system

Abstract

We provide the system. [Solution] A means of collecting information about real estate via a network, A means for preprocessing collected information and converting it into input data for evaluating competitiveness, A method for evaluating the competitiveness score of real estate using generative artificial intelligence, A means of notifying users based on that competitiveness score, A means for generating map information that visualizes the competitiveness of each region for users, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the real estate market, there is a problem that there is a lack of a mechanism to quickly and accurately grasp the competitiveness of properties. In particular, in the selection of popular properties and price negotiations, it is difficult to understand in real time how much competition a property is facing, which becomes an obstacle for users to make optimal decisions. As a result, there is a risk that real estate purchasers and borrowers may not be able to acquire properties at appropriate prices or may suffer opportunity losses.

Means for Solving the Problems

[0005] This invention provides a means for collecting real estate information in real time via a network, preprocessing it, and converting it into data for evaluating competitiveness. Furthermore, it includes a means for evaluating the competitiveness score of properties using generative artificial intelligence and notifying users of the property's competitiveness based on this score. It also generates and provides map information visualizing competitiveness by region to users, thereby supporting the optimization of property selection and negotiation strategies. Moreover, it enables competitive choices in the market by providing personalized advice based on the user's past search history and desired conditions.

[0006] A "network" is a communication system used to interconnect computers and other devices, and is the infrastructure that enables the transmission and reception of data.

[0007] "Real estate" is a general term for land and buildings located on it, and refers to properties that are subject to buying, selling, or leasing.

[0008] "Means of collecting information" refers to the processes and technologies used to gather specific data from sources such as the internet and databases.

[0009] "Preprocessing" refers to a series of processes that transform raw data into a state that can be analyzed and interpreted, and includes steps such as data cleaning and formatting standardization.

[0010] "Means of converting data into input data" refers to the work or process of preparing data into the necessary format and structure for a specific purpose.

[0011] "Generative artificial intelligence" is an AI technology that has the ability to learn from large datasets and generate new data and inferences.

[0012] A "competitiveness score" is an indicator that quantifies the popularity and demand for a particular property in the market, and is used to evaluate the intensity of competition.

[0013] "Means of notifying users" refers to systems and methods for quickly conveying specific information to users, including alerts and push notifications.

[0014] "Map information that visualizes regional competitiveness" refers to map data that visually displays the competitiveness of real estate in each geographical area in an easy-to-understand manner.

[0015] "Search history" is a record of a user's past search activities and represents data that indicates their individual interests and preferences.

[0016] "Personalized advice" refers to suggestions and instructions optimized based on the individual user's needs and history. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be described.

[0020] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the 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.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0031] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system that evaluates the competitiveness of real estate properties and provides users with valuable information in real time. This system particularly utilizes artificial intelligence to support property selection and negotiation.

[0039] First, the server collects information from various real estate-related data sources via the network. This information includes property prices, locations, amenities, nearby amenities, and past transaction history. Furthermore, it collects word-of-mouth and trend information about properties from social media and news sites.

[0040] Once the information is collected, the server preprocesses it. Preprocessing involves filling in missing data, removing outliers, and standardizing the data to create input data suitable for generative artificial intelligence.

[0041] Next, the server uses generative artificial intelligence to evaluate the competitiveness of the properties. The AI ​​model learns from historical market data and trend information and calculates a competitiveness score for each property. This quantifies the popularity and demand for each property.

[0042] Based on this competitiveness score, the server identifies properties that match the user's desired criteria and properties that are highly competitive in the market. Furthermore, it provides the user with personalized advice on property selection and purchase negotiations based on competitiveness.

[0043] The device notifies users via push notifications about competitiveness scores and new popular properties. Furthermore, it displays a heatmap visually showing property competitiveness by region, aiding in intuitive understanding.

[0044] For example, if a user is looking for a new apartment in a certain area, the server calculates a competitiveness score for that area, and the terminal displays the result to the user. Furthermore, for particularly competitive areas or properties, the system provides negotiation advice and suggests strategies to the user, such as when to take action.

[0045] This invention makes it possible to appropriately and efficiently select properties in the real estate market and conduct transactions under the best possible conditions.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server collects property information from real estate portal sites and data providers on the internet. It uses crawling technology and APIs to obtain detailed property data such as price, location, floor plan, and year of construction.

[0049] Step 2:

[0050] The server analyzes social media and news sites to collect trends and user interest in the real estate market. This allows it to extract the popularity of reviews and topics related to properties.

[0051] Step 3:

[0052] The server preprocesses the collected data. It prepares the data into an analyzable dataset by imputing missing values ​​and removing outliers. It also standardizes the data to format it so that it can be read by AI models.

[0053] Step 4:

[0054] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​model learns from historical market data and trend data, predicting the popularity and future demand of properties to assign scores.

[0055] Step 5:

[0056] The server identifies properties that match the user's desired criteria based on competitiveness scores. It also lists particularly popular properties and newly listed properties. Based on this information, it prepares push notifications.

[0057] Step 6:

[0058] The device will notify users via push notifications about new property listings and changes in the competitiveness of properties. This allows users to check the information immediately.

[0059] Step 7:

[0060] The server generates a heat map that visualizes the competitiveness of each region. This allows you to understand the level of geographical competition in the area where the property is located.

[0061] Step 8:

[0062] The device displays a competitive heatmap to the user, allowing them to identify highly competitive areas in a given location using different colors. It also provides personalized advice for property selection and negotiation based on the user's past activity history.

[0063] Through this series of steps, the system provides users with fast and accurate information on the real estate market, supporting effective property selection and negotiation.

[0064] (Example 1)

[0065] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] The real estate market is vast in terms of property information, making it difficult for users to quickly and efficiently select the most suitable property. In particular, there is a need to accurately evaluate the competitive advantages of properties and provide users with valuable information in real time. This invention aims to solve these problems and optimize real estate property selection and transactions.

[0067] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0068] In this invention, the server includes means for collecting data on the real estate market via a network, means for preprocessing the collected data and converting it into input information for artificial intelligence, and means for providing prompt sentences to generative artificial intelligence to evaluate the competitive advantages of real estate. As a result, users can receive real-time notifications based on competitive advantages and make optimal real estate selections and negotiations.

[0069] A "network" is a communication system that transmits data and enables the collection and distribution of real estate-related information.

[0070] "Data related to the real estate market" includes information such as property prices, location, amenities, nearby facilities, and past transaction history.

[0071] "Preprocessing" is the process of preparing collected data into a format that can be analyzed by artificial intelligence, including imputing missing values, removing outliers, and standardizing the data.

[0072] "Artificial intelligence" is an algorithm or system that learns from collected data and analyzes specific patterns and trends.

[0073] A "prompt" is a phrase used to convey instructions or questions to a generative artificial intelligence.

[0074] "Real estate competitive advantage" is an indicator that shows how advantageous a particular real estate property is compared to other properties in the market.

[0075] "Real-time notification" is a communication method that instantly informs users about information or changes that may interest them.

[0076] "Visualized information showing competitive advantages in each region" refers to information that visually represents the competitive advantages of real estate properties in a specific region using maps, graphs, etc.

[0077] This invention relates to an information provision device for evaluating the competitive advantages of real estate properties and providing valuable information to users. This device mainly consists of a server and terminals.

[0078] First, the server collects data about the real estate market via the network. This data includes property prices, locations, amenities, nearby facilities, and past transaction history. Furthermore, the server uses APIs and other methods to gather trending information and word-of-mouth from social media and news feeds.

[0079] The collected data is preprocessed by the server. Specifically, missing data is filled in, outliers are removed, and the data is standardized. This process is important to convert the collected data into a format that can be easily analyzed by generative artificial intelligence.

[0080] Next, the server uses generative artificial intelligence to evaluate the competitive advantages of the properties. Here, the AI ​​utilizes pre-trained market data and trend information to calculate a competitive advantage score for each property. In this step, a prompt such as "Calculate the competitiveness score of this property in this region" is used.

[0081] Based on the evaluation results, the server identifies properties that match the user's specified criteria. This information is notified to the user's device in real time. The device then provides a visual representation of the competitive advantages of properties in each region. Specifically, it uses heatmaps and other tools to help users intuitively understand the information.

[0082] For example, if a user is searching for a new property in a specific area, the server calculates the competitive advantage score for that area and generates a list of the most competitive properties. This list and related advice are then communicated to the user via their device, improving the efficiency of property selection and negotiation. This enables users to make appropriate and efficient decisions in the real estate market.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server collects data on the real estate market through the network. Inputs include API access from various real estate portal sites and local real estate agent databases. This outputs information such as property prices, locations, amenities, nearby facilities, and past transaction history. It also scans social media APIs and news feeds to obtain trend information and word-of-mouth. This provides a rich dataset for understanding the current market situation.

[0086] Step 2:

[0087] The server preprocesses the collected data. The input includes the raw data collected in step 1. Specific data processing involves imputing missing values ​​and detecting and removing outliers. This process eliminates outliers such as extremely low or high property prices and also standardizes the data. As a result of this processing, a clean dataset is output that can be directly input into the generating AI model.

[0088] Step 3:

[0089] The server provides pre-processed data as input to a generative artificial intelligence to evaluate the competitive advantages of the properties. A possible prompt used here would be, "Calculate the competitiveness score of this property in this region." The AI ​​model takes into account the learned market data and trend information to calculate a competitive advantage score for each property and outputs it as a numerical value.

[0090] Step 4:

[0091] The server creates a list of properties that match the user's desired criteria based on the generated competitive advantage score. The inputs for this step are the score obtained in step 3 and the user's desired criteria. The data calculation involves filtering properties that match the desired criteria, taking the competitive advantage score into consideration. The output is a list of the most suitable property suggestions for the user.

[0092] Step 5:

[0093] The device notifies the user of the results. Specifically, it sends push notifications with recommended properties and competitive advantage scores. The input is the property list generated in step 4. Furthermore, the device provides a visual representation of competitive advantages for each region, for example, outputting it as a heatmap. This makes it easier for the user to visually understand the competitive situation in a region.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] In current real estate transactions, despite the abundance of information available, it is difficult to concisely understand that information and determine the true value of a property. Furthermore, there is a lack of means to grasp the competitiveness of real estate in real time and to intuitively evaluate it. As a result, users spend a great deal of effort in selecting and deciding on the purchase of real estate.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, and means for generating information for visually displaying property data on an augmented reality display device and performing a real-time visual evaluation of real estate. This enables users to intuitively grasp the competitiveness of real estate in real time and efficiently select valuable real estate.

[0099] A "network" is a communication infrastructure for exchanging information with one another.

[0100] "Real estate information" refers to data such as price, location, facilities, nearby amenities, and past transaction history for real estate properties.

[0101] "Means of collection" refers to the methods and techniques used to obtain necessary data from specific sources.

[0102] "Preprocessing" refers to the data processing steps that prepare raw data into a format suitable for analysis and evaluation.

[0103] "Input data" refers to pre-formatted data supplied to data analysis or AI models, tailored to a specific purpose.

[0104] "Generative artificial intelligence" is an AI technology that generates new information and predictions based on previously learned data.

[0105] A "competitiveness score" is an evaluation index that quantifies the market value and popularity of a particular property.

[0106] "Means of notification" refers to methods or devices for conveying information or results to users.

[0107] "Visualized map information" refers to information in map format that geographically arranges specific data and presents it in a visually easy-to-understand manner.

[0108] An "augmented reality display device" is a device that overlays digital information onto the real world's field of view.

[0109] "Visual evaluation" is an information processing technology that helps humans intuitively understand things through visual information.

[0110] The system implementing this invention consists of a server, terminals, and users. The server collects data from various real estate-related data sources via the internet. This includes basic property information such as price, location, facilities, and other related data, such as nearby amenities and past transaction history. The server also collects word-of-mouth and trend information from social media and news sites. This information is preprocessed and standardized into a format suitable for evaluating the competitiveness score of real estate.

[0111] The server uses a generative AI model to calculate a property's competitiveness score from this data. This AI model is trained on historical market data and trends, enabling highly accurate competitiveness assessments. The calculated competitiveness score is notified to the terminal in real time. Based on this information, the terminal performs a visual evaluation of the property via an augmented reality display. This allows the user to intuitively understand the competitiveness of surrounding properties and helps in making a purchase decision.

[0112] As a concrete example, when a user visits a new area and looks around while wearing smart glasses, the competitiveness score and heat map of each property are overlaid on the glasses' display based on data transmitted from the server. This visual evaluation provides important information for property selection. An example of a prompt to be input into the generating AI model is: "Collect the latest property information in real time around the area the user is interested in, calculate the competitiveness score, and instantly analyze and visually guide the user to which property is the most popular and suitable for purchase."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server collects information from real estate-related data sources via the internet. This information includes property prices, locations, amenities, nearby facilities, past transaction history, and even word-of-mouth and trend information from social media and news sites. The server aggregates this diverse data and outputs it as a real estate information dataset.

[0116] Step 2:

[0117] The server preprocesses the collected real estate information dataset. The input for this preprocessing is the data aggregated in step 1. By supplementing incomplete data, removing outliers, and standardizing the data, it transforms it into a format suitable for the AI ​​model. The output is a formatted dataset for evaluating competitiveness scores.

[0118] Step 3:

[0119] The server receives a pre-formatted dataset and uses a generative AI model to evaluate the competitiveness score of each property. This evaluation utilizes an AI model that has learned from historical market data and trends. The input is a pre-formatted dataset, and the output is a list of competitiveness scores for each property.

[0120] Step 4:

[0121] The server transfers the generated competitiveness score to the terminal and provides real-time notifications. The input for these notifications is a list of competitiveness scores, and the output to the terminal displays information on highly competitive properties. Based on this, the terminal enables a visual evaluation of the properties using an augmented reality display device.

[0122] Step 5:

[0123] Users can view property scores while walking around the city through augmented reality displays. In this step, visible property information is the input, and competitive scores and heatmaps are displayed on the user's screen as output, allowing for intuitive property evaluation.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention provides a system that evaluates the competitiveness of real estate properties and combines it with an emotion engine that recognizes user emotions. This invention supports property selection and negotiation from an emotional perspective, realizing a more refined user experience.

[0126] First, the server collects a wide range of real estate information via the network. This information includes basic property data (price, location, area, etc.) as well as trend information extracted from social media and news articles. This data is then preprocessed to create a standard format that can be analyzed.

[0127] Based on this dataset, the server uses generative artificial intelligence to calculate a competitiveness score for each property. The competitiveness score is a numerical indicator of a property's market popularity and demand forecast. The score is dynamically adjusted using collected trend information.

[0128] Furthermore, the newly added emotion engine analyzes the user's emotional state in real time. Through voice and text input, the system detects the user's emotional responses and generates corresponding data. For example, it analyzes the user's emotions from their voice while they are browsing properties to determine whether they are excited or anxious.

[0129] This sentiment data, along with competitive scores and search history, is reflected in the notifications and advice provided to users. For example, if a user shows strong interest in a particular property but is emotionally unstable, the server will provide advice to encourage a more cautious purchase.

[0130] The device provides users with personalized notifications and advice based on sentiment analysis results and competitiveness scores. It visually displays a competitiveness heatmap to users and offers suggestions tailored to their emotions, supporting them in finding the optimal property.

[0131] Based on the above, this invention provides advanced decision-making in the real estate market based on data analysis and emotional insights, enabling property selection using an effective and human-centered approach.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server automatically collects property-related data from online real estate information platforms. This data includes property prices, locations, sizes, and surrounding facilities, as well as trend information and public opinion obtained through social media and news sites.

[0135] Step 2:

[0136] The server preprocesses the collected data. Specifically, it cleans the data, imputing missing values ​​and removing outliers. It also converts the data to a standard format so that it can be analyzed by the AI ​​model.

[0137] Step 3:

[0138] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​learns from historical market data and transaction trends, scoring the property's popularity and predicting future demand. Real-time trend data is also incorporated at this stage.

[0139] Step 4:

[0140] The server utilizes an emotion engine to analyze the user's emotions in real time. Through voice interfaces and text analysis, it determines the user's emotional state (excitement, reassurance, confusion, etc.) while they are inspecting the property.

[0141] Step 5:

[0142] The server integrates sentiment analysis results and competitive scores to determine the most appropriate notifications for the user. This allows for the adjustment of property selection advice and purchase recommendations based on the user's emotions.

[0143] Step 6:

[0144] The device sends push notifications to the user, including noteworthy properties, recommended areas, and even personalized advice tailored to the user's mood. It also visually displays a competitive heatmap to make it easier to understand the competitive landscape in each area.

[0145] Step 7:

[0146] Users utilize information provided by their devices to select properties and make market decisions. Emotion-based feedback enriches their decision-making during negotiations and purchases.

[0147] Through this series of processes, the system provides users with detailed and emotionally intelligent support for real estate transactions.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] In the real estate market, traditional methods for selecting properties often focus solely on market competitiveness, failing to adequately reflect the emotional aspects of the user's needs. This can lead to users being unable to choose the optimal property based on their emotional state, resulting in anxiety and dissatisfaction with their purchase or selection process. Furthermore, there is a need for information that combines dynamically changing market conditions with the emotional needs of users.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into a standard format, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for analyzing the emotional state of users and generating data thereof, and means for providing notifications based on the competitiveness score and the user's emotional data. This enables highly accurate property selection that takes into account the user's emotions and the provision of appropriate advice based on competitiveness information.

[0153] A "network" is an infrastructure for transmitting information and data between interconnected systems.

[0154] "Real estate" refers to assets that include land and any buildings or structures fixed to it.

[0155] "Means of collecting information" refers to the methods and technologies used to acquire data and incorporate it into a system.

[0156] "Preprocessing" refers to a series of processes performed to prepare data into an analyzable format.

[0157] A "standard format" is a predetermined format that allows data to be handled consistently across different systems and processes.

[0158] "Generative artificial intelligence" refers to advanced algorithms that use models to analyze and predict data collected from it.

[0159] A "competitiveness score" is an evaluation index that quantifies the popularity and demand for a property in the market.

[0160] "Emotional state" refers to the emotional response that an individual user exhibits in response to a specific situation.

[0161] "Means of notification" refers to methods and technologies for providing information and advice to users.

[0162] This invention is a system that uses a network to collect information on real estate, utilizes generative artificial intelligence to analyze the competitiveness of properties, and takes into account user sentiment data to support the selection of the optimal property. An embodiment of this system is shown below.

[0163] The server uses technologies such as APIs and web scraping to collect real estate-related information over the internet. This information includes basic data such as property price, location, and size, as well as trend information obtained from social media and news articles. The server collects this data, performs preprocessing such as data cleaning and format conversion, and adjusts it to a standard format.

[0164] Furthermore, the server uses generative artificial intelligence to evaluate the competitiveness score of real estate. This is done by analyzing data collected by machine learning algorithms and quantifying the market popularity and demand forecast of properties. By utilizing generative artificial intelligence, the score is dynamically adjusted to reflect the latest market trends.

[0165] On the other hand, users analyze their emotions through voice and text input using an engine. The device captures this emotional data and measures the user's emotional state in real time. This allows the system to determine the emotional state the user exhibits while viewing properties, such as excitement or anxiety, and store this information in a database.

[0166] The device provides users with personalized notifications and advice based on competitive scores and sentiment data provided by the server. Users are shown a heatmap visualizing competitiveness and are given property selection suggestions tailored to their emotions.

[0167] As a concrete example, a user might input a prompt into the system stating, "I'm looking for a property in Tokyo that costs under 50 million yen and gives me emotional peace of mind." Based on this prompt, the server and terminal can work together to provide property information that matches the user's preferences.

[0168] This invention aims to provide a better user experience in the real estate market by enabling a more humane property selection process that incorporates the user's emotions.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server collects real estate information via the internet. Input data comes from publicly available APIs and web pages. Specifically, it uses web scraping techniques to obtain basic real estate data (price, location, area, etc.) and trend information. The output is a dataset containing this raw data.

[0172] Step 2:

[0173] The server preprocesses the collected data. It uses the raw data obtained in step 1 as input. Specifically, it performs data cleaning (removing duplicates and imputing missing values), format conversion, and standardization. As a result, it outputs a dataset converted to an analyzable standard format.

[0174] Step 3:

[0175] The server uses a generative AI model to evaluate the competitiveness score of real estate properties. Pre-processed data is used as input. Specifically, it applies machine learning algorithms to assess the market popularity and demand for properties and scores their competitiveness. The output is the competitiveness score for each property.

[0176] Step 4:

[0177] The user provides emotional data via voice or text through the device. Input includes the user's voice and written data. Specifically, the device captures data using the microphone or keyboard, and an emotional analysis engine processes it in real time. The output is data indicating the user's emotional state.

[0178] Step 5:

[0179] The server integrates competitive scores and user sentiment data to generate personalized notifications and advice. Inputs include competitive scores, sentiment data, and user search history. Specifically, it combines this data to recommend the best property based on the user's emotional state. Outputs are individual notifications and advice.

[0180] Step 6:

[0181] The terminal displays notifications and advice from the server to the user. The input consists of notifications and advice received from the server. Specifically, the terminal displays competitive heatmaps and sentiment-based property selection suggestions on the screen. The output consists of visualized information and suggestions.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In selecting real estate properties, traditional methods suffer from insufficient information analysis and a failure to adequately reflect the user's emotions. As a result, it becomes difficult to understand the user's potential desires and circumstances, and thus difficult to support them in choosing the optimal property.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for detecting the user's gaze using a visual device and automatically providing information on properties of interest, and means for analyzing the user's emotions using voice analysis technology and reflecting this in the property selection. This makes it possible to detect the user's interests and preferences using a visual device and provide personalized property suggestions that match their emotional state.

[0187] A "network" is a collection of connected systems used for transmitting data.

[0188] "Means of collecting information" refers to the methods and techniques used to gather necessary information from data sources.

[0189] "Preprocessing" refers to the preparatory work required to convert data into an analyzable format.

[0190] "Generative artificial intelligence" is an algorithm that generates new information and predictions based on vast amounts of data.

[0191] A "competitiveness score" is an indicator that quantifies the popularity and demand for real estate in the market.

[0192] "Means of notification" refers to methods and technologies for conveying information to users.

[0193] "Visualized map information" refers to information in map format that visually displays data for each region.

[0194] A "visual device" is a device used to provide users with images or videos.

[0195] "Eye-gaze detection" is a technology that identifies the point and direction in which a user is looking.

[0196] "Voice analysis technology" is a technology that processes voice data to understand its content and emotions.

[0197] "Analyzing emotions" is the process of evaluating the psychological state of a user.

[0198] "Property recommendation" refers to the process of recommending the most suitable real estate property to the user.

[0199] To implement this invention, a server first collects a wide range of information about real estate via a network. This information includes basic real estate data, as well as trend information and the user's past search history. This data is preprocessed and formatted into a standard format for evaluating competitiveness.

[0200] The server utilizes generative artificial intelligence to dynamically calculate the competitiveness score of real estate properties. Technologies used include speech analysis and eye-tracking, particularly Google® Cloud Speech-to-Text API and IBM Watson® Tone Analyzer. This allows for real-time analysis of which properties users are interested in and their emotional responses to them.

[0201] Users receive visual information through smart glasses, and information tailored to their interests is automatically presented. Eye-tracking technology plays a crucial role here; when the user's gaze lingers on a particular property, details about that property are instantly displayed. Voice responses are also analyzed simultaneously to determine the user's emotions and provide advice as needed.

[0202] For example, if a user shows strong interest in a particular property, but their tone of voice indicates they are feeling uneasy, the server can generate a prompt such as, "Would you like to see more information to alleviate your concerns about this property?"

[0203] An example of a prompt to input into the generating AI model is, "Which properties are you interested in? Please tell us any positive opinions or concerns you have about those properties." By doing so, it becomes possible to provide personalized property suggestions to the user, resulting in an efficient and user-friendly real estate selection experience overall.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects information about real estate via the network. In this step, it obtains basic data about the target property (price, location, area) and trend information extracted from social media and news articles. The input is an external data source, and the output is a set of collected raw data. The server uses this to prepare for data preprocessing in the next step.

[0207] Step 2:

[0208] The server preprocesses the collected raw data and formats it into a standard format for evaluating competitiveness. This process includes removing duplicate data, imputing missing values, and normalizing the data. The input is the raw dataset from step 1, and the output is an analyzable, standardized dataset. The server performs data cleaning and transformation tasks here.

[0209] Step 3:

[0210] The server uses generative artificial intelligence to calculate the competitiveness score of real estate. Here, a standardized dataset is input into the AI ​​algorithm, and the score is further adjusted to account for trend information. The input is a standardized dataset, and the output is the competitiveness score for each property. This algorithm accurately reflects market trends.

[0211] Step 4:

[0212] The server processes the user's gaze data and uses a visual device to identify the property they are focusing on. This step leverages the Google Cloud Vision API. The input is the user's gaze data, and the output is a list of the properties being focused on. The server operates through eye-tracking technology.

[0213] Step 5:

[0214] The device uses speech analysis technology to obtain sentiment data from the user's voice. This step uses the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. The input is the user's voice data, and the output is the analyzed sentiment data. The device processes the user's utterances in real time.

[0215] Step 6:

[0216] The server generates and provides prompts to the user based on sentiment data and competitiveness scores. In this step, a generative AI model is used to create the prompt text. The inputs are competitiveness scores and sentiment data, and the output is a customized prompt text. The server automates the prompt generation process.

[0217] Step 7:

[0218] The user selects properties based on information and prompts provided through smart glasses. In this step, the user receives visual instructions and voice assistance. Input is the prompt text, and output is the selected property information. The user can experience an interactive selection process.

[0219] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0220] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0226] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0230] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0232] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0235] This invention is a system that evaluates the competitiveness of real estate properties and provides users with valuable information in real time. This system particularly utilizes artificial intelligence to support property selection and negotiation.

[0236] First, the server collects information from various real estate-related data sources via the network. This information includes property prices, locations, amenities, nearby amenities, and past transaction history. Furthermore, it collects word-of-mouth and trend information about properties from social media and news sites.

[0237] Once the information is collected, the server preprocesses it. Preprocessing involves filling in missing data, removing outliers, and standardizing the data to create input data suitable for generative artificial intelligence.

[0238] Next, the server uses generative artificial intelligence to evaluate the competitiveness of the properties. The AI ​​model learns from historical market data and trend information and calculates a competitiveness score for each property. This quantifies the popularity and demand for each property.

[0239] Based on this competitiveness score, the server identifies properties that match the user's specified criteria and properties that are highly competitive in the market. Furthermore, it provides the user with personalized advice on property selection and purchase negotiations based on competitiveness.

[0240] The device notifies users via push notifications about competitiveness scores and new popular properties. Furthermore, it displays a heatmap visually showing property competitiveness by region, aiding in intuitive understanding.

[0241] For example, if a user is looking for a new apartment in a certain area, the server calculates a competitiveness score for that area, and the terminal displays the result to the user. Furthermore, for particularly competitive areas or properties, the system provides negotiation advice and suggests strategies to the user, such as when to take action.

[0242] This invention makes it possible to appropriately and efficiently select properties in the real estate market and conduct transactions under the best possible conditions.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server collects property information from real estate portal sites and data providers on the internet. During this process, it uses crawling technology and APIs to obtain detailed property data such as price, location, floor plan, and year of construction.

[0246] Step 2:

[0247] The server analyzes social media and news sites to collect trends and user interest in the real estate market. This allows it to extract the popularity of reviews and topics related to properties.

[0248] Step 3:

[0249] The server preprocesses the collected data. It prepares the data into an analyzable dataset by imputing missing values ​​and removing outliers. It also standardizes the data to format it so that it can be read by AI models.

[0250] Step 4:

[0251] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​model learns from historical market data and trend data, predicting the popularity and future demand of properties to assign scores.

[0252] Step 5:

[0253] The server identifies properties that match the user's desired criteria based on competitiveness scores. It also lists particularly popular properties and newly listed properties. Based on this information, it prepares push notifications.

[0254] Step 6:

[0255] The device will notify users via push notifications about new property listings and changes in the competitiveness of properties. This allows users to check the information immediately.

[0256] Step 7:

[0257] The server generates a heat map that visualizes the competitiveness of each region. This allows you to understand the level of geographical competition in the area where the property is located.

[0258] Step 8:

[0259] The device displays a competitive heatmap to the user, allowing them to identify highly competitive areas in a given location using different colors. It also provides personalized advice for property selection and negotiation based on the user's past activity history.

[0260] Through this series of steps, the system provides users with fast and accurate information on the real estate market, supporting effective property selection and negotiation.

[0261] (Example 1)

[0262] Next, we will describe Example 1. 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."

[0263] The real estate market is vast in terms of property information, making it difficult for users to quickly and efficiently select the most suitable property. In particular, there is a need to accurately evaluate the competitive advantages of properties and provide users with valuable information in real time. This invention aims to solve these problems and optimize real estate property selection and transactions.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes means for collecting data on the real estate market via a network, means for preprocessing the collected data and converting it into input information for artificial intelligence, and means for providing prompt sentences to generative artificial intelligence to evaluate the competitive advantages of real estate. As a result, users can receive real-time notifications based on competitive advantages and make optimal real estate selections and negotiations.

[0266] A "network" is a communication system that transmits data and enables the collection and distribution of real estate-related information.

[0267] "Data related to the real estate market" includes information such as property prices, location, amenities, nearby facilities, and past transaction history.

[0268] "Preprocessing" is the process of preparing collected data into a format that can be analyzed by artificial intelligence, including imputing missing values, removing outliers, and standardizing the data.

[0269] "Artificial intelligence" is an algorithm or system that learns from collected data and analyzes specific patterns and trends.

[0270] A "prompt" is a phrase used to convey instructions or questions to a generative artificial intelligence.

[0271] "Real estate competitive advantage" is an indicator that shows how advantageous a particular real estate property is compared to other properties in the market.

[0272] "Real-time notification" is a communication method that instantly informs users about information or changes that may interest them.

[0273] "Visualized information showing competitive advantages in each region" refers to information that visually represents the competitive advantages of real estate properties in a specific region using maps, graphs, etc.

[0274] This invention relates to an information provision device for evaluating the competitive advantages of real estate properties and providing valuable information to users. This device mainly consists of a server and terminals.

[0275] First, the server collects data about the real estate market via the network. This data includes property prices, locations, amenities, nearby facilities, and past transaction history. Furthermore, the server uses APIs and other methods to gather trending information and word-of-mouth from social media and news feeds.

[0276] The collected data is preprocessed by the server. Specifically, missing data is filled in, outliers are removed, and the data is standardized. This process is important to convert the collected data into a format that can be easily analyzed by generative artificial intelligence.

[0277] Next, the server uses generative artificial intelligence to evaluate the competitive advantages of the properties. Here, the AI ​​utilizes pre-trained market data and trend information to calculate a competitive advantage score for each property. In this step, a prompt such as "Calculate the competitiveness score of this property in this region" is used.

[0278] Based on the evaluation results, the server identifies properties that match the user's specified criteria. This information is notified to the user's device in real time. The device then provides a visual representation of the competitive advantages of properties in each region. Specifically, it uses heatmaps and other tools to help users intuitively understand the information.

[0279] For example, if a user is searching for a new property in a specific area, the server calculates the competitive advantage score for that area and generates a list of the most competitive properties. This list and related advice are then communicated to the user via their device, improving the efficiency of property selection and negotiation. This enables users to make appropriate and efficient decisions in the real estate market.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The server collects data on the real estate market through the network. The inputs include API access from various real estate portal sites and the databases of local real estate agents. As a result, information such as property prices, locations, facilities, neighboring facilities, and past transaction histories is output. In addition, it scans the APIs of social media and news feeds to obtain trend information and word-of-mouth. Thus, a rich dataset for understanding the current market situation is obtained.

[0283] Step 2:

[0284] The server preprocesses the collected data. The inputs include the raw data collected in Step 1. Specific data processing includes filling in missing values, detecting and removing outliers. In this process, outliers such as extremely low or high property prices are excluded, and data normalization is also carried out. As a result of this processing, a clean dataset that can be directly input into the generative AI model is output.

[0285] Step 3:

[0286] The server gives the preprocessed data as input to the generative artificial intelligence to evaluate the competitive advantage of the property. As the prompt text used here, an instruction such as "Calculate the competitiveness score of this property in this area" can be considered. The AI model takes into account the learned market data and trend information, calculates the competitive advantage score for each individual property, and outputs it as a numerical value.

[0287] Step 4:

[0288] The server creates a list of properties that meet the user's desired conditions based on the generated competitive advantage score. The inputs for this step are the score obtained in Step 3 and the desired conditions set by the user. As data calculation, a process of filtering properties that match the desired conditions considering the competitive advantage score is performed. As the output, a list of optimal property proposals for the user is obtained.

[0289] Step 5:

[0290] The device notifies the user of the results. Specifically, it sends push notifications with recommended properties and competitive advantage scores. The input is the property list generated in step 4. Furthermore, the device provides a visual representation of competitive advantages for each region, for example, outputting it as a heatmap. This makes it easier for the user to visually understand the competitive situation in a region.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] In current real estate transactions, despite the abundance of information available, it is difficult to concisely understand that information and determine the true value of a property. Furthermore, there is a lack of means to grasp the competitiveness of real estate in real time and to intuitively evaluate it. As a result, users spend a great deal of effort in selecting and deciding on the purchase of real estate.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, and means for generating information for visually displaying property data on an augmented reality display device and performing a real-time visual evaluation of real estate. This enables users to intuitively grasp the competitiveness of real estate in real time and efficiently select valuable real estate.

[0296] A "network" is a communication infrastructure for exchanging information with one another.

[0297] "Real estate information" refers to data such as price, location, facilities, nearby amenities, and past transaction history for real estate properties.

[0298] "Means of collection" refers to the methods and techniques used to obtain necessary data from specific sources.

[0299] "Preprocessing" refers to the data processing steps that prepare raw data into a format suitable for analysis and evaluation.

[0300] "Input data" refers to pre-formatted data supplied to data analysis or AI models, tailored to a specific purpose.

[0301] "Generative artificial intelligence" is an AI technology that generates new information and predictions based on previously learned data.

[0302] A "competitiveness score" is an evaluation index that quantifies the market value and popularity of a particular property.

[0303] "Means of notification" refers to methods or devices for conveying information or results to users.

[0304] "Visualized map information" refers to information in map format that geographically arranges specific data and presents it in a visually easy-to-understand manner.

[0305] An "augmented reality display device" is a device that overlays digital information onto the real world's field of view.

[0306] "Visual evaluation" is an information processing technology that helps humans intuitively understand things through visual information.

[0307] The system for implementing this invention consists of a server, a terminal, and a user. The server collects data from various real estate - related data sources via the Internet. This includes the price, location, facilities of the property, and other related data, such as nearby convenience facilities and past transaction histories. The server also collects word - of - mouth and trend information from social media and news sites. These information are pre - processed and standardized into a format suitable for evaluating the competitiveness score of real estate.

[0308] The server uses a generative AI model to calculate the competitiveness score of the property from these data. This AI model is trained based on past market data and trends, enabling highly accurate competitiveness evaluation. The calculated competitiveness score is notified to the terminal in real - time. The terminal conducts a visual evaluation of the property via an augmented reality display device based on this information. Thereby, the user can intuitively understand the competitiveness of the surrounding real estate properties and assist in making a purchase decision.

[0309] As a specific example, when a user visits a new area and wears smart glasses to look around, based on the data sent from the server, the competitiveness score and heat map of each property are overlaid and displayed on the glasses' display. This visual evaluation becomes important information for property selection. An example of the prompt text input into the generative AI model is: "Collect the latest property information around the area that the user is interested in in real - time, calculate the competitiveness score, and then instantly analyze which property is the most popular and suitable for purchase and provide visual guidance."

[0310] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0311] Step 1:

[0312] The server collects information from real estate-related data sources via the internet. This information includes property prices, locations, amenities, nearby facilities, past transaction history, and even word-of-mouth and trend information from social media and news sites. The server aggregates this diverse data and outputs it as a real estate information dataset.

[0313] Step 2:

[0314] The server preprocesses the collected real estate information dataset. The input for this preprocessing is the data aggregated in step 1. By supplementing incomplete data, removing outliers, and standardizing the data, it transforms it into a format suitable for the AI ​​model. The output is a formatted dataset for evaluating competitiveness scores.

[0315] Step 3:

[0316] The server receives a pre-formatted dataset and uses a generative AI model to evaluate the competitiveness score of each property. This evaluation utilizes an AI model that has learned from historical market data and trends. The input is a pre-formatted dataset, and the output is a list of competitiveness scores for each property.

[0317] Step 4:

[0318] The server transfers the generated competitiveness score to the terminal and provides real-time notifications. The input for these notifications is a list of competitiveness scores, and the output to the terminal displays information on highly competitive properties. Based on this, the terminal enables a visual evaluation of the properties using an augmented reality display device.

[0319] Step 5:

[0320] Users can view property scores while walking around the city through augmented reality displays. In this step, visible property information is the input, and competitive scores and heatmaps are displayed on the user's screen as output, allowing for intuitive property evaluation.

[0321] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0322] This invention provides a system that evaluates the competitiveness of real estate properties and combines it with an emotion engine that recognizes user emotions. This invention supports property selection and negotiation from an emotional perspective, realizing a more refined user experience.

[0323] First, the server collects a wide range of real estate information via the network. This information includes basic property data (price, location, area, etc.) as well as trend information extracted from social media and news articles. This data is then preprocessed to create a standard format that can be analyzed.

[0324] Based on this dataset, the server uses generative artificial intelligence to calculate a competitiveness score for each property. The competitiveness score is a numerical indicator of a property's market popularity and demand forecast. The score is dynamically adjusted using collected trend information.

[0325] Furthermore, the newly added emotion engine analyzes the user's emotional state in real time. Through voice and text input, the system detects the user's emotional responses and generates corresponding data. For example, it analyzes the user's emotions from their voice while they are browsing properties to determine whether they are excited or anxious.

[0326] This sentiment data, along with competitive scores and search history, is reflected in the notifications and advice provided to users. For example, if a user shows strong interest in a particular property but is emotionally unstable, the server will provide advice to encourage a more cautious purchase.

[0327] The device provides users with personalized notifications and advice based on sentiment analysis results and competitiveness scores. It visually displays a competitiveness heatmap to users and offers suggestions tailored to their emotions, supporting them in finding the optimal property.

[0328] Based on the above, this invention provides advanced decision-making in the real estate market based on data analysis and emotional insights, enabling property selection using an effective and human-centered approach.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] The server automatically collects property-related data from online real estate information platforms. This data includes property prices, locations, sizes, and surrounding facilities, as well as trend information and public opinion obtained through social media and news sites.

[0332] Step 2:

[0333] The server preprocesses the collected data. Specifically, it cleans the data, imputing missing values ​​and removing outliers. It also converts the data to a standard format so that it can be analyzed by the AI ​​model.

[0334] Step 3:

[0335] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​learns from historical market data and transaction trends, scoring the property's popularity and predicting future demand. Real-time trend data is also incorporated at this stage.

[0336] Step 4:

[0337] The server utilizes an emotion engine to analyze the user's emotions in real time. Through voice interfaces and text analysis, it determines the user's emotional state (excitement, reassurance, confusion, etc.) while they are inspecting the property.

[0338] Step 5:

[0339] The server integrates sentiment analysis results and competitive scores to determine the most appropriate notifications for the user. This allows for the adjustment of property selection advice and purchase recommendations based on the user's emotions.

[0340] Step 6:

[0341] The device sends push notifications to the user, including noteworthy properties, recommended areas, and even personalized advice tailored to the user's mood. It also visually displays a competitive heatmap to make it easier to understand the competitive landscape in each area.

[0342] Step 7:

[0343] Users utilize information provided by their devices to select properties and make market decisions. Emotion-based feedback enriches their decision-making during negotiations and purchases.

[0344] Through this series of processes, the system provides users with detailed and emotionally intelligent support for real estate transactions.

[0345] (Example 2)

[0346] Next, we will describe Example 2. 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".

[0347] In the real estate market, traditional methods for selecting properties often focus solely on market competitiveness, failing to adequately reflect the emotional aspects of the user's needs. This can lead to users being unable to choose the optimal property based on their emotional state, resulting in anxiety and dissatisfaction with their purchase or selection process. Furthermore, there is a need for information that combines dynamically changing market conditions with the emotional needs of users.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into a standard format, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for analyzing the emotional state of users and generating data thereof, and means for providing notifications based on the competitiveness score and the user's emotional data. This enables highly accurate property selection that takes into account the user's emotions and the provision of appropriate advice based on competitiveness information.

[0350] A "network" is an infrastructure for transmitting information and data between interconnected systems.

[0351] "Real estate" refers to assets that include land and any buildings or structures fixed to it.

[0352] "Means of collecting information" refers to the methods and technologies used to acquire data and incorporate it into a system.

[0353] "Preprocessing" refers to a series of processes performed to prepare data into an analyzable format.

[0354] A "standard format" is a predetermined format that allows data to be handled consistently across different systems and processes.

[0355] "Generative artificial intelligence" refers to advanced algorithms that use models to analyze and predict data collected from it.

[0356] A "competitiveness score" is an evaluation index that quantifies the popularity and demand for a property in the market.

[0357] "Emotional state" refers to the emotional response that an individual user exhibits in response to a specific situation.

[0358] "Means of notification" refers to methods and technologies for providing information and advice to users.

[0359] This invention is a system that uses a network to collect information on real estate, utilizes generative artificial intelligence to analyze the competitiveness of properties, and takes into account user sentiment data to support the selection of the optimal property. An embodiment of this system is shown below.

[0360] The server uses technologies such as APIs and web scraping to collect real estate-related information over the internet. This information includes basic data such as property price, location, and size, as well as trend information obtained from social media and news articles. The server collects this data, performs preprocessing such as data cleaning and format conversion, and adjusts it to a standard format.

[0361] Furthermore, the server uses generative artificial intelligence to evaluate the competitiveness score of real estate. This is done by analyzing data collected by machine learning algorithms and quantifying the market popularity and demand forecast of properties. By utilizing generative artificial intelligence, the score is dynamically adjusted to reflect the latest market trends.

[0362] On the other hand, users analyze their emotions through voice and text input using an engine. The device captures this emotional data and measures the user's emotional state in real time. This allows the system to determine the emotional state the user exhibits while viewing properties, such as excitement or anxiety, and store this information in a database.

[0363] The device provides users with personalized notifications and advice based on competitive scores and sentiment data provided by the server. Users are shown a heatmap visualizing competitiveness and are given property selection suggestions tailored to their emotions.

[0364] As a concrete example, a user might input a prompt into the system stating, "I'm looking for a property in Tokyo that costs under 50 million yen and gives me emotional peace of mind." Based on this prompt, the server and terminal can work together to provide property information that matches the user's preferences.

[0365] This invention aims to provide a better user experience in the real estate market by enabling a more humane property selection process that incorporates the user's emotions.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] The server collects real estate information via the internet. Input data comes from publicly available APIs and web pages. Specifically, it uses web scraping techniques to obtain basic real estate data (price, location, area, etc.) and trend information. The output is a dataset containing this raw data.

[0369] Step 2:

[0370] The server preprocesses the collected data. It uses the raw data obtained in step 1 as input. Specifically, it performs data cleaning (removing duplicates and imputing missing values), format conversion, and standardization. As a result, it outputs a dataset converted to an analyzable standard format.

[0371] Step 3:

[0372] The server uses a generative AI model to evaluate the competitiveness score of real estate properties. Pre-processed data is used as input. Specifically, it applies machine learning algorithms to assess the market popularity and demand for properties and scores their competitiveness. The output is the competitiveness score for each property.

[0373] Step 4:

[0374] The user provides emotional data via voice or text through the device. Input includes the user's voice and written data. Specifically, the device captures data using the microphone or keyboard, and an emotional analysis engine processes it in real time. The output is data indicating the user's emotional state.

[0375] Step 5:

[0376] The server integrates competitive scores and user sentiment data to generate personalized notifications and advice. Inputs include competitive scores, sentiment data, and user search history. Specifically, it combines this data to recommend the best property based on the user's emotional state. Outputs are individual notifications and advice.

[0377] Step 6:

[0378] The terminal displays notifications and advice from the server to the user. The input consists of notifications and advice received from the server. Specifically, the terminal displays competitive heatmaps and sentiment-based property selection suggestions on the screen. The output consists of visualized information and suggestions.

[0379] (Application Example 2)

[0380] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0381] In selecting real estate properties, traditional methods suffer from insufficient information analysis and a failure to adequately reflect the user's emotions. As a result, it becomes difficult to understand the user's potential desires and circumstances, and thus difficult to support them in choosing the optimal property.

[0382] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0383] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for detecting the user's gaze using a visual device and automatically providing information on properties of interest, and means for analyzing the user's emotions using voice analysis technology and reflecting this in the property selection. This makes it possible to detect the user's interests and preferences using a visual device and provide personalized property suggestions that match their emotional state.

[0384] A "network" is a collection of connected systems used for transmitting data.

[0385] "Means of collecting information" refers to the methods and techniques used to gather necessary information from data sources.

[0386] "Preprocessing" refers to the preparatory work required to convert data into an analyzable format.

[0387] "Generative artificial intelligence" is an algorithm that generates new information and predictions based on vast amounts of data.

[0388] A "competitiveness score" is an indicator that quantifies the popularity and demand for real estate in the market.

[0389] "Means of notification" refers to methods and technologies for conveying information to users.

[0390] "Visualized map information" refers to information in map format that visually displays data for each region.

[0391] A "visual device" is a device used to provide users with images or videos.

[0392] "Eye-gaze detection" is a technology that identifies the point and direction in which a user is looking.

[0393] "Voice analysis technology" is a technology that processes voice data to understand its content and emotions.

[0394] "Analyzing emotions" is the process of evaluating the psychological state of a user.

[0395] "Property recommendation" refers to the process of recommending the most suitable real estate property to the user.

[0396] To implement this invention, a server first collects a wide range of information about real estate via a network. This information includes basic real estate data, as well as trend information and the user's past search history. This data is preprocessed and formatted into a standard format for evaluating competitiveness.

[0397] The server utilizes generative artificial intelligence to dynamically calculate the competitiveness score of real estate properties. Technologies used include speech analysis and eye-tracking, particularly the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. This allows for real-time analysis of which properties users are interested in and their emotional responses to them.

[0398] Users receive visual information through smart glasses, and information tailored to their interests is automatically presented. Eye-tracking technology plays a crucial role here; when the user's gaze lingers on a particular property, details about that property are instantly displayed. Voice responses are also analyzed simultaneously to determine the user's emotions and provide advice as needed.

[0399] For example, if a user shows strong interest in a particular property, but their tone of voice indicates they are feeling uneasy, the server can generate a prompt such as, "Would you like to see more information to alleviate your concerns about this property?"

[0400] An example of a prompt to input into the generating AI model is, "Which properties are you interested in? Please tell us any positive opinions or concerns you have about those properties." By doing so, it becomes possible to provide personalized property suggestions to the user, resulting in an efficient and user-friendly real estate selection experience overall.

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server collects information about real estate via the network. In this step, it obtains basic data about the target property (price, location, area) and trend information extracted from social media and news articles. The input is an external data source, and the output is a set of collected raw data. The server uses this to prepare for data preprocessing in the next step.

[0404] Step 2:

[0405] The server preprocesses the collected raw data and formats it into a standard format for evaluating competitiveness. This process includes removing duplicate data, imputing missing values, and normalizing the data. The input is the raw dataset from step 1, and the output is an analyzable, standardized dataset. The server performs data cleaning and transformation tasks here.

[0406] Step 3:

[0407] The server uses generative artificial intelligence to calculate the competitiveness score of real estate. Here, a standardized dataset is input into the AI ​​algorithm, and the score is further adjusted to account for trend information. The input is a standardized dataset, and the output is the competitiveness score for each property. This algorithm accurately reflects market trends.

[0408] Step 4:

[0409] The server processes the user's gaze data and uses a visual device to identify the property they are focusing on. This step leverages the Google Cloud Vision API. The input is the user's gaze data, and the output is a list of the properties being focused on. The server operates through eye-tracking technology.

[0410] Step 5:

[0411] The device uses speech analysis technology to obtain sentiment data from the user's voice. This step uses the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. The input is the user's voice data, and the output is the analyzed sentiment data. The device processes the user's utterances in real time.

[0412] Step 6:

[0413] The server generates and provides prompts to the user based on sentiment data and competitiveness scores. In this step, a generative AI model is used to create the prompt text. The inputs are competitiveness scores and sentiment data, and the output is a customized prompt text. The server automates the prompt generation process.

[0414] Step 7:

[0415] The user selects properties based on information and prompts provided through smart glasses. In this step, the user receives visual instructions and voice assistance. Input is the prompt text, and output is the selected property information. The user can experience an interactive selection process.

[0416] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0417] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0422] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0424] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0426] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0427] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0428] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0429] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0431] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0432] This invention is a system that evaluates the competitiveness of real estate properties and provides users with valuable information in real time. This system particularly utilizes artificial intelligence to support property selection and negotiation.

[0433] First, the server collects information from various real estate-related data sources via the network. This information includes property prices, locations, amenities, nearby amenities, and past transaction history. Furthermore, it collects word-of-mouth and trend information about properties from social media and news sites.

[0434] Once the information is collected, the server preprocesses it. Preprocessing involves filling in missing data, removing outliers, and standardizing the data to create input data suitable for generative artificial intelligence.

[0435] Next, the server uses generative artificial intelligence to evaluate the competitiveness of the properties. The AI ​​model learns from historical market data and trend information and calculates a competitiveness score for each property. This quantifies the popularity and demand for each property.

[0436] Based on this competitiveness score, the server identifies properties that match the user's desired criteria and properties that are highly competitive in the market. Furthermore, it provides the user with personalized advice on property selection and purchase negotiations based on competitiveness.

[0437] The device notifies users via push notifications about competitiveness scores and new popular properties. Furthermore, it displays a heatmap visually showing property competitiveness by region, aiding in intuitive understanding.

[0438] For example, if a user is looking for a new apartment in a certain area, the server calculates a competitiveness score for that area, and the terminal displays the result to the user. Furthermore, for particularly competitive areas or properties, the system provides negotiation advice and suggests strategies to the user, such as when to take action.

[0439] This invention makes it possible to appropriately and efficiently select properties in the real estate market and conduct transactions under the best possible conditions.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The server collects property information from real estate portal sites and data providers on the internet. It uses crawling technology and APIs to obtain detailed property data such as price, location, floor plan, and year of construction.

[0443] Step 2:

[0444] The server analyzes social media and news sites to collect trends and user interest in the real estate market. This allows it to extract the popularity of reviews and topics related to properties.

[0445] Step 3:

[0446] The server preprocesses the collected data. It prepares the data into an analyzable dataset by imputing missing values ​​and removing outliers. It also standardizes the data to format it so that it can be read by AI models.

[0447] Step 4:

[0448] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​model learns from historical market data and trend data, predicting the popularity and future demand of properties to assign scores.

[0449] Step 5:

[0450] The server identifies properties that match the user's desired criteria based on competitiveness scores. It also lists particularly popular properties and newly listed properties. Based on this information, it prepares push notifications.

[0451] Step 6:

[0452] The device will notify users via push notifications about new property listings and changes in the competitiveness of properties. This allows users to check the information immediately.

[0453] Step 7:

[0454] The server generates a heat map that visualizes the competitiveness of each region. This allows you to understand the level of geographical competition in the area where the property is located.

[0455] Step 8:

[0456] The device displays a competitive heatmap to the user, allowing them to identify highly competitive areas in a given location using different colors. It also provides personalized advice for property selection and negotiation based on the user's past activity history.

[0457] Through this series of steps, the system provides users with fast and accurate information on the real estate market, supporting effective property selection and negotiation.

[0458] (Example 1)

[0459] Next, we will describe Example 1. 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."

[0460] The real estate market is vast in terms of property information, making it difficult for users to quickly and efficiently select the most suitable property. In particular, there is a need to accurately evaluate the competitive advantages of properties and provide users with valuable information in real time. This invention aims to solve these problems and optimize real estate property selection and transactions.

[0461] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0462] In this invention, the server includes means for collecting data on the real estate market via a network, means for preprocessing the collected data and converting it into input information for artificial intelligence, and means for providing prompt sentences to generative artificial intelligence to evaluate the competitive advantages of real estate. As a result, users can receive real-time notifications based on competitive advantages and make optimal real estate selections and negotiations.

[0463] A "network" is a communication system that transmits data and enables the collection and distribution of real estate-related information.

[0464] "Data related to the real estate market" includes information such as property prices, location, amenities, nearby facilities, and past transaction history.

[0465] "Preprocessing" is the process of preparing collected data into a format that can be analyzed by artificial intelligence, including imputing missing values, removing outliers, and standardizing the data.

[0466] "Artificial intelligence" is an algorithm or system that learns from collected data and analyzes specific patterns and trends.

[0467] A "prompt" is a phrase used to convey instructions or questions to a generative artificial intelligence.

[0468] "Real estate competitive advantage" is an indicator that shows how advantageous a particular real estate property is compared to other properties in the market.

[0469] "Real-time notification" is a communication method that instantly informs users about information or changes that may interest them.

[0470] "Visualized information showing competitive advantages in each region" refers to information that visually represents the competitive advantages of real estate properties in a specific region using maps, graphs, etc.

[0471] This invention relates to an information provision device for evaluating the competitive advantages of real estate properties and providing valuable information to users. This device mainly consists of a server and terminals.

[0472] First, the server collects data about the real estate market via the network. This data includes property prices, locations, amenities, nearby facilities, and past transaction history. Furthermore, the server uses APIs and other methods to gather trending information and word-of-mouth from social media and news feeds.

[0473] The collected data is preprocessed by the server. Specifically, missing data is filled in, outliers are removed, and the data is standardized. This process is important to convert the collected data into a format that can be easily analyzed by generative artificial intelligence.

[0474] Next, the server uses generative artificial intelligence to evaluate the competitive advantages of the properties. Here, the AI ​​utilizes pre-trained market data and trend information to calculate a competitive advantage score for each property. In this step, a prompt such as "Calculate the competitiveness score of this property in this region" is used.

[0475] Based on the evaluation results, the server identifies properties that match the user's specified criteria. This information is notified to the user's device in real time. The device then provides a visual representation of the competitive advantages of properties in each region. Specifically, it uses heatmaps and other tools to help users intuitively understand the information.

[0476] For example, if a user is searching for a new property in a specific area, the server calculates the competitive advantage score for that area and generates a list of the most competitive properties. This list and related advice are then communicated to the user via their device, improving the efficiency of property selection and negotiation. This enables users to make appropriate and efficient decisions in the real estate market.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The server collects data on the real estate market through the network. Inputs include API access from various real estate portal sites and local real estate agent databases. This outputs information such as property prices, locations, amenities, nearby facilities, and past transaction history. It also scans social media APIs and news feeds to obtain trend information and word-of-mouth. This provides a rich dataset for understanding the current market situation.

[0480] Step 2:

[0481] The server preprocesses the collected data. The input includes the raw data collected in step 1. Specific data processing involves imputing missing values ​​and detecting and removing outliers. This process eliminates outliers such as extremely low or high property prices and also standardizes the data. As a result of this processing, a clean dataset is output that can be directly input into the generating AI model.

[0482] Step 3:

[0483] The server provides pre-processed data as input to a generative artificial intelligence to evaluate the competitive advantages of the properties. A possible prompt used here would be, "Calculate the competitiveness score of this property in this region." The AI ​​model takes into account the learned market data and trend information to calculate a competitive advantage score for each property and outputs it as a numerical value.

[0484] Step 4:

[0485] The server creates a list of properties that match the user's desired criteria based on the generated competitive advantage score. The inputs for this step are the score obtained in step 3 and the user's desired criteria. The data calculation involves filtering properties that match the desired criteria, taking the competitive advantage score into consideration. The output is a list of the most suitable property suggestions for the user.

[0486] Step 5:

[0487] The device notifies the user of the results. Specifically, it sends push notifications with recommended properties and competitive advantage scores. The input is the property list generated in step 4. Furthermore, the device provides a visual representation of competitive advantages for each region, for example, outputting it as a heatmap. This makes it easier for the user to visually understand the competitive situation in a region.

[0488] (Application Example 1)

[0489] Next, we will explain Application Example 1. In the following explanation, 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."

[0490] In current real estate transactions, despite the abundance of information available, it is difficult to concisely understand that information and determine the true value of a property. Furthermore, there is a lack of means to grasp the competitiveness of real estate in real time and to intuitively evaluate it. As a result, users spend a great deal of effort in selecting and deciding on the purchase of real estate.

[0491] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0492] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, and means for generating information for visually displaying property data on an augmented reality display device and performing a real-time visual evaluation of real estate. This enables users to intuitively grasp the competitiveness of real estate in real time and efficiently select valuable real estate.

[0493] A "network" is a communication infrastructure for exchanging information with one another.

[0494] "Real estate information" refers to data such as price, location, facilities, nearby amenities, and past transaction history for real estate properties.

[0495] "Means of collection" refers to the methods and techniques used to obtain necessary data from specific sources.

[0496] "Preprocessing" refers to the data processing steps that prepare raw data into a format suitable for analysis and evaluation.

[0497] "Input data" refers to pre-formatted data supplied to data analysis or AI models, tailored to a specific purpose.

[0498] "Generative artificial intelligence" is an AI technology that generates new information and predictions based on previously learned data.

[0499] A "competitiveness score" is an evaluation index that quantifies the market value and popularity of a particular property.

[0500] "Means of notification" refers to methods or devices for conveying information or results to users.

[0501] "Visualized map information" refers to information in map format that geographically arranges specific data and presents it in a visually easy-to-understand manner.

[0502] An "augmented reality display device" is a device that overlays digital information onto the real world's field of view.

[0503] "Visual evaluation" is an information processing technology that helps humans intuitively understand things through visual information.

[0504] The system implementing this invention consists of a server, terminals, and users. The server collects data from various real estate-related data sources via the internet. This includes basic property information such as price, location, facilities, and other related data, such as nearby amenities and past transaction history. The server also collects word-of-mouth and trend information from social media and news sites. This information is preprocessed and standardized into a format suitable for evaluating the competitiveness score of real estate.

[0505] The server uses a generative AI model to calculate a property's competitiveness score from this data. This AI model is trained on historical market data and trends, enabling highly accurate competitiveness assessments. The calculated competitiveness score is notified to the terminal in real time. Based on this information, the terminal performs a visual evaluation of the property via an augmented reality display. This allows the user to intuitively understand the competitiveness of surrounding properties and helps in making a purchase decision.

[0506] As a concrete example, when a user visits a new area and looks around while wearing smart glasses, the competitiveness score and heat map of each property are overlaid on the glasses' display based on data transmitted from the server. This visual evaluation provides important information for property selection. An example of a prompt to be input into the generating AI model is: "Collect the latest property information in real time around the area the user is interested in, calculate the competitiveness score, and instantly analyze and visually guide the user to which property is the most popular and suitable for purchase."

[0507] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0508] Step 1:

[0509] The server collects information from real estate-related data sources via the internet. This information includes property prices, locations, amenities, nearby facilities, past transaction history, and even word-of-mouth and trend information from social media and news sites. The server aggregates this diverse data and outputs it as a real estate information dataset.

[0510] Step 2:

[0511] The server preprocesses the collected real estate information dataset. The input for this preprocessing is the data aggregated in step 1. By supplementing incomplete data, removing outliers, and standardizing the data, it transforms it into a format suitable for the AI ​​model. The output is a formatted dataset for evaluating competitiveness scores.

[0512] Step 3:

[0513] The server receives a pre-formatted dataset and uses a generative AI model to evaluate the competitiveness score of each property. This evaluation utilizes an AI model that has learned from historical market data and trends. The input is a pre-formatted dataset, and the output is a list of competitiveness scores for each property.

[0514] Step 4:

[0515] The server transfers the generated competitiveness score to the terminal and provides real-time notifications. The input for these notifications is a list of competitiveness scores, and the output to the terminal displays information on highly competitive properties. Based on this, the terminal enables a visual evaluation of the properties using an augmented reality display device.

[0516] Step 5:

[0517] Users can view property scores while walking around the city through augmented reality displays. In this step, visible property information is the input, and competitive scores and heatmaps are displayed on the user's screen as output, allowing for intuitive property evaluation.

[0518] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0519] This invention provides a system that evaluates the competitiveness of real estate properties and combines it with an emotion engine that recognizes user emotions. This invention supports property selection and negotiation from an emotional perspective, realizing a more refined user experience.

[0520] First, the server collects a wide range of real estate information via the network. This information includes basic property data (price, location, area, etc.) as well as trend information extracted from social media and news articles. This data is then preprocessed to create a standard format that can be analyzed.

[0521] Based on this dataset, the server uses generative artificial intelligence to calculate a competitiveness score for each property. The competitiveness score is a numerical indicator of a property's market popularity and demand forecast. The score is dynamically adjusted using collected trend information.

[0522] Furthermore, the newly added emotion engine analyzes the user's emotional state in real time. Through voice and text input, the system detects the user's emotional responses and generates corresponding data. For example, it analyzes the user's emotions from their voice while they are browsing properties to determine whether they are excited or anxious.

[0523] This sentiment data, along with competitive scores and search history, is reflected in the notifications and advice provided to users. For example, if a user shows strong interest in a particular property but is emotionally unstable, the server will provide advice to encourage a more cautious purchase.

[0524] The device provides users with personalized notifications and advice based on sentiment analysis results and competitiveness scores. It visually displays a competitiveness heatmap to users and offers suggestions tailored to their emotions, supporting them in finding the optimal property.

[0525] Based on the above, this invention provides advanced decision-making in the real estate market based on data analysis and emotional insights, enabling property selection using an effective and human-centered approach.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The server automatically collects property-related data from online real estate information platforms. This data includes property prices, locations, sizes, and surrounding facilities, as well as trend information and public opinion obtained through social media and news sites.

[0529] Step 2:

[0530] The server preprocesses the collected data. Specifically, it cleans the data, imputing missing values ​​and removing outliers. It also converts the data to a standard format so that it can be analyzed by the AI ​​model.

[0531] Step 3:

[0532] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​learns from historical market data and transaction trends, scoring the property's popularity and predicting future demand. Real-time trend data is also incorporated at this stage.

[0533] Step 4:

[0534] The server utilizes an emotion engine to analyze the user's emotions in real time. Through voice interfaces and text analysis, it determines the user's emotional state (excitement, reassurance, confusion, etc.) while they are inspecting the property.

[0535] Step 5:

[0536] The server integrates sentiment analysis results and competitive scores to determine the most appropriate notifications for the user. This allows for the adjustment of property selection advice and purchase recommendations based on the user's emotions.

[0537] Step 6:

[0538] The device sends push notifications to the user, including noteworthy properties, recommended areas, and even personalized advice tailored to the user's mood. It also visually displays a competitive heatmap to make it easier to understand the competitive landscape in each area.

[0539] Step 7:

[0540] Users utilize information provided by their devices to select properties and make market decisions. Emotion-based feedback enriches their decision-making during negotiations and purchases.

[0541] Through this series of processes, the system provides users with detailed and emotionally intelligent support for real estate transactions.

[0542] (Example 2)

[0543] Next, we will describe Example 2. 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."

[0544] In the real estate market, traditional methods for selecting properties often focus solely on market competitiveness, failing to adequately reflect the emotional aspects of the user's needs. This can lead to users being unable to choose the optimal property based on their emotional state, resulting in anxiety and dissatisfaction with their purchase or selection process. Furthermore, there is a need for information that combines dynamically changing market conditions with the emotional needs of users.

[0545] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0546] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into a standard format, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for analyzing the emotional state of users and generating data thereof, and means for providing notifications based on the competitiveness score and the user's emotional data. This enables highly accurate property selection that takes into account the user's emotions and the provision of appropriate advice based on competitiveness information.

[0547] A "network" is an infrastructure for transmitting information and data between interconnected systems.

[0548] "Real estate" refers to assets that include land and any buildings or structures fixed to it.

[0549] "Means of collecting information" refers to the methods and technologies used to acquire data and incorporate it into a system.

[0550] "Preprocessing" refers to a series of processes performed to prepare data into an analyzable format.

[0551] A "standard format" is a predetermined format that allows data to be handled consistently across different systems and processes.

[0552] "Generative artificial intelligence" refers to advanced algorithms that use models to analyze and predict data collected from it.

[0553] A "competitiveness score" is an evaluation index that quantifies the popularity and demand for a property in the market.

[0554] "Emotional state" refers to the emotional response that an individual user exhibits in response to a specific situation.

[0555] "Means of notification" refers to methods and technologies for providing information and advice to users.

[0556] This invention is a system that uses a network to collect information on real estate, utilizes generative artificial intelligence to analyze the competitiveness of properties, and takes into account user sentiment data to support the selection of the optimal property. An embodiment of this system is shown below.

[0557] The server uses technologies such as APIs and web scraping to collect real estate-related information over the internet. This information includes basic data such as property price, location, and size, as well as trend information obtained from social media and news articles. The server collects this data, performs preprocessing such as data cleaning and format conversion, and adjusts it to a standard format.

[0558] Furthermore, the server uses generative artificial intelligence to evaluate the competitiveness score of real estate. This is done by analyzing data collected by machine learning algorithms and quantifying the market popularity and demand forecast of properties. By utilizing generative artificial intelligence, the score is dynamically adjusted to reflect the latest market trends.

[0559] On the other hand, users analyze their emotions through voice and text input using an engine. The device captures this emotional data and measures the user's emotional state in real time. This allows the system to determine the emotional state the user exhibits while viewing properties, such as excitement or anxiety, and store this information in a database.

[0560] The device provides users with personalized notifications and advice based on competitive scores and sentiment data provided by the server. Users are shown a heatmap visualizing competitiveness and are given property selection suggestions tailored to their emotions.

[0561] As a concrete example, a user might input a prompt into the system stating, "I'm looking for a property in Tokyo that costs under 50 million yen and gives me emotional peace of mind." Based on this prompt, the server and terminal can work together to provide property information that matches the user's preferences.

[0562] This invention aims to provide a better user experience in the real estate market by enabling a more humane property selection process that incorporates the user's emotions.

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] The server collects real estate information via the internet. Input data comes from publicly available APIs and web pages. Specifically, it uses web scraping techniques to obtain basic real estate data (price, location, area, etc.) and trend information. The output is a dataset containing this raw data.

[0566] Step 2:

[0567] The server preprocesses the collected data. It uses the raw data obtained in step 1 as input. Specifically, it performs data cleaning (removing duplicates and imputing missing values), format conversion, and standardization. As a result, it outputs a dataset converted to an analyzable standard format.

[0568] Step 3:

[0569] The server uses a generative AI model to evaluate the competitiveness score of real estate properties. Pre-processed data is used as input. Specifically, it applies machine learning algorithms to assess the market popularity and demand for properties and scores their competitiveness. The output is the competitiveness score for each property.

[0570] Step 4:

[0571] The user provides emotional data via voice or text through the device. Input includes the user's voice and written data. Specifically, the device captures data using the microphone or keyboard, and an emotional analysis engine processes it in real time. The output is data indicating the user's emotional state.

[0572] Step 5:

[0573] The server integrates competitive scores and user sentiment data to generate personalized notifications and advice. Inputs include competitive scores, sentiment data, and user search history. Specifically, it combines this data to recommend the best property based on the user's emotional state. Outputs are individual notifications and advice.

[0574] Step 6:

[0575] The terminal displays notifications and advice from the server to the user. The input consists of notifications and advice received from the server. Specifically, the terminal displays competitive heatmaps and sentiment-based property selection suggestions on the screen. The output consists of visualized information and suggestions.

[0576] (Application Example 2)

[0577] Next, we will explain application example 2. In the following explanation, 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."

[0578] In selecting real estate properties, traditional methods suffer from insufficient information analysis and a failure to adequately reflect the user's emotions. As a result, it becomes difficult to understand the user's potential desires and circumstances, and thus difficult to support them in choosing the optimal property.

[0579] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0580] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for detecting the user's gaze using a visual device and automatically providing information on properties of interest, and means for analyzing the user's emotions using voice analysis technology and reflecting this in the property selection. This makes it possible to detect the user's interests and preferences using a visual device and provide personalized property suggestions that match their emotional state.

[0581] A "network" is a collection of connected systems used for transmitting data.

[0582] "Means of collecting information" refers to the methods and techniques used to gather necessary information from data sources.

[0583] "Preprocessing" refers to the preparatory work required to convert data into an analyzable format.

[0584] "Generative artificial intelligence" is an algorithm that generates new information and predictions based on vast amounts of data.

[0585] A "competitiveness score" is an indicator that quantifies the popularity and demand for real estate in the market.

[0586] "Means of notification" refers to methods and technologies for conveying information to users.

[0587] "Visualized map information" refers to information in map format that visually displays data for each region.

[0588] A "visual device" is a device used to provide users with images or videos.

[0589] "Eye-gaze detection" is a technology that identifies the point and direction in which a user is looking.

[0590] "Voice analysis technology" is a technology that processes voice data to understand its content and emotions.

[0591] "Analyzing emotions" is the process of evaluating the psychological state of a user.

[0592] "Property recommendation" refers to the process of recommending the most suitable real estate property to the user.

[0593] To implement this invention, a server first collects a wide range of information about real estate via a network. This information includes basic real estate data, as well as trend information and the user's past search history. This data is preprocessed and formatted into a standard format for evaluating competitiveness.

[0594] The server utilizes generative artificial intelligence to dynamically calculate the competitiveness score of real estate properties. Technologies used include speech analysis and eye-tracking, particularly the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. This allows for real-time analysis of which properties users are interested in and their emotional responses to them.

[0595] Users receive visual information through smart glasses, and information tailored to their interests is automatically presented. Eye-tracking technology plays a crucial role here; when the user's gaze lingers on a particular property, details about that property are instantly displayed. Voice responses are also analyzed simultaneously to determine the user's emotions and provide advice as needed.

[0596] For example, if a user shows strong interest in a particular property, but their tone of voice indicates they are feeling uneasy, the server can generate a prompt such as, "Would you like to see more information to alleviate your concerns about this property?"

[0597] An example of a prompt to input into the generating AI model is, "Which properties are you interested in? Please tell us any positive opinions or concerns you have about those properties." By doing so, it becomes possible to provide personalized property suggestions to the user, resulting in an efficient and user-friendly real estate selection experience overall.

[0598] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0599] Step 1:

[0600] The server collects information about real estate via the network. In this step, it obtains basic data about the target property (price, location, area) and trend information extracted from social media and news articles. The input is an external data source, and the output is a set of collected raw data. The server uses this to prepare for data preprocessing in the next step.

[0601] Step 2:

[0602] The server preprocesses the collected raw data and formats it into a standard format for evaluating competitiveness. This process includes removing duplicate data, imputing missing values, and normalizing the data. The input is the raw dataset from step 1, and the output is an analyzable, standardized dataset. The server performs data cleaning and transformation tasks here.

[0603] Step 3:

[0604] The server uses generative artificial intelligence to calculate the competitiveness score of real estate. Here, a standardized dataset is input into the AI ​​algorithm, and the score is further adjusted to account for trend information. The input is a standardized dataset, and the output is the competitiveness score for each property. This algorithm accurately reflects market trends.

[0605] Step 4:

[0606] The server processes the user's gaze data and uses a visual device to identify the property they are focusing on. This step leverages the Google Cloud Vision API. The input is the user's gaze data, and the output is a list of the properties being focused on. The server operates through eye-tracking technology.

[0607] Step 5:

[0608] The device uses speech analysis technology to obtain sentiment data from the user's voice. This step uses the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. The input is the user's voice data, and the output is the analyzed sentiment data. The device processes the user's utterances in real time.

[0609] Step 6:

[0610] The server generates and provides prompts to the user based on sentiment data and competitiveness scores. In this step, a generative AI model is used to create the prompt text. The inputs are competitiveness scores and sentiment data, and the output is a customized prompt text. The server automates the prompt generation process.

[0611] Step 7:

[0612] The user selects properties based on information and prompts provided through smart glasses. In this step, the user receives visual instructions and voice assistance. Input is the prompt text, and output is the selected property information. The user can experience an interactive selection process.

[0613] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0614] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] As shown in Figure 7, the 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.

[0619] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0621] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0623] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0624] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0625] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0626] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0627] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0628] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0629] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] This invention is a system that evaluates the competitiveness of real estate properties and provides users with valuable information in real time. This system particularly utilizes artificial intelligence to support property selection and negotiation.

[0631] First, the server collects information from various real estate-related data sources via the network. This information includes property prices, locations, amenities, nearby amenities, and past transaction history. Furthermore, it collects word-of-mouth and trend information about properties from social media and news sites.

[0632] Once the information is collected, the server preprocesses it. Preprocessing involves filling in missing data, removing outliers, and standardizing the data to create input data suitable for generative artificial intelligence.

[0633] Next, the server uses generative artificial intelligence to evaluate the competitiveness of the properties. The AI ​​model learns from historical market data and trend information and calculates a competitiveness score for each property. This quantifies the popularity and demand for each property.

[0634] Based on this competitiveness score, the server identifies properties that match the user's desired criteria and properties that are highly competitive in the market. Furthermore, it provides the user with personalized advice on property selection and purchase negotiations based on competitiveness.

[0635] The device notifies users via push notifications about competitiveness scores and new popular properties. Furthermore, it displays a heatmap visually showing property competitiveness by region, aiding in intuitive understanding.

[0636] For example, if a user is looking for a new apartment in a certain area, the server calculates a competitiveness score for that area, and the terminal displays the result to the user. Furthermore, for particularly competitive areas or properties, the system provides negotiation advice and suggests strategies to the user, such as when to take action.

[0637] This invention makes it possible to appropriately and efficiently select properties in the real estate market and conduct transactions under the best possible conditions.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The server collects property information from real estate portal sites and data providers on the internet. It uses crawling technology and APIs to obtain detailed property data such as price, location, floor plan, and year of construction.

[0641] Step 2:

[0642] The server analyzes social media and news sites to collect trends and user interest in the real estate market. This allows it to extract the popularity of reviews and topics related to properties.

[0643] Step 3:

[0644] The server preprocesses the collected data. It prepares the data into an analyzable dataset by imputing missing values ​​and removing outliers. It also standardizes the data to format it so that it can be read by AI models.

[0645] Step 4:

[0646] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​model learns from historical market data and trend data, predicting the popularity and future demand of properties to assign scores.

[0647] Step 5:

[0648] The server identifies properties that match the user's desired criteria based on competitiveness scores. It also lists particularly popular properties and newly listed properties. Based on this information, it prepares push notifications.

[0649] Step 6:

[0650] The device will notify users via push notifications about new property listings and changes in the competitiveness of properties. This allows users to check the information immediately.

[0651] Step 7:

[0652] The server generates a heat map that visualizes the competitiveness of each region. This allows you to understand the level of geographical competition in the area where the property is located.

[0653] Step 8:

[0654] The device displays a competitive heatmap to the user, allowing them to identify highly competitive areas in a given location using different colors. It also provides personalized advice for property selection and negotiation based on the user's past activity history.

[0655] Through this series of steps, the system provides users with fast and accurate information on the real estate market, supporting effective property selection and negotiation.

[0656] (Example 1)

[0657] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] The real estate market is vast in terms of property information, making it difficult for users to quickly and efficiently select the most suitable property. In particular, there is a need to accurately evaluate the competitive advantages of properties and provide users with valuable information in real time. This invention aims to solve these problems and optimize real estate property selection and transactions.

[0659] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0660] In this invention, the server includes means for collecting data on the real estate market via a network, means for preprocessing the collected data and converting it into input information for artificial intelligence, and means for providing prompt sentences to generative artificial intelligence to evaluate the competitive advantages of real estate. As a result, users can receive real-time notifications based on competitive advantages and make optimal real estate selections and negotiations.

[0661] A "network" is a communication system that transmits data and enables the collection and distribution of real estate-related information.

[0662] "Data related to the real estate market" includes information such as property prices, location, amenities, nearby facilities, and past transaction history.

[0663] "Preprocessing" is the process of preparing collected data into a format that can be analyzed by artificial intelligence, including imputing missing values, removing outliers, and standardizing the data.

[0664] "Artificial intelligence" is an algorithm or system that learns from collected data and analyzes specific patterns and trends.

[0665] A "prompt" is a phrase used to convey instructions or questions to a generative artificial intelligence.

[0666] "Real estate competitive advantage" is an indicator that shows how advantageous a particular real estate property is compared to other properties in the market.

[0667] "Real-time notification" is a communication method that instantly informs users about information or changes that may interest them.

[0668] "Visualized information showing competitive advantages in each region" refers to information that visually represents the competitive advantages of real estate properties in a specific region using maps, graphs, etc.

[0669] This invention relates to an information provision device for evaluating the competitive advantages of real estate properties and providing valuable information to users. This device mainly consists of a server and terminals.

[0670] First, the server collects data about the real estate market via the network. This data includes property prices, locations, amenities, nearby facilities, and past transaction history. Furthermore, the server uses APIs and other methods to gather trending information and word-of-mouth from social media and news feeds.

[0671] The collected data is preprocessed by the server. Specifically, missing data is filled in, outliers are removed, and the data is standardized. This process is important to convert the collected data into a format that can be easily analyzed by generative artificial intelligence.

[0672] Next, the server uses generative artificial intelligence to evaluate the competitive advantages of the properties. Here, the AI ​​utilizes pre-trained market data and trend information to calculate a competitive advantage score for each property. In this step, a prompt such as "Calculate the competitiveness score of this property in this region" is used.

[0673] Based on the evaluation results, the server identifies properties that match the user's specified criteria. This information is notified to the user's device in real time. The device then provides a visual representation of the competitive advantages of properties in each region. Specifically, it uses heatmaps and other tools to help users intuitively understand the information.

[0674] For example, if a user is searching for a new property in a specific area, the server calculates the competitive advantage score for that area and generates a list of the most competitive properties. This list and related advice are then communicated to the user via their device, improving the efficiency of property selection and negotiation. This enables users to make appropriate and efficient decisions in the real estate market.

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] The server collects data on the real estate market through the network. Inputs include API access from various real estate portal sites and local real estate agent databases. This outputs information such as property prices, locations, amenities, nearby facilities, and past transaction history. It also scans social media APIs and news feeds to obtain trend information and word-of-mouth. This provides a rich dataset for understanding the current market situation.

[0678] Step 2:

[0679] The server preprocesses the collected data. The input includes the raw data collected in step 1. Specific data processing involves imputing missing values ​​and detecting and removing outliers. This process eliminates outliers such as extremely low or high property prices and also standardizes the data. As a result of this processing, a clean dataset is output that can be directly input into the generating AI model.

[0680] Step 3:

[0681] The server provides pre-processed data as input to a generative artificial intelligence to evaluate the competitive advantages of the properties. A possible prompt used here would be, "Calculate the competitiveness score of this property in this region." The AI ​​model takes into account the learned market data and trend information to calculate a competitive advantage score for each property and outputs it as a numerical value.

[0682] Step 4:

[0683] The server creates a list of properties that match the user's desired criteria based on the generated competitive advantage score. The inputs for this step are the score obtained in step 3 and the user's desired criteria. The data calculation involves filtering properties that match the desired criteria, taking the competitive advantage score into consideration. The output is a list of the most suitable property suggestions for the user.

[0684] Step 5:

[0685] The device notifies the user of the results. Specifically, it sends push notifications with recommended properties and competitive advantage scores. The input is the property list generated in step 4. Furthermore, the device provides a visual representation of competitive advantages for each region, for example, outputting it as a heatmap. This makes it easier for the user to visually understand the competitive situation in a region.

[0686] (Application Example 1)

[0687] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0688] In current real estate transactions, despite the abundance of information available, it is difficult to concisely understand that information and determine the true value of a property. Furthermore, there is a lack of means to grasp the competitiveness of real estate in real time and to intuitively evaluate it. As a result, users spend a great deal of effort in selecting and deciding on the purchase of real estate.

[0689] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0690] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, and means for generating information for visually displaying property data on an augmented reality display device and performing a real-time visual evaluation of real estate. This enables users to intuitively grasp the competitiveness of real estate in real time and efficiently select valuable real estate.

[0691] A "network" is a communication infrastructure for exchanging information with one another.

[0692] "Real estate information" refers to data such as price, location, facilities, nearby amenities, and past transaction history for real estate properties.

[0693] "Means of collection" refers to the methods and techniques used to obtain necessary data from specific sources.

[0694] "Preprocessing" refers to the data processing steps that prepare raw data into a format suitable for analysis and evaluation.

[0695] "Input data" refers to pre-formatted data supplied to data analysis or AI models, tailored to a specific purpose.

[0696] "Generative artificial intelligence" is an AI technology that generates new information and predictions based on previously learned data.

[0697] A "competitiveness score" is an evaluation index that quantifies the market value and popularity of a particular property.

[0698] "Means of notification" refers to methods or devices for conveying information or results to users.

[0699] "Visualized map information" refers to information in map format that geographically arranges specific data and presents it in a visually easy-to-understand manner.

[0700] An "augmented reality display device" is a device that overlays digital information onto the real world's field of view.

[0701] "Visual evaluation" is an information processing technology that helps humans intuitively understand things through visual information.

[0702] The system implementing this invention consists of a server, terminals, and users. The server collects data from various real estate-related data sources via the internet. This includes basic property information such as price, location, facilities, and other related data, such as nearby amenities and past transaction history. The server also collects word-of-mouth and trend information from social media and news sites. This information is preprocessed and standardized into a format suitable for evaluating the competitiveness score of real estate.

[0703] The server uses a generative AI model to calculate a property's competitiveness score from this data. This AI model is trained on historical market data and trends, enabling highly accurate competitiveness assessments. The calculated competitiveness score is notified to the terminal in real time. Based on this information, the terminal performs a visual evaluation of the property via an augmented reality display. This allows the user to intuitively understand the competitiveness of surrounding properties and helps in making a purchase decision.

[0704] As a concrete example, when a user visits a new area and looks around while wearing smart glasses, the competitiveness score and heat map of each property are overlaid on the glasses' display based on data transmitted from the server. This visual evaluation provides important information for property selection. An example of a prompt to be input into the generating AI model is: "Collect the latest property information in real time around the area the user is interested in, calculate the competitiveness score, and instantly analyze and visually guide the user to which property is the most popular and suitable for purchase."

[0705] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0706] Step 1:

[0707] The server collects information from real estate-related data sources via the internet. This information includes property prices, locations, amenities, nearby facilities, past transaction history, and even word-of-mouth and trend information from social media and news sites. The server aggregates this diverse data and outputs it as a real estate information dataset.

[0708] Step 2:

[0709] The server preprocesses the collected real estate information dataset. The input for this preprocessing is the data aggregated in step 1. By supplementing incomplete data, removing outliers, and standardizing the data, it transforms it into a format suitable for the AI ​​model. The output is a formatted dataset for evaluating competitiveness scores.

[0710] Step 3:

[0711] The server receives a pre-formatted dataset and uses a generative AI model to evaluate the competitiveness score of each property. This evaluation utilizes an AI model that has learned from historical market data and trends. The input is a pre-formatted dataset, and the output is a list of competitiveness scores for each property.

[0712] Step 4:

[0713] The server transfers the generated competitiveness score to the terminal and provides real-time notifications. The input for these notifications is a list of competitiveness scores, and the output to the terminal displays information on highly competitive properties. Based on this, the terminal enables a visual evaluation of the properties using an augmented reality display device.

[0714] Step 5:

[0715] Through augmented reality, users can view property scores while walking around the city. In this step, visible property information is the input, and competitive scores and heatmaps are displayed on the user's screen as output, allowing for intuitive property evaluation.

[0716] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0717] This invention provides a system that evaluates the competitiveness of real estate properties and combines it with an emotion engine that recognizes user emotions. This invention supports property selection and negotiation from an emotional perspective, realizing a more refined user experience.

[0718] First, the server collects a wide range of real estate information via the network. This information includes basic property data (price, location, area, etc.) as well as trend information extracted from social media and news articles. This data is then preprocessed to create a standard format that can be analyzed.

[0719] Based on this dataset, the server uses generative artificial intelligence to calculate a competitiveness score for each property. The competitiveness score is a numerical indicator that quantifies the property's market popularity and demand forecast. The score is dynamically adjusted using collected trend information.

[0720] Furthermore, the newly added emotion engine analyzes the user's emotional state in real time. Through voice and text input, the system detects the user's emotional responses and generates corresponding data. For example, it analyzes the user's emotions from their voice while they are browsing properties to determine whether they are excited or anxious.

[0721] This sentiment data, along with competitive scores and search history, is reflected in the notifications and advice provided to users. For example, if a user shows strong interest in a particular property but is emotionally unstable, the server will provide advice to encourage a more cautious purchase.

[0722] The device provides users with personalized notifications and advice based on sentiment analysis results and competitiveness scores. It visually displays a competitiveness heatmap to users and offers suggestions tailored to their emotions, supporting them in finding the optimal property.

[0723] Based on the above, this invention provides advanced decision-making in the real estate market based on data analysis and emotional insights, enabling property selection using an effective and human-centered approach.

[0724] The following describes the processing flow.

[0725] Step 1:

[0726] The server automatically collects property-related data from online real estate information platforms. This data includes property prices, locations, sizes, and surrounding facilities, as well as trend information and public opinion obtained through social media and news sites.

[0727] Step 2:

[0728] The server preprocesses the collected data. Specifically, it cleans the data, imputing missing values ​​and removing outliers. It also converts the data to a standard format so that it can be analyzed by the AI ​​model.

[0729] Step 3:

[0730] The server uses generative artificial intelligence to calculate a competitiveness score for each property. The AI ​​learns from historical market data and transaction trends, scoring the property's popularity and predicting future demand. Real-time trend data is also incorporated at this stage.

[0731] Step 4:

[0732] The server utilizes an emotion engine to analyze the user's emotions in real time. Through voice interfaces and text analysis, it determines the user's emotional state (excitement, reassurance, confusion, etc.) while they are inspecting the property.

[0733] Step 5:

[0734] The server integrates sentiment analysis results and competitive scores to determine the most appropriate notifications for the user. This allows for the adjustment of property selection advice and purchase recommendations based on the user's emotions.

[0735] Step 6:

[0736] The device sends push notifications to the user, including noteworthy properties, recommended areas, and even personalized advice tailored to the user's mood. It also visually displays a competitive heatmap to make it easier to understand the competitive landscape in each area.

[0737] Step 7:

[0738] Users utilize information provided by their devices to select properties and make market decisions. Emotion-based feedback enriches their decision-making during negotiations and purchases.

[0739] Through this series of processes, the system provides users with detailed and emotionally intelligent support for real estate transactions.

[0740] (Example 2)

[0741] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] In the real estate market, traditional methods for selecting properties often focus solely on market competitiveness, failing to adequately reflect the emotional aspects of the user's needs. This can lead to users being unable to choose the optimal property based on their emotional state, resulting in anxiety and dissatisfaction with their purchase or selection process. Furthermore, there is a need for information that combines dynamically changing market conditions with the emotional needs of users.

[0743] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0744] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into a standard format, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for analyzing the emotional state of users and generating data thereof, and means for providing notifications based on the competitiveness score and the user's emotional data. This enables highly accurate property selection that takes into account the user's emotions and the provision of appropriate advice based on competitiveness information.

[0745] A "network" is an infrastructure for transmitting information and data between interconnected systems.

[0746] "Real estate" refers to assets that include land and any buildings or structures fixed to it.

[0747] "Means of collecting information" refers to the methods and technologies used to acquire data and incorporate it into a system.

[0748] "Preprocessing" refers to a series of processes performed to prepare data into an analyzable format.

[0749] A "standard format" is a predetermined format that allows data to be handled consistently across different systems and processes.

[0750] "Generative artificial intelligence" refers to advanced algorithms that use models to analyze and predict data collected from it.

[0751] A "competitiveness score" is an evaluation index that quantifies the popularity and demand for a property in the market.

[0752] "Emotional state" refers to the emotional response that an individual user exhibits in response to a specific situation.

[0753] "Means of notification" refers to methods and technologies for providing information and advice to users.

[0754] This invention is a system that uses a network to collect information on real estate, utilizes generative artificial intelligence to analyze the competitiveness of properties, and takes into account user sentiment data to support the selection of the optimal property. An embodiment of this system is shown below.

[0755] The server uses technologies such as APIs and web scraping to collect real estate-related information over the internet. This information includes basic data such as property price, location, and size, as well as trend information obtained from social media and news articles. The server collects this data, performs preprocessing such as data cleaning and format conversion, and adjusts it to a standard format.

[0756] Furthermore, the server uses generative artificial intelligence to evaluate the competitiveness score of real estate. This is done by analyzing data collected by machine learning algorithms and quantifying the market popularity and demand forecast of properties. By utilizing generative artificial intelligence, the score is dynamically adjusted to reflect the latest market trends.

[0757] On the other hand, users analyze their emotions through voice and text input using an engine. The device captures this emotional data and measures the user's emotional state in real time. This allows the system to determine the emotional state the user exhibits while viewing properties, such as excitement or anxiety, and store this information in a database.

[0758] The device provides users with personalized notifications and advice based on competitive scores and sentiment data provided by the server. Users are shown a heatmap visualizing competitiveness and are given property selection suggestions tailored to their emotions.

[0759] As a concrete example, a user might input a prompt into the system stating, "I'm looking for a property in Tokyo that costs under 50 million yen and gives me emotional peace of mind." Based on this prompt, the server and terminal can work together to provide property information that matches the user's preferences.

[0760] This invention aims to provide a better user experience in the real estate market by enabling a more humane property selection process that incorporates the user's emotions.

[0761] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0762] Step 1:

[0763] The server collects real estate information via the internet. Input data comes from publicly available APIs and web pages. Specifically, it uses web scraping techniques to obtain basic real estate data (price, location, area, etc.) and trend information. The output is a dataset containing this raw data.

[0764] Step 2:

[0765] The server preprocesses the collected data. It uses the raw data obtained in step 1 as input. Specifically, it performs data cleaning (removing duplicates and imputing missing values), format conversion, and standardization. As a result, it outputs a dataset converted to an analyzable standard format.

[0766] Step 3:

[0767] The server uses a generative AI model to evaluate the competitiveness score of real estate properties. Pre-processed data is used as input. Specifically, it applies machine learning algorithms to assess the market popularity and demand for properties and scores their competitiveness. The output is the competitiveness score for each property.

[0768] Step 4:

[0769] The user provides emotional data via voice or text through the device. Input includes the user's voice and written data. Specifically, the device captures data using the microphone or keyboard, and an emotional analysis engine processes it in real time. The output is data indicating the user's emotional state.

[0770] Step 5:

[0771] The server integrates competitive scores and user sentiment data to generate personalized notifications and advice. Inputs include competitive scores, sentiment data, and user search history. Specifically, it combines this data to recommend the best property based on the user's emotional state. Outputs are individual notifications and advice.

[0772] Step 6:

[0773] The terminal displays notifications and advice from the server to the user. The input consists of notifications and advice received from the server. Specifically, the terminal displays competitive heatmaps and sentiment-based property selection suggestions on the screen. The output consists of visualized information and suggestions.

[0774] (Application Example 2)

[0775] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0776] In selecting real estate properties, traditional methods suffer from insufficient information analysis and a failure to adequately reflect the user's emotions. As a result, it becomes difficult to understand the user's potential desires and circumstances, and thus difficult to support them in choosing the optimal property.

[0777] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0778] In this invention, the server includes means for collecting information about real estate via a network, means for preprocessing the collected information and converting it into input data for evaluating competitiveness, means for evaluating the competitiveness score of real estate using generative artificial intelligence, means for detecting the user's gaze using a visual device and automatically providing information on properties of interest, and means for analyzing the user's emotions using voice analysis technology and reflecting this in the property selection. This makes it possible to detect the user's interests and preferences using a visual device and provide personalized property suggestions that match their emotional state.

[0779] A "network" is a collection of connected systems used for transmitting data.

[0780] "Means of collecting information" refers to the methods and techniques used to gather necessary information from data sources.

[0781] "Preprocessing" refers to the preparatory work required to convert data into an analyzable format.

[0782] "Generative artificial intelligence" is an algorithm that generates new information and predictions based on vast amounts of data.

[0783] A "competitiveness score" is an indicator that quantifies the popularity and demand for real estate in the market.

[0784] "Means of notification" refers to methods and technologies for conveying information to users.

[0785] "Visualized map information" refers to information in map format that visually displays data for each region.

[0786] A "visual device" is a device used to provide users with images or videos.

[0787] "Eye-gaze detection" is a technology that identifies the point and direction in which a user is looking.

[0788] "Voice analysis technology" is a technology that processes voice data to understand its content and emotions.

[0789] "Analyzing emotions" is the process of evaluating the psychological state of a user.

[0790] "Property recommendation" refers to the process of recommending the most suitable real estate property to the user.

[0791] To implement this invention, a server first collects a wide range of information about real estate via a network. This information includes basic real estate data, as well as trend information and the user's past search history. This data is preprocessed and formatted into a standard format for evaluating competitiveness.

[0792] The server utilizes generative artificial intelligence to dynamically calculate the competitiveness score of real estate properties. Technologies used include speech analysis and eye-tracking, particularly the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. This allows for real-time analysis of which properties users are interested in and their emotional responses to them.

[0793] Users receive visual information through smart glasses, and information tailored to their interests is automatically presented. Eye-tracking technology plays a crucial role here; when the user's gaze lingers on a particular property, details about that property are instantly displayed. Voice responses are also analyzed simultaneously to determine the user's emotions and provide advice as needed.

[0794] For example, if a user shows strong interest in a particular property, but their tone of voice indicates they are feeling uneasy, the server can generate a prompt such as, "Would you like to see more information to alleviate your concerns about this property?"

[0795] An example of a prompt to input into the generating AI model is, "Which properties are you interested in? Please tell us any positive opinions or concerns you have about those properties." By doing so, it becomes possible to provide personalized property suggestions to the user, resulting in an efficient and user-friendly real estate selection experience overall.

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The server collects information about real estate via the network. In this step, it obtains basic data about the target property (price, location, area) and trend information extracted from social media and news articles. The input is an external data source, and the output is a set of collected raw data. The server uses this to prepare for data preprocessing in the next step.

[0799] Step 2:

[0800] The server preprocesses the collected raw data and formats it into a standard format for evaluating competitiveness. This process includes removing duplicate data, imputing missing values, and normalizing the data. The input is the raw dataset from step 1, and the output is an analyzable, standardized dataset. The server performs data cleaning and transformation tasks here.

[0801] Step 3:

[0802] The server uses generative artificial intelligence to calculate the competitiveness score of real estate. Here, a standardized dataset is input into the AI ​​algorithm, and the score is further adjusted to account for trend information. The input is a standardized dataset, and the output is the competitiveness score for each property. This algorithm accurately reflects market trends.

[0803] Step 4:

[0804] The server processes the user's gaze data and uses a visual device to identify the property they are focusing on. This step leverages the Google Cloud Vision API. The input is the user's gaze data, and the output is a list of the properties being focused on. The server operates through eye-tracking technology.

[0805] Step 5:

[0806] The device uses speech analysis technology to obtain sentiment data from the user's voice. This step uses the Google Cloud Speech-to-Text API and IBM Watson Tone Analyzer. The input is the user's voice data, and the output is the analyzed sentiment data. The device processes the user's utterances in real time.

[0807] Step 6:

[0808] The server generates and provides prompts to the user based on sentiment data and competitiveness scores. In this step, a generative AI model is used to create the prompt text. The inputs are competitiveness scores and sentiment data, and the output is a customized prompt text. The server automates the prompt generation process.

[0809] Step 7:

[0810] The user selects properties based on information and prompts provided through smart glasses. In this step, the user receives visual instructions and voice assistance. Input is the prompt text, and output is the selected property information. The user can experience an interactive selection process.

[0811] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0812] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0813] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0814] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0815] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0816] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0817] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0818] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0819] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0820] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0821] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0822] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0823] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0824] 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.

[0825] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0826] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0827] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0828] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0829] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0830] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0831] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0832] The following is further disclosed regarding the embodiments described above.

[0833] (Claim 1)

[0834] A means of collecting information about real estate via a network,

[0835] A means for preprocessing collected information and converting it into input data for evaluating competitiveness,

[0836] A method for evaluating the competitiveness score of real estate using generative artificial intelligence,

[0837] A means of notifying users based on that competitiveness score,

[0838] A means for generating map information that visualizes the competitiveness of each region for users,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, further comprising means for providing competitive advice based on the user's past search history and desired conditions.

[0842] (Claim 3)

[0843] The system according to claim 1, further comprising means for collecting real estate-related trend information and modifying the competitive score based on that information.

[0844] "Example 1"

[0845] (Claim 1)

[0846] A means of collecting data on the real estate market via a network,

[0847] A means for preprocessing collected data and converting it into input information for artificial intelligence,

[0848] A method for evaluating the competitive advantage of real estate by providing prompt sentences to generative artificial intelligence,

[0849] A means of providing real-time notifications to users based on that evaluation score,

[0850] A means for generating display information that visualizes regional competitive advantages for users,

[0851] An information-providing device that includes [this].

[0852] (Claim 2)

[0853] The information providing device according to claim 1, further comprising means for providing strategic advice on competitive advantage based on the user's past history and desired conditions.

[0854] (Claim 3)

[0855] The information providing device according to claim 1, further comprising means for aggregating real estate market trend information and adjusting a competitive advantage score based on that information.

[0856] "Application Example 1"

[0857] (Claim 1)

[0858] A means of collecting information about real estate via a network,

[0859] A means for preprocessing collected information and converting it into input data for evaluating competitiveness,

[0860] A method for evaluating the competitiveness score of real estate using generative artificial intelligence,

[0861] A means of notifying users based on that competitiveness score,

[0862] A means for generating map information that visualizes the competitiveness of each region for users,

[0863] A means for generating information to visually display property data on an augmented reality display device and for performing a real-time visual evaluation of real estate,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising means for providing competitive advice based on the user's past search history and desired conditions.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for collecting real estate-related trend information and modifying the competitive score based on that information.

[0869] "Example 2 of combining an emotion engine"

[0870] (Claim 1)

[0871] A means of collecting information about real estate via a network,

[0872] A means for preprocessing the collected information and converting it to a standard format,

[0873] A method for evaluating the competitiveness score of real estate using generative artificial intelligence,

[0874] A means of analyzing the emotional state of users and generating data from that analysis,

[0875] A means of providing notifications based on competitive scores and user sentiment data,

[0876] A means for generating map information that visualizes the competitiveness of each region for users,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising means for providing competitive advice based on the user's past search history and emotional state.

[0880] (Claim 3)

[0881] The system according to claim 1, further comprising means for collecting real estate-related trend information and modifying the competitive score based on that information.

[0882] "Application example 2 when combining with an emotional engine"

[0883] (Claim 1)

[0884] A means of collecting information about real estate via a network,

[0885] A means for preprocessing collected information and converting it into input data for evaluating competitiveness,

[0886] A method for evaluating the competitiveness score of real estate using generative artificial intelligence,

[0887] A means of notifying users based on that competitiveness score,

[0888] A means for generating map information that visualizes the competitiveness of each region for users,

[0889] A means of detecting the user's gaze using a visual device and automatically providing information on properties of interest,

[0890] A method for analyzing users' emotions using voice analysis technology and reflecting that in property selection,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising means for providing competitive advice based on the user's past search history and desired conditions.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for collecting real estate-related trend information and modifying competitive scores based on that information, and means for optimizing property proposals based on sentiment analysis results. [Explanation of Symbols]

[0896] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting information about real estate via a network, A means for preprocessing collected information and converting it into input data for evaluating competitiveness, A method for evaluating the competitiveness score of real estate using generative artificial intelligence, A means of notifying users based on that competitiveness score, A means for generating map information that visualizes the competitiveness of each region for users, A system that includes this.

2. The system according to claim 1, further comprising means for providing competitive advice based on the user's past search history and desired conditions.

3. The system according to claim 1, further comprising means for collecting real estate-related trend information and modifying the competitive score based on that information.

Images