System

Abstract

To provide a system for enabling a user to select an optimal real estate property by efficiently and accurately evaluating a peripheral environment or convenience, and predicting a future peripheral environment.SOLUTION: This system is provided with a means for collecting peripheral facility information, a means for cleaning the collected peripheral facility information, converting it into a unified format and storing it in a data base, a means for converting the address of a property inputted by a user into latitude / longitude information and a means for searching the database based on the latitude / longitude information. This system includes a means for acquiring facility information around a property from a database, a means for mapping and displaying the acquired peripheral facility information on a map, a means for evaluating the convenience around the property based on the setting of a user, a means for generating future prediction information around the property by using a generation AI, and a means for displaying the future prediction information on the map.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When selecting a real estate property, users place great importance on the surrounding environment and convenience, but collecting and evaluating information for this purpose requires a great deal of time and effort. Furthermore, it is extremely difficult to predict future changes in the surrounding environment, which makes it difficult to make a real estate purchase decision. The purpose of this invention is to solve these problems and enable users to select the optimal real estate property by efficiently and accurately evaluating the surrounding environment and convenience, and even predicting future changes in the surrounding environment. [Means for solving the problem]

[0005] The present invention is a system including the following means.

[0006] The system includes a means for collecting information on surrounding facilities and a means for cleaning the collected information, converting it into a unified format, and storing it in a database, thereby providing accurate and consistent data.

[0007] Furthermore, the system includes a means for converting the address of the property entered by the user into latitude and longitude information, and a means for retrieving information on facilities around the property from a database based on the latitude and longitude information, thereby enabling a quick evaluation of the surrounding environment of the property.

[0008] The system provides a means to display the acquired information on surrounding facilities on a map, making it easier for users to understand visually. It also includes a means to evaluate the convenience of the area around the property based on the user's settings, enabling evaluations tailored to individual needs.

[0009] Furthermore, the system analyzes past data and uses AI to generate future forecasts of the surrounding area, allowing users to make long-term property selection decisions.

[0010] Finally, we provide a means to display the above future prediction information on a map, providing users with visual information about the future surrounding environment. These means realize a system that efficiently provides the information necessary for real estate selection, allowing users to select the most suitable property.

[0011] "Information about surrounding facilities" refers to information about various facilities related to the user's daily life, such as schools, supermarkets, hospitals, stations, and parks located near the property.

[0012] "Cleaning" is the process of removing duplication and errors from collected data and processing it into a consistent form.

[0013] A "uniform format" is a standardized format that converts various types of data into a consistent format to increase data consistency and usability.

[0014] "Latitude and longitude information" is coordinate data that indicates a specific point on Earth and is used as geographic information.

[0015] A "database" is a collection of information constructed to efficiently store, manage, and search collected information.

[0016] "Mapping" is the process of visually displaying acquired data on a map to make specific information spatially easier to understand.

[0017] A "means for evaluating convenience" refers to a method or device for quantitatively evaluating the convenience of the environment and facilities surrounding a property based on criteria set by the user.

[0018] "Past data" refers to data that records events and situations up to a specific point in time, and is used as basic information for making future predictions.

[0019] "Generative AI" is a system that uses artificial intelligence technology to analyze data, make future predictions, and generate new information.

[0020] "Future forecast information" refers to information that predicts future situations and environments based on past data and current trends. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

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

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] The present invention provides a system for efficiently evaluating the surrounding environment and convenience when selecting a real estate property, and for predicting the future surrounding environment. The following describes an embodiment of the present invention.

[0043] System configuration

[0044] The system is primarily composed of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, running the evaluation algorithm, and training and running the generative AI. The terminal allows users to input information and displays the results. Users input property addresses, set evaluation criteria, and check the results.

[0045] Program processing

[0046] Information collection and database construction

[0047] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[0048] Mapping function on the map

[0049] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0050] Evaluation based on preferences and priorities

[0051] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0052] Generate future prediction maps

[0053] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0054] Specific examples

[0055] For example, suppose User A is considering purchasing a new home. User A enters the address of a property of interest on their device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[0056] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. Based on this, the server calculates the property's convenience score and displays it to User A.

[0057] Furthermore, the server uses the generation AI to predict the future of the property's surroundings, providing information such as when new commercial facilities are planned to be built or when new train stations are scheduled to open. Based on this information, User A can select a property taking into account future convenience.

[0058] The present invention is a system that efficiently executes this series of processes and supports the user in selecting the most suitable real estate property.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[0062] Step 2:

[0063] The server cleans the collected data, removing duplicates and errors.

[0064] Step 3:

[0065] The server converts the cleaned data into a unified format and stores it in a central database.

[0066] Step 4:

[0067] The user uses the terminal to input the address of the property.

[0068] Step 5:

[0069] The server converts the address information into latitude and longitude information using a geographic information API.

[0070] Step 6:

[0071] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[0072] Step 7:

[0073] The server maps the acquired information about nearby facilities on a map using a map API.

[0074] Step 8:

[0075] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[0076] Step 9:

[0077] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[0078] Step 10:

[0079] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[0080] Step 11:

[0081] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[0082] Step 12:

[0083] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[0084] Step 13:

[0085] The server maps the future prediction information onto a map using a map API.

[0086] Step 14:

[0087] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] Conventional real estate property selection systems do not adequately evaluate the surrounding environment and convenience of properties, and do not provide enough information to support users in selecting the appropriate property. In addition, there is no method to predict future surrounding environments, making it difficult to select properties that take future changes in convenience into account. This poses a challenge, as it is difficult for users to obtain sufficient information to select the optimal property.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting it into a unified format and storing it in a database, means for converting property location information entered by a user into geographic coordinate information, means for acquiring facility information around the property from the database based on the geographic coordinate information, means for mapping and displaying the acquired surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generative AI model, and means for displaying the future prediction information on a map. This allows a user to select the optimal property based on multifaceted information including detailed information about the surrounding environment and future predictions.

[0093] "Information about surrounding facilities" is information about all facilities related to daily life, such as schools, supermarkets, hospitals, stations, and parks, that exist around the property.

[0094] "Means of collection" refers to the technology and methods for automatically obtaining the desired data from data sources such as the Internet.

[0095] "Cleaning means" refers to operations or processes used to remove duplication and errors from collected data and improve the quality of the data.

[0096] A "means for converting into a unified format" is a method for converting data of different formats or structures into a consistent format.

[0097] "Means for storing data in a database" refers to a method for registering data in a database system so that the data can be managed efficiently and accessed quickly when needed.

[0098] "Means for converting into geographic coordinate information" refers to technology for converting location information such as addresses into geographic coordinate information such as latitude and longitude.

[0099] The "means for acquiring facility information" refers to a technique or method for searching and extracting related surrounding facility information from a database based on specified geographic coordinate information.

[0100] "Means for mapping and displaying on a map" refers to technology for arranging acquired information on a map in a visually easy-to-understand manner and displaying it to the user.

[0101] A "means for evaluating convenience" is a method for evaluating the convenience of the surrounding environment of a property as a numerical value or score based on criteria set by the user.

[0102] "Historical data analysis methods" are techniques and methods for statistically analyzing and extracting information from all previously collected and stored data sets.

[0103] "Means for generating future prediction information using a generative AI model" refers to a technology that uses a generative AI model to predict future changes in the surrounding environment based on past data and current trends.

[0104] "Means for displaying future prediction information on a map" refers to technology for visually displaying future information predicted by a generative AI model on a map.

[0105] The embodiment of the present invention is a system that evaluates the surrounding environment and convenience, and also predicts the future surrounding environment. This system is mainly composed of three entities: a server, a terminal, and a user. The specific configuration and operation of the system are described below.

[0106] System Configuration

[0107] The system consists of three components: a server, a terminal, and a user. The server is responsible for collecting information on nearby facilities, cleaning the data, managing the database, running the evaluation algorithm, and training and running the generative AI model. The terminal is used by users to input information and display the results. Users input property addresses, set evaluation criteria, and check the results.

[0108] Hardware and software used

[0109] Hardware:

[0110] Server: Use a high-performance server machine

[0111] Devices: personal computers, tablets, smartphones, etc.

[0112] software:

[0113] Data collection: Python's BeautifulSoup, Selenium

[0114] Database: MySQL (registered trademark), PostgreSQL

[0115] Geographical information API: Google (registered trademark) Maps API, Geocoding API

[0116] Data Cleaning: Pandas

[0117] Generative AI models: GPT-3 (registered trademark), BERT, etc.

[0118] Program processing

[0119] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[0120] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0121] Furthermore, the user sets evaluation criteria on their device. For example, they can set "proximity to schools" and "convenience of public transportation" as important items. The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0122] The server then analyzes past data and current trends and uses a generative AI model to predict the future surrounding environment. This includes plans for commercial development and new transportation infrastructure. The prediction results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0123] Specific examples

[0124] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[0125] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. The server calculates the property's convenience score based on this and displays it to User A.

[0126] Furthermore, the server uses the generative AI model to predict the future of the area around the property, providing information such as when new commercial facilities are planned to be built and when new transportation infrastructure is planned to be developed. Based on this information, User A can select a property taking into account future convenience.

[0127] Prompt Sentence Examples

[0128] "I'm looking for real estate around Shin-Kamagaya Station. The key evaluation criteria are distance to the nearest station, proximity to schools, and access to hospitals. I'd also like to know if there are any plans for new commercial facilities or transportation infrastructure in the future."

[0129] In this way, the system of the present invention integrates and provides a variety of information to assist the user in selecting the most suitable real estate property.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Program processing flow

[0132] Step 1: Scraping the data

[0133] The server scrapes information about nearby facilities from the internet, using Python's BeautifulSoup and Selenium libraries.

[0134] Input: List of target website URLs

[0135] Data processing: HTML analysis, extraction of necessary data (school, supermarket, hospital, station, park name, address, contact details, etc.)

[0136] Output: Raw data list (extracted information on nearby facilities)

[0137] Step 2: Cleaning the data

[0138] The server uses the Pandas library to clean the scraped data.

[0139] Input: Raw data list (extracted surrounding facility information)

[0140] Data processing: Removing duplicate data, correcting outliers, and filling in missing data

[0141] Output: Cleaned data

[0142] Step 3: Convert data format and save to database

[0143] The server converts the cleaned data into a unified format (e.g., CSV, JSON) and stores it in a database.

[0144] Input: Cleaned data

[0145] Data processing: Conversion to a unified format

[0146] Output: Data stored in a database

[0147] Step 4: Enter the property address

[0148] The user inputs the address of the property into the input form on the terminal.

[0149] Input: Property address

[0150] Output: Data sent to the server (property address)

[0151] Step 5: Convert address to latitude and longitude

[0152] The server uses the Geocoding API to convert the entered property address into latitude and longitude information.

[0153] Input: Property address

[0154] Data calculation: Latitude and longitude conversion using Geocoding API

[0155] Output: Latitude and longitude information

[0156] Step 6: Obtaining information about nearby facilities

[0157] The server searches the database for information on nearby facilities based on the property's latitude and longitude information.

[0158] Input: Latitude and longitude information

[0159] Data search: Search for nearby facilities using database queries

[0160] Output: List of nearby facilities

[0161] Step 7: Mapping information onto a map

[0162] The server maps the acquired information about nearby facilities onto a map using the Google Maps API.

[0163] Input: List of nearby facilities

[0164] Data calculation: Mapping processing using Google Maps API

[0165] Output: Map data (surrounding facility information mapped)

[0166] Step 8: Display the map

[0167] The server transmits the mapped map data to the terminal.

[0168] Input: Map data

[0169] Output: Data sent to the device (map data)

[0170] The terminal displays the received map data to the user, allowing the user to visually check the surrounding environment of the property.

[0171] Step 9: Set evaluation criteria

[0172] The user sets evaluation criteria on the terminal, such as "distance to the nearest station" or "proximity to schools."

[0173] Input: User-defined criteria

[0174] Output: Data sent to the server (evaluation criteria)

[0175] Step 10: Run the evaluation algorithm and score

[0176] The server runs a rating algorithm based on the rating criteria set by the user.

[0177] Input: Evaluation criteria, information on nearby facilities

[0178] Data calculation: Score calculation using weighting algorithm

[0179] Output: Usability score

[0180] Step 11: Displaying the score to the user

[0181] The server transmits the calculated usability score to the user's terminal.

[0182] Input: Usability score

[0183] Output: Data sent to the device (convenience score)

[0184] The terminal displays the received score to the user, allowing the user to check the convenience of each property.

[0185] Step 12: Historical data and trend analysis

[0186] The server analyzes historical data and current trend data.

[0187] Input: Historical data, trend data

[0188] Data calculation: data analysis, trend analysis

[0189] Output: Trend information, analysis results

[0190] Step 13: Generative AI predicts the future

[0191] The server uses a generative AI model (e.g., GPT-3 or BERT) to predict future surroundings.

[0192] Input: Historical data, trend information

[0193] Data Computation: Predicting the Future with Generative AI Models

[0194] Output: Future prediction information

[0195] Step 14: Map mapping and display of prediction results

[0196] The server uses a map API to map the future prediction data created by the generative AI model onto a map.

[0197] Input: Future prediction information

[0198] Data calculation: Mapping processing using map API

[0199] Output: Predicted map data

[0200] The server transmits the predicted map data to the terminal.

[0201] Input: Predicted map data

[0202] Output: Data sent to the device (predictive map data)

[0203] The terminal displays the received predicted map data to the user, who can then select a property based on this future prediction information, taking into account the future environment.

[0204] (Application example 1)

[0205] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0206] Conventional real estate property selection systems have difficulty effectively evaluating the surrounding environment and convenience of a property, and lack the ability to predict future surrounding conditions. Furthermore, users must actually visit the property to view it, making it difficult to efficiently select a property. The present invention aims to solve these problems by providing a system that allows users to view properties in a virtual space, evaluate the surrounding environment, and check future prediction information.

[0207] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0208] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting the collected information into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving facility information around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generation AI, means for displaying the future prediction information on a map, means for allowing a user to view the property in a virtual space, and means for the user to check the surrounding facility information and future predictions in the virtual space. This allows a user to view the property in a virtual space while centrally checking detailed information about the surrounding environment and predictions of future environmental changes.

[0209] "Nearby facility information" is information about facilities such as schools, supermarkets, hospitals, stations, and parks that exist around the property.

[0210] "Cleaning" is the process of removing duplication and errors from collected data and converting the data into a unified format.

[0211] "Latitude and longitude information" refers to coordinate information that indicates a point on the Earth, and is used to indicate the specific location of a property.

[0212] A "database" is an electronic storage system for efficiently storing, retrieving, and managing data.

[0213] "Mapping" is the visualization and display of specific information on a map.

[0214] "Evaluation criteria" are a set of factors that users use as criteria when evaluating the convenience of a property, and include, for example, "proximity to schools" and "convenience of public transportation."

[0215] "Generative AI" is an artificial intelligence model that learns from large amounts of data to predict future trends and patterns.

[0216] "Future prediction information" is information generated by the generating AI, which analyzes past data and predicts future changes in the surrounding environment and plans for new facility construction.

[0217] "Virtual space" refers to a virtual three-dimensional space generated using computer technology, which is used by users to view properties.

[0218] A "viewing" refers to a user being able to check the interior and surroundings of a property through a virtual space without actually visiting the property.

[0219] "Convenience" is an indicator that evaluates the degree to which the surrounding environment of a property provides convenience for daily life.

[0220] The present invention is a system that allows a user to view a real estate property in a virtual space and evaluate the surrounding environment and future changes to the environment.

[0221] System configuration

[0222] The system is configured using the following hardware and software.

[0223] 1. Hardware:

[0224] server

[0225] Devices (smartphones, smart glasses, head-mounted displays)

[0226] 2. Software:

[0227] API (geographical information API, map API)

[0228] Machine learning library (scikit-learn)

[0229] Database Management Systems

[0230] Visualization tool (folium)

[0231] Program processing description

[0232] The server first scrapes information about nearby facilities from the internet, cleans the data, converts it into a unified format, and stores it in a database, ensuring that the data is free of duplicates and errors.

[0233] Next, when the user enters the property address using the terminal, the server converts the address into latitude and longitude information using the geographic information API. An example of a specific prompt is as follows:

[0234] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[0235] The server retrieves information about nearby facilities from the database based on this latitude and longitude information and maps it on a map using a map API, allowing users to visually check the environment around the property.

[0236] Users can also set evaluation criteria on their devices, such as "distance to the nearest station," "proximity to schools," and "presence of parks" as important factors. The server runs an evaluation algorithm based on these criteria and scores the convenience of the property. The calculated score is sent to the user's device, allowing them to check the convenience of the property.

[0237] Furthermore, the server uses generative AI to predict the future surrounding environment. It analyzes past data and current trends to predict, for example, new commercial facility development plans and transportation infrastructure improvement plans. This future prediction information is also mapped on a map, which users can refer to.

[0238] Users can use a smartphone, smart glasses, or a head-mounted display to virtually view a property, allowing them to see the interior and surroundings of the property in real time while simultaneously viewing future predictions.

[0239] As a concrete example, consider user B considering purchasing a new property and using the following prompt:

[0240] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[0241] This allows User B to view the property in virtual space while checking the surrounding environment and future forecast information in one place. This system allows users to make efficient and informative real estate selections.

[0242] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0243] Step 1:

[0244] A user uses a terminal to enter a property address using a prompt, for example, "Please enter the address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"".

[0245] Step 2:

[0246] The server receives the address entered by the user and converts it into latitude and longitude information using a geographic information API (such as Google Maps API). This allows specific location information to be obtained. The input is an address, and the output is latitude and longitude information.

[0247] Step 3:

[0248] The server searches the database for information on nearby facilities based on the acquired latitude and longitude information. This information includes schools, supermarkets, hospitals, stations, parks, etc. The input is latitude and longitude information, and the output is information on nearby facilities.

[0249] Step 4:

[0250] The server cleans the acquired nearby facility information, removes duplicates and errors, and converts it into a unified format. This information is then stored in a database. The input is nearby facility information, and the output is the cleaned data.

[0251] Step 5:

[0252] The server maps the information about the surrounding facilities after cleaning on a map using a map API (e.g., Google Maps API). This allows users to visually check the surrounding facilities. The input is the cleaned data, and the output is the information mapped on the map.

[0253] Step 6:

[0254] The user sets the evaluation criteria on the terminal. For example, they can select "distance to the nearest station," "proximity to schools," "presence of parks," etc. This allows them to individually evaluate convenience. The input is the evaluation criteria, and the output is the set evaluation criteria information.

[0255] Step 7:

[0256] The server runs an evaluation algorithm based on the set evaluation criteria and scores the convenience of the area around the property. This quantifies the convenience of the property. The input is evaluation criteria information and information on surrounding facilities, and the output is a convenience score.

[0257] Step 8:

[0258] The server analyzes past data and uses a generative AI model to generate future predictions for the surrounding area, including plans for new commercial developments and transportation infrastructure improvements. The input is past data, and the output is future predictions.

[0259] Step 9:

[0260] The server then uses the map API to map the generated future prediction information and sends it to the device, allowing the user to check the future surroundings. The input is the future prediction information, and the output is the future prediction information mapped on the map.

[0261] Step 10:

[0262] Users can view a property in a virtual space and simultaneously check the surrounding environment and future forecast information using a smartphone, smart glasses, or a head-mounted display, enabling a more comprehensive property evaluation. The input is the start of the virtual viewing, and the output is visual information in the virtual space.

[0263] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0264] The present invention is a system that efficiently evaluates the surrounding environment and convenience when selecting a real estate property, and furthermore predicts the future surrounding environment, as well as a system that recognizes the user's emotions and automatically adjusts the evaluation criteria based on the emotions.

[0265] System configuration

[0266] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[0267] Program processing

[0268] Information collection and database construction

[0269] The server scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned to remove duplicates and errors, then converted into a unified format and stored in a central database.

[0270] Mapping function on the map

[0271] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0272] Evaluation based on preferences and priorities

[0273] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0274] Generate future prediction maps

[0275] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0276] Emotion recognition and auto-tuning

[0277] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, tone of voice, etc.). The server uses an emotion engine to analyze this data and recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[0278] Automatic adjustment of evaluation criteria based on emotions

[0279] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data. For example, if the user expresses strong satisfaction with the proximity of schools, the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with the convenience of public transportation, the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[0280] Specific examples

[0281] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device and checks information about the surrounding area. User A also sets the proximity to schools, convenience of public transportation, and the presence of parks as important criteria.

[0282] The server evaluates the user based on this and provides a convenience score. At the same time, the device collects user A's facial expressions and tone of voice and sends them to the server as emotion data. The server then analyzes user A's emotions using its emotion engine and recognizes that user A is highly satisfied with the proximity of the school.

[0283] Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weight of proximity to schools. This allows User A to select properties based on the most important points.

[0284] By efficiently executing this series of processes, the present invention realizes a system that supports users in selecting the most suitable real estate property. Furthermore, by utilizing an emotion engine, user satisfaction can be further increased.

[0285] The processing flow will be explained below.

[0286] Step 1:

[0287] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[0288] Step 2:

[0289] The server cleans the collected data, removing duplicates and errors.

[0290] Step 3:

[0291] The server converts the cleaned data into a unified format and stores it in a central database.

[0292] Step 4:

[0293] The user uses the terminal to input the address of the property.

[0294] Step 5:

[0295] The server converts the address information into latitude and longitude information using a geographic information API.

[0296] Step 6:

[0297] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[0298] Step 7:

[0299] The server maps the acquired information about nearby facilities on a map using a map API.

[0300] Step 8:

[0301] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[0302] Step 9:

[0303] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[0304] Step 10:

[0305] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[0306] Step 11:

[0307] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[0308] Step 12:

[0309] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.).

[0310] Step 13:

[0311] The server uses an emotion engine to analyze the collected emotion data and recognize the user's emotional state.

[0312] Step 14:

[0313] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data.

[0314] Step 15:

[0315] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[0316] Step 16:

[0317] The server maps the future prediction information onto a map using a map API.

[0318] Step 17:

[0319] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[0320] Specific examples

[0321] For example, suppose user A is considering purchasing a new home. User A enters the address of the property he or she is interested in on the device and checks information about the surrounding area.

[0322] Next, User A sets evaluation criteria. For example, he or she may set "proximity to schools," "convenience of public transportation," and "presence of parks" as important items. The server evaluates the properties based on these criteria and provides a convenience score.

[0323] At the same time, the device collects user A's facial expressions and voice tone and sends them as emotion data to the server. The server then uses an emotion engine to analyze this data and determine whether user A is satisfied with certain criteria. For example, if user A is satisfied with the proximity of schools, the server will assign a higher weight to this criterion.

[0324] The server automatically adjusts the weighting of the evaluation criteria to emphasize the points that are most important to User A. This allows User A to select the optimal property based on their own feelings and preferences. The server also uses generative AI to predict the future and provides planning information for new commercial facilities and transportation infrastructure. This allows User A to select a property taking future convenience into consideration.

[0325] Example 2

[0326] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0327] Existing real estate property selection systems are insufficient in providing sufficient information and responding to individual user needs when evaluating the convenience of the surrounding area or predicting future environmental changes. Furthermore, they lack the functionality to reflect changes in user emotions and preferences in real time, which limits their ability to support optimal property selection.

[0328] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0329] In this invention, the server includes means for collecting information on surrounding facilities, means for cleaning the collected information on surrounding facilities, converting the collected information on surrounding facilities into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving information on facilities around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved information on surrounding facilities on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information for the area around the property using a generation AI, means for displaying the future prediction information on a map, means for collecting user emotion data, means for analyzing the collected emotion data and recognizing the user's emotional state, and means for automatically adjusting evaluation criteria based on the recognized emotional state. This allows users to check convenience and future prediction information in real time when selecting a property, and further enables them to select the optimal property that reflects feedback based on their own emotions.

[0330] "Nearby facility information" is data about public and commercial facilities around the property, such as schools, supermarkets, hospitals, stations, and parks.

[0331] "Cleaning" is the process of removing redundancies and errors from collected data and formatting it accurately and consistently.

[0332] "Unified format" refers to converting data collected from different sources into the same format to ensure consistency.

[0333] A "database" is a system in which collected data can be efficiently stored, managed, and retrieved.

[0334] "Latitude and longitude information" is coordinate data that indicates a geographical location and is used to identify a specific point.

[0335] "Generative AI" refers to artificial intelligence technology that makes future predictions based on past data and trends.

[0336] "Emotion data" is information about the user's emotional state obtained from facial expressions, tone of voice, and the like.

[0337] "Evaluation criteria" refers to the points or items that are important when evaluating property options, such as proximity to schools or public transportation.

[0338] This invention is a system that can efficiently evaluate the surrounding environment and convenience when selecting a real estate property, and can also predict the future surrounding environment. The invention also combines a function that recognizes the user's emotions and automatically adjusts the evaluation criteria based on those emotions. Specific embodiments for implementing the invention are described below.

[0339] System configuration

[0340] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[0341] Information collection and database construction

[0342] The server uses Python's BeautifulSoup and Scrapy scraping libraries to collect information on nearby facilities from the internet. This includes schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas and Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[0343] Mapping function on the map

[0344] The user uses a smartphone or PC to input the address of a property of interest into the device. The server converts this address into latitude and longitude information using a Geocoding API (for example, Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, maps the acquired information on a map using a map API, and sends it to the device. This allows the user to visually check the surrounding environment of the property.

[0345] Evaluation based on preferences and priorities

[0346] Users use the device interface to set evaluation criteria such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0347] Generate future prediction maps

[0348] The server analyzes past data and current trends based on a database and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. This includes plans for commercial facility development and new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this information, users can select properties taking into account the future environment.

[0349] Emotion recognition and auto-tuning

[0350] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.). The server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[0351] Automatic adjustment of evaluation criteria based on emotions

[0352] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[0353] Specific examples

[0354] For example, suppose User A is considering purchasing a new home. User A enters the address of a property they are interested in on their device and checks information about the surrounding area. User A also sets "proximity to schools," "convenience of public transportation," and "presence of parks" as important criteria. The server evaluates the properties based on this and provides a convenience score. At the same time, the device collects User A's facial expressions and voice tone and sends them to the server as emotion data. The server uses an emotion engine to analyze User A's emotions and recognizes that User A is highly satisfied with the proximity to schools. Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weighting of proximity to schools. This allows User A to select a property based on the most important points.

[0355] Prompt Sentence Examples

[0356] "Please rate the surrounding environment and convenience of a property based on the following conditions: Address: 2-8-1 Nishi-Shinjuku, Shinjuku-ku, Tokyo. Important points to consider are proximity to schools, convenience of public transportation, and the presence of parks. Furthermore, please automatically adjust the evaluation criteria based on sentiment data provided by the user."

[0357] The above is a specific embodiment for carrying out the present invention. This system utilizes advanced technology to assist users in selecting the most suitable real estate property.

[0358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0359] Step 1: Collecting information and building a database

[0360] The server scrapes information about nearby facilities from the internet using Python scraping libraries such as BeautifulSoup and Scrapy. The collected data includes information about schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas or Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[0361] Input: Information about nearby facilities on the Internet

[0362] Data processing: scraping, data cleaning, format conversion

[0363] Output: Information on nearby facilities stored in the database

[0364] Specific operation: The server periodically runs scripts to collect information on the Internet and performs various data processing to ensure the quality of the collected data.

[0365] Step 2: Mapping function on the map

[0366] The user uses a device to input the address of a property they are interested in. The server converts this address into latitude and longitude information using a Geocoding API (e.g., Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, and maps the retrieved information on a map using a map API. Finally, this map information is sent to the user's device.

[0367] Input: The property address entered by the user

[0368] Data calculation: address latitude / longitude conversion, database search, map mapping

[0369] Output: Information about nearby facilities mapped on a map

[0370] Specific operation: The user enters an address into the input field on the device, and the server uses that information to identify the location using a map API and visualizes the surrounding information.

[0371] Step 3: Evaluate based on preferences and priorities

[0372] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the area around the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0373] Input: User-defined evaluation criteria

[0374] Data calculation: Scoring by evaluation algorithm

[0375] Output: User experience score sent to the user device

[0376] Specific operation: The user selects the points of importance on the device's rating setting screen, and the server evaluates the distance and accessibility of each facility based on those criteria.

[0377] Step 4: Generate a future prediction map

[0378] The server retrieves past data and current trends from a database such as MongoDB and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. Predictions include commercial facility development plans and new transportation infrastructure construction schedules. These predictions are visualized using a map API and sent to the user's device.

[0379] Input: Historical data and trend information

[0380] Data Computation: Predicting the Future with Generative AI

[0381] Output: Future prediction information mapped on a map

[0382] How it works: The server retrieves the necessary information from the database, trains a generative AI model to make future predictions, and visually displays the results on a map.

[0383] Step 5: Emotion Recognition and Auto-Tuning

[0384] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.), and the server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state.

[0385] Input: Emotion data collected by camera and microphone

[0386] Data Computation: Emotion Analysis with Emotion Engine

[0387] Output: Recognized emotional state of the user

[0388] Specific operation: The device captures the user's facial expressions and voice, sends them to the server in real time, and analyzes the information to evaluate the user's emotions.

[0389] Step 6: Automatic adjustment of evaluation criteria based on emotions

[0390] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the weighting of that criterion will be increased. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the weighting of that criterion will be decreased. This adjustment is made automatically, and the results are reflected on the user's device.

[0391] Input: Perceived emotional state of the user

[0392] Data calculation: Automatic adjustment of evaluation criteria

[0393] Output: Results reflecting the adjusted evaluation criteria

[0394] Specific operation: The server dynamically resets the evaluation criteria based on the results of sentiment analysis and makes suggestions to improve user satisfaction.

[0395] (Application example 2)

[0396] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0397] Conventional surrounding environment evaluation systems evaluate properties based only on current facility information, making it difficult to predict future changes in the environment. Furthermore, there was no system that adjusted evaluation criteria based on the user's emotional state, making it difficult to select properties and products that reflected the user's true satisfaction. Furthermore, there was a lack of real-time product suggestions and navigation to improve the customer experience in actual stores.

[0398] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting surrounding environment information, means for cleaning the collected surrounding environment information, converting it into a unified format, and storing it in a database, means for converting the address of a location entered by the user into location information, means for retrieving surrounding environment information from the database based on the location information, means for visually mapping and displaying the retrieved surrounding environment information, means for evaluating the convenience of the surrounding environment based on the user's settings, means for analyzing past data and generating future prediction information about the surrounding environment using a generating AI, means for displaying the future prediction information on a map, means for recognizing and analyzing the customer's emotional state, means for automatically adjusting evaluation criteria based on the customer's emotional state, means for using a generating AI to suggest the customer's next action and products, means for identifying the customer's location information in a store and providing navigation to the most suitable product, and means for adjusting the weighting of product categories based on the customer's emotional state. This enables future environment predictions based on past data and emotional information, thereby realizing property selection and product suggestions that will satisfy the user. The in-store customer experience will also be improved, offering real-time product suggestions and navigation.

[0399] "Nearby Environment Information" refers to information about the surroundings of a specific place or property that a user is interested in. This includes information about facilities such as shops, schools, public transportation, and medical facilities, as well as public safety and local characteristics.

[0400] "Database" means a collection of collected information that is organized, stored, and managed so that it can be efficiently searched and used when needed.

[0401] "Location Information" means geographical data such as latitude and longitude that indicates a specific location. This data is obtained using technologies such as GPS and beacons.

[0402] "Emotional state" refers to the psychological state of a user analyzed from facial expressions, tone of voice, etc. This includes states such as satisfaction, dissatisfaction, excitement, and relaxation.

[0403] "Navigation" means guidance that provides a route or direction for a user to reach a destination, including map displays and audio guidance.

[0404] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to predict and classify future outcomes based on large amounts of data, including neural networks and deep learning.

[0405] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to estimate their emotional state. It uses machine learning and computer vision algorithms.

[0406] "Future forecast information" refers to information about future surrounding environments and market trends that is generated by analyzing past data and current trends.

[0407] "Product Recommendations" means the presentation of recommended products and services based on a user's preferences and behavioral data, including personalized recommendations.

[0408] "Weighting" refers to the assignment of greater or lesser importance to a particular factor in determining the evaluation criteria, which is reflected in a numerical score or ranking.

[0409] The present invention is a system that improves customer experience in shopping malls and large brick-and-mortar stores, and is composed of three entities: a server, a terminal, and a user.

[0410] System configuration

[0411] Gathering information on the surrounding environment

[0412] The server scrapes surrounding environment information from the internet, cleans it, removes duplicates and errors, converts it into a unified format, and stores it in a central database.

[0413] Obtaining location information

[0414] When a user enters the address of a place of interest into their device, the server converts the address into location information (latitude and longitude) using a geographic information API.

[0415] Mapping of surrounding environment information

[0416] The server retrieves information about the surrounding environment from a database based on the acquired location information. This information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment through the device.

[0417] Usability evaluation

[0418] The user sets evaluation criteria on their device, such as "specific product category" or "store congestion level." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding environment. The calculated score is sent to the user's device, allowing them to check the convenience.

[0419] Generating future prediction information

[0420] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device, allowing the user to select the optimal location and product based on the future environment.

[0421] Emotion recognition and evaluation criteria adjustment

[0422] The device collects emotional data from the user using a camera and microphone. The server analyzes this data with an emotion engine to recognize the user's emotional state. For example, it analyzes facial expressions and tone of voice while the user is reviewing product recommendations to determine whether the user is satisfied.

[0423] Product suggestions and navigation

[0424] The server automatically adjusts evaluation criteria based on the customer's emotional state and makes optimal product recommendations. It also identifies the customer's current location in the store in real time using GPS information and Bluetooth beacons, providing navigation information so that customers can easily access the products they are looking for.

[0425] Specific examples

[0426] For example, when a customer visits a brick-and-mortar shopping mall, they put on the smart glasses and input the product categories they are interested in (e.g., clothing, home appliances). The server retrieves information about related products based on those interests and displays it on the smart glasses along with navigation information. If, after analyzing the customer's facial expressions and tone of voice, the server finds that the customer is satisfied with the reviews of a particular product, it automatically adjusts the weighting of that category and determines the next product to be prioritized.

[0427] Prompt Sentence Examples

[0428] "To predict future purchasing trends and provide the best customer experience, we use sales data and customer sentiment data from the past three years to determine the next product and promotion strategy we should offer."

[0429] As described above, the present invention provides a concrete means for realizing a surrounding environment evaluation system, which allows users to select properties and products that will give them greater satisfaction, and also significantly improves the customer experience in stores.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The server scrapes surrounding environment information from the internet. For example, it collects information on facilities such as shops, schools, hospitals, and public transportation, cleans it by removing duplicates and errors, and converts it into a unified format. This data is stored in a central database. The input here is raw data from the internet, and the output is the cleaned database.

[0433] Step 2:

[0434] The user inputs the address of a place of interest into the device. The device retrieves this address and sends it to the server. The server uses a geographic information API to convert the address into location information (latitude and longitude). The input is address information, and the output is the location information corresponding to that address.

[0435] Step 3:

[0436] The server searches and retrieves surrounding environment information from a central database based on the acquired location information. The acquired surrounding environment information is mapped on a map using a map API and sent to the device. The input is location information, and the output is a map with the surrounding environment information mapped on it.

[0437] Step 4:

[0438] The user visually checks the surrounding environment information on the device and sets evaluation criteria. For example, they set "specific product category" or "store congestion level." These evaluation criteria are sent from the device to the server. The input is the user-set evaluation criteria, and the output is the evaluation criteria data sent to the server.

[0439] Step 5:

[0440] The server runs an evaluation algorithm based on the evaluation criteria set by the user, scores the usability of the surrounding environment, and sends the score to the user's device. The input is the evaluation criteria and surrounding environment information, and the output is the calculated usability score.

[0441] Step 6:

[0442] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device. The input is past data and an evaluation algorithm, and the output is future prediction information.

[0443] Step 7:

[0444] The device uses a camera and microphone to collect the user's emotional data, including facial expressions and vocal tones. The collected data is sent to a server. The input is the user's emotional data, and the output is the emotional data sent to the server.

[0445] Step 8:

[0446] The server uses an emotion engine to analyze the user's emotional state and automatically adjusts the evaluation criteria based on the emotional data. For example, if a user expresses high satisfaction with a particular product, it increases the weighting of that product category. The input is emotional data, and the output is the adjusted evaluation criteria.

[0447] Step 9:

[0448] The server uses generative AI to make optimal product suggestions to customers based on emotional data and real-time location information. Product suggestions and navigation information are sent to the device in real time, allowing users to easily access the desired products. The input is emotional state and real-time location information, and the output is product suggestions and navigation information.

[0449] Step 10:

[0450] Users use smart glasses or terminals to check the suggested products and move around the store. The server collects user behavior data in real time and maintains a loop throughout the system. The input is user behavior data, and the output is continuous data collection and improvement information.

[0451] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0452] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0454] [Second embodiment]

[0455] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0456] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0457] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0458] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0459] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0460] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0461] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0462] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0463] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0464] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0465] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0466] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0467] The present invention provides a system for efficiently evaluating the surrounding environment and convenience when selecting a real estate property, and for predicting the future surrounding environment. The following describes an embodiment of the present invention.

[0468] System configuration

[0469] The system is primarily composed of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, running the evaluation algorithm, and training and running the generative AI. The terminal allows users to input information and displays the results. Users input property addresses, set evaluation criteria, and check the results.

[0470] Program processing

[0471] Information collection and database construction

[0472] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[0473] Mapping function on the map

[0474] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0475] Evaluation based on preferences and priorities

[0476] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0477] Generate future prediction maps

[0478] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0479] Specific examples

[0480] For example, suppose User A is considering purchasing a new home. User A enters the address of a property of interest on their device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[0481] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. Based on this, the server calculates the property's convenience score and displays it to User A.

[0482] Furthermore, the server uses the generation AI to predict the future of the property's surroundings, providing information such as when new commercial facilities are planned to be built or when new train stations are scheduled to open. Based on this information, User A can select a property taking into account future convenience.

[0483] The present invention is a system that efficiently executes this series of processes and supports the user in selecting the most suitable real estate property.

[0484] The processing flow will be explained below.

[0485] Step 1:

[0486] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[0487] Step 2:

[0488] The server cleans the collected data, removing duplicates and errors.

[0489] Step 3:

[0490] The server converts the cleaned data into a unified format and stores it in a central database.

[0491] Step 4:

[0492] The user uses the terminal to input the address of the property.

[0493] Step 5:

[0494] The server converts the address information into latitude and longitude information using a geographic information API.

[0495] Step 6:

[0496] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[0497] Step 7:

[0498] The server maps the acquired information about nearby facilities on a map using a map API.

[0499] Step 8:

[0500] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[0501] Step 9:

[0502] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[0503] Step 10:

[0504] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[0505] Step 11:

[0506] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[0507] Step 12:

[0508] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[0509] Step 13:

[0510] The server maps the future prediction information onto a map using a map API.

[0511] Step 14:

[0512] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[0513] Example 1

[0514] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0515] Conventional real estate property selection systems do not adequately evaluate the surrounding environment and convenience of properties, and do not provide enough information to support users in selecting the appropriate property. In addition, there is no method to predict future surrounding environments, making it difficult to select properties that take future changes in convenience into account. This poses a challenge, as it is difficult for users to obtain sufficient information to select the optimal property.

[0516] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0517] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting it into a unified format and storing it in a database, means for converting property location information entered by a user into geographic coordinate information, means for acquiring facility information around the property from the database based on the geographic coordinate information, means for mapping and displaying the acquired surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generative AI model, and means for displaying the future prediction information on a map. This allows a user to select the optimal property based on multifaceted information including detailed information about the surrounding environment and future predictions.

[0518] "Information about surrounding facilities" is information about all facilities related to daily life, such as schools, supermarkets, hospitals, stations, and parks, that exist around the property.

[0519] "Means of collection" refers to the technology and methods for automatically obtaining the desired data from data sources such as the Internet.

[0520] "Cleaning means" refers to operations or processes used to remove duplication and errors from collected data and improve the quality of the data.

[0521] A "means for converting into a unified format" is a method for converting data of different formats or structures into a consistent format.

[0522] "Means for storing data in a database" refers to a method for registering data in a database system so that the data can be managed efficiently and accessed quickly when needed.

[0523] "Means for converting into geographic coordinate information" refers to technology for converting location information such as addresses into geographic coordinate information such as latitude and longitude.

[0524] The "means for acquiring facility information" refers to a technique or method for searching and extracting related surrounding facility information from a database based on specified geographic coordinate information.

[0525] "Means for mapping and displaying on a map" refers to technology for arranging acquired information on a map in a visually easy-to-understand manner and displaying it to the user.

[0526] A "means for evaluating convenience" is a method for evaluating the convenience of the surrounding environment of a property as a numerical value or score based on criteria set by the user.

[0527] "Historical data analysis methods" are techniques and methods for statistically analyzing and extracting information from all previously collected and stored data sets.

[0528] "Means for generating future prediction information using a generative AI model" refers to a technology that uses a generative AI model to predict future changes in the surrounding environment based on past data and current trends.

[0529] "Means for displaying future prediction information on a map" refers to technology for visually displaying future information predicted by a generative AI model on a map.

[0530] The embodiment of the present invention is a system that evaluates the surrounding environment and convenience, and also predicts the future surrounding environment. This system is mainly composed of three entities: a server, a terminal, and a user. The specific configuration and operation of the system are described below.

[0531] System Configuration

[0532] The system consists of three components: a server, a terminal, and a user. The server is responsible for collecting information on nearby facilities, cleaning the data, managing the database, running the evaluation algorithm, and training and running the generative AI model. The terminal is used by users to input information and display the results. Users input property addresses, set evaluation criteria, and check the results.

[0533] Hardware and software used

[0534] Hardware:

[0535] Server: Use a high-performance server machine

[0536] Devices: personal computers, tablets, smartphones, etc.

[0537] software:

[0538] Data collection: Python's BeautifulSoup, Selenium

[0539] Database: MySQL, PostgreSQL

[0540] Geographical information API: Google Maps API, Geocoding API

[0541] Data Cleaning: Pandas

[0542] Generative AI models: GPT-3, BERT, etc.

[0543] Program processing

[0544] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[0545] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0546] Furthermore, the user sets evaluation criteria on their device. For example, they can set "proximity to schools" and "convenience of public transportation" as important items. The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0547] The server then analyzes past data and current trends and uses a generative AI model to predict the future surrounding environment. This includes plans for commercial development and new transportation infrastructure. The prediction results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0548] Specific examples

[0549] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[0550] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. The server calculates the property's convenience score based on this and displays it to User A.

[0551] Furthermore, the server uses the generative AI model to predict the future of the area around the property, providing information such as when new commercial facilities are planned to be built and when new transportation infrastructure is planned to be developed. Based on this information, User A can select a property taking into account future convenience.

[0552] Prompt Sentence Examples

[0553] "I'm looking for real estate around Shin-Kamagaya Station. The key evaluation criteria are distance to the nearest station, proximity to schools, and access to hospitals. I'd also like to know if there are any plans for new commercial facilities or transportation infrastructure in the future."

[0554] In this way, the system of the present invention integrates and provides a variety of information to assist the user in selecting the most suitable real estate property.

[0555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0556] Program processing flow

[0557] Step 1: Scraping the data

[0558] The server scrapes information about nearby facilities from the internet, using Python's BeautifulSoup and Selenium libraries.

[0559] Input: List of target website URLs

[0560] Data processing: HTML analysis, extraction of necessary data (school, supermarket, hospital, station, park name, address, contact details, etc.)

[0561] Output: Raw data list (extracted information on nearby facilities)

[0562] Step 2: Cleaning the data

[0563] The server uses the Pandas library to clean the scraped data.

[0564] Input: Raw data list (extracted surrounding facility information)

[0565] Data processing: Removing duplicate data, correcting outliers, and filling in missing data

[0566] Output: Cleaned data

[0567] Step 3: Convert data format and save to database

[0568] The server converts the cleaned data into a unified format (e.g., CSV, JSON) and stores it in a database.

[0569] Input: Cleaned data

[0570] Data processing: Conversion to a unified format

[0571] Output: Data stored in a database

[0572] Step 4: Enter the property address

[0573] The user inputs the address of the property into the input form on the terminal.

[0574] Input: Property address

[0575] Output: Data sent to the server (property address)

[0576] Step 5: Convert address to latitude and longitude

[0577] The server uses the Geocoding API to convert the entered property address into latitude and longitude information.

[0578] Input: Property address

[0579] Data calculation: Latitude and longitude conversion using Geocoding API

[0580] Output: Latitude and longitude information

[0581] Step 6: Obtaining information about nearby facilities

[0582] The server searches the database for information on nearby facilities based on the property's latitude and longitude information.

[0583] Input: Latitude and longitude information

[0584] Data search: Search for nearby facilities using database queries

[0585] Output: List of nearby facilities

[0586] Step 7: Mapping information onto a map

[0587] The server maps the acquired information about nearby facilities onto a map using the Google Maps API.

[0588] Input: List of nearby facilities

[0589] Data calculation: Mapping processing using Google Maps API

[0590] Output: Map data (surrounding facility information mapped)

[0591] Step 8: Display the map

[0592] The server transmits the mapped map data to the terminal.

[0593] Input: Map data

[0594] Output: Data sent to the device (map data)

[0595] The terminal displays the received map data to the user, allowing the user to visually check the surrounding environment of the property.

[0596] Step 9: Set evaluation criteria

[0597] The user sets evaluation criteria on the terminal, such as "distance to the nearest station" or "proximity to schools."

[0598] Input: User-defined criteria

[0599] Output: Data sent to the server (evaluation criteria)

[0600] Step 10: Run the evaluation algorithm and score

[0601] The server runs a rating algorithm based on the rating criteria set by the user.

[0602] Input: Evaluation criteria, information on nearby facilities

[0603] Data calculation: Score calculation using weighting algorithm

[0604] Output: Usability score

[0605] Step 11: Displaying the score to the user

[0606] The server transmits the calculated usability score to the user's terminal.

[0607] Input: Usability score

[0608] Output: Data sent to the device (convenience score)

[0609] The terminal displays the received score to the user, allowing the user to check the convenience of each property.

[0610] Step 12: Historical data and trend analysis

[0611] The server analyzes historical data and current trend data.

[0612] Input: Historical data, trend data

[0613] Data calculation: data analysis, trend analysis

[0614] Output: Trend information, analysis results

[0615] Step 13: Generative AI predicts the future

[0616] The server uses a generative AI model (e.g., GPT-3 or BERT) to predict future surroundings.

[0617] Input: Historical data, trend information

[0618] Data Computation: Predicting the Future with Generative AI Models

[0619] Output: Future prediction information

[0620] Step 14: Map mapping and display of prediction results

[0621] The server uses a map API to map the future prediction data created by the generative AI model onto a map.

[0622] Input: Future prediction information

[0623] Data calculation: Mapping processing using map API

[0624] Output: Predicted map data

[0625] The server transmits the predicted map data to the terminal.

[0626] Input: Predicted map data

[0627] Output: Data sent to the device (predictive map data)

[0628] The terminal displays the received predicted map data to the user, who can then select a property based on this future prediction information, taking into account the future environment.

[0629] (Application example 1)

[0630] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0631] Conventional real estate property selection systems have difficulty effectively evaluating the surrounding environment and convenience of a property, and lack the ability to predict future surrounding conditions. Furthermore, users must actually visit the property to view it, making it difficult to efficiently select a property. The present invention aims to solve these problems by providing a system that allows users to view properties in a virtual space, evaluate the surrounding environment, and check future prediction information.

[0632] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0633] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting the collected information into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving facility information around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generation AI, means for displaying the future prediction information on a map, means for allowing a user to view the property in a virtual space, and means for the user to check the surrounding facility information and future predictions in the virtual space. This allows a user to view the property in a virtual space while centrally checking detailed information about the surrounding environment and predictions of future environmental changes.

[0634] "Nearby facility information" is information about facilities such as schools, supermarkets, hospitals, stations, and parks that exist around the property.

[0635] "Cleaning" is the process of removing duplication and errors from collected data and converting the data into a unified format.

[0636] "Latitude and longitude information" refers to coordinate information that indicates a point on the Earth, and is used to indicate the specific location of a property.

[0637] A "database" is an electronic storage system for efficiently storing, retrieving, and managing data.

[0638] "Mapping" is the visualization and display of specific information on a map.

[0639] "Evaluation criteria" are a set of factors that users use as criteria when evaluating the convenience of a property, and include, for example, "proximity to schools" and "convenience of public transportation."

[0640] "Generative AI" is an artificial intelligence model that learns from large amounts of data to predict future trends and patterns.

[0641] "Future prediction information" is information generated by the generating AI, which analyzes past data and predicts future changes in the surrounding environment and plans for new facility construction.

[0642] "Virtual space" refers to a virtual three-dimensional space generated using computer technology, which is used by users to view properties.

[0643] A "viewing" refers to a user being able to check the interior and surroundings of a property through a virtual space without actually visiting the property.

[0644] "Convenience" is an indicator that evaluates the degree to which the surrounding environment of a property provides convenience for daily life.

[0645] The present invention is a system that allows a user to view a real estate property in a virtual space and evaluate the surrounding environment and future changes to the environment.

[0646] System configuration

[0647] The system is configured using the following hardware and software.

[0648] 1. Hardware:

[0649] server

[0650] Devices (smartphones, smart glasses, head-mounted displays)

[0651] 2. Software:

[0652] API (geographical information API, map API)

[0653] Machine learning library (scikit-learn)

[0654] Database Management Systems

[0655] Visualization tool (folium)

[0656] Program processing description

[0657] The server first scrapes information about nearby facilities from the internet, cleans the data, converts it into a unified format, and stores it in a database, ensuring that the data is free of duplicates and errors.

[0658] Next, when the user enters the property address using the terminal, the server converts the address into latitude and longitude information using the geographic information API. An example of a specific prompt is as follows:

[0659] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[0660] The server retrieves information about nearby facilities from the database based on this latitude and longitude information and maps it on a map using a map API, allowing users to visually check the environment around the property.

[0661] Users can also set evaluation criteria on their devices, such as "distance to the nearest station," "proximity to schools," and "presence of parks" as important factors. The server runs an evaluation algorithm based on these criteria and scores the convenience of the property. The calculated score is sent to the user's device, allowing them to check the convenience of the property.

[0662] Furthermore, the server uses generative AI to predict the future surrounding environment. It analyzes past data and current trends to predict, for example, new commercial facility development plans and transportation infrastructure improvement plans. This future prediction information is also mapped on a map, which users can refer to.

[0663] Users can use a smartphone, smart glasses, or a head-mounted display to virtually view a property, allowing them to see the interior and surroundings of the property in real time while simultaneously viewing future predictions.

[0664] As a concrete example, consider user B considering purchasing a new property and using the following prompt:

[0665] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[0666] This allows User B to view the property in virtual space while checking the surrounding environment and future forecast information in one place. This system allows users to make efficient and informative real estate selections.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] A user uses a terminal to enter a property address using a prompt, for example, "Please enter the address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"".

[0670] Step 2:

[0671] The server receives the address entered by the user and converts it into latitude and longitude information using a geographic information API (such as Google Maps API). This allows specific location information to be obtained. The input is an address, and the output is latitude and longitude information.

[0672] Step 3:

[0673] The server searches the database for information on nearby facilities based on the acquired latitude and longitude information. This information includes schools, supermarkets, hospitals, stations, parks, etc. The input is latitude and longitude information, and the output is information on nearby facilities.

[0674] Step 4:

[0675] The server cleans the acquired nearby facility information, removes duplicates and errors, and converts it into a unified format. This information is then stored in a database. The input is nearby facility information, and the output is the cleaned data.

[0676] Step 5:

[0677] The server maps the information about the surrounding facilities after cleaning on a map using a map API (e.g., Google Maps API). This allows users to visually check the surrounding facilities. The input is the cleaned data, and the output is the information mapped on the map.

[0678] Step 6:

[0679] The user sets the evaluation criteria on the terminal. For example, they can select "distance to the nearest station," "proximity to schools," "presence of parks," etc. This allows them to individually evaluate convenience. The input is the evaluation criteria, and the output is the set evaluation criteria information.

[0680] Step 7:

[0681] The server runs an evaluation algorithm based on the set evaluation criteria and scores the convenience of the area around the property. This quantifies the convenience of the property. The input is evaluation criteria information and information on surrounding facilities, and the output is a convenience score.

[0682] Step 8:

[0683] The server analyzes past data and uses a generative AI model to generate future predictions for the surrounding area, including plans for new commercial developments and transportation infrastructure improvements. The input is past data, and the output is future predictions.

[0684] Step 9:

[0685] The server then uses the map API to map the generated future prediction information and sends it to the device, allowing the user to check the future surroundings. The input is the future prediction information, and the output is the future prediction information mapped on the map.

[0686] Step 10:

[0687] Users can view a property in a virtual space and simultaneously check the surrounding environment and future forecast information using a smartphone, smart glasses, or a head-mounted display, enabling a more comprehensive property evaluation. The input is the start of the virtual viewing, and the output is visual information in the virtual space.

[0688] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0689] The present invention is a system that efficiently evaluates the surrounding environment and convenience when selecting a real estate property, and furthermore predicts the future surrounding environment, as well as a system that recognizes the user's emotions and automatically adjusts the evaluation criteria based on the emotions.

[0690] System configuration

[0691] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[0692] Program processing

[0693] Information collection and database construction

[0694] The server scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned to remove duplicates and errors, then converted into a unified format and stored in a central database.

[0695] Mapping function on the map

[0696] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0697] Evaluation based on preferences and priorities

[0698] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0699] Generate future prediction maps

[0700] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0701] Emotion recognition and auto-tuning

[0702] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, tone of voice, etc.). The server uses an emotion engine to analyze this data and recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[0703] Automatic adjustment of evaluation criteria based on emotions

[0704] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data. For example, if the user expresses strong satisfaction with the proximity of schools, the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with the convenience of public transportation, the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[0705] Specific examples

[0706] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device and checks information about the surrounding area. User A also sets the proximity to schools, convenience of public transportation, and the presence of parks as important criteria.

[0707] The server evaluates the data and provides a convenience score. At the same time, the device collects User A's facial expressions and tone of voice, and sends them to the server as emotion data. The server then analyzes User A's emotions using its emotion engine and recognizes that User A is highly satisfied with the proximity of the school.

[0708] Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weight of proximity to schools. This allows User A to select properties based on the most important points.

[0709] By efficiently executing this series of processes, the present invention realizes a system that supports users in selecting the most suitable real estate property. Furthermore, by utilizing an emotion engine, user satisfaction can be further increased.

[0710] The processing flow will be explained below.

[0711] Step 1:

[0712] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[0713] Step 2:

[0714] The server cleans the collected data, removing duplicates and errors.

[0715] Step 3:

[0716] The server converts the cleaned data into a unified format and stores it in a central database.

[0717] Step 4:

[0718] The user uses the terminal to input the address of the property.

[0719] Step 5:

[0720] The server converts the address information into latitude and longitude information using a geographic information API.

[0721] Step 6:

[0722] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[0723] Step 7:

[0724] The server maps the acquired information about nearby facilities on a map using a map API.

[0725] Step 8:

[0726] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[0727] Step 9:

[0728] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[0729] Step 10:

[0730] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[0731] Step 11:

[0732] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[0733] Step 12:

[0734] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.).

[0735] Step 13:

[0736] The server uses an emotion engine to analyze the collected emotion data and recognize the user's emotional state.

[0737] Step 14:

[0738] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data.

[0739] Step 15:

[0740] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[0741] Step 16:

[0742] The server maps the future prediction information onto a map using a map API.

[0743] Step 17:

[0744] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[0745] Specific examples

[0746] For example, suppose user A is considering purchasing a new home. User A enters the address of the property he or she is interested in on the device and checks information about the surrounding area.

[0747] Next, User A sets evaluation criteria. For example, he or she may set "proximity to schools," "convenience of public transportation," and "presence of parks" as important items. The server evaluates the properties based on these criteria and provides a convenience score.

[0748] At the same time, the device collects user A's facial expressions and voice tone and sends them as emotion data to the server. The server then uses an emotion engine to analyze this data and determine whether user A is satisfied with certain criteria. For example, if user A is satisfied with the proximity of schools, the server will assign a higher weight to this criterion.

[0749] The server automatically adjusts the weighting of the evaluation criteria to emphasize the points that are most important to User A. This allows User A to select the optimal property based on their own feelings and preferences. The server also uses generative AI to predict the future and provides planning information for new commercial facilities and transportation infrastructure. This allows User A to select a property taking future convenience into consideration.

[0750] Example 2

[0751] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0752] Existing real estate property selection systems are insufficient in providing sufficient information and responding to individual user needs when evaluating the convenience of the surrounding area or predicting future environmental changes. Furthermore, they lack the functionality to reflect changes in user emotions and preferences in real time, which limits their ability to support optimal property selection.

[0753] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0754] In this invention, the server includes means for collecting information on surrounding facilities, means for cleaning the collected information on surrounding facilities, converting the collected information on surrounding facilities into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving information on facilities around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved information on surrounding facilities on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information for the area around the property using a generation AI, means for displaying the future prediction information on a map, means for collecting user emotion data, means for analyzing the collected emotion data and recognizing the user's emotional state, and means for automatically adjusting evaluation criteria based on the recognized emotional state. This allows users to check convenience and future prediction information in real time when selecting a property, and further enables them to select the optimal property that reflects feedback based on their own emotions.

[0755] "Nearby facility information" is data about public and commercial facilities around the property, such as schools, supermarkets, hospitals, stations, and parks.

[0756] "Cleaning" is the process of removing redundancies and errors from collected data and formatting it accurately and consistently.

[0757] "Unified format" refers to converting data collected from different sources into the same format to ensure consistency.

[0758] A "database" is a system in which collected data can be efficiently stored, managed, and retrieved.

[0759] "Latitude and longitude information" is coordinate data that indicates a geographical location and is used to identify a specific point.

[0760] "Generative AI" refers to artificial intelligence technology that makes future predictions based on past data and trends.

[0761] "Emotion data" is information about the user's emotional state obtained from facial expressions, tone of voice, and the like.

[0762] "Evaluation criteria" refers to the points or items that are important when evaluating property options, such as proximity to schools or public transportation.

[0763] This invention is a system that can efficiently evaluate the surrounding environment and convenience when selecting a real estate property, and can also predict the future surrounding environment. The invention also combines a function that recognizes the user's emotions and automatically adjusts the evaluation criteria based on those emotions. Specific embodiments for implementing the invention are described below.

[0764] System configuration

[0765] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[0766] Information collection and database construction

[0767] The server uses Python's BeautifulSoup and Scrapy scraping libraries to collect information on nearby facilities from the internet. This includes schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas and Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[0768] Mapping function on the map

[0769] The user uses a smartphone or PC to input the address of a property of interest into the device. The server converts this address into latitude and longitude information using a Geocoding API (for example, Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, maps the acquired information on a map using a map API, and sends it to the device. This allows the user to visually check the surrounding environment of the property.

[0770] Evaluation based on preferences and priorities

[0771] Users use the device interface to set evaluation criteria such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0772] Generate future prediction maps

[0773] The server analyzes past data and current trends based on a database and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. This includes plans for commercial facility development and new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this information, users can select properties taking into account the future environment.

[0774] Emotion recognition and auto-tuning

[0775] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.). The server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[0776] Automatic adjustment of evaluation criteria based on emotions

[0777] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[0778] Specific examples

[0779] For example, suppose User A is considering purchasing a new home. User A enters the address of a property they are interested in on their device and checks information about the surrounding area. User A also sets "proximity to schools," "convenience of public transportation," and "presence of parks" as important criteria. The server evaluates the properties based on this and provides a convenience score. At the same time, the device collects User A's facial expressions and voice tone and sends them to the server as emotion data. The server uses an emotion engine to analyze User A's emotions and recognizes that User A is highly satisfied with the proximity to schools. Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weighting of proximity to schools. This allows User A to select a property based on the most important points.

[0780] Prompt Sentence Examples

[0781] "Please rate the surrounding environment and convenience of a property based on the following conditions: Address: 2-8-1 Nishi-Shinjuku, Shinjuku-ku, Tokyo. Important points to consider are proximity to schools, convenience of public transportation, and the presence of parks. Furthermore, please automatically adjust the evaluation criteria based on sentiment data provided by the user."

[0782] The above is a specific embodiment for carrying out the present invention. This system utilizes advanced technology to assist users in selecting the most suitable real estate property.

[0783] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0784] Step 1: Collecting information and building a database

[0785] The server scrapes information about nearby facilities from the internet using Python scraping libraries such as BeautifulSoup and Scrapy. The collected data includes information about schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas or Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[0786] Input: Information about nearby facilities on the Internet

[0787] Data processing: scraping, data cleaning, format conversion

[0788] Output: Information on nearby facilities stored in the database

[0789] Specific operation: The server periodically runs scripts to collect information on the Internet and performs various data processing to ensure the quality of the collected data.

[0790] Step 2: Mapping function on the map

[0791] The user uses a device to input the address of a property they are interested in. The server converts this address into latitude and longitude information using a Geocoding API (e.g., Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, and maps the retrieved information on a map using a map API. Finally, this map information is sent to the user's device.

[0792] Input: The property address entered by the user

[0793] Data calculation: address latitude / longitude conversion, database search, map mapping

[0794] Output: Information about nearby facilities mapped on a map

[0795] Specific operation: The user enters an address into the input field on the device, and the server uses that information to identify the location using a map API and visualizes the surrounding information.

[0796] Step 3: Evaluate based on preferences and priorities

[0797] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the area around the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0798] Input: User-defined evaluation criteria

[0799] Data calculation: Scoring by evaluation algorithm

[0800] Output: User experience score sent to the user device

[0801] Specific operation: The user selects the points of importance on the device's rating setting screen, and the server evaluates the distance and accessibility of each facility based on those criteria.

[0802] Step 4: Generate a future prediction map

[0803] The server retrieves past data and current trends from a database such as MongoDB and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. Predictions include commercial facility development plans and new transportation infrastructure construction schedules. These predictions are visualized using a map API and sent to the user's device.

[0804] Input: Historical data and trend information

[0805] Data Computation: Predicting the Future with Generative AI

[0806] Output: Future prediction information mapped on a map

[0807] How it works: The server retrieves the necessary information from the database, trains a generative AI model to make future predictions, and visually displays the results on a map.

[0808] Step 5: Emotion Recognition and Auto-Tuning

[0809] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.), and the server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state.

[0810] Input: Emotion data collected by camera and microphone

[0811] Data Computation: Emotion Analysis with Emotion Engine

[0812] Output: Recognized emotional state of the user

[0813] Specific operation: The device captures the user's facial expressions and voice, sends them to the server in real time, and analyzes the information to evaluate the user's emotions.

[0814] Step 6: Automatic adjustment of evaluation criteria based on emotions

[0815] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the weighting of that criterion will be increased. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the weighting of that criterion will be decreased. This adjustment is made automatically, and the results are reflected on the user's device.

[0816] Input: Perceived emotional state of the user

[0817] Data calculation: Automatic adjustment of evaluation criteria

[0818] Output: Results reflecting the adjusted evaluation criteria

[0819] Specific operation: The server dynamically resets the evaluation criteria based on the results of sentiment analysis and makes suggestions to improve user satisfaction.

[0820] (Application example 2)

[0821] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0822] Conventional surrounding environment evaluation systems evaluate properties based only on current facility information, making it difficult to predict future changes in the environment. Furthermore, there was no system that adjusted evaluation criteria based on the user's emotional state, making it difficult to select properties and products that reflected the user's true satisfaction. Furthermore, there was a lack of real-time product suggestions and navigation to improve the customer experience in actual stores.

[0823] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting surrounding environment information, means for cleaning the collected surrounding environment information, converting it into a unified format, and storing it in a database, means for converting the address of a location entered by the user into location information, means for retrieving surrounding environment information from the database based on the location information, means for visually mapping and displaying the retrieved surrounding environment information, means for evaluating the convenience of the surrounding environment based on the user's settings, means for analyzing past data and generating future prediction information about the surrounding environment using a generating AI, means for displaying the future prediction information on a map, means for recognizing and analyzing the customer's emotional state, means for automatically adjusting evaluation criteria based on the customer's emotional state, means for using a generating AI to suggest the customer's next action and products, means for identifying the customer's location information in a store and providing navigation to the most suitable product, and means for adjusting the weighting of product categories based on the customer's emotional state. This enables future environment predictions based on past data and emotional information, thereby realizing property selection and product suggestions that will satisfy the user. The in-store customer experience will also be improved, offering real-time product suggestions and navigation.

[0824] "Nearby Environment Information" refers to information about the surroundings of a specific place or property that a user is interested in. This includes information about facilities such as shops, schools, public transportation, and medical facilities, as well as public safety and local characteristics.

[0825] "Database" means a collection of collected information that is organized, stored, and managed so that it can be efficiently searched and used when needed.

[0826] "Location Information" means geographical data such as latitude and longitude that indicates a specific location. This data is obtained using technologies such as GPS and beacons.

[0827] "Emotional state" refers to the psychological state of a user analyzed from facial expressions, tone of voice, etc. This includes states such as satisfaction, dissatisfaction, excitement, and relaxation.

[0828] "Navigation" means guidance that provides a route or direction for a user to reach a destination, including map displays and audio guidance.

[0829] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to predict and classify future outcomes based on large amounts of data, including neural networks and deep learning.

[0830] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to estimate their emotional state. It uses machine learning and computer vision algorithms.

[0831] "Future forecast information" refers to information about future surrounding environments and market trends that is generated by analyzing past data and current trends.

[0832] "Product Recommendations" means the presentation of recommended products and services based on a user's preferences and behavioral data, including personalized recommendations.

[0833] "Weighting" refers to the assignment of greater or lesser importance to a particular factor in determining the evaluation criteria, which is reflected in a numerical score or ranking.

[0834] The present invention is a system that improves customer experience in shopping malls and large brick-and-mortar stores, and is composed of three entities: a server, a terminal, and a user.

[0835] System configuration

[0836] Gathering information on the surrounding environment

[0837] The server scrapes surrounding environment information from the internet, cleans it, removes duplicates and errors, converts it into a unified format, and stores it in a central database.

[0838] Obtaining location information

[0839] When a user enters the address of a place of interest into their device, the server converts the address into location information (latitude and longitude) using a geographic information API.

[0840] Mapping of surrounding environment information

[0841] The server retrieves information about the surrounding environment from a database based on the acquired location information. This information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment through the device.

[0842] Usability evaluation

[0843] The user sets evaluation criteria on their device, such as "specific product category" or "store congestion level." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding environment. The calculated score is sent to the user's device, allowing them to check the convenience.

[0844] Generating future prediction information

[0845] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device, allowing the user to select the optimal location and product based on the future environment.

[0846] Emotion recognition and evaluation criteria adjustment

[0847] The device collects emotional data from the user using a camera and microphone. The server analyzes this data with an emotion engine to recognize the user's emotional state. For example, it analyzes facial expressions and tone of voice while the user is reviewing product recommendations to determine whether the user is satisfied.

[0848] Product suggestions and navigation

[0849] The server automatically adjusts evaluation criteria based on the customer's emotional state and makes optimal product recommendations. It also identifies the customer's current location in the store in real time using GPS information and Bluetooth beacons, providing navigation information so that customers can easily access the products they are looking for.

[0850] Specific examples

[0851] For example, when a customer visits a brick-and-mortar shopping mall, they put on the smart glasses and input the product categories they are interested in (e.g., clothing, home appliances). The server retrieves information about related products based on those interests and displays it on the smart glasses along with navigation information. If, after analyzing the customer's facial expressions and tone of voice, the server finds that the customer is satisfied with the reviews of a particular product, it automatically adjusts the weighting of that category and determines the next product to be prioritized.

[0852] Prompt Sentence Examples

[0853] "To predict future purchasing trends and provide the best customer experience, we use sales data and customer sentiment data from the past three years to determine the next product and promotion strategy we should offer."

[0854] As described above, the present invention provides a concrete means for realizing a surrounding environment evaluation system, which allows users to select properties and products that will give them greater satisfaction, and also significantly improves the customer experience in stores.

[0855] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0856] Step 1:

[0857] The server scrapes surrounding environment information from the internet. For example, it collects information on facilities such as shops, schools, hospitals, and public transportation, cleans it by removing duplicates and errors, and converts it into a unified format. This data is stored in a central database. The input here is raw data from the internet, and the output is the cleaned database.

[0858] Step 2:

[0859] The user inputs the address of a place of interest into the device. The device retrieves this address and sends it to the server. The server uses a geographic information API to convert the address into location information (latitude and longitude). The input is address information, and the output is the location information corresponding to that address.

[0860] Step 3:

[0861] The server searches and retrieves surrounding environment information from a central database based on the acquired location information. The acquired surrounding environment information is mapped on a map using a map API and sent to the device. The input is location information, and the output is a map with the surrounding environment information mapped on it.

[0862] Step 4:

[0863] The user visually checks the surrounding environment information on the device and sets evaluation criteria. For example, they set "specific product category" or "store congestion level." These evaluation criteria are sent from the device to the server. The input is the user-set evaluation criteria, and the output is the evaluation criteria data sent to the server.

[0864] Step 5:

[0865] The server runs an evaluation algorithm based on the evaluation criteria set by the user, scores the usability of the surrounding environment, and sends the score to the user's device. The input is the evaluation criteria and surrounding environment information, and the output is the calculated usability score.

[0866] Step 6:

[0867] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device. The input is past data and an evaluation algorithm, and the output is future prediction information.

[0868] Step 7:

[0869] The device uses a camera and microphone to collect the user's emotional data, including facial expressions and vocal tones. The collected data is sent to a server. The input is the user's emotional data, and the output is the emotional data sent to the server.

[0870] Step 8:

[0871] The server uses an emotion engine to analyze the user's emotional state and automatically adjusts the evaluation criteria based on the emotional data. For example, if a user expresses high satisfaction with a particular product, it increases the weighting of that product category. The input is emotional data, and the output is the adjusted evaluation criteria.

[0872] Step 9:

[0873] The server uses generative AI to make optimal product suggestions to customers based on emotional data and real-time location information. Product suggestions and navigation information are sent to the device in real time, allowing users to easily access the desired products. The input is emotional state and real-time location information, and the output is product suggestions and navigation information.

[0874] Step 10:

[0875] Users use smart glasses or terminals to check the suggested products and move around the store. The server collects user behavior data in real time and maintains a loop throughout the system. The input is user behavior data, and the output is continuous data collection and improvement information.

[0876] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0877] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0878] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0879] [Third embodiment]

[0880] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0881] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0882] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0883] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0884] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0885] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0886] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0887] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0888] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0889] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0890] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0891] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0892] The present invention provides a system for efficiently evaluating the surrounding environment and convenience when selecting a real estate property, and for predicting the future surrounding environment. The following describes an embodiment of the present invention.

[0893] System configuration

[0894] The system is primarily composed of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, running the evaluation algorithm, and training and running the generative AI. The terminal allows users to input information and displays the results. Users input property addresses, set evaluation criteria, and check the results.

[0895] Program processing

[0896] Information collection and database construction

[0897] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[0898] Mapping function on the map

[0899] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0900] Evaluation based on preferences and priorities

[0901] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0902] Generate future prediction maps

[0903] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0904] Specific examples

[0905] For example, suppose User A is considering purchasing a new home. User A enters the address of a property of interest on their device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[0906] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. Based on this, the server calculates the property's convenience score and displays it to User A.

[0907] Furthermore, the server uses the generation AI to predict the future of the property's surroundings, providing information such as when new commercial facilities are planned to be built or when new train stations are scheduled to open. Based on this information, User A can select a property taking into account future convenience.

[0908] The present invention is a system that efficiently executes this series of processes and supports the user in selecting the most suitable real estate property.

[0909] The processing flow will be explained below.

[0910] Step 1:

[0911] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[0912] Step 2:

[0913] The server cleans the collected data, removing duplicates and errors.

[0914] Step 3:

[0915] The server converts the cleaned data into a unified format and stores it in a central database.

[0916] Step 4:

[0917] The user uses the terminal to input the address of the property.

[0918] Step 5:

[0919] The server converts the address information into latitude and longitude information using a geographic information API.

[0920] Step 6:

[0921] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[0922] Step 7:

[0923] The server maps the acquired information about nearby facilities on a map using a map API.

[0924] Step 8:

[0925] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[0926] Step 9:

[0927] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[0928] Step 10:

[0929] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[0930] Step 11:

[0931] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[0932] Step 12:

[0933] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[0934] Step 13:

[0935] The server maps the future prediction information onto a map using a map API.

[0936] Step 14:

[0937] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[0938] Example 1

[0939] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0940] Conventional real estate property selection systems do not adequately evaluate the surrounding environment and convenience of properties, and do not provide enough information to support users in selecting the appropriate property. In addition, there is no method to predict future surrounding environments, making it difficult to select properties that take future changes in convenience into account. This poses a challenge, as it is difficult for users to obtain sufficient information to select the optimal property.

[0941] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0942] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting it into a unified format and storing it in a database, means for converting property location information entered by a user into geographic coordinate information, means for acquiring facility information around the property from the database based on the geographic coordinate information, means for mapping and displaying the acquired surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generative AI model, and means for displaying the future prediction information on a map. This allows a user to select the optimal property based on multifaceted information including detailed information about the surrounding environment and future predictions.

[0943] "Information about surrounding facilities" is information about all facilities related to daily life, such as schools, supermarkets, hospitals, stations, and parks, that exist around the property.

[0944] "Means of collection" refers to the technology and methods for automatically obtaining the desired data from data sources such as the Internet.

[0945] "Cleaning means" refers to operations or processes used to remove duplication and errors from collected data and improve the quality of the data.

[0946] A "means for converting into a unified format" is a method for converting data of different formats or structures into a consistent format.

[0947] "Means for storing data in a database" refers to a method for registering data in a database system so that the data can be managed efficiently and accessed quickly when needed.

[0948] "Means for converting into geographic coordinate information" refers to technology for converting location information such as addresses into geographic coordinate information such as latitude and longitude.

[0949] The "means for acquiring facility information" refers to a technique or method for searching and extracting related surrounding facility information from a database based on specified geographic coordinate information.

[0950] "Means for mapping and displaying on a map" refers to technology for arranging acquired information on a map in a visually easy-to-understand manner and displaying it to the user.

[0951] A "means for evaluating convenience" is a method for evaluating the convenience of the surrounding environment of a property as a numerical value or score based on criteria set by the user.

[0952] "Historical data analysis methods" are techniques and methods for statistically analyzing and extracting information from all previously collected and stored data sets.

[0953] "Means for generating future prediction information using a generative AI model" refers to a technology that uses a generative AI model to predict future changes in the surrounding environment based on past data and current trends.

[0954] "Means for displaying future prediction information on a map" refers to technology for visually displaying future information predicted by a generative AI model on a map.

[0955] The embodiment of the present invention is a system that evaluates the surrounding environment and convenience, and also predicts the future surrounding environment. This system is mainly composed of three entities: a server, a terminal, and a user. The specific configuration and operation of the system are described below.

[0956] System Configuration

[0957] The system consists of three components: a server, a terminal, and a user. The server is responsible for collecting information on nearby facilities, cleaning the data, managing the database, running the evaluation algorithm, and training and running the generative AI model. The terminal is used by users to input information and display the results. Users input property addresses, set evaluation criteria, and check the results.

[0958] Hardware and software used

[0959] Hardware:

[0960] Server: Use a high-performance server machine

[0961] Devices: personal computers, tablets, smartphones, etc.

[0962] software:

[0963] Data collection: Python's BeautifulSoup, Selenium

[0964] Database: MySQL, PostgreSQL

[0965] Geographical information API: Google Maps API, Geocoding API

[0966] Data Cleaning: Pandas

[0967] Generative AI models: GPT-3, BERT, etc.

[0968] Program processing

[0969] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[0970] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[0971] Furthermore, the user sets evaluation criteria on their device. For example, they can set "proximity to schools" and "convenience of public transportation" as important items. The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[0972] The server then analyzes past data and current trends and uses a generative AI model to predict the future surrounding environment. This includes plans for commercial development and new transportation infrastructure. The prediction results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[0973] Specific examples

[0974] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[0975] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. The server calculates the property's convenience score based on this and displays it to User A.

[0976] Furthermore, the server uses the generative AI model to predict the future of the area around the property, providing information such as when new commercial facilities are planned to be built and when new transportation infrastructure is planned to be developed. Based on this information, User A can select a property taking into account future convenience.

[0977] Prompt Sentence Examples

[0978] "I'm looking for real estate around Shin-Kamagaya Station. The key evaluation criteria are distance to the nearest station, proximity to schools, and access to hospitals. I'd also like to know if there are any plans for new commercial facilities or transportation infrastructure in the future."

[0979] In this way, the system of the present invention integrates and provides a variety of information to assist the user in selecting the most suitable real estate property.

[0980] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0981] Program processing flow

[0982] Step 1: Scraping the data

[0983] The server scrapes information about nearby facilities from the internet, using Python's BeautifulSoup and Selenium libraries.

[0984] Input: List of target website URLs

[0985] Data processing: HTML analysis, extraction of necessary data (school, supermarket, hospital, station, park name, address, contact details, etc.)

[0986] Output: Raw data list (extracted information on nearby facilities)

[0987] Step 2: Cleaning the data

[0988] The server uses the Pandas library to clean the scraped data.

[0989] Input: Raw data list (extracted surrounding facility information)

[0990] Data processing: Removing duplicate data, correcting outliers, and filling in missing data

[0991] Output: Cleaned data

[0992] Step 3: Convert data format and save to database

[0993] The server converts the cleaned data into a unified format (e.g., CSV, JSON) and stores it in a database.

[0994] Input: Cleaned data

[0995] Data processing: Conversion to a unified format

[0996] Output: Data stored in a database

[0997] Step 4: Enter the property address

[0998] The user inputs the address of the property into the input form on the terminal.

[0999] Input: Property address

[1000] Output: Data sent to the server (property address)

[1001] Step 5: Convert address to latitude and longitude

[1002] The server uses the Geocoding API to convert the entered property address into latitude and longitude information.

[1003] Input: Property address

[1004] Data calculation: Latitude and longitude conversion using Geocoding API

[1005] Output: Latitude and longitude information

[1006] Step 6: Obtaining information about nearby facilities

[1007] The server searches the database for information on nearby facilities based on the property's latitude and longitude information.

[1008] Input: Latitude and longitude information

[1009] Data search: Search for nearby facilities using database queries

[1010] Output: List of nearby facilities

[1011] Step 7: Mapping information onto a map

[1012] The server maps the acquired information about nearby facilities onto a map using the Google Maps API.

[1013] Input: List of nearby facilities

[1014] Data calculation: Mapping processing using Google Maps API

[1015] Output: Map data (surrounding facility information mapped)

[1016] Step 8: Display the map

[1017] The server transmits the mapped map data to the terminal.

[1018] Input: Map data

[1019] Output: Data sent to the device (map data)

[1020] The terminal displays the received map data to the user, allowing the user to visually check the surrounding environment of the property.

[1021] Step 9: Set evaluation criteria

[1022] The user sets evaluation criteria on the terminal, such as "distance to the nearest station" or "proximity to schools."

[1023] Input: User-defined criteria

[1024] Output: Data sent to the server (evaluation criteria)

[1025] Step 10: Run the evaluation algorithm and score

[1026] The server runs a rating algorithm based on the rating criteria set by the user.

[1027] Input: Evaluation criteria, information on nearby facilities

[1028] Data calculation: Score calculation using weighting algorithm

[1029] Output: Usability score

[1030] Step 11: Displaying the score to the user

[1031] The server transmits the calculated usability score to the user's terminal.

[1032] Input: Usability score

[1033] Output: Data sent to the device (convenience score)

[1034] The terminal displays the received score to the user, allowing the user to check the convenience of each property.

[1035] Step 12: Historical data and trend analysis

[1036] The server analyzes historical data and current trend data.

[1037] Input: Historical data, trend data

[1038] Data calculation: data analysis, trend analysis

[1039] Output: Trend information, analysis results

[1040] Step 13: Generative AI predicts the future

[1041] The server uses a generative AI model (e.g., GPT-3 or BERT) to predict future surroundings.

[1042] Input: Historical data, trend information

[1043] Data Computation: Predicting the Future with Generative AI Models

[1044] Output: Future prediction information

[1045] Step 14: Map mapping and display of prediction results

[1046] The server uses a map API to map the future prediction data created by the generative AI model onto a map.

[1047] Input: Future prediction information

[1048] Data calculation: Mapping processing using map API

[1049] Output: Predicted map data

[1050] The server transmits the predicted map data to the terminal.

[1051] Input: Predicted map data

[1052] Output: Data sent to the device (predictive map data)

[1053] The terminal displays the received predicted map data to the user, who can then select a property based on this future prediction information, taking into account the future environment.

[1054] (Application example 1)

[1055] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1056] Conventional real estate property selection systems have difficulty effectively evaluating the surrounding environment and convenience of a property, and lack the ability to predict future surrounding conditions. Furthermore, users must actually visit the property to view it, making it difficult to efficiently select a property. The present invention aims to solve these problems by providing a system that allows users to view properties in a virtual space, evaluate the surrounding environment, and check future prediction information.

[1057] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1058] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting the collected information into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving facility information around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generation AI, means for displaying the future prediction information on a map, means for allowing a user to view the property in a virtual space, and means for the user to check the surrounding facility information and future predictions in the virtual space. This allows a user to view the property in a virtual space while centrally checking detailed information about the surrounding environment and predictions of future environmental changes.

[1059] "Nearby facility information" is information about facilities such as schools, supermarkets, hospitals, stations, and parks that exist around the property.

[1060] "Cleaning" is the process of removing duplication and errors from collected data and converting the data into a unified format.

[1061] "Latitude and longitude information" refers to coordinate information that indicates a point on the Earth, and is used to indicate the specific location of a property.

[1062] A "database" is an electronic storage system for efficiently storing, retrieving, and managing data.

[1063] "Mapping" is the visualization and display of specific information on a map.

[1064] "Evaluation criteria" are a set of factors that users use as criteria when evaluating the convenience of a property, and include, for example, "proximity to schools" and "convenience of public transportation."

[1065] "Generative AI" is an artificial intelligence model that learns from large amounts of data to predict future trends and patterns.

[1066] "Future prediction information" is information generated by the generating AI, which analyzes past data and predicts future changes in the surrounding environment and plans for new facility construction.

[1067] "Virtual space" refers to a virtual three-dimensional space generated using computer technology, which is used by users to view properties.

[1068] A "viewing" refers to a user being able to check the interior and surroundings of a property through a virtual space without actually visiting the property.

[1069] "Convenience" is an indicator that evaluates the degree to which the surrounding environment of a property provides convenience for daily life.

[1070] The present invention is a system that allows a user to view a real estate property in a virtual space and evaluate the surrounding environment and future changes to the environment.

[1071] System configuration

[1072] The system is configured using the following hardware and software.

[1073] 1. Hardware:

[1074] server

[1075] Devices (smartphones, smart glasses, head-mounted displays)

[1076] 2. Software:

[1077] API (geographical information API, map API)

[1078] Machine learning library (scikit-learn)

[1079] Database Management Systems

[1080] Visualization tool (folium)

[1081] Program processing description

[1082] The server first scrapes information about nearby facilities from the internet, cleans the data, converts it into a unified format, and stores it in a database, ensuring that the data is free of duplicates and errors.

[1083] Next, when the user enters the property address using the terminal, the server converts the address into latitude and longitude information using the geographic information API. An example of a specific prompt is as follows:

[1084] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[1085] The server retrieves information about nearby facilities from the database based on this latitude and longitude information and maps it on a map using a map API, allowing users to visually check the environment around the property.

[1086] Users can also set evaluation criteria on their devices, such as "distance to the nearest station," "proximity to schools," and "presence of parks" as important factors. The server runs an evaluation algorithm based on these criteria and scores the convenience of the property. The calculated score is sent to the user's device, allowing them to check the convenience of the property.

[1087] Furthermore, the server uses generative AI to predict the future surrounding environment. It analyzes past data and current trends to predict, for example, new commercial facility development plans and transportation infrastructure improvement plans. This future prediction information is also mapped on a map, which users can refer to.

[1088] Users can use a smartphone, smart glasses, or a head-mounted display to virtually view a property, allowing them to see the interior and surroundings of the property in real time while simultaneously viewing future predictions.

[1089] As a concrete example, consider user B considering purchasing a new property and using the following prompt:

[1090] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[1091] This allows User B to view the property in virtual space while checking the surrounding environment and future forecast information in one place. This system allows users to make efficient and informative real estate selections.

[1092] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1093] Step 1:

[1094] A user uses a terminal to enter a property address using a prompt, for example, "Please enter the address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"".

[1095] Step 2:

[1096] The server receives the address entered by the user and converts it into latitude and longitude information using a geographic information API (such as Google Maps API). This allows specific location information to be obtained. The input is an address, and the output is latitude and longitude information.

[1097] Step 3:

[1098] The server searches the database for information on nearby facilities based on the acquired latitude and longitude information. This information includes schools, supermarkets, hospitals, stations, parks, etc. The input is latitude and longitude information, and the output is information on nearby facilities.

[1099] Step 4:

[1100] The server cleans the acquired nearby facility information, removes duplicates and errors, and converts it into a unified format. This information is then stored in a database. The input is nearby facility information, and the output is the cleaned data.

[1101] Step 5:

[1102] The server maps the information about the surrounding facilities after cleaning on a map using a map API (e.g., Google Maps API). This allows users to visually check the surrounding facilities. The input is the cleaned data, and the output is the information mapped on the map.

[1103] Step 6:

[1104] The user sets the evaluation criteria on the terminal. For example, they can select "distance to the nearest station," "proximity to schools," "presence of parks," etc. This allows them to individually evaluate convenience. The input is the evaluation criteria, and the output is the set evaluation criteria information.

[1105] Step 7:

[1106] The server runs an evaluation algorithm based on the set evaluation criteria and scores the convenience of the area around the property. This quantifies the convenience of the property. The input is evaluation criteria information and information on surrounding facilities, and the output is a convenience score.

[1107] Step 8:

[1108] The server analyzes past data and uses a generative AI model to generate future predictions for the surrounding area, including plans for new commercial developments and transportation infrastructure improvements. The input is past data, and the output is future predictions.

[1109] Step 9:

[1110] The server then uses the map API to map the generated future prediction information and sends it to the device, allowing the user to check the future surroundings. The input is the future prediction information, and the output is the future prediction information mapped on the map.

[1111] Step 10:

[1112] Users can view a property in a virtual space and simultaneously check the surrounding environment and future forecast information using a smartphone, smart glasses, or a head-mounted display, enabling a more comprehensive property evaluation. The input is the start of the virtual viewing, and the output is visual information in the virtual space.

[1113] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1114] The present invention is a system that efficiently evaluates the surrounding environment and convenience when selecting a real estate property, and furthermore predicts the future surrounding environment, as well as a system that recognizes the user's emotions and automatically adjusts the evaluation criteria based on the emotions.

[1115] System configuration

[1116] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[1117] Program processing

[1118] Information collection and database construction

[1119] The server scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned to remove duplicates and errors, then converted into a unified format and stored in a central database.

[1120] Mapping function on the map

[1121] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[1122] Evaluation based on preferences and priorities

[1123] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1124] Generate future prediction maps

[1125] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[1126] Emotion recognition and auto-tuning

[1127] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, tone of voice, etc.). The server uses an emotion engine to analyze this data and recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[1128] Automatic adjustment of evaluation criteria based on emotions

[1129] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data. For example, if the user expresses strong satisfaction with the proximity of schools, the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with the convenience of public transportation, the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[1130] Specific examples

[1131] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device and checks information about the surrounding area. User A also sets the proximity to schools, convenience of public transportation, and the presence of parks as important criteria.

[1132] The server evaluates the user based on this and provides a convenience score. At the same time, the device collects user A's facial expressions and tone of voice and sends them to the server as emotion data. The server then analyzes user A's emotions using its emotion engine and recognizes that user A is highly satisfied with the proximity of the school.

[1133] Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weight of proximity to schools. This allows User A to select properties based on the most important points.

[1134] By efficiently executing this series of processes, the present invention realizes a system that supports users in selecting the most suitable real estate property. Furthermore, by utilizing an emotion engine, user satisfaction can be further increased.

[1135] The processing flow will be explained below.

[1136] Step 1:

[1137] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[1138] Step 2:

[1139] The server cleans the collected data, removing duplicates and errors.

[1140] Step 3:

[1141] The server converts the cleaned data into a unified format and stores it in a central database.

[1142] Step 4:

[1143] The user uses the terminal to input the address of the property.

[1144] Step 5:

[1145] The server converts the address information into latitude and longitude information using a geographic information API.

[1146] Step 6:

[1147] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[1148] Step 7:

[1149] The server maps the acquired information about nearby facilities on a map using a map API.

[1150] Step 8:

[1151] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[1152] Step 9:

[1153] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[1154] Step 10:

[1155] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[1156] Step 11:

[1157] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[1158] Step 12:

[1159] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.).

[1160] Step 13:

[1161] The server uses an emotion engine to analyze the collected emotion data and recognize the user's emotional state.

[1162] Step 14:

[1163] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data.

[1164] Step 15:

[1165] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[1166] Step 16:

[1167] The server maps the future prediction information onto a map using a map API.

[1168] Step 17:

[1169] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[1170] Specific examples

[1171] For example, suppose user A is considering purchasing a new home. User A enters the address of the property he or she is interested in on the device and checks information about the surrounding area.

[1172] Next, User A sets evaluation criteria. For example, he or she may set "proximity to schools," "convenience of public transportation," and "presence of parks" as important items. The server evaluates the properties based on these criteria and provides a convenience score.

[1173] At the same time, the device collects user A's facial expressions and voice tone and sends them as emotion data to the server. The server then uses an emotion engine to analyze this data and determine whether user A is satisfied with certain criteria. For example, if user A is satisfied with the proximity of schools, the server will assign a higher weight to this criterion.

[1174] The server automatically adjusts the weighting of the evaluation criteria to emphasize the points that are most important to User A. This allows User A to select the optimal property based on their own feelings and preferences. The server also uses generative AI to predict the future and provides planning information for new commercial facilities and transportation infrastructure. This allows User A to select a property taking future convenience into consideration.

[1175] Example 2

[1176] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1177] Existing real estate property selection systems are insufficient in providing sufficient information and responding to individual user needs when evaluating the convenience of the surrounding area or predicting future environmental changes. Furthermore, they lack the functionality to reflect changes in user emotions and preferences in real time, which limits their ability to support optimal property selection.

[1178] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1179] In this invention, the server includes means for collecting information on surrounding facilities, means for cleaning the collected information on surrounding facilities, converting the collected information on surrounding facilities into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving information on facilities around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved information on surrounding facilities on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information for the area around the property using a generation AI, means for displaying the future prediction information on a map, means for collecting user emotion data, means for analyzing the collected emotion data and recognizing the user's emotional state, and means for automatically adjusting evaluation criteria based on the recognized emotional state. This allows users to check convenience and future prediction information in real time when selecting a property, and further enables them to select the optimal property that reflects feedback based on their own emotions.

[1180] "Nearby facility information" is data about public and commercial facilities around the property, such as schools, supermarkets, hospitals, stations, and parks.

[1181] "Cleaning" is the process of removing redundancies and errors from collected data and formatting it accurately and consistently.

[1182] "Unified format" refers to converting data collected from different sources into the same format to ensure consistency.

[1183] A "database" is a system in which collected data can be efficiently stored, managed, and retrieved.

[1184] "Latitude and longitude information" is coordinate data that indicates a geographical location and is used to identify a specific point.

[1185] "Generative AI" refers to artificial intelligence technology that makes future predictions based on past data and trends.

[1186] "Emotion data" is information about the user's emotional state obtained from facial expressions, tone of voice, and the like.

[1187] "Evaluation criteria" refers to the points or items that are important when evaluating property options, such as proximity to schools or public transportation.

[1188] This invention is a system that can efficiently evaluate the surrounding environment and convenience when selecting a real estate property, and can also predict the future surrounding environment. The invention also combines a function that recognizes the user's emotions and automatically adjusts the evaluation criteria based on those emotions. Specific embodiments for implementing the invention are described below.

[1189] System configuration

[1190] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[1191] Information collection and database construction

[1192] The server uses Python's BeautifulSoup and Scrapy scraping libraries to collect information on nearby facilities from the internet. This includes schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas and Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[1193] Mapping function on the map

[1194] The user uses a smartphone or PC to input the address of a property of interest into the device. The server converts this address into latitude and longitude information using a Geocoding API (for example, Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, maps the acquired information on a map using a map API, and sends it to the device. This allows the user to visually check the surrounding environment of the property.

[1195] Evaluation based on preferences and priorities

[1196] Users use the device interface to set evaluation criteria such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1197] Generate future prediction maps

[1198] The server analyzes past data and current trends based on a database and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. This includes plans for commercial facility development and new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this information, users can select properties taking into account the future environment.

[1199] Emotion recognition and auto-tuning

[1200] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.). The server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[1201] Automatic adjustment of evaluation criteria based on emotions

[1202] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[1203] Specific examples

[1204] For example, suppose User A is considering purchasing a new home. User A enters the address of a property they are interested in on their device and checks information about the surrounding area. User A also sets "proximity to schools," "convenience of public transportation," and "presence of parks" as important criteria. The server evaluates the properties based on this and provides a convenience score. At the same time, the device collects User A's facial expressions and voice tone and sends them to the server as emotion data. The server uses an emotion engine to analyze User A's emotions and recognizes that User A is highly satisfied with the proximity to schools. Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weighting of proximity to schools. This allows User A to select a property based on the most important points.

[1205] Prompt Sentence Examples

[1206] "Please rate the surrounding environment and convenience of a property based on the following conditions: Address: 2-8-1 Nishi-Shinjuku, Shinjuku-ku, Tokyo. Important points to consider are proximity to schools, convenience of public transportation, and the presence of parks. Furthermore, please automatically adjust the evaluation criteria based on sentiment data provided by the user."

[1207] The above is a specific embodiment for carrying out the present invention. This system utilizes advanced technology to assist users in selecting the most suitable real estate property.

[1208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1209] Step 1: Collecting information and building a database

[1210] The server scrapes information about nearby facilities from the internet using Python scraping libraries such as BeautifulSoup and Scrapy. The collected data includes information about schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas or Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[1211] Input: Information about nearby facilities on the Internet

[1212] Data processing: scraping, data cleaning, format conversion

[1213] Output: Information on nearby facilities stored in the database

[1214] Specific operation: The server periodically runs scripts to collect information on the Internet and performs various data processing to ensure the quality of the collected data.

[1215] Step 2: Mapping function on the map

[1216] The user uses a device to input the address of a property they are interested in. The server converts this address into latitude and longitude information using a Geocoding API (e.g., Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, and maps the retrieved information on a map using a map API. Finally, this map information is sent to the user's device.

[1217] Input: The property address entered by the user

[1218] Data calculation: address latitude / longitude conversion, database search, map mapping

[1219] Output: Information about nearby facilities mapped on a map

[1220] Specific operation: The user enters an address into the input field on the device, and the server uses that information to identify the location using a map API and visualizes the surrounding information.

[1221] Step 3: Evaluate based on preferences and priorities

[1222] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the area around the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1223] Input: User-defined evaluation criteria

[1224] Data calculation: Scoring by evaluation algorithm

[1225] Output: User experience score sent to the user device

[1226] Specific operation: The user selects the points of importance on the device's rating setting screen, and the server evaluates the distance and accessibility of each facility based on those criteria.

[1227] Step 4: Generate a future prediction map

[1228] The server retrieves past data and current trends from a database such as MongoDB and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. Predictions include commercial facility development plans and new transportation infrastructure construction schedules. These predictions are visualized using a map API and sent to the user's device.

[1229] Input: Historical data and trend information

[1230] Data Computation: Predicting the Future with Generative AI

[1231] Output: Future prediction information mapped on a map

[1232] How it works: The server retrieves the necessary information from the database, trains a generative AI model to make future predictions, and visually displays the results on a map.

[1233] Step 5: Emotion Recognition and Auto-Tuning

[1234] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.), and the server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state.

[1235] Input: Emotion data collected by camera and microphone

[1236] Data Computation: Emotion Analysis with Emotion Engine

[1237] Output: Recognized emotional state of the user

[1238] Specific operation: The device captures the user's facial expressions and voice, sends them to the server in real time, and analyzes the information to evaluate the user's emotions.

[1239] Step 6: Automatic adjustment of evaluation criteria based on emotions

[1240] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the weighting of that criterion will be increased. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the weighting of that criterion will be decreased. This adjustment is made automatically, and the results are reflected on the user's device.

[1241] Input: Perceived emotional state of the user

[1242] Data calculation: Automatic adjustment of evaluation criteria

[1243] Output: Results reflecting the adjusted evaluation criteria

[1244] Specific operation: The server dynamically resets the evaluation criteria based on the results of sentiment analysis and makes suggestions to improve user satisfaction.

[1245] (Application example 2)

[1246] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1247] Conventional surrounding environment evaluation systems evaluate properties based only on current facility information, making it difficult to predict future changes in the environment. Furthermore, there was no system that adjusted evaluation criteria based on the user's emotional state, making it difficult to select properties and products that reflected the user's true satisfaction. Furthermore, there was a lack of real-time product suggestions and navigation to improve the customer experience in actual stores.

[1248] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting surrounding environment information, means for cleaning the collected surrounding environment information, converting it into a unified format, and storing it in a database, means for converting the address of a location entered by the user into location information, means for retrieving surrounding environment information from the database based on the location information, means for visually mapping and displaying the retrieved surrounding environment information, means for evaluating the convenience of the surrounding environment based on the user's settings, means for analyzing past data and generating future prediction information about the surrounding environment using a generating AI, means for displaying the future prediction information on a map, means for recognizing and analyzing the customer's emotional state, means for automatically adjusting evaluation criteria based on the customer's emotional state, means for using a generating AI to suggest the customer's next action and products, means for identifying the customer's location information in a store and providing navigation to the most suitable product, and means for adjusting the weighting of product categories based on the customer's emotional state. This enables future environment predictions based on past data and emotional information, thereby realizing property selection and product suggestions that will satisfy the user. The in-store customer experience will also be improved, offering real-time product suggestions and navigation.

[1249] "Nearby Environment Information" refers to information about the surroundings of a specific place or property that a user is interested in. This includes information about facilities such as shops, schools, public transportation, and medical facilities, as well as public safety and local characteristics.

[1250] "Database" means a collection of collected information that is organized, stored, and managed so that it can be efficiently searched and used when needed.

[1251] "Location Information" means geographical data such as latitude and longitude that indicates a specific location. This data is obtained using technologies such as GPS and beacons.

[1252] "Emotional state" refers to the psychological state of a user analyzed from facial expressions, tone of voice, etc. This includes states such as satisfaction, dissatisfaction, excitement, and relaxation.

[1253] "Navigation" means guidance that provides a route or direction for a user to reach a destination, including map displays and audio guidance.

[1254] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to predict and classify future outcomes based on large amounts of data, including neural networks and deep learning.

[1255] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to estimate their emotional state. It uses machine learning and computer vision algorithms.

[1256] "Future forecast information" refers to information about future surrounding environments and market trends that is generated by analyzing past data and current trends.

[1257] "Product Recommendations" means the presentation of recommended products and services based on a user's preferences and behavioral data, including personalized recommendations.

[1258] "Weighting" refers to the assignment of greater or lesser importance to a particular factor in determining the evaluation criteria, which is reflected in a numerical score or ranking.

[1259] The present invention is a system that improves customer experience in shopping malls and large brick-and-mortar stores, and is composed of three entities: a server, a terminal, and a user.

[1260] System configuration

[1261] Gathering information on the surrounding environment

[1262] The server scrapes surrounding environment information from the internet, cleans it, removes duplicates and errors, converts it into a unified format, and stores it in a central database.

[1263] Obtaining location information

[1264] When a user enters the address of a place of interest into their device, the server converts the address into location information (latitude and longitude) using a geographic information API.

[1265] Mapping of surrounding environment information

[1266] The server retrieves information about the surrounding environment from a database based on the acquired location information. This information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment through the device.

[1267] Usability evaluation

[1268] The user sets evaluation criteria on their device, such as "specific product category" or "store congestion level." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding environment. The calculated score is sent to the user's device, allowing them to check the convenience.

[1269] Generating future prediction information

[1270] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device, allowing the user to select the optimal location and product based on the future environment.

[1271] Emotion recognition and evaluation criteria adjustment

[1272] The device collects emotional data from the user using a camera and microphone. The server analyzes this data with an emotion engine to recognize the user's emotional state. For example, it analyzes facial expressions and tone of voice while the user is reviewing product recommendations to determine whether the user is satisfied.

[1273] Product suggestions and navigation

[1274] The server automatically adjusts evaluation criteria based on the customer's emotional state and makes optimal product recommendations. It also identifies the customer's current location in the store in real time using GPS information and Bluetooth beacons, providing navigation information so that customers can easily access the products they are looking for.

[1275] Specific examples

[1276] For example, when a customer visits a brick-and-mortar shopping mall, they put on the smart glasses and input the product categories they are interested in (e.g., clothing, home appliances). The server retrieves information about related products based on those interests and displays it on the smart glasses along with navigation information. If, after analyzing the customer's facial expressions and tone of voice, the server finds that the customer is satisfied with the reviews of a particular product, it automatically adjusts the weighting of that category and determines the next product to be prioritized.

[1277] Prompt Sentence Examples

[1278] "To predict future purchasing trends and provide the best customer experience, we use sales data and customer sentiment data from the past three years to determine the next product and promotion strategy we should offer."

[1279] As described above, the present invention provides a concrete means for realizing a surrounding environment evaluation system, which allows users to select properties and products that will give them greater satisfaction, and also significantly improves the customer experience in stores.

[1280] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1281] Step 1:

[1282] The server scrapes surrounding environment information from the internet. For example, it collects information on facilities such as shops, schools, hospitals, and public transportation, cleans it by removing duplicates and errors, and converts it into a unified format. This data is stored in a central database. The input here is raw data from the internet, and the output is the cleaned database.

[1283] Step 2:

[1284] The user inputs the address of a place of interest into the device. The device retrieves this address and sends it to the server. The server uses a geographic information API to convert the address into location information (latitude and longitude). The input is address information, and the output is the location information corresponding to that address.

[1285] Step 3:

[1286] The server searches and retrieves surrounding environment information from a central database based on the acquired location information. The acquired surrounding environment information is mapped on a map using a map API and sent to the device. The input is location information, and the output is a map with the surrounding environment information mapped on it.

[1287] Step 4:

[1288] The user visually checks the surrounding environment information on the device and sets evaluation criteria. For example, they set "specific product category" or "store congestion level." These evaluation criteria are sent from the device to the server. The input is the user-set evaluation criteria, and the output is the evaluation criteria data sent to the server.

[1289] Step 5:

[1290] The server runs an evaluation algorithm based on the evaluation criteria set by the user, scores the usability of the surrounding environment, and sends the score to the user's device. The input is the evaluation criteria and surrounding environment information, and the output is the calculated usability score.

[1291] Step 6:

[1292] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device. The input is past data and an evaluation algorithm, and the output is future prediction information.

[1293] Step 7:

[1294] The device uses a camera and microphone to collect the user's emotional data, including facial expressions and vocal tones. The collected data is sent to a server. The input is the user's emotional data, and the output is the emotional data sent to the server.

[1295] Step 8:

[1296] The server uses an emotion engine to analyze the user's emotional state and automatically adjusts the evaluation criteria based on the emotional data. For example, if a user expresses high satisfaction with a particular product, it increases the weighting of that product category. The input is emotional data, and the output is the adjusted evaluation criteria.

[1297] Step 9:

[1298] The server uses generative AI to make optimal product suggestions to customers based on emotional data and real-time location information. Product suggestions and navigation information are sent to the device in real time, allowing users to easily access the desired products. The input is emotional state and real-time location information, and the output is product suggestions and navigation information.

[1299] Step 10:

[1300] Users use smart glasses or terminals to check the suggested products and move around the store. The server collects user behavior data in real time and maintains a loop throughout the system. The input is user behavior data, and the output is continuous data collection and improvement information.

[1301] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1302] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1303] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1304] [Fourth embodiment]

[1305] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1306] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1307] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1308] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1309] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1310] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1311] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1312] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1313] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1314] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1315] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1316] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1317] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1318] The present invention provides a system for efficiently evaluating the surrounding environment and convenience when selecting a real estate property, and for predicting the future surrounding environment. The following describes an embodiment of the present invention.

[1319] System configuration

[1320] The system is primarily composed of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, running the evaluation algorithm, and training and running the generative AI. The terminal allows users to input information and displays the results. Users input property addresses, set evaluation criteria, and check the results.

[1321] Program processing

[1322] Information collection and database construction

[1323] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[1324] Mapping function on the map

[1325] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[1326] Evaluation based on preferences and priorities

[1327] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1328] Generate future prediction maps

[1329] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[1330] Specific examples

[1331] For example, suppose User A is considering purchasing a new home. User A enters the address of a property of interest on their device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[1332] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. Based on this, the server calculates the property's convenience score and displays it to User A.

[1333] Furthermore, the server uses the generation AI to predict the future of the property's surroundings, providing information such as when new commercial facilities are planned to be built or when new train stations are scheduled to open. Based on this information, User A can select a property taking into account future convenience.

[1334] The present invention is a system that efficiently executes this series of processes and supports the user in selecting the most suitable real estate property.

[1335] The processing flow will be explained below.

[1336] Step 1:

[1337] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[1338] Step 2:

[1339] The server cleans the collected data, removing duplicates and errors.

[1340] Step 3:

[1341] The server converts the cleaned data into a unified format and stores it in a central database.

[1342] Step 4:

[1343] The user uses the terminal to input the address of the property.

[1344] Step 5:

[1345] The server converts the address information into latitude and longitude information using a geographic information API.

[1346] Step 6:

[1347] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[1348] Step 7:

[1349] The server maps the acquired information about nearby facilities on a map using a map API.

[1350] Step 8:

[1351] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[1352] Step 9:

[1353] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[1354] Step 10:

[1355] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[1356] Step 11:

[1357] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[1358] Step 12:

[1359] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[1360] Step 13:

[1361] The server maps the future prediction information onto a map using a map API.

[1362] Step 14:

[1363] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[1364] Example 1

[1365] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1366] Conventional real estate property selection systems do not adequately evaluate the surrounding environment and convenience of properties, and do not provide enough information to support users in selecting the appropriate property. In addition, there is no method to predict future surrounding environments, making it difficult to select properties that take future changes in convenience into account. This poses a challenge, as it is difficult for users to obtain sufficient information to select the optimal property.

[1367] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1368] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting it into a unified format and storing it in a database, means for converting property location information entered by a user into geographic coordinate information, means for acquiring facility information around the property from the database based on the geographic coordinate information, means for mapping and displaying the acquired surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generative AI model, and means for displaying the future prediction information on a map. This allows a user to select the optimal property based on multifaceted information including detailed information about the surrounding environment and future predictions.

[1369] "Information about surrounding facilities" is information about all facilities related to daily life, such as schools, supermarkets, hospitals, stations, and parks, that exist around the property.

[1370] "Means of collection" refers to the technology and methods for automatically obtaining the desired data from data sources such as the Internet.

[1371] "Cleaning means" refers to operations or processes used to remove duplication and errors from collected data and improve the quality of the data.

[1372] A "means for converting into a unified format" is a method for converting data of different formats or structures into a consistent format.

[1373] "Means for storing data in a database" refers to a method for registering data in a database system so that the data can be managed efficiently and accessed quickly when needed.

[1374] "Means for converting into geographic coordinate information" refers to technology for converting location information such as addresses into geographic coordinate information such as latitude and longitude.

[1375] The "means for acquiring facility information" refers to a technique or method for searching and extracting related surrounding facility information from a database based on specified geographic coordinate information.

[1376] "Means for mapping and displaying on a map" refers to technology for arranging acquired information on a map in a visually easy-to-understand manner and displaying it to the user.

[1377] A "means for evaluating convenience" is a method for evaluating the convenience of the surrounding environment of a property as a numerical value or score based on criteria set by the user.

[1378] "Historical data analysis methods" are techniques and methods for statistically analyzing and extracting information from all previously collected and stored data sets.

[1379] "Means for generating future prediction information using a generative AI model" refers to a technology that uses a generative AI model to predict future changes in the surrounding environment based on past data and current trends.

[1380] "Means for displaying future prediction information on a map" refers to technology for visually displaying future information predicted by a generative AI model on a map.

[1381] The embodiment of the present invention is a system that evaluates the surrounding environment and convenience, and also predicts the future surrounding environment. This system is mainly composed of three entities: a server, a terminal, and a user. The specific configuration and operation of the system are described below.

[1382] System Configuration

[1383] The system consists of three components: a server, a terminal, and a user. The server is responsible for collecting information on nearby facilities, cleaning the data, managing the database, running the evaluation algorithm, and training and running the generative AI model. The terminal is used by users to input information and display the results. Users input property addresses, set evaluation criteria, and check the results.

[1384] Hardware and software used

[1385] Hardware:

[1386] Server: Use a high-performance server machine

[1387] Devices: personal computers, tablets, smartphones, etc.

[1388] software:

[1389] Data collection: Python's BeautifulSoup, Selenium

[1390] Database: MySQL, PostgreSQL

[1391] Geographical information API: Google Maps API, Geocoding API

[1392] Data Cleaning: Pandas

[1393] Generative AI models: GPT-3, BERT, etc.

[1394] Program processing

[1395] The server first scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is then cleaned to remove duplicates and errors, and the data is then converted into a unified format and stored in a central database.

[1396] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[1397] Furthermore, the user sets evaluation criteria on their device. For example, they can set "proximity to schools" and "convenience of public transportation" as important items. The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1398] The server then analyzes past data and current trends and uses a generative AI model to predict the future surrounding environment. This includes plans for commercial development and new transportation infrastructure. The prediction results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[1399] Specific examples

[1400] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device. The server converts the address into latitude and longitude, obtains information about nearby schools, supermarkets, hospitals, stations, parks, etc., and displays it on a map. User A can check the surrounding environment of the property while looking at the map.

[1401] Next, User A sets evaluation criteria. For example, he or she may set that "distance to the nearest station," "proximity to schools," and "presence of parks" are important. The server calculates the property's convenience score based on this and displays it to User A.

[1402] Furthermore, the server uses the generative AI model to predict the future of the area around the property, providing information such as when new commercial facilities are planned to be built and when new transportation infrastructure is planned to be developed. Based on this information, User A can select a property taking into account future convenience.

[1403] Prompt Sentence Examples

[1404] "I'm looking for real estate around Shin-Kamagaya Station. The key evaluation criteria are distance to the nearest station, proximity to schools, and access to hospitals. I'd also like to know if there are any plans for new commercial facilities or transportation infrastructure in the future."

[1405] In this way, the system of the present invention integrates and provides a variety of information to assist the user in selecting the most suitable real estate property.

[1406] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1407] Program processing flow

[1408] Step 1: Scraping the data

[1409] The server scrapes information about nearby facilities from the internet, using Python's BeautifulSoup and Selenium libraries.

[1410] Input: List of target website URLs

[1411] Data processing: HTML analysis, extraction of necessary data (school, supermarket, hospital, station, park name, address, contact details, etc.)

[1412] Output: Raw data list (extracted information on nearby facilities)

[1413] Step 2: Cleaning the data

[1414] The server uses the Pandas library to clean the scraped data.

[1415] Input: Raw data list (extracted surrounding facility information)

[1416] Data processing: Removing duplicate data, correcting outliers, and filling in missing data

[1417] Output: Cleaned data

[1418] Step 3: Convert data format and save to database

[1419] The server converts the cleaned data into a unified format (e.g., CSV, JSON) and stores it in a database.

[1420] Input: Cleaned data

[1421] Data processing: Conversion to a unified format

[1422] Output: Data stored in a database

[1423] Step 4: Enter the property address

[1424] The user inputs the address of the property into the input form on the terminal.

[1425] Input: Property address

[1426] Output: Data sent to the server (property address)

[1427] Step 5: Convert address to latitude and longitude

[1428] The server uses the Geocoding API to convert the entered property address into latitude and longitude information.

[1429] Input: Property address

[1430] Data calculation: Latitude and longitude conversion using Geocoding API

[1431] Output: Latitude and longitude information

[1432] Step 6: Obtaining information about nearby facilities

[1433] The server searches the database for information on nearby facilities based on the property's latitude and longitude information.

[1434] Input: Latitude and longitude information

[1435] Data search: Search for nearby facilities using database queries

[1436] Output: List of nearby facilities

[1437] Step 7: Mapping information onto a map

[1438] The server maps the acquired information about nearby facilities onto a map using the Google Maps API.

[1439] Input: List of nearby facilities

[1440] Data calculation: Mapping processing using Google Maps API

[1441] Output: Map data (surrounding facility information mapped)

[1442] Step 8: Display the map

[1443] The server transmits the mapped map data to the terminal.

[1444] Input: Map data

[1445] Output: Data sent to the device (map data)

[1446] The terminal displays the received map data to the user, allowing the user to visually check the surrounding environment of the property.

[1447] Step 9: Set evaluation criteria

[1448] The user sets evaluation criteria on the terminal, such as "distance to the nearest station" or "proximity to schools."

[1449] Input: User-defined criteria

[1450] Output: Data sent to the server (evaluation criteria)

[1451] Step 10: Run the evaluation algorithm and score

[1452] The server runs a rating algorithm based on the rating criteria set by the user.

[1453] Input: Evaluation criteria, information on nearby facilities

[1454] Data calculation: Score calculation using weighting algorithm

[1455] Output: Usability score

[1456] Step 11: Displaying the score to the user

[1457] The server transmits the calculated usability score to the user's terminal.

[1458] Input: Usability score

[1459] Output: Data sent to the device (convenience score)

[1460] The terminal displays the received score to the user, allowing the user to check the convenience of each property.

[1461] Step 12: Historical data and trend analysis

[1462] The server analyzes historical data and current trend data.

[1463] Input: Historical data, trend data

[1464] Data calculation: data analysis, trend analysis

[1465] Output: Trend information, analysis results

[1466] Step 13: Generative AI predicts the future

[1467] The server uses a generative AI model (e.g., GPT-3 or BERT) to predict future surroundings.

[1468] Input: Historical data, trend information

[1469] Data Computation: Predicting the Future with Generative AI Models

[1470] Output: Future prediction information

[1471] Step 14: Map mapping and display of prediction results

[1472] The server uses a map API to map the future prediction data created by the generative AI model onto a map.

[1473] Input: Future prediction information

[1474] Data calculation: Mapping processing using map API

[1475] Output: Predicted map data

[1476] The server transmits the predicted map data to the terminal.

[1477] Input: Predicted map data

[1478] Output: Data sent to the device (predictive map data)

[1479] The terminal displays the received predicted map data to the user, who can then select a property based on this future prediction information, taking into account the future environment.

[1480] (Application example 1)

[1481] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1482] Conventional real estate property selection systems have difficulty effectively evaluating the surrounding environment and convenience of a property, and lack the ability to predict future surrounding conditions. Furthermore, users must actually visit the property to view it, making it difficult to efficiently select a property. The present invention aims to solve these problems by providing a system that allows users to view properties in a virtual space, evaluate the surrounding environment, and check future prediction information.

[1483] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1484] In this invention, the server includes means for collecting surrounding facility information, means for cleaning the collected surrounding facility information, converting the collected information into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving facility information around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved surrounding facility information on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information around the property using a generation AI, means for displaying the future prediction information on a map, means for allowing a user to view the property in a virtual space, and means for the user to check the surrounding facility information and future predictions in the virtual space. This allows a user to view the property in a virtual space while centrally checking detailed information about the surrounding environment and predictions of future environmental changes.

[1485] "Nearby facility information" is information about facilities such as schools, supermarkets, hospitals, stations, and parks that exist around the property.

[1486] "Cleaning" is the process of removing duplication and errors from collected data and converting the data into a unified format.

[1487] "Latitude and longitude information" refers to coordinate information that indicates a point on the Earth, and is used to indicate the specific location of a property.

[1488] A "database" is an electronic storage system for efficiently storing, retrieving, and managing data.

[1489] "Mapping" is the visualization and display of specific information on a map.

[1490] "Evaluation criteria" are a set of factors that users use as criteria when evaluating the convenience of a property, and include, for example, "proximity to schools" and "convenience of public transportation."

[1491] "Generative AI" is an artificial intelligence model that learns from large amounts of data to predict future trends and patterns.

[1492] "Future prediction information" is information generated by the generating AI, which analyzes past data and predicts future changes in the surrounding environment and plans for new facility construction.

[1493] "Virtual space" refers to a virtual three-dimensional space generated using computer technology, which is used by users to view properties.

[1494] A "viewing" refers to a user being able to check the interior and surroundings of a property through a virtual space without actually visiting the property.

[1495] "Convenience" is an indicator that evaluates the degree to which the surrounding environment of a property provides convenience for daily life.

[1496] The present invention is a system that allows a user to view a real estate property in a virtual space and evaluate the surrounding environment and future changes to the environment.

[1497] System configuration

[1498] The system is configured using the following hardware and software.

[1499] 1. Hardware:

[1500] server

[1501] Devices (smartphones, smart glasses, head-mounted displays)

[1502] 2. Software:

[1503] API (geographical information API, map API)

[1504] Machine learning library (scikit-learn)

[1505] Database Management Systems

[1506] Visualization tool (folium)

[1507] Program processing description

[1508] The server first scrapes information about nearby facilities from the internet, cleans the data, converts it into a unified format, and stores it in a database, ensuring that the data is free of duplicates and errors.

[1509] Next, when the user enters the property address using the terminal, the server converts the address into latitude and longitude information using the geographic information API. An example of a specific prompt is as follows:

[1510] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[1511] The server retrieves information about nearby facilities from the database based on this latitude and longitude information and maps it on a map using a map API, allowing users to visually check the environment around the property.

[1512] Users can also set evaluation criteria on their devices, such as "distance to the nearest station," "proximity to schools," and "presence of parks" as important factors. The server runs an evaluation algorithm based on these criteria and scores the convenience of the property. The calculated score is sent to the user's device, allowing them to check the convenience of the property.

[1513] Furthermore, the server uses generative AI to predict the future surrounding environment. It analyzes past data and current trends to predict, for example, new commercial facility development plans and transportation infrastructure improvement plans. This future prediction information is also mapped on a map, which users can refer to.

[1514] Users can use a smartphone, smart glasses, or a head-mounted display to virtually view a property, allowing them to see the interior and surroundings of the property in real time while simultaneously viewing future predictions.

[1515] As a concrete example, consider user B considering purchasing a new property and using the following prompt:

[1516] Enter your address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"

[1517] This allows User B to view the property in virtual space while checking the surrounding environment and future forecast information in one place. This system allows users to make efficient and informative real estate selections.

[1518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1519] Step 1:

[1520] A user uses a terminal to enter a property address using a prompt, for example, "Please enter the address: "1-2-3 Jingumae, Shibuya-ku, Tokyo"".

[1521] Step 2:

[1522] The server receives the address entered by the user and converts it into latitude and longitude information using a geographic information API (such as Google Maps API). This allows specific location information to be obtained. The input is an address, and the output is latitude and longitude information.

[1523] Step 3:

[1524] The server searches the database for information on nearby facilities based on the acquired latitude and longitude information. This information includes schools, supermarkets, hospitals, stations, parks, etc. The input is latitude and longitude information, and the output is information on nearby facilities.

[1525] Step 4:

[1526] The server cleans the acquired nearby facility information, removes duplicates and errors, and converts it into a unified format. This information is then stored in a database. The input is nearby facility information, and the output is the cleaned data.

[1527] Step 5:

[1528] The server maps the information about the surrounding facilities after cleaning on a map using a map API (e.g., Google Maps API). This allows users to visually check the surrounding facilities. The input is the cleaned data, and the output is the information mapped on the map.

[1529] Step 6:

[1530] The user sets the evaluation criteria on the terminal. For example, they can select "distance to the nearest station," "proximity to schools," "presence of parks," etc. This allows them to individually evaluate convenience. The input is the evaluation criteria, and the output is the set evaluation criteria information.

[1531] Step 7:

[1532] The server runs an evaluation algorithm based on the set evaluation criteria and scores the convenience of the area around the property. This quantifies the convenience of the property. The input is evaluation criteria information and information on surrounding facilities, and the output is a convenience score.

[1533] Step 8:

[1534] The server analyzes past data and uses a generative AI model to generate future predictions for the surrounding area, including plans for new commercial developments and transportation infrastructure improvements. The input is past data, and the output is future predictions.

[1535] Step 9:

[1536] The server then uses the map API to map the generated future prediction information and sends it to the device, allowing the user to check the future surroundings. The input is the future prediction information, and the output is the future prediction information mapped on the map.

[1537] Step 10:

[1538] Users can view a property in a virtual space and simultaneously check the surrounding environment and future forecast information using a smartphone, smart glasses, or a head-mounted display, enabling a more comprehensive property evaluation. The input is the start of the virtual viewing, and the output is visual information in the virtual space.

[1539] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1540] The present invention is a system that efficiently evaluates the surrounding environment and convenience when selecting a real estate property, and furthermore predicts the future surrounding environment, as well as a system that recognizes the user's emotions and automatically adjusts the evaluation criteria based on the emotions.

[1541] System configuration

[1542] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[1543] Program processing

[1544] Information collection and database construction

[1545] The server scrapes information about nearby facilities from the internet, including schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned to remove duplicates and errors, then converted into a unified format and stored in a central database.

[1546] Mapping function on the map

[1547] The user uses the device to input the address of the property they are interested in. The server converts this address into latitude and longitude information using a geographic information API. The server then searches and retrieves information about nearby facilities from a database based on this latitude and longitude information. The retrieved information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment of the property through the device.

[1548] Evaluation based on preferences and priorities

[1549] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1550] Generate future prediction maps

[1551] The server analyzes past data and current trends and uses generative AI to predict the future surrounding environment. This includes commercial facility development plans and plans for new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this future prediction information, users can select properties taking into account the future environment.

[1552] Emotion recognition and auto-tuning

[1553] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, tone of voice, etc.). The server uses an emotion engine to analyze this data and recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[1554] Automatic adjustment of evaluation criteria based on emotions

[1555] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data. For example, if the user expresses strong satisfaction with the proximity of schools, the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with the convenience of public transportation, the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[1556] Specific examples

[1557] For example, suppose User A is considering purchasing a new home. User A enters the address of the property he or she is interested in on his or her device and checks information about the surrounding area. User A also sets the proximity to schools, convenience of public transportation, and the presence of parks as important criteria.

[1558] The server evaluates the user based on this and provides a convenience score. At the same time, the device collects user A's facial expressions and tone of voice and sends them to the server as emotion data. The server then analyzes user A's emotions using its emotion engine and recognizes that user A is highly satisfied with the proximity of the school.

[1559] Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weight of proximity to schools. This allows User A to select properties based on the most important points.

[1560] By efficiently executing this series of processes, the present invention realizes a system that supports users in selecting the most suitable real estate property. Furthermore, by utilizing an emotion engine, user satisfaction can be further increased.

[1561] The processing flow will be explained below.

[1562] Step 1:

[1563] The server scrapes information about nearby facilities (schools, supermarkets, hospitals, stations, parks, etc.) from the Internet.

[1564] Step 2:

[1565] The server cleans the collected data, removing duplicates and errors.

[1566] Step 3:

[1567] The server converts the cleaned data into a unified format and stores it in a central database.

[1568] Step 4:

[1569] The user uses the terminal to input the address of the property.

[1570] Step 5:

[1571] The server converts the address information into latitude and longitude information using a geographic information API.

[1572] Step 6:

[1573] The server searches for and obtains information about nearby facilities from a central database based on latitude and longitude information.

[1574] Step 7:

[1575] The server maps the acquired information about nearby facilities on a map using a map API.

[1576] Step 8:

[1577] The server transmits the mapping results to the terminal, and the user checks the map on the terminal.

[1578] Step 9:

[1579] The user sets evaluation criteria (e.g., proximity to schools, convenience of public transportation, etc.) on the terminal.

[1580] Step 10:

[1581] The server runs a rating algorithm based on the user's settings to calculate a usability score.

[1582] Step 11:

[1583] The server transmits the calculated score to the terminal, and the user checks the score on the terminal.

[1584] Step 12:

[1585] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.).

[1586] Step 13:

[1587] The server uses an emotion engine to analyze the collected emotion data and recognize the user's emotional state.

[1588] Step 14:

[1589] The server automatically adjusts the user's evaluation criteria based on the recognized emotion data.

[1590] Step 15:

[1591] The server analyzes past data and uses AI to generate future predictions for the area around the property.

[1592] Step 16:

[1593] The server maps the future prediction information onto a map using a map API.

[1594] Step 17:

[1595] The server transmits the future prediction map to the terminal, and the user checks the future prediction information on the terminal.

[1596] Specific examples

[1597] For example, suppose user A is considering purchasing a new home. User A enters the address of the property he or she is interested in on the device and checks information about the surrounding area.

[1598] Next, User A sets evaluation criteria. For example, he or she may set "proximity to schools," "convenience of public transportation," and "presence of parks" as important items. The server evaluates the properties based on these criteria and provides a convenience score.

[1599] At the same time, the device collects user A's facial expressions and voice tone and sends them as emotion data to the server. The server then uses an emotion engine to analyze this data and determine whether user A is satisfied with certain criteria. For example, if user A is satisfied with the proximity of schools, the server will assign a higher weight to this criterion.

[1600] The server automatically adjusts the weighting of the evaluation criteria to emphasize the points that are most important to User A. This allows User A to select the optimal property based on their own feelings and preferences. The server also uses generative AI to predict the future and provides planning information for new commercial facilities and transportation infrastructure. This allows User A to select a property taking future convenience into consideration.

[1601] Example 2

[1602] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1603] Existing real estate property selection systems are insufficient in providing sufficient information and responding to individual user needs when evaluating the convenience of the surrounding area or predicting future environmental changes. Furthermore, they lack the functionality to reflect changes in user emotions and preferences in real time, which limits their ability to support optimal property selection.

[1604] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1605] In this invention, the server includes means for collecting information on surrounding facilities, means for cleaning the collected information on surrounding facilities, converting the collected information on surrounding facilities into a unified format, and storing the information in a database, means for converting a property address entered by a user into latitude and longitude information, means for retrieving information on facilities around the property from a database based on the latitude and longitude information, means for mapping and displaying the retrieved information on surrounding facilities on a map, means for evaluating the convenience of the area around the property based on user settings, means for analyzing past data and generating future prediction information for the area around the property using a generation AI, means for displaying the future prediction information on a map, means for collecting user emotion data, means for analyzing the collected emotion data and recognizing the user's emotional state, and means for automatically adjusting evaluation criteria based on the recognized emotional state. This allows users to check convenience and future prediction information in real time when selecting a property, and further enables them to select the optimal property that reflects feedback based on their own emotions.

[1606] "Nearby facility information" is data about public and commercial facilities around the property, such as schools, supermarkets, hospitals, stations, and parks.

[1607] "Cleaning" is the process of removing redundancies and errors from collected data and formatting it accurately and consistently.

[1608] "Unified format" refers to converting data collected from different sources into the same format to ensure consistency.

[1609] A "database" is a system in which collected data can be efficiently stored, managed, and retrieved.

[1610] "Latitude and longitude information" is coordinate data that indicates a geographical location and is used to identify a specific point.

[1611] "Generative AI" refers to artificial intelligence technology that makes future predictions based on past data and trends.

[1612] "Emotion data" is information about the user's emotional state obtained from facial expressions, tone of voice, and the like.

[1613] "Evaluation criteria" refers to the points or items that are important when evaluating property options, such as proximity to schools or public transportation.

[1614] This invention is a system that can efficiently evaluate the surrounding environment and convenience when selecting a real estate property, and can also predict the future surrounding environment. The invention also combines a function that recognizes the user's emotions and automatically adjusts the evaluation criteria based on those emotions. Specific embodiments for implementing the invention are described below.

[1615] System configuration

[1616] The system mainly consists of three components: a server, a terminal, and a user. The server is responsible for data collection, cleaning, database management, execution of evaluation algorithms, training and execution of generative AI, emotion recognition and analysis using an emotion engine, and automatic adjustment of evaluation criteria. The terminal allows users to input information, displays results, and collects emotional data. The user inputs property addresses, sets and confirms evaluation criteria, and interacts based on their emotional state.

[1617] Information collection and database construction

[1618] The server uses Python's BeautifulSoup and Scrapy scraping libraries to collect information on nearby facilities from the internet. This includes schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas and Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[1619] Mapping function on the map

[1620] The user uses a smartphone or PC to input the address of a property of interest into the device. The server converts this address into latitude and longitude information using a Geocoding API (for example, Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, maps the acquired information on a map using a map API, and sends it to the device. This allows the user to visually check the surrounding environment of the property.

[1621] Evaluation based on preferences and priorities

[1622] Users use the device interface to set evaluation criteria such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding area of ​​the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1623] Generate future prediction maps

[1624] The server analyzes past data and current trends based on a database and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. This includes plans for commercial facility development and new transportation infrastructure. The predicted results are mapped on a map and sent to the user's device. Based on this information, users can select properties taking into account the future environment.

[1625] Emotion recognition and auto-tuning

[1626] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.). The server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state. For example, when a user checks a property's convenience score, it determines whether the user is satisfied.

[1627] Automatic adjustment of evaluation criteria based on emotions

[1628] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the server increases the weighting of that criterion. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the server decreases the weighting of that criterion. This adjustment simplifies the process of setting evaluation criteria and enables the user to select a property that satisfies them more.

[1629] Specific examples

[1630] For example, suppose User A is considering purchasing a new home. User A enters the address of a property they are interested in on their device and checks information about the surrounding area. User A also sets "proximity to schools," "convenience of public transportation," and "presence of parks" as important criteria. The server evaluates the properties based on this and provides a convenience score. At the same time, the device collects User A's facial expressions and voice tone and sends them to the server as emotion data. The server uses an emotion engine to analyze User A's emotions and recognizes that User A is highly satisfied with the proximity to schools. Based on this evaluation, the server automatically adjusts the weighting of User A's important points, increasing the weighting of proximity to schools. This allows User A to select a property based on the most important points.

[1631] Prompt Sentence Examples

[1632] "Please rate the surrounding environment and convenience of a property based on the following conditions: Address: 2-8-1 Nishi-Shinjuku, Shinjuku-ku, Tokyo. Important points to consider are proximity to schools, convenience of public transportation, and the presence of parks. Furthermore, please automatically adjust the evaluation criteria based on sentiment data provided by the user."

[1633] The above is a specific embodiment for carrying out the present invention. This system utilizes advanced technology to assist users in selecting the most suitable real estate property.

[1634] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1635] Step 1: Collecting information and building a database

[1636] The server scrapes information about nearby facilities from the internet using Python scraping libraries such as BeautifulSoup and Scrapy. The collected data includes information about schools, supermarkets, hospitals, train stations, parks, etc. The collected data is cleaned using Pandas or Numpy to remove duplicates and errors. The data is then converted into a unified format and stored in a database such as PostgreSQL.

[1637] Input: Information about nearby facilities on the Internet

[1638] Data processing: scraping, data cleaning, format conversion

[1639] Output: Information on nearby facilities stored in the database

[1640] Specific operation: The server periodically runs scripts to collect information on the Internet and performs various data processing to ensure the quality of the collected data.

[1641] Step 2: Mapping function on the map

[1642] The user uses a device to input the address of a property they are interested in. The server converts this address into latitude and longitude information using a Geocoding API (e.g., Google Maps API). The server then searches a database for information about nearby facilities based on this latitude and longitude information, and maps the retrieved information on a map using a map API. Finally, this map information is sent to the user's device.

[1643] Input: The property address entered by the user

[1644] Data calculation: address latitude / longitude conversion, database search, map mapping

[1645] Output: Information about nearby facilities mapped on a map

[1646] Specific operation: The user enters an address into the input field on the device, and the server uses that information to identify the location using a map API and visualizes the surrounding information.

[1647] Step 3: Evaluate based on preferences and priorities

[1648] Users set evaluation criteria on their devices. For example, they can set priorities such as "proximity to schools" and "convenience of public transportation." The server runs an evaluation algorithm based on these criteria and scores the convenience of the area around the property. The calculated score is sent to the user's device, allowing the user to check the convenience of the property.

[1649] Input: User-defined evaluation criteria

[1650] Data calculation: Scoring by evaluation algorithm

[1651] Output: User experience score sent to the user device

[1652] Specific operation: The user selects the points of importance on the device's rating setting screen, and the server evaluates the distance and accessibility of each facility based on those criteria.

[1653] Step 4: Generate a future prediction map

[1654] The server retrieves past data and current trends from a database such as MongoDB and uses a generative AI model (e.g., a time-series forecasting model) to predict the future surrounding environment. Predictions include commercial facility development plans and new transportation infrastructure construction schedules. These predictions are visualized using a map API and sent to the user's device.

[1655] Input: Historical data and trend information

[1656] Data Computation: Predicting the Future with Generative AI

[1657] Output: Future prediction information mapped on a map

[1658] How it works: The server retrieves the necessary information from the database, trains a generative AI model to make future predictions, and visually displays the results on a map.

[1659] Step 5: Emotion Recognition and Auto-Tuning

[1660] The device uses a camera and microphone to collect the user's emotional data (e.g., facial expressions, voice tone, etc.), and the server analyzes this data using an emotion engine (e.g., Google Cloud Vision API or Amazon Rekognition) to recognize the user's emotional state.

[1661] Input: Emotion data collected by camera and microphone

[1662] Data Computation: Emotion Analysis with Emotion Engine

[1663] Output: Recognized emotional state of the user

[1664] Specific operation: The device captures the user's facial expressions and voice, sends them to the server in real time, and analyzes the information to evaluate the user's emotions.

[1665] Step 6: Automatic adjustment of evaluation criteria based on emotions

[1666] The server automatically adjusts the user's evaluation criteria based on the recognized emotional data. For example, if the user expresses satisfaction with "proximity to schools," the weighting of that criterion will be increased. On the other hand, if the user expresses dissatisfaction with "convenience of public transportation," the weighting of that criterion will be decreased. This adjustment is made automatically, and the results are reflected on the user's device.

[1667] Input: Perceived emotional state of the user

[1668] Data calculation: Automatic adjustment of evaluation criteria

[1669] Output: Results reflecting the adjusted evaluation criteria

[1670] Specific operation: The server dynamically resets the evaluation criteria based on the results of sentiment analysis and makes suggestions to improve user satisfaction.

[1671] (Application example 2)

[1672] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1673] Conventional surrounding environment evaluation systems evaluate properties based only on current facility information, making it difficult to predict future changes in the environment. Furthermore, there was no system that adjusted evaluation criteria based on the user's emotional state, making it difficult to select properties and products that reflected the user's true satisfaction. Furthermore, there was a lack of real-time product suggestions and navigation to improve the customer experience in actual stores.

[1674] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting surrounding environment information, means for cleaning the collected surrounding environment information, converting it into a unified format, and storing it in a database, means for converting the address of a location entered by the user into location information, means for retrieving surrounding environment information from the database based on the location information, means for visually mapping and displaying the retrieved surrounding environment information, means for evaluating the convenience of the surrounding environment based on the user's settings, means for analyzing past data and generating future prediction information about the surrounding environment using a generating AI, means for displaying the future prediction information on a map, means for recognizing and analyzing the customer's emotional state, means for automatically adjusting evaluation criteria based on the customer's emotional state, means for using a generating AI to suggest the customer's next action and products, means for identifying the customer's location information in a store and providing navigation to the most suitable product, and means for adjusting the weighting of product categories based on the customer's emotional state. This enables future environment predictions based on past data and emotional information, thereby realizing property selection and product suggestions that will satisfy the user. The in-store customer experience will also be improved, offering real-time product suggestions and navigation.

[1675] "Nearby Environment Information" refers to information about the surroundings of a specific place or property that a user is interested in. This includes information about facilities such as shops, schools, public transportation, and medical facilities, as well as public safety and local characteristics.

[1676] "Database" means a collection of collected information that is organized, stored, and managed so that it can be efficiently searched and used when needed.

[1677] "Location Information" means geographical data such as latitude and longitude that indicates a specific location. This data is obtained using technologies such as GPS and beacons.

[1678] "Emotional state" refers to the psychological state of a user analyzed from facial expressions, tone of voice, etc. This includes states such as satisfaction, dissatisfaction, excitement, and relaxation.

[1679] "Navigation" means guidance that provides a route or direction for a user to reach a destination, including map displays and audio guidance.

[1680] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to predict and classify future outcomes based on large amounts of data, including neural networks and deep learning.

[1681] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to estimate their emotional state. It uses machine learning and computer vision algorithms.

[1682] "Future forecast information" refers to information about future surrounding environments and market trends that is generated by analyzing past data and current trends.

[1683] "Product Recommendations" means the presentation of recommended products and services based on a user's preferences and behavioral data, including personalized recommendations.

[1684] "Weighting" refers to the assignment of greater or lesser importance to a particular factor in determining the evaluation criteria, which is reflected in a numerical score or ranking.

[1685] The present invention is a system that improves customer experience in shopping malls and large brick-and-mortar stores, and is composed of three entities: a server, a terminal, and a user.

[1686] System configuration

[1687] Gathering information on the surrounding environment

[1688] The server scrapes surrounding environment information from the internet, cleans it, removes duplicates and errors, converts it into a unified format, and stores it in a central database.

[1689] Obtaining location information

[1690] When a user enters the address of a place of interest into their device, the server converts the address into location information (latitude and longitude) using a geographic information API.

[1691] Mapping of surrounding environment information

[1692] The server retrieves information about the surrounding environment from a database based on the acquired location information. This information is mapped on a map using a map API and sent to the device. The user can then visually check the surrounding environment through the device.

[1693] Usability evaluation

[1694] The user sets evaluation criteria on their device, such as "specific product category" or "store congestion level." The server runs an evaluation algorithm based on these criteria and scores the convenience of the surrounding environment. The calculated score is sent to the user's device, allowing them to check the convenience.

[1695] Generating future prediction information

[1696] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device, allowing the user to select the optimal location and product based on the future environment.

[1697] Emotion recognition and evaluation criteria adjustment

[1698] The device collects emotional data from the user using a camera and microphone. The server analyzes this data with an emotion engine to recognize the user's emotional state. For example, it analyzes facial expressions and tone of voice while the user is reviewing product recommendations to determine whether the user is satisfied.

[1699] Product suggestions and navigation

[1700] The server automatically adjusts evaluation criteria based on the customer's emotional state and makes optimal product recommendations. It also identifies the customer's current location in the store in real time using GPS information and Bluetooth beacons, providing navigation information so that customers can easily access the products they are looking for.

[1701] Specific examples

[1702] For example, when a customer visits a brick-and-mortar shopping mall, they put on the smart glasses and input the product categories they are interested in (e.g., clothing, home appliances). The server retrieves information about related products based on those interests and displays it on the smart glasses along with navigation information. If, after analyzing the customer's facial expressions and tone of voice, the server finds that the customer is satisfied with the reviews of a particular product, it automatically adjusts the weighting of that category and determines the next product to be prioritized.

[1703] Prompt Sentence Examples

[1704] "To predict future purchasing trends and provide the best customer experience, we use sales data and customer sentiment data from the past three years to determine the next product and promotion strategy we should offer."

[1705] As described above, the present invention provides a concrete means for realizing a surrounding environment evaluation system, which allows users to select properties and products that will give them greater satisfaction, and also significantly improves the customer experience in stores.

[1706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1707] Step 1:

[1708] The server scrapes surrounding environment information from the internet. For example, it collects information on facilities such as shops, schools, hospitals, and public transportation, cleans it by removing duplicates and errors, and converts it into a unified format. This data is stored in a central database. The input here is raw data from the internet, and the output is the cleaned database.

[1709] Step 2:

[1710] The user inputs the address of a place of interest into the device. The device retrieves this address and sends it to the server. The server uses a geographic information API to convert the address into location information (latitude and longitude). The input is address information, and the output is the location information corresponding to that address.

[1711] Step 3:

[1712] The server searches and retrieves surrounding environment information from a central database based on the acquired location information. The acquired surrounding environment information is mapped on a map using a map API and sent to the device. The input is location information, and the output is a map with the surrounding environment information mapped on it.

[1713] Step 4:

[1714] The user visually checks the surrounding environment information on the device and sets evaluation criteria. For example, they set "specific product category" or "store congestion level." These evaluation criteria are sent from the device to the server. The input is the user-set evaluation criteria, and the output is the evaluation criteria data sent to the server.

[1715] Step 5:

[1716] The server runs an evaluation algorithm based on the evaluation criteria set by the user, scores the usability of the surrounding environment, and sends the score to the user's device. The input is the evaluation criteria and surrounding environment information, and the output is the calculated usability score.

[1717] Step 6:

[1718] The server analyzes past data and current trends and uses a generative AI model to predict future surrounding environment information. The prediction results are mapped on a map and sent to the user's device. The input is past data and an evaluation algorithm, and the output is future prediction information.

[1719] Step 7:

[1720] The device uses a camera and microphone to collect the user's emotional data, including facial expressions and vocal tones. The collected data is sent to a server. The input is the user's emotional data, and the output is the emotional data sent to the server.

[1721] Step 8:

[1722] The server uses an emotion engine to analyze the user's emotional state and automatically adjusts the evaluation criteria based on the emotional data. For example, if a user expresses high satisfaction with a particular product, it increases the weighting of that product category. The input is emotional data, and the output is the adjusted evaluation criteria.

[1723] Step 9:

[1724] The server uses generative AI to make optimal product suggestions to customers based on emotional data and real-time location information. Product suggestions and navigation information are sent to the device in real time, allowing users to easily access the desired products. The input...

Claims

1. A means for collecting information on surrounding facilities; A means to clean the collected information on surrounding facilities, convert it into a unified format, and store it in a database; A means of converting the property address entered by the user into latitude and longitude information, A means for acquiring facility information around the property from a database based on the latitude and longitude information; a means for mapping and displaying the acquired information about surrounding facilities on a map; A means to evaluate the convenience of the surrounding area based on the user's preferences, and A method for analyzing past data and generating future prediction information for the area around the property using AI. A system including means for displaying the future prediction information on a map.

2. 10. The system of claim 1, further comprising means for a user to set evaluation criteria.

3. 10. The system of claim 1, further comprising means for analyzing historical data for training the generative AI.

Images