc., and the output is the recognized user emotion data. The device acquires video data using the cv2.VideoCapture() method and applies the emotion recognition algorithm.

[0695] Step 9:

[0696] The emotion engine customizes information based on the user's recognized emotions. Specifically, it dynamically changes CSS and JavaScript to provide softer colors and simpler explanations for stressed users and more detailed information for more active users. The input required is the emotion data output by the emotion engine, and the output is a customized user interface. The emotion engine uses if statements to change the UI depending on the conditions.

[0697] Step 10:

[0698] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it uses a scheduler to periodically check the contract expiration date and sends emails and in-app notifications at the appropriate time. The input requires the user's contract information, and the output is a notification proposing rent revisions. The server performs periodic checks using the schedule library and sends notifications using the send_email() method.

[0699] Step 11:

[0700] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user. Specifically, it uses a push notification service such as Google Firebase. The input requires the user's set conditions and new property information, and the output is a notification to the user's device. The server uses the Firebase API to send a push notification every time new property data is received.

[0701] (Application example 2)

[0702] 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."

[0703] In today's real estate market, it is difficult to quickly and accurately predict fair prices. This is especially true for investors and individual owners, who find it difficult to make accurate decisions when renewing leases or purchasing new properties. Furthermore, there is a lack of systems for providing personalized information that takes user emotions into account, leaving room for improvement in the user experience.

[0704] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting real estate data from a public database, means for predicting a fair price using the collected real estate data with a generative AI model, means for visually displaying the predicted fair price, means for sending push notifications of property information that matches the desired rental area conditions, means for recognizing the user's emotions using the device's camera, and means for customizing the visual display based on the emotion recognition results. This allows users to quickly and accurately grasp fair property prices and rental conditions, and also enables the provision of personalized information according to emotions.

[0705] "Public Database" means any publicly accessible online or offline data source that contains market information or real estate-related data.

[0706] "Real estate data" refers to all information related to real estate, such as the property's address, price, area, age, and surrounding facilities.

[0707] "Fair value" refers to the reasonable and fair assessment of the value of real estate, taking into account past trends and current market conditions.

[0708] A "generative AI model" is a model built using machine learning and artificial intelligence technologies, and is an algorithm for predicting the fair price of real estate based on large amounts of data.

[0709] "Visual display means" refers to methods of presenting information to users in an easy-to-understand manner, such as using graphs, charts, or interactive maps.

[0710] "Property information that matches the conditions of the desired rental area" is information on rental properties that match the area, budget, and other requirements set by the user.

[0711] "Push notification" is a technology that notifies a device in real time of new property or rental information that matches the conditions specified by the user.

[0712] "Terminal" refers to any device that a user uses to view information, such as a smartphone, head-mounted display, or tablet.

[0713] "Means for recognizing a user's emotions using a camera" refers to technology that uses a camera or other sensors installed on the device to analyze the user's facial expressions and voice and identify their emotions.

[0714] "Means for customizing visual displays based on emotion recognition results" refers to a method for providing information optimized for individual users by adjusting the display content and interface according to the user's emotion data.

[0715] "Personalized information provision" refers to a general service that individually customizes appropriate property information and visual displays based on the user's situation and preferences.

[0716] This invention is a system that collects real estate data from public databases, uses that data to predict fair prices using a generative AI model, and also recognizes the user's emotions to provide visually customized information.

[0717] The server first accesses public databases and automatically collects real estate data. During data collection, it normalizes and filters duplicate data to ensure data quality. It then uses a generative AI model to analyze the collected real estate data and predict the appropriate price. This prediction takes into account past trends and current market conditions.

[0718] Users can visually check property information using devices such as smartphones or head-mounted displays (HMDs). The devices are equipped with cameras that capture the user's facial expressions while they are viewing the information. The facial expression data captured by the camera is analyzed in real time by an emotion recognition algorithm to identify the user's emotions (e.g., stress, excitement, etc.).

[0719] Emotional data is used to customize the format and content of the property information displayed. For example, if a user is stressed, the interface may be softened and the amount of information displayed may be simplified. On the other hand, if the user is interested, more detailed information or additional data may be provided.

[0720] For example, when a user uploads a photo of a property from their device, the server automatically extracts property information from the photo and uses a generative AI model to predict the appropriate price. The device then visually presents the appropriate price and surrounding market information to the user. Furthermore, the system analyzes the user's emotional state, and if it determines that the user is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0721] The app also has a push notification feature that sends real-time information about properties that match the area the user is looking to rent in. When the user receives the information, emotion recognition is activated, and if a positive emotion is detected, detailed property information will be provided.

[0722] An example of a prompt is as follows:

[0723] Emotion recognition prompts:

[0724] input: "Recognize emotions from images where the user is facing the camera."

[0725] output: "User emotion is stress."

[0726] Price prediction prompt:

[0727] input: "Enter price data for a specific real estate area and predict the fair value."

[0728] output: "The fair price for this property is 50 million yen."

[0729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0730] Step 1:

[0731] The server accesses public databases and automatically collects real estate data, such as the property's address, price, area, age, and surrounding facilities. The collected data is then stored in the database.

[0732] Step 2:

[0733] The server normalizes the collected data and filters duplicate data, ensuring data quality. Data normalization involves converting data from different formats into a unified format and filtering duplicate data.

[0734] Step 3:

[0735] The server uses a generative AI model to predict the fair price based on the normalized data. The collected data is input into the generative AI model, which then obtains a predicted fair price that takes into account past trends and current market conditions.

[0736] Step 4:

[0737] The server stores the predicted fair price in a database, where it is stored along with other information for later visual presentation to the user.

[0738] Step 5:

[0739] Users upload property photos using their devices, which receive the photo data and send it to the server.

[0740] Step 6:

[0741] The server automatically extracts property information from uploaded photos, using image analysis algorithms to extract characteristic information such as floor plan and age, and adds it to a database.

[0742] Step 7:

[0743] The device visually displays the property's fair value and surrounding market information to the user, for example by generating interactive charts and graphs, in a format that allows the user to easily understand the property's value.

[0744] Step 8:

[0745] The device's camera captures the user's facial expressions and analyzes the data in real time. An emotion engine is used to recognize the user's emotions, such as stress or excitement.

[0746] Step 9:

[0747] The server customizes the visual display based on the emotion recognition results. If the user is stressed, the interface changes to softer colors and provides less information. If the user is interested, more detailed information is displayed.

[0748] Step 10:

[0749] The server pushes real-time information about properties that match the desired rental area, filters the data based on the conditions set by the user, and sends the relevant property information to the device.

[0750] Step 11:

[0751] The user checks the push notification received on their device, and their emotional data is also analyzed. If a positive emotion is detected, the server will provide additional detailed property information.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] [Third embodiment]

[0756] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0757] 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.

[0758] 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).

[0759] 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.

[0760] 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.

[0761] 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).

[0762] 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. 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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."

[0768] The present invention is a system for predicting the fair price of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following describes an embodiment of the present invention.

[0769] This system is mainly composed of three entities: a server, a terminal, and a user.

[0770] Data collection

[0771] Step 1: Collect real estate data from publicly available databases.

[0772] The server accesses databases containing publicly available real estate information (e.g., public land price data, social media trend data, property information from real estate companies, etc.) and automatically collects real estate data.

[0773] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[0774] Step 2: Cleanse the data you get.

[0775] The server filters out duplicate and inaccurate data to ensure data quality.

[0776] Data analysis

[0777] Step 3: Use a generative AI model to predict the fair price.

[0778] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[0779] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[0780] Step 4: Save the prediction results

[0781] The server stores the fair prices predicted by the generative AI model in a database.

[0782] User Interface

[0783] Step 5: Upload your property

[0784] The user uploads a property photo using a device, for example, by selecting a property photo from a smartphone or PC and clicking the upload button.

[0785] Step 6: Automatic information extraction

[0786] The server automatically extracts property information from these photos, using image analysis algorithms to extract features such as floor plan and age of the building, and stores them in a database.

[0787] Step 7: Visualize the information

[0788] The device can visually display information about the property's fair value and surrounding market prices to the user, for example by generating interactive charts and graphs and displaying them on the device's UI.

[0789] Pricing & Notifications

[0790] Step 8: Set and update rents

[0791] The server proposes appropriate rent revisions when a rental contract is renewed, and proposes rent increases or maintenance based on the desired rental area set by the user.

[0792] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[0793] Step 9: Push Notifications

[0794] Property information that matches the desired rental area conditions set by the user will be sent via push notification.

[0795] The server extracts matching property information in real time and notifies the user's terminal.

[0796] This system allows users to easily upload property information, receive highly accurate fair price assessments using generative AI models, and intuitively confirm the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications. This is expected to enable individual owners and investors to enter the real estate market more rationally and efficiently, stimulating the market.

[0797] The processing flow will be explained below.

[0798] Step 1:

[0799] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[0800] Step 2:

[0801] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[0802] Step 3:

[0803] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[0804] Step 4:

[0805] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[0806] Step 5:

[0807] The server stores the predicted fair prices in a database.

[0808] Step 6:

[0809] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[0810] Step 7:

[0811] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[0812] Step 8:

[0813] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0814] Step 9:

[0815] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[0816] Step 10:

[0817] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0818] Example 1

[0819] 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."

[0820] The purpose of this invention is to provide efficient and accurate price predictions in real estate transactions, enabling individual owners and investors to enter the market more rationally. By accurately predicting the fair price of real estate and providing intuitive information to users, the invention also enables efficient real estate transactions by proposing appropriate rent revisions and providing real-time notifications of property information that matches the user's conditions.

[0821] 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.

[0822] In this invention, the server includes means for automatically collecting real estate data from a public database, means for performing data cleansing on the collected real estate data and filtering out duplicate and inaccurate data to ensure data quality, means for predicting a fair price using the collected real estate data with a generative AI model, means for saving the predicted fair price in a database, means for having a user upload photos of property information and automatically extracting property information from the photos using an image analysis algorithm, means for saving the extracted property information in a database, means for visually displaying the predicted fair price, means for proposing a fair rent revision when renewing a rental contract, and means for sending push notifications of property information that matches the conditions of the desired rental area. This allows users to easily upload property information, receive highly accurate price evaluations from the generative AI model, and conduct real estate transactions efficiently and intuitively.

[0823] A "publicly accessible database" is a collection of information that is made available in a publicly accessible form and that includes real estate data.

[0824] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0825] "Data cleansing" is a process for removing duplicate data and inaccurate data from collected data and ensuring the quality of the data.

[0826] A "generative AI model" is an artificial intelligence model trained using historical data to predict the fair value of a property.

[0827] A "fair price" is a price that is fair and in line with market value, calculated based on market conditions and past trends.

[0828] A "database" is an information management system for efficiently storing and managing large amounts of data.

[0829] "Image analysis algorithm" refers to a computational method for extracting specific information or features from image data.

[0830] A "visual display" is a method of presenting data or information to a user in a visual form, such as a graph or chart.

[0831] "Rent revision" is the process of reevaluating and proposing an appropriate rent when renewing a rental property contract.

[0832] "Push notification" is a mechanism that sends new information that matches certain conditions to a user's device in real time.

[0833] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system is mainly composed of three entities: a server, a terminal, and a user.

[0834] Data collection

[0835] The server automatically collects real estate data from publicly available databases. These databases include, for example, public land price data, social media trend data, and property information from real estate companies. The server automatically collects data from each database using a Python scraping library (e.g., BeautifulSoup or Scrapy). If an API is provided, the server uses the requests library to send queries to the API and retrieve data in JSON format.

[0836] Data Cleansing

[0837] The server then cleanses the collected data, a process that uses the Pandas library to filter out duplicates and inaccurate data and ensure data quality. The cleansed data is then stored in a standardized format, ready to be fed into generative AI models.

[0838] Fair price forecast

[0839] The server uses the cleansed data to predict the fair price using a generative AI model. This generative AI model is built using TensorFlow and PyTorch and is trained on past transaction data. This allows for highly accurate prediction of the fair price for each property. The performance of the generative AI model is evaluated using cross-validation and test data, and measures are taken to prevent overfitting.

[0840] Saving prediction results

[0841] The predicted fair prices are stored in a database by the server. This database uses a relational database such as MySQL or PostgreSQL, which allows for efficient storage and management of prediction results.

[0842] Property information upload and automatic information extraction

[0843] Users upload photos of properties using their devices (e.g., smartphones or PCs). These photos are temporarily stored in cloud storage (e.g., AWS S3), and the URL is sent to the server. The server then runs image analysis algorithms using OpenCV or TensorFlow to automatically extract property information (e.g., floor plan, age) from the photos and store it in a database.

[0844] Information Visualization

[0845] The terminal uses D3.js and Chart.js to generate interactive charts and graphs, visually displaying information on the property's fair value and surrounding market price, allowing users to intuitively understand the property's value.

[0846] Rent setting and push notifications

[0847] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, by using Python's Sched library to schedule periodic rent evaluations, it can send notifications proposing new rents to users. It also detects property information that matches the conditions set by the user in real time and sends it to the device using a push notification service such as Firebase or OneSignal. This allows users to receive new property information promptly.

[0848] Examples of concrete examples and prompts

[0849] As a specific example, for a user looking for a 2LDK apartment in Shibuya Ward, Tokyo, the system works as follows:

[0850] 1. The user uploads a photo of a 2LDK apartment in Shibuya Ward from their device.

[0851] 2. The server automatically extracts information such as the floor plan and age of the building from the photo and stores it in a database.

[0852] 3. The server accesses the real estate database, cleanses the collected data, and generates a high-quality dataset.

[0853] 4. The server inputs this dataset into a generative AI model to predict the fair price.

[0854] 5. The server stores the prediction results in a database and simultaneously displays them visually on the device (as graphs or charts).

[0855] 6. When the lease is about to expire, the server sends a notification to the user suggesting a reasonable rent.

[0856] 7. The server sends push notifications of property information that matches the conditions set by the user.

[0857] Example prompt sentence:

[0858] "Please estimate the fair price of a 2LDK apartment in Shibuya Ward. The area is 70 square meters, the building is 10 years old, and the nearest station is Shibuya Station."

[0859] This system allows users to easily upload property information and receive highly accurate price valuations from a generative AI model. It also provides real-time push notifications and offers appropriate rent revisions, enabling efficient real estate transactions.

[0860] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0861] Processing flow and specific explanation

[0862] Step 1:

[0863] The server accesses public databases and automatically collects real estate data. Specifically, it uses Python scraping libraries (e.g., BeautifulSoup, Scrapy) to obtain detailed information such as property addresses, prices, area sizes, ages, and surrounding facilities from each database. It also uses the requests library to obtain data from databases that provide APIs. The input is the database URL or API endpoint, and the output is a list of collected real estate data.

[0864] Step 2:

[0865] The server performs data cleansing on the collected real estate data. This process uses the Pandas library to filter out duplicate and inaccurate data and ensure data quality. For example, it removes duplicate entries in the database and eliminates records with incorrect values. The input is the collected real estate data, and the output is a cleansed, high-quality dataset.

[0866] Step 3:

[0867] The server inputs the cleansed real estate data into a generative AI model to predict the fair price. The generative AI model, built using TensorFlow and PyTorch, predicts the price based on the property's past transaction data and market trends. As a specific example, the model is trained using past transaction data and its performance is evaluated using cross-validation. The input is the cleansed dataset, and the output is the predicted fair price.

[0868] Step 4:

[0869] The server stores the fair price predicted by the generative AI model in a database. Here, a relational database such as MySQL or PostgreSQL is used for the storage process. The input is the predicted fair price data, and the output is the predicted price information stored in the database.

[0870] Step 5:

[0871] A user uploads a property photo using a device. For example, by selecting a property photo from a smartphone or PC and clicking the upload button, the property information is sent to the server. The input is the uploaded property photo, and the output is the image URL sent to the server.

[0872] Step 6:

[0873] The server automatically extracts property information from uploaded property photos using an image analysis algorithm. Specifically, it uses image processing with OpenCV and TensorFlow to extract information such as floor plan and age of the building, and stores it in a database. The input is a property photo, and the output is the extracted property information.

[0874] Step 7:

[0875] The terminal visually displays predicted fair prices and surrounding market information to the user. Interactive charts and graphs are generated using D3.js and Chart.js and displayed in the user interface. The input is predicted fair price data and surrounding market data, and the output is an interactive display.

[0876] Step 8:

[0877] The server proposes appropriate rent revisions when a rental contract is renewed. It uses Python's Sched library to periodically schedule rental property price evaluations and notify users of proposed rent revisions. The input is rental property information and current market data, and the output is a rent revision proposal notification.

[0878] Step 9:

[0879] The server detects property information that matches the desired rental area conditions set by the user in real time and sends a push notification. Using Firebase or OneSignal, property information that matches the conditions is sent to the user's device. The input is new property information and the user's conditions, and the output is a push notification.

[0880] end

[0881] By processing in this step-by-step format, users can efficiently and intuitively perform fair value assessments, lease renewals, and receive property information.

[0882] (Application example 1)

[0883] 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."

[0884] Current real estate transaction systems require a great deal of time and effort to collect property data, predict fair prices, and visualize property information. Even when users upload property photos, the information is not accurately extracted, making it difficult to link to price predictions. Furthermore, real-time notification of property information in the most suitable rental areas hinders efficient real estate transactions.

[0885] 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.

[0886] In this invention, the server includes a means for automatically collecting real estate data from a public database, a means for using the collected real estate data to predict fair prices using a generative AI model, a means for automatically extracting property information from uploaded images, a means for visually displaying the predicted fair prices, and a means for sending push notifications of property information that matches the desired rental area. This allows users to easily upload property information, receive highly accurate fair price assessments, and intuitively confirm the value of the property. Furthermore, efficient real estate transactions are enabled through pricing of rental properties, appropriate rent proposals at the time of renewal, and real-time push notifications.

[0887] A database is a system that systematically organizes and stores information and allows it to be quickly retrieved when needed.

[0888] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0889] A "generative AI model" is an artificial intelligence model that is trained to achieve a specific purpose (e.g., price prediction) based on large amounts of data.

[0890] "Prediction" is the act of estimating future values ​​or situations based on collected data.

[0891] "Image analysis" is the process of automatically extracting useful information from image data.

[0892] A "fair price" is a fair and reasonable price calculated based on the market supply and demand situation and the characteristics of the property.

[0893] "Visualization" refers to the representation of data or information using visual means such as charts and graphs.

[0894] "Push notifications" are real-time notifications that are automatically sent from a server to a user's device.

[0895] This invention is a system for predicting the fair value of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following components and procedures are required to implement this invention.

[0896] System configuration

[0897] It mainly consists of three entities: a server, a terminal, and a user.

[0898] Data Collection and Cleansing

[0899] The server automatically collects real estate data by accessing databases containing publicly available real estate information (e.g., public databases, social media trend data, real estate agency property information, etc.). It uses programming languages ​​such as Python to send queries to the database via APIs to obtain detailed information such as the property's address, price, area, age, and surrounding facilities. The server then normalizes the data and filters out duplicate data to ensure data quality.

[0900] Fair price forecast

[0901] The server inputs the collected real estate data into a generative AI model to analyze detailed information for each property. At this stage, an AI framework such as TensorFlow is used to train a price prediction model based on past data, enabling fair and highly accurate price predictions. The generative AI model also takes into account past trends and current market conditions to predict future value fluctuations.

[0902] Upload and auto-extract property information

[0903] Users upload property photos using their devices (smartphones or PCs). For example, they select a property photo from their smartphone or PC and click the upload button. The server automatically extracts property information from this photo. Using an image analysis algorithm, it extracts features such as floor plan and age of the building and stores them in a database.

[0904] Information Visualization

[0905] The device visually displays information about the property's fair value and surrounding market prices to the user. For example, in a smartphone app developed using React Native, interactive charts and graphs are generated and displayed using D3.js, allowing users to intuitively check the property's value.

[0906] Rent setting and push notifications

[0907] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, the server monitors the expiration of the rental contract and sends a notification proposing a new rent when it's time for renewal, based on the desired rental area set by the user. Furthermore, the server sends real-time push notifications of property information that matches the desired rental area set by the user. Specifically, the server compares real estate data with the user's conditions and immediately notifies the user's device of any matching property information. This push notification function allows users to receive the latest information in a timely manner, making real estate transactions more efficient.

[0908] Examples and prompts

[0909] A specific use case might involve a user uploading a photo of a 10-year-old, 100-square-meter house in Tokyo, and predicting the appropriate price for that property. The prompt might look like this:

[0910] "This property is located in Tokyo, is a 10-year-old house with an area of ​​100 square meters. Please estimate the fair price for this property."

[0911] This system allows individual owners and investors to easily upload property information, receive highly accurate fair price assessments, and intuitively check the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications, which is expected to revitalize the real estate market.

[0912] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0913] Step 1:

[0914] The server automatically collects real estate data by accessing a public database. Specifically, it uses an API to send queries to the database and obtain detailed information such as the property's address, price, area, age, surrounding facilities, etc. The input is the query to the database, and the output is the collected real estate data.

[0915] Step 2:

[0916] The server cleanses the collected data. Specifically, it removes duplicate data, filters inaccurate data, and normalizes it. The input is the collected real estate data, and the output is the cleansed real estate data. Python is used for this data cleansing.

[0917] Step 3:

[0918] The server inputs the cleansed real estate data into a generative AI model to predict fair prices. The generative AI model uses TensorFlow to train a predictive model based on historical data, taking into account past trends and current market conditions. The input is the cleansed data and a prompt for the AI ​​model, and the output is a predicted fair price.

[0919] Step 4:

[0920] The user uploads a property photo using a device. For example, they select a property photo from their smartphone or PC and click the upload button. The input is the user uploading the photo, and the output is sending the photo data to the server.

[0921] Step 5:

[0922] The server automatically extracts property information from uploaded photos. Specifically, it uses an image analysis algorithm to extract features such as floor plan and age of the building and stores them in a database. The input is the photo data, and the output is the property information extracted from the photo. This analysis uses computer vision technology.

[0923] Step 6:

[0924] The terminal visually displays information about the property's fair price and surrounding market prices to the user. Specifically, interactive charts and graphs are generated and displayed using D3.js using React Native. The input is the predicted fair price and property information, and the output is the visually displayed data.

[0925] Step 7:

[0926] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it proposes rent increases or maintenance based on the desired rental area set by the user. The input is the desired area and property data set by the user, and the output is the proposed new rent.

[0927] Step 8:

[0928] The server sends push notifications of property information that matches the user's desired rental area. The server compares real estate data with the user's conditions and notifies the user's device of matching property information in real time. The input is the user's desired conditions and the latest real estate data, and the output is a push notification.

[0929] 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.

[0930] The present invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. Furthermore, the system aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotions. The following describes an embodiment of the present invention.

[0931] Data collection

[0932] Step 1: Collect real estate data from publicly available databases.

[0933] The server accesses databases containing publicly available real estate information (e.g., public land price data, property information from real estate companies, etc.) and automatically collects real estate data.

[0934] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[0935] Step 2: Cleanse the data you get.

[0936] The server filters out duplicate and inaccurate data to ensure data quality.

[0937] Data analysis

[0938] Step 3: Use a generative AI model to predict the fair price.

[0939] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[0940] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[0941] Step 4: Save the prediction results

[0942] The server stores the fair prices predicted by the generative AI model in a database.

[0943] User Interface

[0944] Step 5: Upload your property

[0945] Users upload property photos using their device. Specifically, they select property photos from their smartphone or PC and click the upload button.

[0946] Step 6: Automatic information extraction

[0947] The server automatically extracts property information from these photos, using image analysis algorithms to analyze characteristic information such as floor plan and age of the building, and stores the information in a database.

[0948] Step 7: Visualize the information

[0949] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0950] Emotion Engine

[0951] Step 8: Recognizing User Emotions

[0952] The device recognizes the user's emotions using the user's voice input, facial expression analysis, or data from biometric sensors.

[0953] For example, a camera captures a user's facial expression while they are looking at property information, and the emotion engine analyzes the captured emotion data in real time.

[0954] Step 9: Customize the presentation of information

[0955] The emotion engine customizes the displayed information based on the user's perceived emotions.

[0956] For example, if a user is feeling stressed, provide an interface with softer colors and simpler explanations, whereas if a user is feeling positive, provide more detailed information and additional data.

[0957] Pricing & Notifications

[0958] Step 10: Set and update rents

[0959] The server proposes appropriate rent revisions when a rental contract is renewed. It proposes rent increases or maintenance based on the desired rental area set by the user.

[0960] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[0961] Step 11: Push Notifications

[0962] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0963] Specific examples

[0964] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[0965] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[0966] In this way, individual owners and investors can make better decisions by making real estate transactions at fair prices and receiving appropriate information based on user emotions. The introduction of an emotion engine will improve the user experience and promote efficient and fair real estate transactions.

[0967] The processing flow will be explained below.

[0968] Step 1:

[0969] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[0970] Step 2:

[0971] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[0972] Step 3:

[0973] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[0974] Step 4:

[0975] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[0976] Step 5:

[0977] The server stores the predicted fair price in a database, making it available for subsequent processes.

[0978] Step 6:

[0979] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[0980] Step 7:

[0981] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[0982] Step 8:

[0983] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[0984] Step 9:

[0985] The device can recognize the user's emotions using voice input, facial expression analysis, or data from biometric sensors. For example, a camera captures the user's facial expressions, which are then analyzed by an emotion engine.

[0986] Step 10:

[0987] The emotion engine customizes the displayed information based on the user's perceived emotions. For example, if the user is feeling stressed, the interface will be softened in color and a simple explanation will be provided.

[0988] Step 11:

[0989] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[0990] Step 12:

[0991] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[0992] Example 2

[0993] 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."

[0994] The present invention aims to solve problems in real estate transactions, such as the lack of fair price evaluations, data reliability issues, and improving the user experience. It also aims to seamlessly perform automatic collection and cleansing of real estate data, fair price prediction, and information provision based on user sentiment. With conventional technology, there was no system that could perform all of these tasks in an integrated manner, making it difficult to conduct efficient and fair real estate transactions.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0996] In this invention, the server includes: means for automatically collecting real estate data from a public database; means for cleansing the collected real estate data; means for predicting a fair price using a generative AI model based on the cleansed real estate data; means for saving the predicted fair price in a database; means for uploading property photos; means for automatically extracting information from the uploaded photos; means for visually displaying the fair price; means for recognizing a user's emotions; means for customizing information based on the recognized emotions; and means for sending push notifications of property information matching the desired rental area. This allows users to receive reliable real estate price assessments in real time and personalized information based on their emotions. It also promotes efficient and fair real estate transactions.

[0997] A "public database" is a database that collects real estate-related information that is made publicly available on the Internet by public institutions and private companies.

[0998] "Real estate data" refers to all information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[0999] "Cleansing" refers to the process of removing duplicate and incorrect data from collected data to ensure data quality.

[1000] A "generative AI model" is an artificial intelligence model trained using machine learning techniques to predict the fair value of real estate.

[1001] "Fair price" refers to the fair and accurate market price of a property predicted by the generative AI model based on collected real estate data.

[1002] "Storing in a database" means storing the predicted fair price and collected real estate data in a database in an appropriate format.

[1003] "Property photos" are images uploaded by users that show the exterior and interior of a property.

[1004] "Automatic information extraction" refers to the use of image analysis algorithms to extract specific information, such as floor plan and age, from uploaded property photos.

[1005] "Visually displaying" means presenting the collected and predicted real estate data and fair prices to the user in an interactive format such as graphs and charts.

[1006] "Recognizing user emotions" means analyzing the user's emotional state through voice input, facial expression analysis, and data from biometric sensors.

[1007] "Customizing information" means adjusting the content and presentation of information based on the user's recognized emotions.

[1008] "Push notification" means notifying the user's device in real time of new real estate information that matches the conditions specified by the user.

[1009] MODE FOR CARRYING OUT THE INVENTION

[1010] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system not only collects real estate data from public databases and predicts the fair price using a generative AI model, but also improves the user experience by recognizing user emotions and customizing information.

[1011] Hardware and software used

[1012] The server uses a computer with high-performance computing resources, specifically a web server using programming languages ​​such as Python or JavaScript, and machine learning libraries such as Sklearn or TensorFlow.

[1013] The terminal refers to the smartphone or personal computer operated by the user, on which the web browser and dedicated applications run.

[1014] The database used is a relational database management system such as MySQL or PostgreSQL.

[1015] Processing Details

[1016] 1. Collecting real estate data from public databases

[1017] The server accesses public real estate databases (e.g., land price announcement data, property information from real estate companies) to collect the necessary data. Specifically, it sends HTTP requests using the Python requests library and saves the retrieved data in JSON format.

[1018] 2. Data Cleansing

[1019] The server uses the Pandas library to cleanse the collected data: it processes the data in data frame format, removes duplicate data with the drop_duplicates() method, and imputes missing values ​​with the fillna() method.

[1020] 3. Fair price prediction

[1021] The server inputs the cleansed data into a generative AI model to predict the appropriate price. The price prediction model is trained using TensorFlow and PyTorch, and predicts fair and accurate prices based on detailed information about each property.

[1022] 4. Saving the results

[1023] The server stores the fair prices predicted by the generative AI model in a database. It connects to the database using SQLAlchemy or Django ORM and inserts the prediction results into the appropriate tables.

[1024] 5. Upload property information

[1025] Users upload property photos from their devices, select image files and send them through their browsers, and the server receives them using web frameworks such as Flask or Django.

[1026] 6. Automatic Information Extraction

[1027] The server uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age of the building from the uploaded photos.

[1028] 7. Information Visualization

[1029] The terminal visually displays fair value and surrounding market information to the user, using D3.js and Chart.js to generate interactive graphs and charts.

[1030] 8. Emotional Recognition

[1031] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. It analyzes the user's facial expressions using OpenCV and a pre-trained model for emotion recognition.

[1032] 9. Customizing Information

[1033] The emotion engine customizes information based on the user's recognized emotions, dynamically modifying front-end CSS and JavaScript based on emotion recognition data to provide softer colors and simpler explanations for stressed users and more detailed information for more proactive users.

[1034] 10. Rent Setting and Renewal

[1035] The server proposes appropriate rent revisions when a rental property contract is renewed. It periodically checks contract expiration dates using a scheduler and sends emails and in-app notifications at the appropriate times.

[1036] 11. Push Notifications

[1037] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user, using push notification services such as Google Firebase to send the information to the user's device.

[1038] Specific examples

[1039] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[1040] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[1041] Prompt Sentence Examples

[1042] "How can I gather real estate information from public databases and predict fair prices?"

[1043] "Please explain the algorithm that automatically extracts information from uploaded property photos."

[1044] "Tell me more about how you can recognize a user's emotions and customize the information based on them."

[1045] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1046] Step 1:

[1047] The server accesses public databases to collect real estate data. Specifically, the server uses Python's requests library to send HTTP requests to obtain public land price data, property information from real estate companies, and other information. The API endpoint URL is required as input, and the output is JSON-formatted data containing detailed information such as the property's address, price, area, age, and surrounding facilities. The server temporarily stores this data in storage.

[1048] Step 2:

[1049] The server cleanses the collected data. Specifically, it processes the data in data frame format using the Pandas library. The input required is the JSON data obtained in step 1, and the output is high-quality data with duplicate data and missing values ​​filled in. The server removes duplicate data using the drop_duplicates() method and fills in missing values ​​using the fillna() method.

[1050] Step 3:

[1051] The server inputs the cleansed data into a generative AI model to predict the appropriate price. Specifically, it trains the AI ​​model using TensorFlow and PyTorch to predict prices based on detailed information about each property. High-quality cleansed data is required as input, and the output is the predicted price for each property. The server inputs the data into the trained model and uses the predict() method to make price predictions.

[1052] Step 4:

[1053] The server saves the fair price predicted by the generative AI model to a database. Specifically, it connects to the database using SQLAlchemy or Django ORM and inserts the predicted results into the appropriate table. The input is the predicted fair price, and the output is the predicted price information stored in the database. The server inserts the data using the session.add() and session.commit() methods.

[1054] Step 5:

[1055] The user uploads a property photo from their device. Specifically, they select an image file from their smartphone or PC, send it through the browser, and click the upload button. The input is a photo file of the property, and the output is the photo data stored on the server. The device sends the photo to the server using an HTTP POST request.

[1056] Step 6:

[1057] The server automatically extracts information from uploaded property photos. Specifically, it uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age from the photos. The input is the uploaded photo data, and the output is the extracted property information. The server reads the image using the cv2.imread() method and applies image analysis algorithms to extract information.

[1058] Step 7:

[1059] The terminal visually displays fair price and surrounding market information to the user. Specifically, it generates interactive graphs and charts using D3.js and Chart.js. The input required is predicted price information retrieved from a database, and the output is a graph or chart displayed in the browser. The terminal uses the JavaScript chart.draw() method to draw.

[1060] Step 8:

[1061] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. Specifically, it uses OpenCV and a pre-trained model for emotion recognition. The input requires sensor data acquired from a camera, microphone, etc., and the output is the recognized user emotion data. The device acquires video data using the cv2.VideoCapture() method and applies the emotion recognition algorithm.

[1062] Step 9:

[1063] The emotion engine customizes information based on the user's recognized emotions. Specifically, it dynamically changes CSS and JavaScript to provide softer colors and simpler explanations for stressed users and more detailed information for more active users. The input required is the emotion data output by the emotion engine, and the output is a customized user interface. The emotion engine uses if statements to change the UI depending on the conditions.

[1064] Step 10:

[1065] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it uses a scheduler to periodically check the contract expiration date and sends emails and in-app notifications at the appropriate time. The input requires the user's contract information, and the output is a notification proposing rent revisions. The server performs periodic checks using the schedule library and sends notifications using the send_email() method.

[1066] Step 11:

[1067] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user. Specifically, it uses a push notification service such as Google Firebase. The input requires the user's set conditions and new property information, and the output is a notification to the user's device. The server uses the Firebase API to send a push notification every time new property data is received.

[1068] (Application example 2)

[1069] 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."

[1070] In today's real estate market, it is difficult to quickly and accurately predict fair prices. This is especially true for investors and individual owners, who find it difficult to make accurate decisions when renewing leases or purchasing new properties. Furthermore, there is a lack of systems for providing personalized information that takes user emotions into account, leaving room for improvement in the user experience.

[1071] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting real estate data from a public database, means for predicting a fair price using the collected real estate data with a generative AI model, means for visually displaying the predicted fair price, means for sending push notifications of property information that matches the desired rental area conditions, means for recognizing the user's emotions using the device's camera, and means for customizing the visual display based on the emotion recognition results. This allows users to quickly and accurately grasp fair property prices and rental conditions, and also enables the provision of personalized information according to emotions.

[1072] "Public Database" means any publicly accessible online or offline data source that contains market information or real estate-related data.

[1073] "Real estate data" refers to all information related to real estate, such as the property's address, price, area, age, and surrounding facilities.

[1074] "Fair value" refers to the reasonable and fair assessment of the value of real estate, taking into account past trends and current market conditions.

[1075] A "generative AI model" is a model built using machine learning and artificial intelligence technologies, and is an algorithm for predicting the fair price of real estate based on large amounts of data.

[1076] "Visual display means" refers to methods of presenting information to users in an easy-to-understand manner, such as using graphs, charts, or interactive maps.

[1077] "Property information that matches the conditions of the desired rental area" is information on rental properties that match the area, budget, and other requirements set by the user.

[1078] "Push notification" is a technology that notifies a device in real time of new property or rental information that matches the conditions specified by the user.

[1079] "Terminal" refers to any device that a user uses to view information, such as a smartphone, head-mounted display, or tablet.

[1080] "Means for recognizing a user's emotions using a camera" refers to technology that uses a camera or other sensors installed on the device to analyze the user's facial expressions and voice and identify their emotions.

[1081] "Means for customizing visual displays based on emotion recognition results" refers to a method for providing information optimized for individual users by adjusting the display content and interface according to the user's emotion data.

[1082] "Personalized information provision" refers to a general service that individually customizes appropriate property information and visual displays based on the user's situation and preferences.

[1083] This invention is a system that collects real estate data from public databases, uses that data to predict fair prices using a generative AI model, and also recognizes the user's emotions to provide visually customized information.

[1084] The server first accesses public databases and automatically collects real estate data. During data collection, it normalizes and filters duplicate data to ensure data quality. It then uses a generative AI model to analyze the collected real estate data and predict the appropriate price. This prediction takes into account past trends and current market conditions.

[1085] Users can visually check property information using devices such as smartphones or head-mounted displays (HMDs). The devices are equipped with cameras that capture the user's facial expressions while they are viewing the information. The facial expression data captured by the camera is analyzed in real time by an emotion recognition algorithm to identify the user's emotions (e.g., stress, excitement, etc.).

[1086] Emotional data is used to customize the format and content of the property information displayed. For example, if a user is stressed, the interface may be softened and the amount of information displayed may be simplified. On the other hand, if the user is interested, more detailed information or additional data may be provided.

[1087] For example, when a user uploads a photo of a property from their device, the server automatically extracts property information from the photo and uses a generative AI model to predict the appropriate price. The device then visually presents the appropriate price and surrounding market information to the user. Furthermore, the system analyzes the user's emotional state, and if it determines that the user is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[1088] The app also has a push notification feature that sends real-time information about properties that match the area the user is looking to rent in. When the user receives the information, emotion recognition is activated, and if a positive emotion is detected, detailed property information will be provided.

[1089] An example of a prompt is as follows:

[1090] Emotion recognition prompts:

[1091] input: "Recognize emotions from images where the user is facing the camera."

[1092] output: "User emotion is stress."

[1093] Price prediction prompt:

[1094] input: "Enter price data for a specific real estate area and predict the fair value."

[1095] output: "The fair price for this property is 50 million yen."

[1096] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1097] Step 1:

[1098] The server accesses public databases and automatically collects real estate data, such as the property's address, price, area, age, and surrounding facilities. The collected data is then stored in the database.

[1099] Step 2:

[1100] The server normalizes the collected data and filters duplicate data, ensuring data quality. Data normalization involves converting data from different formats into a unified format and filtering duplicate data.

[1101] Step 3:

[1102] The server uses a generative AI model to predict the fair price based on the normalized data. The collected data is input into the generative AI model, which then obtains a predicted fair price that takes into account past trends and current market conditions.

[1103] Step 4:

[1104] The server stores the predicted fair price in a database, where it is stored along with other information for later visual presentation to the user.

[1105] Step 5:

[1106] Users upload property photos using their devices, which receive the photo data and send it to the server.

[1107] Step 6:

[1108] The server automatically extracts property information from uploaded photos, using image analysis algorithms to extract characteristic information such as floor plan and age, and adds it to a database.

[1109] Step 7:

[1110] The device visually displays the property's fair value and surrounding market information to the user, for example by generating interactive charts and graphs, in a format that allows the user to easily understand the property's value.

[1111] Step 8:

[1112] The device's camera captures the user's facial expressions and analyzes the data in real time. An emotion engine is used to recognize the user's emotions, such as stress or excitement.

[1113] Step 9:

[1114] The server customizes the visual display based on the emotion recognition results. If the user is stressed, the interface changes to softer colors and provides less information. If the user is interested, more detailed information is displayed.

[1115] Step 10:

[1116] The server pushes real-time information about properties that match the desired rental area, filters the data based on the conditions set by the user, and sends the relevant property information to the device.

[1117] Step 11:

[1118] The user checks the push notification received on their device, and their emotional data is also analyzed. If a positive emotion is detected, the server will provide additional detailed property information.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] [Fourth embodiment]

[1123] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1124] 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.

[1125] 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).

[1126] 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.

[1127] 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.

[1128] 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).

[1129] 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. 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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."

[1136] The present invention is a system for predicting the fair price of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following describes an embodiment of the present invention.

[1137] This system is mainly composed of three entities: a server, a terminal, and a user.

[1138] Data collection

[1139] Step 1: Collect real estate data from publicly available databases.

[1140] The server accesses databases containing publicly available real estate information (e.g., public land price data, social media trend data, property information from real estate companies, etc.) and automatically collects real estate data.

[1141] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[1142] Step 2: Cleanse the data you get.

[1143] The server filters out duplicate and inaccurate data to ensure data quality.

[1144] Data analysis

[1145] Step 3: Use a generative AI model to predict the fair price.

[1146] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[1147] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[1148] Step 4: Save the prediction results

[1149] The server stores the fair prices predicted by the generative AI model in a database.

[1150] User Interface

[1151] Step 5: Upload your property

[1152] The user uploads a property photo using a device, for example, by selecting a property photo from a smartphone or PC and clicking the upload button.

[1153] Step 6: Automatic information extraction

[1154] The server automatically extracts property information from these photos, using image analysis algorithms to extract features such as floor plan and age of the building, and stores them in a database.

[1155] Step 7: Visualize the information

[1156] The device can visually display information about the property's fair value and surrounding market prices to the user, for example by generating interactive charts and graphs and displaying them on the device's UI.

[1157] Pricing & Notifications

[1158] Step 8: Set and update rents

[1159] The server proposes appropriate rent revisions when a rental contract is renewed, and proposes rent increases or maintenance based on the desired rental area set by the user.

[1160] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[1161] Step 9: Push Notifications

[1162] Property information that matches the desired rental area conditions set by the user will be sent via push notification.

[1163] The server extracts matching property information in real time and notifies the user's terminal.

[1164] This system allows users to easily upload property information, receive highly accurate fair price assessments using generative AI models, and intuitively confirm the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications. This is expected to enable individual owners and investors to enter the real estate market more rationally and efficiently, stimulating the market.

[1165] The processing flow will be explained below.

[1166] Step 1:

[1167] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[1168] Step 2:

[1169] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[1170] Step 3:

[1171] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[1172] Step 4:

[1173] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[1174] Step 5:

[1175] The server stores the predicted fair prices in a database.

[1176] Step 6:

[1177] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[1178] Step 7:

[1179] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[1180] Step 8:

[1181] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[1182] Step 9:

[1183] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[1184] Step 10:

[1185] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[1186] Example 1

[1187] 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."

[1188] The purpose of this invention is to provide efficient and accurate price predictions in real estate transactions, enabling individual owners and investors to enter the market more rationally. By accurately predicting the fair price of real estate and providing intuitive information to users, the invention also enables efficient real estate transactions by proposing appropriate rent revisions and providing real-time notifications of property information that matches the user's conditions.

[1189] 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.

[1190] In this invention, the server includes means for automatically collecting real estate data from a public database, means for performing data cleansing on the collected real estate data and filtering out duplicate and inaccurate data to ensure data quality, means for predicting a fair price using the collected real estate data with a generative AI model, means for saving the predicted fair price in a database, means for having a user upload photos of property information and automatically extracting property information from the photos using an image analysis algorithm, means for saving the extracted property information in a database, means for visually displaying the predicted fair price, means for proposing a fair rent revision when renewing a rental contract, and means for sending push notifications of property information that matches the conditions of the desired rental area. This allows users to easily upload property information, receive highly accurate price evaluations from the generative AI model, and conduct real estate transactions efficiently and intuitively.

[1191] A "publicly accessible database" is a collection of information that is made available in a publicly accessible form and that includes real estate data.

[1192] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[1193] "Data cleansing" is a process for removing duplicate data and inaccurate data from collected data and ensuring the quality of the data.

[1194] A "generative AI model" is an artificial intelligence model trained using historical data to predict the fair value of a property.

[1195] A "fair price" is a price that is fair and in line with market value, calculated based on market conditions and past trends.

[1196] A "database" is an information management system for efficiently storing and managing large amounts of data.

[1197] "Image analysis algorithm" refers to a computational method for extracting specific information or features from image data.

[1198] A "visual display" is a method of presenting data or information to a user in a visual form, such as a graph or chart.

[1199] "Rent revision" is the process of reevaluating and proposing an appropriate rent when renewing a rental property contract.

[1200] "Push notification" is a mechanism that sends new information that matches certain conditions to a user's device in real time.

[1201] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system is mainly composed of three entities: a server, a terminal, and a user.

[1202] Data collection

[1203] The server automatically collects real estate data from publicly available databases. These databases include, for example, public land price data, social media trend data, and property information from real estate companies. The server automatically collects data from each database using a Python scraping library (e.g., BeautifulSoup or Scrapy). If an API is provided, the server uses the requests library to send queries to the API and retrieve data in JSON format.

[1204] Data Cleansing

[1205] The server then cleanses the collected data, a process that uses the Pandas library to filter out duplicates and inaccurate data and ensure data quality. The cleansed data is then stored in a standardized format, ready to be fed into generative AI models.

[1206] Fair price forecast

[1207] The server uses the cleansed data to predict the fair price using a generative AI model. This generative AI model is built using TensorFlow and PyTorch and is trained on past transaction data. This allows for highly accurate prediction of the fair price for each property. The performance of the generative AI model is evaluated using cross-validation and test data, and measures are taken to prevent overfitting.

[1208] Saving prediction results

[1209] The predicted fair prices are stored in a database by the server. This database uses a relational database such as MySQL or PostgreSQL, which allows for efficient storage and management of prediction results.

[1210] Property information upload and automatic information extraction

[1211] Users upload photos of properties using their devices (e.g., smartphones or PCs). These photos are temporarily stored in cloud storage (e.g., AWS S3), and the URL is sent to the server. The server then runs image analysis algorithms using OpenCV or TensorFlow to automatically extract property information (e.g., floor plan, age) from the photos and store it in a database.

[1212] Information Visualization

[1213] The terminal uses D3.js and Chart.js to generate interactive charts and graphs, visually displaying information on the property's fair value and surrounding market price, allowing users to intuitively understand the property's value.

[1214] Rent setting and push notifications

[1215] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, by using Python's Sched library to schedule periodic rent evaluations, it can send notifications proposing new rents to users. It also detects property information that matches the conditions set by the user in real time and sends it to the device using a push notification service such as Firebase or OneSignal. This allows users to receive new property information promptly.

[1216] Examples of concrete examples and prompts

[1217] As a specific example, for a user looking for a 2LDK apartment in Shibuya Ward, Tokyo, the system works as follows:

[1218] 1. The user uploads a photo of a 2LDK apartment in Shibuya Ward from their device.

[1219] 2. The server automatically extracts information such as the floor plan and age of the building from the photo and stores it in a database.

[1220] 3. The server accesses the real estate database, cleanses the collected data, and generates a high-quality dataset.

[1221] 4. The server inputs this dataset into a generative AI model to predict the fair price.

[1222] 5. The server stores the prediction results in a database and simultaneously displays them visually on the device (as graphs or charts).

[1223] 6. When the lease is about to expire, the server sends a notification to the user suggesting a reasonable rent.

[1224] 7. The server sends push notifications of property information that matches the conditions set by the user.

[1225] Example prompt sentence:

[1226] "Please estimate the fair price of a 2LDK apartment in Shibuya Ward. The area is 70 square meters, the building is 10 years old, and the nearest station is Shibuya Station."

[1227] This system allows users to easily upload property information and receive highly accurate price valuations from a generative AI model. It also provides real-time push notifications and offers appropriate rent revisions, enabling efficient real estate transactions.

[1228] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1229] Processing flow and specific explanation

[1230] Step 1:

[1231] The server accesses public databases and automatically collects real estate data. Specifically, it uses Python scraping libraries (e.g., BeautifulSoup, Scrapy) to obtain detailed information such as property addresses, prices, area sizes, ages, and surrounding facilities from each database. It also uses the requests library to obtain data from databases that provide APIs. The input is the database URL or API endpoint, and the output is a list of collected real estate data.

[1232] Step 2:

[1233] The server performs data cleansing on the collected real estate data. This process uses the Pandas library to filter out duplicate and inaccurate data and ensure data quality. For example, it removes duplicate entries in the database and eliminates records with incorrect values. The input is the collected real estate data, and the output is a cleansed, high-quality dataset.

[1234] Step 3:

[1235] The server inputs the cleansed real estate data into a generative AI model to predict the fair price. The generative AI model, built using TensorFlow and PyTorch, predicts the price based on the property's past transaction data and market trends. As a specific example, the model is trained using past transaction data and its performance is evaluated using cross-validation. The input is the cleansed dataset, and the output is the predicted fair price.

[1236] Step 4:

[1237] The server stores the fair price predicted by the generative AI model in a database. Here, a relational database such as MySQL or PostgreSQL is used for the storage process. The input is the predicted fair price data, and the output is the predicted price information stored in the database.

[1238] Step 5:

[1239] A user uploads a property photo using a device. For example, by selecting a property photo from a smartphone or PC and clicking the upload button, the property information is sent to the server. The input is the uploaded property photo, and the output is the image URL sent to the server.

[1240] Step 6:

[1241] The server automatically extracts property information from uploaded property photos using an image analysis algorithm. Specifically, it uses image processing with OpenCV and TensorFlow to extract information such as floor plan and age of the building, and stores it in a database. The input is a property photo, and the output is the extracted property information.

[1242] Step 7:

[1243] The terminal visually displays predicted fair prices and surrounding market information to the user. Interactive charts and graphs are generated using D3.js and Chart.js and displayed in the user interface. The input is predicted fair price data and surrounding market data, and the output is an interactive display.

[1244] Step 8:

[1245] The server proposes appropriate rent revisions when a rental contract is renewed. It uses Python's Sched library to periodically schedule rental property price evaluations and notify users of proposed rent revisions. The input is rental property information and current market data, and the output is a rent revision proposal notification.

[1246] Step 9:

[1247] The server detects property information that matches the desired rental area conditions set by the user in real time and sends a push notification. Using Firebase or OneSignal, property information that matches the conditions is sent to the user's device. The input is new property information and the user's conditions, and the output is a push notification.

[1248] end

[1249] By processing in this step-by-step format, users can efficiently and intuitively perform fair value assessments, lease renewals, and receive property information.

[1250] (Application example 1)

[1251] 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."

[1252] Current real estate transaction systems require a great deal of time and effort to collect property data, predict fair prices, and visualize property information. Even when users upload property photos, the information is not accurately extracted, making it difficult to link to price predictions. Furthermore, real-time notification of property information in the most suitable rental areas hinders efficient real estate transactions.

[1253] 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.

[1254] In this invention, the server includes a means for automatically collecting real estate data from a public database, a means for using the collected real estate data to predict fair prices using a generative AI model, a means for automatically extracting property information from uploaded images, a means for visually displaying the predicted fair prices, and a means for sending push notifications of property information that matches the desired rental area. This allows users to easily upload property information, receive highly accurate fair price assessments, and intuitively confirm the value of the property. Furthermore, efficient real estate transactions are enabled through pricing of rental properties, appropriate rent proposals at the time of renewal, and real-time push notifications.

[1255] A database is a system that systematically organizes and stores information and allows it to be quickly retrieved when needed.

[1256] "Real estate data" refers to detailed information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[1257] A "generative AI model" is an artificial intelligence model that is trained to achieve a specific purpose (e.g., price prediction) based on large amounts of data.

[1258] "Prediction" is the act of estimating future values ​​or situations based on collected data.

[1259] "Image analysis" is the process of automatically extracting useful information from image data.

[1260] A "fair price" is a fair and reasonable price calculated based on the market supply and demand situation and the characteristics of the property.

[1261] "Visualization" refers to the representation of data or information using visual means such as charts and graphs.

[1262] "Push notifications" are real-time notifications that are automatically sent from a server to a user's device.

[1263] This invention is a system for predicting the fair value of real estate and enabling individual owners and investors to efficiently conduct real estate transactions. The following components and procedures are required to implement this invention.

[1264] System configuration

[1265] It mainly consists of three entities: a server, a terminal, and a user.

[1266] Data Collection and Cleansing

[1267] The server automatically collects real estate data by accessing databases containing publicly available real estate information (e.g., public databases, social media trend data, real estate agency property information, etc.). It uses programming languages ​​such as Python to send queries to the database via APIs to obtain detailed information such as the property's address, price, area, age, and surrounding facilities. The server then normalizes the data and filters out duplicate data to ensure data quality.

[1268] Fair price forecast

[1269] The server inputs the collected real estate data into a generative AI model to analyze detailed information for each property. At this stage, an AI framework such as TensorFlow is used to train a price prediction model based on past data, enabling fair and highly accurate price predictions. The generative AI model also takes into account past trends and current market conditions to predict future value fluctuations.

[1270] Upload and auto-extract property information

[1271] Users upload property photos using their devices (smartphones or PCs). For example, they select a property photo from their smartphone or PC and click the upload button. The server automatically extracts property information from this photo. Using an image analysis algorithm, it extracts features such as floor plan and age of the building and stores them in a database.

[1272] Information Visualization

[1273] The device visually displays information about the property's fair value and surrounding market prices to the user. For example, in a smartphone app developed using React Native, interactive charts and graphs are generated and displayed using D3.js, allowing users to intuitively check the property's value.

[1274] Rent setting and push notifications

[1275] The server proposes appropriate rent revisions when a rental property contract is renewed. For example, the server monitors the expiration of the rental contract and sends a notification proposing a new rent when it's time for renewal, based on the desired rental area set by the user. Furthermore, the server sends real-time push notifications of property information that matches the desired rental area set by the user. Specifically, the server compares real estate data with the user's conditions and immediately notifies the user's device of any matching property information. This push notification function allows users to receive the latest information in a timely manner, making real estate transactions more efficient.

[1276] Examples and prompts

[1277] A specific use case might involve a user uploading a photo of a 10-year-old, 100-square-meter house in Tokyo, and predicting the appropriate price for that property. The prompt might look like this:

[1278] "This property is located in Tokyo, is a 10-year-old house with an area of ​​100 square meters. Please estimate the fair price for this property."

[1279] This system allows individual owners and investors to easily upload property information, receive highly accurate fair price assessments, and intuitively check the value of their properties. It also enables efficient real estate transactions through pricing of rental properties, appropriate rent proposals for renewals, and real-time push notifications, which is expected to revitalize the real estate market.

[1280] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1281] Step 1:

[1282] The server automatically collects real estate data by accessing a public database. Specifically, it uses an API to send queries to the database and obtain detailed information such as the property's address, price, area, age, surrounding facilities, etc. The input is the query to the database, and the output is the collected real estate data.

[1283] Step 2:

[1284] The server cleanses the collected data. Specifically, it removes duplicate data, filters inaccurate data, and normalizes it. The input is the collected real estate data, and the output is the cleansed real estate data. Python is used for this data cleansing.

[1285] Step 3:

[1286] The server inputs the cleansed real estate data into a generative AI model to predict fair prices. The generative AI model uses TensorFlow to train a predictive model based on historical data, taking into account past trends and current market conditions. The input is the cleansed data and a prompt for the AI ​​model, and the output is a predicted fair price.

[1287] Step 4:

[1288] The user uploads a property photo using a device. For example, they select a property photo from their smartphone or PC and click the upload button. The input is the user uploading the photo, and the output is sending the photo data to the server.

[1289] Step 5:

[1290] The server automatically extracts property information from uploaded photos. Specifically, it uses an image analysis algorithm to extract features such as floor plan and age of the building and stores them in a database. The input is the photo data, and the output is the property information extracted from the photo. This analysis uses computer vision technology.

[1291] Step 6:

[1292] The terminal visually displays information about the property's fair price and surrounding market prices to the user. Specifically, interactive charts and graphs are generated and displayed using D3.js using React Native. The input is the predicted fair price and property information, and the output is the visually displayed data.

[1293] Step 7:

[1294] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it proposes rent increases or maintenance based on the desired rental area set by the user. The input is the desired area and property data set by the user, and the output is the proposed new rent.

[1295] Step 8:

[1296] The server sends push notifications of property information that matches the user's desired rental area. The server compares real estate data with the user's conditions and notifies the user's device of matching property information in real time. The input is the user's desired conditions and the latest real estate data, and the output is a push notification.

[1297] 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.

[1298] The present invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. Furthermore, the system aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotions. The following describes an embodiment of the present invention.

[1299] Data collection

[1300] Step 1: Collect real estate data from publicly available databases.

[1301] The server accesses databases containing publicly available real estate information (e.g., public land price data, property information from real estate companies, etc.) and automatically collects real estate data.

[1302] For example, the server sends a query to a real estate database via an API to obtain detailed information such as the property's address, price, area, age, and surrounding facilities.

[1303] Step 2: Cleanse the data you get.

[1304] The server filters out duplicate and inaccurate data to ensure data quality.

[1305] Data analysis

[1306] Step 3: Use a generative AI model to predict the fair price.

[1307] The server inputs the collected real estate data into a generative AI model and analyzes detailed information for each property.

[1308] For example, we train a price prediction model based on past data and evaluate its performance, which enables fair and highly accurate price predictions.

[1309] Step 4: Save the prediction results

[1310] The server stores the fair prices predicted by the generative AI model in a database.

[1311] User Interface

[1312] Step 5: Upload your property

[1313] Users upload property photos using their device. Specifically, they select property photos from their smartphone or PC and click the upload button.

[1314] Step 6: Automatic information extraction

[1315] The server automatically extracts property information from these photos, using image analysis algorithms to analyze characteristic information such as floor plan and age of the building, and stores the information in a database.

[1316] Step 7: Visualize the information

[1317] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[1318] Emotion Engine

[1319] Step 8: Recognizing User Emotions

[1320] The device recognizes the user's emotions using the user's voice input, facial expression analysis, or data from biometric sensors.

[1321] For example, a camera captures a user's facial expression while they are looking at property information, and the emotion engine analyzes the captured emotion data in real time.

[1322] Step 9: Customize the presentation of information

[1323] The emotion engine customizes the displayed information based on the user's perceived emotions.

[1324] For example, if a user is feeling stressed, provide an interface with softer colors and simpler explanations, whereas if a user is feeling positive, provide more detailed information and additional data.

[1325] Pricing & Notifications

[1326] Step 10: Set and update rents

[1327] The server proposes appropriate rent revisions when a rental contract is renewed. It proposes rent increases or maintenance based on the desired rental area set by the user.

[1328] For example, it monitors lease expiration dates and sends notifications proposing new rents when renewals arrive.

[1329] Step 11: Push Notifications

[1330] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[1331] Specific examples

[1332] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[1333] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[1334] In this way, individual owners and investors can make better decisions by making real estate transactions at fair prices and receiving appropriate information based on user emotions. The introduction of an emotion engine will improve the user experience and promote efficient and fair real estate transactions.

[1335] The processing flow will be explained below.

[1336] Step 1:

[1337] The server accesses public databases and collects real estate data, specifically, public land price data and property information from real estate companies via API, collecting detailed information such as property address, price, area, and age.

[1338] Step 2:

[1339] The server cleanses the collected data by normalizing it, filtering out duplicates, and filling in incomplete data, thereby ensuring the quality of the data.

[1340] Step 3:

[1341] The server preprocesses the cleaned data, specifically by scaling it and encoding categorical variables to convert it into a format that is easy for the generative AI model to use.

[1342] Step 4:

[1343] The server uses a generative AI model to predict the fair price. It trains the price prediction model based on past data and then uses the trained model to calculate the fair price for the latest property data.

[1344] Step 5:

[1345] The server stores the predicted fair price in a database, making it available for subsequent processes.

[1346] Step 6:

[1347] Users upload property photos using their device, by selecting property photos from their smartphone or PC and clicking the upload button.

[1348] Step 7:

[1349] The server automatically extracts property information from the uploaded photos, using an image analysis algorithm to analyze characteristic information such as floor plan and age of the building from the photos, and stores the information in a database.

[1350] Step 8:

[1351] The device visually displays information about the property's fair value and surrounding market prices to the user, generating interactive charts and graphs that allow the user to easily understand the property's value.

[1352] Step 9:

[1353] The device can recognize the user's emotions using voice input, facial expression analysis, or data from biometric sensors. For example, a camera captures the user's facial expressions, which are then analyzed by an emotion engine.

[1354] Step 10:

[1355] The emotion engine customizes the displayed information based on the user's perceived emotions. For example, if the user is feeling stressed, the interface will be softened in color and a simple explanation will be provided.

[1356] Step 11:

[1357] The server will propose appropriate rent revisions when the rental property contract is renewed. Specifically, it will monitor the timing of contract renewals and notify the tenant of the proposed rent based on the renewal date.

[1358] Step 12:

[1359] The server sends push notifications of property information that matches the desired rental area conditions set by the user. Matching property information is extracted in real time and notified to the user's device.

[1360] Example 2

[1361] 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."

[1362] The present invention aims to solve problems in real estate transactions, such as the lack of fair price evaluations, data reliability issues, and improving the user experience. It also aims to seamlessly perform automatic collection and cleansing of real estate data, fair price prediction, and information provision based on user sentiment. With conventional technology, there was no system that could perform all of these tasks in an integrated manner, making it difficult to conduct efficient and fair real estate transactions.

[1363] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1364] In this invention, the server includes: means for automatically collecting real estate data from a public database; means for cleansing the collected real estate data; means for predicting a fair price using a generative AI model based on the cleansed real estate data; means for saving the predicted fair price in a database; means for uploading property photos; means for automatically extracting information from the uploaded photos; means for visually displaying the fair price; means for recognizing a user's emotions; means for customizing information based on the recognized emotions; and means for sending push notifications of property information matching the desired rental area. This allows users to receive reliable real estate price assessments in real time and personalized information based on their emotions. It also promotes efficient and fair real estate transactions.

[1365] A "public database" is a database that collects real estate-related information that is made publicly available on the Internet by public institutions and private companies.

[1366] "Real estate data" refers to all information about real estate, such as the property's address, price, area, age, and surrounding facilities.

[1367] "Cleansing" refers to the process of removing duplicate and incorrect data from collected data to ensure data quality.

[1368] A "generative AI model" is an artificial intelligence model trained using machine learning techniques to predict the fair value of real estate.

[1369] "Fair price" refers to the fair and accurate market price of a property predicted by the generative AI model based on collected real estate data.

[1370] "Storing in a database" means storing the predicted fair price and collected real estate data in a database in an appropriate format.

[1371] "Property photos" are images uploaded by users that show the exterior and interior of a property.

[1372] "Automatic information extraction" refers to the use of image analysis algorithms to extract specific information, such as floor plan and age, from uploaded property photos.

[1373] "Visually displaying" means presenting the collected and predicted real estate data and fair prices to the user in an interactive format such as graphs and charts.

[1374] "Recognizing user emotions" means analyzing the user's emotional state through voice input, facial expression analysis, and data from biometric sensors.

[1375] "Customizing information" means adjusting the content and presentation of information based on the user's recognized emotions.

[1376] "Push notification" means notifying the user's device in real time of new real estate information that matches the conditions specified by the user.

[1377] MODE FOR CARRYING OUT THE INVENTION

[1378] This invention is a system that predicts the fair price of real estate and enables individual owners and investors to efficiently conduct real estate transactions. This system not only collects real estate data from public databases and predicts the fair price using a generative AI model, but also improves the user experience by recognizing user emotions and customizing information.

[1379] Hardware and software used

[1380] The server uses a computer with high-performance computing resources, specifically a web server using programming languages ​​such as Python or JavaScript, and machine learning libraries such as Sklearn or TensorFlow.

[1381] The terminal refers to the smartphone or personal computer operated by the user, on which the web browser and dedicated applications run.

[1382] The database used is a relational database management system such as MySQL or PostgreSQL.

[1383] Processing Details

[1384] 1. Collecting real estate data from public databases

[1385] The server accesses public real estate databases (e.g., land price announcement data, property information from real estate companies) to collect the necessary data. Specifically, it sends HTTP requests using the Python requests library and saves the retrieved data in JSON format.

[1386] 2. Data Cleansing

[1387] The server uses the Pandas library to cleanse the collected data: it processes the data in data frame format, removes duplicate data with the drop_duplicates() method, and imputes missing values ​​with the fillna() method.

[1388] 3. Fair price prediction

[1389] The server inputs the cleansed data into a generative AI model to predict the appropriate price. The price prediction model is trained using TensorFlow and PyTorch, and predicts fair and accurate prices based on detailed information about each property.

[1390] 4. Saving the results

[1391] The server stores the fair prices predicted by the generative AI model in a database. It connects to the database using SQLAlchemy or Django ORM and inserts the prediction results into the appropriate tables.

[1392] 5. Upload property information

[1393] Users upload property photos from their devices, select image files and send them through their browsers, and the server receives them using web frameworks such as Flask or Django.

[1394] 6. Automatic Information Extraction

[1395] The server uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age of the building from the uploaded photos.

[1396] 7. Information Visualization

[1397] The terminal visually displays fair value and surrounding market information to the user, using D3.js and Chart.js to generate interactive graphs and charts.

[1398] 8. Emotional Recognition

[1399] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. It analyzes the user's facial expressions using OpenCV and a pre-trained model for emotion recognition.

[1400] 9. Customizing Information

[1401] The emotion engine customizes information based on the user's recognized emotions, dynamically modifying front-end CSS and JavaScript based on emotion recognition data to provide softer colors and simpler explanations for stressed users and more detailed information for more proactive users.

[1402] 10. Rent Setting and Renewal

[1403] The server proposes appropriate rent revisions when a rental property contract is renewed. It periodically checks contract expiration dates using a scheduler and sends emails and in-app notifications at the appropriate times.

[1404] 11. Push Notifications

[1405] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user, using push notification services such as Google Firebase to send the information to the user's device.

[1406] Specific examples

[1407] Example 1: When User A uploads a photo of a property from their device, the server automatically extracts property information from the photo and predicts the appropriate price using a generative AI model. The device then visually presents User A with the appropriate price and surrounding market information. Furthermore, if User A's emotional state is analyzed and it is determined that he or she is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[1408] Example 2: When User B sets the area where he / she wants to rent, the server will push property information that matches that area in real time. When User B receives the information, the emotion engine will recognize the emotion from the user's facial expression, and if a positive emotion is detected, detailed property information will also be provided.

[1409] Prompt Sentence Examples

[1410] "How can I gather real estate information from public databases and predict fair prices?"

[1411] "Please explain the algorithm that automatically extracts information from uploaded property photos."

[1412] "Tell me more about how you can recognize a user's emotions and customize the information based on them."

[1413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1414] Step 1:

[1415] The server accesses public databases to collect real estate data. Specifically, the server uses Python's requests library to send HTTP requests to obtain public land price data, property information from real estate companies, and other information. The API endpoint URL is required as input, and the output is JSON-formatted data containing detailed information such as the property's address, price, area, age, and surrounding facilities. The server temporarily stores this data in storage.

[1416] Step 2:

[1417] The server cleanses the collected data. Specifically, it processes the data in data frame format using the Pandas library. The input required is the JSON data obtained in step 1, and the output is high-quality data with duplicate data and missing values ​​filled in. The server removes duplicate data using the drop_duplicates() method and fills in missing values ​​using the fillna() method.

[1418] Step 3:

[1419] The server inputs the cleansed data into a generative AI model to predict the appropriate price. Specifically, it trains the AI ​​model using TensorFlow and PyTorch to predict prices based on detailed information about each property. High-quality cleansed data is required as input, and the output is the predicted price for each property. The server inputs the data into the trained model and uses the predict() method to make price predictions.

[1420] Step 4:

[1421] The server saves the fair price predicted by the generative AI model to a database. Specifically, it connects to the database using SQLAlchemy or Django ORM and inserts the predicted results into the appropriate table. The input is the predicted fair price, and the output is the predicted price information stored in the database. The server inserts the data using the session.add() and session.commit() methods.

[1422] Step 5:

[1423] The user uploads a property photo from their device. Specifically, they select an image file from their smartphone or PC, send it through the browser, and click the upload button. The input is a photo file of the property, and the output is the photo data stored on the server. The device sends the photo to the server using an HTTP POST request.

[1424] Step 6:

[1425] The server automatically extracts information from uploaded property photos. Specifically, it uses image analysis models from OpenCV and TensorFlow to extract feature information such as floor plan and age from the photos. The input is the uploaded photo data, and the output is the extracted property information. The server reads the image using the cv2.imread() method and applies image analysis algorithms to extract information.

[1426] Step 7:

[1427] The terminal visually displays fair price and surrounding market information to the user. Specifically, it generates interactive graphs and charts using D3.js and Chart.js. The input required is predicted price information retrieved from a database, and the output is a graph or chart displayed in the browser. The terminal uses the JavaScript chart.draw() method to draw.

[1428] Step 8:

[1429] The device recognizes emotions using the user's voice input, facial expression analysis, and biometric sensor data. Specifically, it uses OpenCV and a pre-trained model for emotion recognition. The input requires sensor data acquired from a camera, microphone, etc., and the output is the recognized user emotion data. The device acquires video data using the cv2.VideoCapture() method and applies the emotion recognition algorithm.

[1430] Step 9:

[1431] The emotion engine customizes information based on the user's recognized emotions. Specifically, it dynamically changes CSS and JavaScript to provide softer colors and simpler explanations for stressed users and more detailed information for more active users. The input required is the emotion data output by the emotion engine, and the output is a customized user interface. The emotion engine uses if statements to change the UI depending on the conditions.

[1432] Step 10:

[1433] The server proposes appropriate rent revisions when a rental property contract is renewed. Specifically, it uses a scheduler to periodically check the contract expiration date and sends emails and in-app notifications at the appropriate time. The input requires the user's contract information, and the output is a notification proposing rent revisions. The server performs periodic checks using the schedule library and sends notifications using the send_email() method.

[1434] Step 11:

[1435] The server sends real-time push notifications of property information that matches the desired rental area conditions set by the user. Specifically, it uses a push notification service such as Google Firebase. The input requires the user's set conditions and new property information, and the output is a notification to the user's device. The server uses the Firebase API to send a push notification every time new property data is received.

[1436] (Application example 2)

[1437] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1438] In today's real estate market, it is difficult to quickly and accurately predict fair prices. This is especially true for investors and individual owners, who find it difficult to make accurate decisions when renewing leases or purchasing new properties. Furthermore, there is a lack of systems for providing personalized information that takes user emotions into account, leaving room for improvement in the user experience.

[1439] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting real estate data from a public database, means for predicting a fair price using the collected real estate data with a generative AI model, means for visually displaying the predicted fair price, means for sending push notifications of property information that matches the desired rental area conditions, means for recognizing the user's emotions using the device's camera, and means for customizing the visual display based on the emotion recognition results. This allows users to quickly and accurately grasp fair property prices and rental conditions, and also enables the provision of personalized information according to emotions.

[1440] "Public Database" means any publicly accessible online or offline data source that contains market information or real estate-related data.

[1441] "Real estate data" refers to all information related to real estate, such as the property's address, price, area, age, and surrounding facilities.

[1442] "Fair value" refers to the reasonable and fair assessment of the value of real estate, taking into account past trends and current market conditions.

[1443] A "generative AI model" is a model built using machine learning and artificial intelligence technologies, and is an algorithm for predicting the fair price of real estate based on large amounts of data.

[1444] "Visual display means" refers to methods of presenting information to users in an easy-to-understand manner, such as using graphs, charts, or interactive maps.

[1445] "Property information that matches the conditions of the desired rental area" is information on rental properties that match the area, budget, and other requirements set by the user.

[1446] "Push notification" is a technology that notifies a device in real time of new property or rental information that matches the conditions specified by the user.

[1447] "Terminal" refers to any device that a user uses to view information, such as a smartphone, head-mounted display, or tablet.

[1448] "Means for recognizing a user's emotions using a camera" refers to technology that uses a camera or other sensors installed on the device to analyze the user's facial expressions and voice and identify their emotions.

[1449] "Means for customizing visual displays based on emotion recognition results" refers to a method for providing information optimized for individual users by adjusting the display content and interface according to the user's emotion data.

[1450] "Personalized information provision" refers to a general service that individually customizes appropriate property information and visual displays based on the user's situation and preferences.

[1451] This invention is a system that collects real estate data from public databases, uses that data to predict fair prices using a generative AI model, and also recognizes the user's emotions to provide visually customized information.

[1452] The server first accesses public databases and automatically collects real estate data. During data collection, it normalizes and filters duplicate data to ensure data quality. It then uses a generative AI model to analyze the collected real estate data and predict the appropriate price. This prediction takes into account past trends and current market conditions.

[1453] Users can visually check property information using devices such as smartphones or head-mounted displays (HMDs). The devices are equipped with cameras that capture the user's facial expressions while they are viewing the information. The facial expression data captured by the camera is analyzed in real time by an emotion recognition algorithm to identify the user's emotions (e.g., stress, excitement, etc.).

[1454] Emotional data is used to customize the format and content of the property information displayed. For example, if a user is stressed, the interface may be softened and the amount of information displayed may be simplified. On the other hand, if the user is interested, more detailed information or additional data may be provided.

[1455] For example, when a user uploads a photo of a property from their device, the server automatically extracts property information from the photo and uses a generative AI model to predict the appropriate price. The device then visually presents the appropriate price and surrounding market information to the user. Furthermore, the system analyzes the user's emotional state, and if it determines that the user is feeling stressed, the interface changes to a softer color scheme and a simple explanation is displayed.

[1456] The app also has a push notification feature that sends real-time information about properties that match the area the user is looking to rent in. When the user receives the information, emotion recognition is activated, and if a positive emotion is detected, detailed property information will be provided.

[1457] An example of a prompt is as follows:

[1458] Emotion recognition prompts:

[1459] input: "Recognize emotions from images where the user is facing the camera."

[1460] output: "User emotion is stress."

[1461] Price prediction prompt:

[1462] input: "Enter price data for a specific real estate area and predict the fair value."

[1463] output: "The fair price for this property is 50 million yen."

[1464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1465] Step 1:

[1466] The server accesses public databases and automatically collects real estate data, such as the property's address, price, area, age, and surrounding facilities. The collected data is then stored in the database.

[1467] Step 2:

[1468] The server normalizes the collected data and filters duplicate data, ensuring data quality. Data normalization involves converting data from different formats into a unified format and filtering duplicate data.

[1469] Step 3:

[1470] The server uses a generative AI model to predict the fair price based on the normalized data. The collected data is input into the generative AI model, which then obtains a predicted fair price that takes into account past trends and current market conditions.

[1471] Step 4:

[1472] The server stores the predicted fair price in a database, where it is stored along with other information for later visual presentation to the user.

[1473] Step 5:

[1474] Users upload property photos using their devices, which receive the photo data and send it to the server.

[1475] Step 6:

[1476] The server automatically extracts property information from uploaded photos, using image analysis algorithms to extract characteristic information such as floor plan and age, and adds it to a database.

[1477] Step 7:

[1478] The device visually displays the property's fair value and surrounding market information to the user, for example by generating interactive charts and graphs, in a format that allows the user to easily understand the property's value.

[1479] Step 8:

[1480] The device's camera captures the user's facial expressions and analyzes the data in real time. An emotion engine is used to recognize the user's emotions, such as stress or excitement.

[1481] Step 9:

[1482] The server customizes the visual display based on the emotion recognition results. If the user is stressed, the interface changes to softer colors and provides less information. If the user is interested, more detailed information is displayed.

[1483] Step 10:

[1484] The server pushes real-time information about properties that match the desired rental area, filters the data based on the conditions set by the user, and sends the relevant property information to the device.

[1485] Step 11:

[1486] The user checks the push notification received on their device, and their emotional data is also analyzed. If a positive emotion is detected, the server will provide additional detailed property information.

[1487] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1488] 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.

[1489] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1490] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1491] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1492] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1493] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1494] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1495] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1496] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1497] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1498] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1499] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1500] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1501] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1502] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1503] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1504] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1505] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1506] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1507] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1508] The following is further disclosed regarding the above embodiment.

[1509] (Claim 1)

[1510] means for automatically collecting real estate data from publicly available databases;

[1511] A method to predict fair prices using collected real estate data and an AI model;

[1512] a means for visually displaying the predicted fair price;

[1513] A means to send push notifications of property information that matches the conditions of the desired rental area,

[1514] A system including:

[1515] (Claim 2)

[1516] 10. The system of claim 1, wherein the means for collecting real estate data from the public database performs data normalization and filtering of duplicate data.

[1517] (Claim 3)

[1518] 2. The system of claim 1, wherein the means for predicting the fair price using a generative AI model takes into account past trends and current market conditions to predict future value fluctuations.

[1519] "Example 1"

[1520] (Claim 1)

[1521] means for automatically collecting real estate data from publicly available databases;

[1522] A method for ensuring data quality by performing data cleansing on collected real estate data and filtering out duplicate and inaccurate data;

[1523] A method to predict fair prices using collected real estate data and an AI model;

[1524] a means for storing the predicted fair price in a database;

[1525] a means for allowing a user to upload a photo of property information and automatically extracting property information from the photo using an image analysis algorithm;

[1526] a means for storing the extracted property information in a database;

[1527] a means for visually displaying the predicted fair price;

[1528] A means to propose appropriate rent revisions when renewing lease agreements,

[1529] A means to send push notifications of property information that matches the conditions of the desired rental area,

[1530] A system including:

[1531] (Claim 2)

[1532] 10. The system of claim 1, wherein the means for collecting real estate data from the public database performs data normalization and filtering of duplicate data.

[1533] (Claim 3)

[1534] 2. The system of claim 1, wherein the means for predicting the fair price using a generative AI model takes into account past trends and current market conditions to predict future value fluctuations.

[1535] "Application Example 1"

[1536] (Claim 1)

[1537] means for automatically collecting real estate data from publicly available databases;

[1538] A method to predict fair prices using collected real estate data and an AI model;

[1539] A means to automatically extract property information from uploaded images,

[1540] a means for visually displaying the predicted fair price;

[1541] A means to send push notifications of property information that matches the conditions of the desired rental area,

[1542] A system including:

[1543] (Claim 2)

[1544] 10. The system of claim 1, wherein the means for collecting real estate data from the public database performs data normalization and filtering of duplicate data.

[1545] (Claim 3)

[1546] 2. The system of claim 1, wherein the means for predicting the fair price using a generative AI model takes into account past trends and current market conditions to predict future value fluctuations.

[1547] "Example 2: Combining Emotion Engines"

[1548] (Claim 1)

[1549] means for automatically collecting real estate data from publicly available databases;

[1550] A means of cleansing the collected real estate data;

[1551] A means to predict fair prices using a generative AI model using cleansed real estate data, and

[1552] a means for storing the predicted fair price in a database;

[1553] A means for uploading photos of the property;

[1554] A means for automatically extracting information from uploaded photos;

[1555] A means of visually displaying fair prices;

[1556] means for recognizing a user's emotion;

[1557] a means for customizing information based on the perceived emotion;

[1558] A means to send push notifications of property information that matches the conditions of the desired rental area,

[1559] A system including:

[1560] (Claim 2)

[1561] 10. The system of claim 1, wherein the means for collecting real estate data from the public database performs data normalization and filtering of duplicate data.

[1562] (Claim 3)

[1563] 2. The system of claim 1, wherein the means for predicting the fair price using a generative AI model takes into account past trends and current market conditions to predict future value fluctuations.

[1564] "Application example 2 when combining emotion engines"

[1565] (Claim 1)

[1566] means for automatically collecting real estate data from publicly available databases;

[1567] A method to predict fair prices using collected real estate data and an AI model;

[1568] a means for visually displaying the predicted fair price;

[1569] A means to send push notifications of property information that matches the conditions of the desired rental area,

[1570] A means for recognizing a user's emotion using a camera of the device;

[1571] means for customizing the visual display based on the emotion recognition results;

[1572] A system including:

[1573] (Claim 2)

[1574] The system of claim 1, wherein the means for collecting real estate data from the public database performs data normalization and filtering of duplicate data, and provides a means for recognizing user emotions using a device camera and various visual displays.

[1575] (Claim 3)

[1576] The system of claim 1, wherein the means for predicting the fair price using a generative AI model predicts future value fluctuations taking into account past trends and current market conditions, and the means for recognizing the user's emotions using the device's camera adjusts the display content based on the emotion recognition results. [Explanation of symbols]

[1577] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for automatically collecting real estate data from publicly available databases; A method to predict fair prices using collected real estate data and an AI model; a means for visually displaying the predicted fair price; A means to send push notifications of property information that matches the conditions of the desired rental area, A system including:

2. The system of claim 1 , wherein the means for collecting real estate data from the public database performs data normalization and filtering of duplicate data.

3. The system of claim 1 , wherein the means for predicting the fair price using a generative AI model takes into account past trends and current market conditions to predict future value fluctuations.

Images