system

Abstract

To provide a system that provides optimal living spaces that maximize personal growth and happiness. [Solution] A system including a means for inputting user data by a user terminal, a means for receiving user data by a server, a means for preprocessing the received data by the server, a means for analyzing the received data by the server, a means for generating a user personality profile by the server, a means for evaluating potential housing sites and generating recommendations by the server, a means for displaying a list of recommendations by the user terminal, a means for collecting feedback on the recommendations by the user terminal, and a means for analyzing the feedback and improving the algorithm by the server.

Description

[Technical Field]

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

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

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

[0004] In modern society, individuals with diverse lifestyles and personalities have difficulty finding the optimal residential location for themselves. Therefore, there is a need for a system that recommends optimal residential locations based on individual lifestyles and personalities. Furthermore, the market lacks effective tools to maximize personal happiness and growth, and more personalized information is needed to improve user satisfaction. The purpose of this invention is to solve the above problems and provide a system that recommends optimal residential locations for individuals. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a user data input means is provided on the user terminal, allowing the user to input their lifestyle and personality information. Next, a server receives this data and uses data preprocessing means to correct the format and complete missing values. Furthermore, a machine learning model is used to generate a personality profile of the user. Based on this profile, a means is provided for evaluating and recommending optimal housing candidate locations. The recommended candidate locations are displayed on the user terminal, and the user can provide feedback on these candidate locations. This feedback is again analyzed on the server and used to improve the algorithm. This realizes a system that provides optimal residential locations that maximize individual growth and happiness.

[0006] A "user terminal" is an electronic device through which a user inputs data and interacts with the system.

[0007] "User Data" is information entered into the system, including information about the user's lifestyle and personality.

[0008] A "server" is a computer system that receives, processes, and analyzes data from user terminals.

[0009] The "data preprocessing means" is a function that cleanses received user data, converts formats, and fills in missing values.

[0010] "Data analysis means" is a function for analyzing received data and generating a personality profile of the user.

[0011] A "personality profile" is a summary of personal information generated by analyzing a user's lifestyle and personality.

[0012] A "machine learning model" is a type of algorithm used to learn patterns from data and perform analysis and predictions.

[0013] "Potential residences" are recommended residence locations based on the user's lifestyle and personality profile.

[0014] The "recommendation generation means" is a function that matches the user's personality profile with smart city data to create a list of the most suitable housing candidates.

[0015] The "feedback collection means" is a function for collecting evaluations and opinions entered by users regarding recommendations.

[0016] "Algorithm improvement means" is a function that analyzes collected feedback and improves the recommendation algorithm. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

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

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

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

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0032] 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.

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

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0039] Program processing flow

[0040] Data Entry

[0041] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[0042] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, and desired residential conditions (e.g., transportation access, medical facilities, educational institutions, and recreational facilities).

[0043] 3. The device sends these input data to the server.

[0044] Data preprocessing and analysis

[0045] 1. The server receives the received user data, completes missing values, and standardizes the format of the data.

[0046] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[0047] 3. The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[0048] Recommendation generation and display

[0049] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0050] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[0051] 3. The device displays the recommendation list to the user, allowing the user to review it.

[0052] Collecting and analyzing feedback

[0053] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[0054] 2. The terminal transmits the user's feedback data to the server.

[0055] 3. The server analyzes the received feedback data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[0056] Specific examples

[0057] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[0058] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[0059] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[0060] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[0061] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[0062] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[0063] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[0064] Thus, the present invention provides a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing their growth and happiness. This system effectively functions using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] A user logs in to the system by entering their user ID and password on the login screen and clicking the login button.

[0068] Step 2:

[0069] The device sends the login information to the server, which authenticates the login information and returns a success message to the user.

[0070] Step 3:

[0071] The user displays a data entry screen for a residential search, which allows the user to specify a desired location for a job transfer or relocation.

[0072] Step 4:

[0073] Users input their lifestyle (hobbies, work style, sleeping habits, diet, etc.) and desired conditions (transportation access, medical facilities, educational institutions, entertainment facilities, etc.).

[0074] Step 5:

[0075] The terminal transmits the input user data to the server, which then retrieves the user's lifestyle information.

[0076] Step 6:

[0077] The server preprocesses the data it receives, standardizing the data format and filling in missing values. It also detects and removes outliers in the data.

[0078] Step 7:

[0079] The server inputs the pre-processed data into a machine learning model to generate a personality profile of the user, which includes the user's personality traits and lifestyle patterns.

[0080] Step 8:

[0081] The server compares the generated personality profile with the smart city database, evaluates multiple residential candidate locations, and calculates an evaluation score.

[0082] Step 9:

[0083] The server generates a list of potential residential locations, including detailed information about each location (e.g., accessibility, amenities, and environmental safety).

[0084] Step 10:

[0085] The server sends the recommendation list to the terminal.

[0086] Step 11:

[0087] The device displays a list of recommendations to the user, who can then view detailed information about each location and make the best choice.

[0088] Step 12:

[0089] Users enter feedback on the recommendations, including location ratings and additional preferences.

[0090] Step 13:

[0091] The terminal sends the user's feedback to the server.

[0092] Step 14:

[0093] The server receives and analyzes the feedback. The feedback data is used to improve the recommendation algorithm.

[0094] Step 15:

[0095] The server uses the improved algorithm to improve the accuracy of future recommendations, and the user's profile is also re-evaluated.

[0096] In this way, users can find the place to live that best suits their individual lifestyle and personality. The entire system is designed to work together and function effectively.

[0097] Example 1

[0098] 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."

[0099] In modern society, users face difficulties in finding a place to live that best suits their lifestyle and personality. Conventional residential search systems often fail to provide satisfactory results because they make recommendations based only on general criteria, without considering the user's detailed personality and lifestyle. Furthermore, they lack mechanisms for improving the accuracy of recommendations based on user feedback.

[0100] 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.

[0101] In this invention, the server includes means for generating a user's lifestyle and personality profile using a machine learning model, means for generating residential property recommendations based on user data and a city database, and means for improving the algorithm and increasing the accuracy of the recommendations in response to user feedback. This allows users to receive recommendations for optimal residential properties based on their detailed lifestyle and personality, and by incorporating the feedback, more accurate recommendations can be provided to each individual user.

[0102] A "user terminal" is a computing device or communication device used by a user.

[0103] "User data" is information provided by a user, including lifestyle, personality information, and desired conditions.

[0104] A "server" is a central computing device that receives and analyzes user data and generates recommendations.

[0105] The "pre-processing means for received data" is a processing means for complementing missing values ​​and standardizing the format of user data received by the server.

[0106] The "means for analyzing received data" refers to the means by which the server analyzes the pre-processed data and generates a profile of the user.

[0107] A "personality profile" is information that describes a user's lifestyle and personality traits, generated using a machine learning model.

[0108] "Possible residence locations" is a list of residence locations suitable for the user, recommended by the server.

[0109] A "recommendation" is a proposal for the optimal place to live generated by the server based on the user's lifestyle and desired conditions.

[0110] The "means for displaying a list of recommendations" is a means for the user terminal to display a list of candidate housing locations to the user.

[0111] The "feedback collection means" is a means for collecting opinions and evaluations of the recommendations from users.

[0112] The "means for analyzing feedback and improving algorithms" refers to the means by which the server analyzes feedback from users and improves the recommendation algorithm based on the analysis.

[0113] A "machine learning model" is an algorithm and its implementation that learns from data and makes predictions and classifications.

[0114] The "urban database" is a database containing information on potential residential locations, and evaluation criteria include transportation access, the availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0115] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0116] Hardware and Software Use

[0117] The system implementation uses the following hardware and software:

[0118] User terminal: A device used by a user to input data, such as a smartphone or computer.

[0119] Server: A high-performance computing device that preprocesses, analyzes, and generates recommendations from received data.

[0120] Machine learning model: Uses Python's Scikit-learn library to generate a user's lifestyle and personality profile.

[0121] Database: A smart city database will be used to manage information such as transportation access, medical facilities, educational institutions, the availability of entertainment facilities, and safety.

[0122] Communication protocol: HTTPS is used to securely transmit data between the user terminal and the server.

[0123] System operation explanation

[0124] 1. When a user logs in to the system, a data entry screen for residential searches is displayed on the terminal. To log in, the user uses their user ID and password.

[0125] 2. Users input their lifestyle (e.g., "active" or "indoor"), hobbies (e.g., "running" or "reading"), work style (e.g., "remote work" or "office work"), sleep habits (e.g., "night owl" or "early to bed, early to rise"), and diet (e.g., "vegetarian" or "gourmet"), and also select the conditions for their desired place of residence (e.g., transportation access, availability of medical facilities, educational institutions, entertainment facilities, safety, etc.).

[0126] 3. The device sends these input data to the server in real time using HTTPS, which encrypts the data.

[0127] 4. The server receives the received user data and performs data imputation and formatting. For example, if there are missing values, it imputes them using the mean or median. It also standardizes the data format (for example, converting "yes / no" to "1 / 0").

[0128] 5. The server generates a lifestyle and personality profile of the user based on the preprocessed data, which is implemented using a machine learning library such as Scikit-learn in Python.

[0129] 6. The server uses the user's personality profile to run a recommendation algorithm, specifically a recommender system (e.g., collaborative filtering or content-based filtering) to determine the appropriate action.

[0130] 7. The server compares the user profile with the smart city database and generates a list of residential options that best suit the user. For example, it selects areas such as "Toyosu," "Shinagawa," and "Shibuya" from the Tokyo database.

[0131] 8. The server creates a list containing detailed information about the recommended housing candidates (e.g., location of the housing, surrounding facilities, environment, rent, etc.) and sends it to the terminal.

[0132] 9. The device displays this list to the user, allowing the user to check detailed information. For example, it may display a map using the Google (registered trademark) Maps API.

[0133] 10. The user enters feedback on the recommendation through the system. For example, they can enter a rating such as "The Toyosu area is very convenient" or additional preferences such as "I would prefer a place with a little more nature."

[0134] 11. The device transmits these feedback data to the server in real time using a secure communication channel.

[0135] 12. The server analyzes the received feedback data and improves the algorithm based on the analysis results. For example, by analyzing the text data of the feedback using natural language processing (NLP) technology, new user needs can be discovered. Based on the feedback, the server also reevaluates the user's personality profile and improves the accuracy of the system's recommendations.

[0136] Specific examples

[0137] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[0138] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[0139] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[0140] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[0141] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[0142] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[0143] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[0144] Thus, the present invention is a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing the user's growth and happiness. This system functions effectively using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[0145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0146] Step 1:

[0147] The user logs into the system and displays a data entry screen for a residence search on the terminal.

[0148] Input: User ID and password

[0149] Output: Data entry screen

[0150] Specific operation: The user launches a browser or app and enters their user ID and password into the login form. The device receives this and sends it to the authentication server. After successful authentication, a data entry screen for a home search is displayed.

[0151] Step 2:

[0152] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, eating habits, and desired place of residence.

[0153] Input: Lifestyle, hobbies, work style, sleeping habits, diet, desired conditions

[0154] Output: Input data

[0155] Specific operation: The user enters information into each field on the data entry screen (e.g., "Lifestyle: Active," "Hobbies: Running," "Work Style: Remote Work," etc.) and presses the "Send" button. The device then compiles this input data and sends it to the server.

[0156] Step 3:

[0157] The terminal transmits these input data to the server.

[0158] Input: User-entered data

[0159] Output: Data sent to the server

[0160] How it works: The device temporarily stores the data entered by the user and then transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[0161] Step 4:

[0162] The server receives the received user data, completes missing values ​​in the data, and standardizes the format.

[0163] Input: Received data

[0164] Output: Preprocessed data

[0165] Specific operation: The server validates the received data and fills in any missing values ​​with the mean or median. It also performs processing such as converting "yes / no" to "1 / 0" to unify the data format.

[0166] Step 5:

[0167] The server generates a lifestyle and personality profile of the user based on the pre-processed data.

[0168] Input: Preprocessed data

[0169] Output: Personality profile

[0170] How it works: The server uses machine learning models to analyze the pre-processed data and generate a profile that characterizes the user's lifestyle and personality.

[0171] Step 6:

[0172] The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[0173] Enter: personality profile

[0174] Output: Recommendation data

[0175] Specific operation: Based on the personality profile, the server runs a recommender system (e.g., collaborative filtering or content-based filtering) to create a list of optimal housing candidates.

[0176] Step 7:

[0177] The server compares the user's personality profile with a smart city database and generates a list of suitable housing options for the user.

[0178] Input: personality profile, smart city database

[0179] Output: List of potential housing locations

[0180] How it works: The server compares the smart city database with the user's personality profile, evaluating factors such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety. Based on this, it generates a list of recommended housing options.

[0181] Step 8:

[0182] The server creates detailed information about the recommended housing candidate locations and sends it to the terminal.

[0183] Input: List of potential housing locations

[0184] Output: A list of recommendations with detailed information

[0185] Specific operation: The server adds detailed information about the potential residence (e.g., location of the residence, surrounding facilities, environment, rent, etc.) to a recommendation list and sends it to the terminal.

[0186] Step 9:

[0187] The terminal displays the recommendation list to the user, allowing the user to check it.

[0188] Input: A list of recommendations with detailed information

[0189] Output: Displayed recommendation list

[0190] Specific operation: The device displays the received recommendation list in GUI format, allowing the user to view detailed information, and displays a map using the Google Maps API if necessary.

[0191] Step 10:

[0192] The user inputs feedback on the recommendation through the terminal.

[0193] Input: Feedback (ratings and desired conditions)

[0194] Output: Feedback data

[0195] Specific operation: After checking the recommendation list, the user inputs their own rating and any additional desired conditions, and presses the "Submit" button. The device then sends this feedback data to the server.

[0196] Step 11:

[0197] The terminal transmits the user feedback data to the server.

[0198] Input: Feedback data

[0199] Output: Data sent to the server

[0200] How it works: The device temporarily stores the user's feedback data and transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[0201] Step 12:

[0202] The server analyzes the received feedback data and uses it to improve existing algorithms, as well as reassess the user's personality profile to improve the accuracy of future recommendations.

[0203] Input: Feedback data

[0204] Output: Improved algorithm, updated personality profile

[0205] How it works: The server analyzes the feedback data using natural language processing (NLP) techniques, improves the recommendation algorithm based on the analysis results, and re-evaluates the user's personality profile based on the feedback to improve the accuracy of future recommendations.

[0206] (Application example 1)

[0207] 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."

[0208] In modern urban life, it is extremely difficult for an individual user to find a residential location that best suits their lifestyle and personality. Furthermore, simply displaying a list or providing text information does not allow the user to fully understand the actual environment of each candidate location, resulting in a decrease in the accuracy of property selection. Furthermore, it is difficult for users to provide detailed feedback on recommended candidate locations, which means the system cannot always reflect the user's latest needs. A system that solves these issues is needed.

[0209] 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.

[0210] In this invention, the server includes means for displaying detailed information about potential housing sites in the form of a virtual tour on a user terminal using augmented reality or virtual reality technology based on the user's lifestyle and personality profile, means for collecting and analyzing user feedback, and means for improving the algorithm based on the feedback. This allows users to check detailed environmental information about the recommended housing sites through the virtual tour before actually visiting them, allowing them to select a home that suits them with greater accuracy. Furthermore, the system can always provide optimal recommendations based on user feedback.

[0211] A "user terminal" is an electronic device used by a user to input data, display and provide feedback.

[0212] "User data" is a collection of information entered by a user based on their lifestyle and personality characteristics.

[0213] A "server" is a computer system that receives user data, performs pre-processing and analysis, generates recommendations, and processes feedback.

[0214] "Preprocessing of received data" refers to data cleaning work performed by the server, such as filling in missing values ​​and standardizing the format of the received data.

[0215] "Analysis of received data" is the process by which the server analyzes user data and generates a personality profile.

[0216] A "personality profile" is profile information that includes characteristics such as a user's lifestyle, hobbies, and work style.

[0217] "Evaluation of potential residential locations" is the process of evaluating conditions such as convenience and environment of selected potential locations by comparing them with a personality profile.

[0218] "Recommendation generation" is the process of suggesting the best possible housing locations based on the analyzed personality profile.

[0219] "Displaying a list of recommendations" means displaying a list of recommended housing candidates on the user terminal.

[0220] "Feedback" refers to the input of a user's opinion on the recommendation results, additional desired conditions, and the like.

[0221] "Feedback collection" is the process of collecting feedback information input by users from their terminals to the server.

[0222] "Algorithm improvement" is the process of updating recommendation algorithms and improving their accuracy based on collected feedback.

[0223] "Augmented reality" is a technology that overlays digital information onto the real world.

[0224] "Virtual reality" is a technology that allows users to experience a three-dimensional virtual environment generated by a computer.

[0225] A "virtual tour" is a feature that uses augmented reality or virtual reality to allow users to explore a location in a virtual space without actually visiting the location.

[0226] In one embodiment of the present invention, a system is used that combines a user terminal, a server, and augmented reality (AR) or virtual reality (VR) technology. The user terminal may be a smartphone, smart glasses, or a head-mounted display.

[0227] 1. Data Entry

[0228] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and recreational facilities). This data is then sent from the device to a server.

[0229] 2. Data Preprocessing and Analysis

[0230] The server receives the data from the user, fills in missing values, and standardizes the format. Once the data is cleaned, a machine learning model is used to generate a personality profile for the user. Pandas and Scikit-learn are used as data analysis tools to generate this profile.

[0231] 3. Recommendation Generation

[0232] The server compares the generated user's personality profile with the smart city database to create a list of recommendations for optimal housing options, including evaluation criteria such as transportation access, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0233] 4. Displaying Recommendations

[0234] The user device not only displays the recommendation list, but also uses augmented reality or virtual reality technology to display detailed information about the recommended housing candidate sites in the form of a virtual tour. This virtual tour allows users to see the interior and surrounding environment of the property without actually visiting it. This is done using development platforms such as ARKit (Apple) and ARCore (Google).

[0235] 5. Feedback collection and analysis

[0236] Users input feedback based on the recommendation results. This feedback includes ratings and additional preferences. The feedback data is sent from the device to the server, which analyzes it and uses it to improve the algorithm. Based on the analysis results, the user's personality profile and the accuracy of the recommendations are improved.

[0237] Specific examples

[0238] If a user plans to relocate to Tokyo, they log in to the system and enter "Tokyo" as the city they will be relocated to. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and pet type (e.g., "dog"). The device sends this information to the server, which preprocesses the data and then uses a machine learning model to generate a personality profile. A recommendation list is created, suggesting potential housing locations such as "Minami-Aoyama" and "Meguro." The user can then put on the smart glasses and experience a virtual tour of these potential locations in augmented reality.

[0239] Example prompts for generative AI models

[0240] "I love reading, I work remotely, and I have a cat. Please recommend the best place to live that meets these criteria."

[0241] As described above, the present invention allows users to efficiently go through the process of finding the home that best suits them.

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

[0243] Program processing flow

[0244] Step 1: Data entry

[0245] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and entertainment facilities). This data is then sent from the device to a server.

[0246] Input: Hobbies, work style, whether you have pets, desired location

[0247] Output: User data is sent to the server

[0248] Step 2: Preprocessing the data

[0249] The server performs missing value imputation and format unification on the data received from the user. Here, Pandas is used to clean the data.

[0250] Input: User data

[0251] Output: Preprocessed data

[0252] Specific operation: Impute missing values ​​and unify data formats

[0253] Step 3: Generate a personality profile

[0254] The server uses a machine learning model, in this case Scikit-learn, to generate a user personality profile from the preprocessed data.

[0255] Input: Preprocessed data

[0256] Output: Personality profile

[0257] What happens: Feed data into a machine learning model to build a personality profile

[0258] Step 4: Recommendation Generation

[0259] The server compares the generated personality profile with the smart city database to create a list of recommendations for optimal housing options, based on evaluation criteria such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety.

[0260] Input: Personality profile, Smart City database

[0261] Output: Recommendation list

[0262] Specific operation: Match the profile with the database and evaluate the candidate site based on each evaluation item.

[0263] Step 5: View recommendations

[0264] The user terminal displays the recommendation list and also displays detailed information about the recommended housing candidates in the form of a virtual tour using augmented reality (AR) or virtual reality (VR) technology.

[0265] Input: Recommendation list

[0266] Output: Detailed information displayed in a virtual tour format

[0267] What it does: Uses ARKit or ARCore to display detailed information in a virtual tour format.

[0268] Step 6: Gather feedback

[0269] The user inputs feedback on the recommendation results, including ratings and additional desired conditions, and the feedback data is sent from the terminal to the server.

[0270] Input: Feedback (rating, additional requirements, etc.)

[0271] Output: Feedback data sent to the server

[0272] What it does: Collects input from users through a feedback form

[0273] Step 7: Analyzing feedback and improving the algorithm

[0274] The server analyzes the collected feedback to improve the recommendation algorithm, which includes the process of optimizing the parameters of the algorithm based on the collected feedback data.

[0275] Input: Feedback data

[0276] Output: An improved recommendation algorithm

[0277] Specific behavior: Analyze feedback data and optimize parameters of recommendation algorithms

[0278] 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.

[0279] This invention combines a system that recommends optimal residential locations based on a user's lifestyle and personality with an emotion engine that recognizes the user's emotions. This system inputs user data and emotion data via the user's terminal, analyzes and processes the data on the server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0280] Program processing flow

[0281] Data Entry

[0282] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[0283] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (e.g., access to transportation, medical facilities, educational institutions, and recreational facilities).

[0284] 3. The device sends these input data to the server.

[0285] Data preprocessing and analysis

[0286] 1. The server receives the user data. It fills in missing values ​​and standardizes the format of the data. The emotion engine also analyzes the user's emotional state.

[0287] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[0288] 3. The emotion engine monitors the user's emotional state in real time and generates analytical results.

[0289] 4. The server applies an algorithm to make optimal recommendations based on the user's personality profile and emotional state.

[0290] Recommendation generation and display

[0291] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0292] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[0293] 3. The device displays the recommendation list to the user, allowing the user to review it.

[0294] Collecting and analyzing feedback

[0295] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[0296] 2. The device sends the user's feedback and emotion data to the server.

[0297] 3. The server analyzes the received feedback and sentiment data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[0298] Specific examples

[0299] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[0300] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), sleep habits (e.g., "night owl"), etc. They also enter their emotional state at the time (e.g., "feeling stressed").

[0301] 2. The device sends this information to the server, which preprocesses the data and analyzes it using machine learning models and an emotion engine.

[0302] 3. The server uses the user's input data and emotional data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[0303] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[0304] 5. The user enters feedback based on their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the device sends this to the server. The emotion engine also analyzes the user's emotional state.

[0305] 6. The server analyzes the feedback and sentiment data to help improve the algorithm and reassess the user's profile to improve future recommendations.

[0306] Thus, the present invention provides a system that recommends optimal residential locations by taking into account the user's lifestyle, personality, and emotional state. This system effectively functions using a user device, a server that performs data preprocessing and analysis, recommendation generation, feedback collection and analysis, and an emotion engine.

[0307] The processing flow will be explained below.

[0308] Step 1:

[0309] The user logs in to the system and the data entry screen for the residence search is displayed on the terminal. The user ID and password are used to log in.

[0310] Step 2:

[0311] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (such as access to transportation, medical facilities, educational institutions, and recreational facilities).

[0312] Step 3:

[0313] The terminal transmits these input data to the server.

[0314] Step 4:

[0315] The server retrieves the user data received, fills in missing values, standardizes the format, and performs data cleansing.

[0316] Step 5:

[0317] The server uses the pre-processed data to feed it into a machine learning model to generate a lifestyle and personality profile of the user.

[0318] Step 6:

[0319] The emotion engine analyzes the user's emotional state from input data, and performs emotion recognition through text and voice analysis.

[0320] Step 7:

[0321] The server integrates the emotion data obtained from the emotion engine with the personality profile to generate a comprehensive profile of the user.

[0322] Step 8:

[0323] The server compares the user's profile with the smart city database and performs an evaluation to recommend the most suitable place to live.

[0324] Step 9:

[0325] The server calculates the evaluation score of each residential location and generates a list of suitable residential locations for the user, including detailed information about each location (such as transportation access, availability of facilities, and environmental safety).

[0326] Step 10:

[0327] The server sends the recommendation list and detailed information to the terminal.

[0328] Step 11:

[0329] The device displays a recommendation list to the user, who can then browse the list and view detailed information about the potential residences.

[0330] Step 12:

[0331] The user selects the best place to live based on the recommendations and then enters the results and feedback, including the location's rating and emotional state.

[0332] Step 13:

[0333] The device sends the user's feedback and emotion data to the server.

[0334] Step 14:

[0335] The server analyzes the received feedback and sentiment data. The feedback data is used to analyze and improve the recommendation algorithm.

[0336] Step 15:

[0337] The server updates the algorithm based on the feedback analysis results that reflect the emotional data, improving the accuracy of future recommendations. It also reevaluates the user's profile and generates a new one.

[0338] In this way, users can find the place to live that best suits their individual lifestyle, personality, and even emotional state. The entire system is designed to work together to maximize the user's growth and happiness.

[0339] Example 2

[0340] 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."

[0341] There is a need for a system that can recommend optimal residential locations by taking into account users' diverse lifestyles, personalities, and emotional states. Conventional systems are based on fixed information about users and have the problem of being unable to respond to emotions or real-time changes in the situation. Therefore, it is necessary to provide more accurate recommendations that also take into account the user's emotional state.

[0342] 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.

[0343] In this invention, the server includes means for receiving user data, means for preprocessing the received data, means for analyzing the received data, means for generating a user's personality profile, means for evaluating potential housing sites and generating recommendations, means for analyzing feedback and improving algorithms, means for receiving and analyzing emotional data, and means for optimizing recommendations based on the emotional state, thereby enabling highly accurate residential site recommendations that reflect the user's emotional state in addition to their lifestyle and personality.

[0344] "User data" refers to information such as the user's lifestyle, personality information, emotional state, and desired conditions regarding the place of residence.

[0345] A "user terminal" is a device that a user uses to input data and check recommendations, and includes smartphones, personal computers, etc.

[0346] "Server" means the computer system that operates centrally to analyze and process data received from Users and generate recommendations.

[0347] "Means for preprocessing received data" refers to a process for standardizing user data, complementing missing values, and standardizing formats.

[0348] "Analysis Means" means the methods and techniques used to analyze and interpret the received data and generate a lifestyle and personality profile of the User.

[0349] A "personality profile" is a profile of personal characteristics generated based on a user's lifestyle, hobbies, and behavioral patterns.

[0350] The "recommendation generation means" is a process that selects and lists the most suitable housing candidates based on the user's profile.

[0351] "Emotion data" is information that indicates the user's current emotional state, and includes stress, happiness, satisfaction, and the like.

[0352] The "emotion engine" is a system that analyzes the user's emotional state from input data and monitors changes in emotions in real time.

[0353] "Feedback collection means" is the process of collecting user-entered ratings and additional requests for recommendations.

[0354] "Algorithm improvement" is the process of analyzing collected feedback and sentiment data to improve the recommendation algorithm.

[0355] An "optimizer" is a method that takes into account the user's emotional state to adjust recommendations and suggest the most suitable place to live for the user.

[0356] A "collaborative filtering algorithm" is a method for comparing data from multiple users and making recommendations based on similarities.

[0357] MODE FOR CARRYING OUT THE INVENTION

[0358] The present invention is a system that recommends optimal residential locations by taking into consideration not only the user's lifestyle and personality, but also the user's emotional state. This system is composed of hardware and software, such as a user terminal, a server, and an emotion engine.

[0359] Overall structure

[0360] First, a user accesses the system through a user terminal and inputs the necessary data, including their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired residential location. This data is then sent from the user terminal to the server.

[0361] The server preprocesses the data received from users, filling in missing values ​​and standardizing formats. It then uses machine learning models to analyze the data and generate personality profiles. It also uses an emotion engine to analyze users' emotional data and monitor their emotional state in real time.

[0362] The server then applies a recommendation algorithm based on the user's generated personality profile and emotional state to generate a list of optimal residential location recommendations, including detailed information on potential locations based on evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety.

[0363] Next, the device displays a list of recommended housing options to the user. The user can review the options and view detailed information. For example, a recommendation could include information such as, "I'm planning to be transferred to Tokyo, my hobby is running, I often work remotely, I'm a night owl, and I feel stressed."

[0364] Users can provide feedback on the recommendations, and the feedback and emotional data are sent back to the server, which can then use this feedback to improve existing algorithms and reassess the user's personality profile to improve the accuracy of future recommendations.

[0365] Hardware and software used

[0366] User device: A device such as a smartphone or PC is used to input user data and display a list of recommendations.

[0367] Server: A computer system that performs central data analysis and recommendation generation.

[0368] Emotion Engine: A software module for recognizing and analyzing a user's emotional state. It uses natural language processing techniques to extract emotions from text.

[0369] Machine learning models: Generate user profiles using techniques such as k-nearest neighbors and decision trees, and generate recommendations using collaborative filtering algorithms.

[0370] Specific examples

[0371] For example, if a user enters "I'm planning to transfer to Tokyo, I mostly work remotely, my hobby is running, I'm a night owl, and I've been feeling stressed lately," the system will act as follows:

[0372] 1. The user enters the necessary information on the user terminal and sends it to the server.

[0373] 2. The server preprocesses the received data and analyzes it using machine learning models and an emotion engine.

[0374] 3. The server generates a list of recommended housing candidates and sends it to the device.

[0375] 4. The device displays the recommendation list to the user, and the user checks the details.

[0376] 5. The user enters feedback on the recommendation and sends it to the server via the device.

[0377] 6. The server analyzes the feedback data to improve the algorithm and re-evaluate the user profile.

[0378] This method makes it possible to provide highly accurate recommendations that reflect the user's lifestyle and emotional state.

[0379] Prompt Sentence Examples

[0380] "I'm planning to be transferred to Tokyo. I do a lot of remote work at work, and my hobby is running. I'm a night owl, and I've been feeling stressed lately. Could you please tell me the best place to live?"

[0381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0382] Step 1:

[0383] A user logs into the system using a terminal. The user enters a username and password and is authenticated. If the login is successful, a data entry screen for a residence search is displayed on the terminal.

[0384] Input: Username, Password

[0385] Output: Display of data entry screen

[0386] Step 2:

[0387] Users enter information such as their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired place of residence into a data entry screen. Specifically, they enter information such as "running," "remote work," "night owl," "feeling stressed," and "Tokyo."

[0388] Input: Lifestyle, hobbies, work style, sleep habits, diet, emotional state, desired location

[0389] Output: Prepare input data for sending

[0390] Step 3:

[0391] The device sends this input data to the server, where it is encrypted and securely delivered to the server.

[0392] Input: Input data

[0393] Output: Data sent to the server

[0394] Step 4:

[0395] The server preprocesses the user data it receives. This involves filling in missing values ​​and standardizing data formats. For example, if there is missing information in the input data, it is filled in based on past data or statistical models.

[0396] Input: User data

[0397] Output: Preprocessed data

[0398] Step 5:

[0399] The server analyzes the pre-processed data and uses machine learning models to generate a lifestyle and personality profile of the user. Models used include k-nearest neighbors and decision trees.

[0400] Input: Preprocessed data

[0401] Output: Personality profile

[0402] Step 6:

[0403] The emotion engine monitors the user's emotional state in real time and generates analytical results. It uses natural language processing technology to extract emotions from the user's text input.

[0404] Input: User emotion data

[0405] Output: Emotion analysis results

[0406] Step 7:

[0407] The server applies a recommendation algorithm based on the user's personality profile and emotional state, and uses a collaborative filtering algorithm to recommend the best place to live.

[0408] Input: Personality profile, emotion analysis results

[0409] Output: Recommendation list

[0410] Step 8:

[0411] The server generates a recommendation list and sends it to the device. The list includes detailed information about potential housing locations, including evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety. For example, the list includes candidate locations such as "Toyosu," "Shinagawa," and "Shibuya."

[0412] Input: Recommendation list

[0413] Output: List sent to terminal

[0414] Step 9:

[0415] The device displays a list of recommendations to the user, who can then browse detailed information and select a location that best suits their needs.

[0416] Input: Recommendation list

[0417] Output: The list displayed to the user

[0418] Step 10:

[0419] The user enters feedback on the recommendation. The feedback includes an evaluation of the place of residence and any additional desired conditions. For example, the user can enter content such as "I am very satisfied with the convenience of Toyosu."

[0420] Input: Feedback

[0421] Output: Feedback ready to be sent

[0422] Step 11:

[0423] The device sends the user's feedback and emotional data to the server, where it is again encrypted and transmitted securely.

[0424] Input: Feedback, emotion data

[0425] Output: Feedback and emotion data sent to the server

[0426] Step 12:

[0427] The server analyzes the feedback and sentiment data, improving existing algorithms and reassessing the user's personality profile to improve the accuracy of future recommendations.

[0428] Input: Feedback, emotion data

[0429] Output: Improved algorithm and re-evaluated profile

[0430] (Application example 2)

[0431] 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."

[0432] Conventional food delivery recommendation systems make recommendations based on a user's eating habits and preferences, but they are unable to make recommendations that take into account the user's real-time emotional state. This makes it difficult for users to select the optimal food delivery service that matches their emotional state at any given time. Furthermore, the lack of monitoring and analysis of the user's real-time emotional state makes it difficult to provide more personalized recommendations.

[0433] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0434] In this invention, the server includes means for real-time monitoring of the user's emotional state using an emotion analysis engine, and means for the server to generate food delivery options based on the user's personality profile and emotional state, thereby enabling personalized food delivery recommendations that take into account the user's real-time emotional state.

[0435] A "user terminal" is an electronic device that allows a user to access the system and input and display data.

[0436] "User data" refers to data that includes information about a user's lifestyle, personality, diet, emotional state, and so on.

[0437] A "server" is a computer system for receiving, preprocessing, and analyzing user data, and for generating and displaying recommendations.

[0438] The "receiving means" is a function for the server to receive data sent from the user terminal.

[0439] The "preprocessing means" is a function that complements missing values ​​and standardizes the format of received data.

[0440] The "analysis means" is a function that analyzes the pre-processed data and generates a personality profile and emotional state of the user.

[0441] A "personality profile" is a profile generated based on a user's lifestyle and personality characteristics.

[0442] An "emotion analysis engine" is an algorithm and software for analyzing a user's real-time emotional state.

[0443] A "recommendation" is a list of best candidates provided to a user.

[0444] "Feedback" refers to collected data of users' ratings and opinions on recommendations.

[0445] "Means for improving algorithms" is a function for improving existing algorithms based on feedback data.

[0446] "Food delivery options" are the food and meal options available for delivery to a user.

[0447] The invention is a system that recommends food delivery options based on a user's lifestyle, personality information, and real-time emotional state. Specifically, the system is implemented as follows.

[0448] Overall system configuration

[0449] The system includes a user terminal, a server, a sentiment analysis engine, and a machine learning model. The user terminal is responsible for inputting user data and displaying recommendations, while the server performs data preprocessing, analysis, recommendation generation, feedback collection, and algorithm improvement. The sentiment analysis engine monitors and analyzes the user's emotional state in real time.

[0450] Hardware and software used

[0451] Hardware: Smartphones (e.g., iPhone (registered trademark), Android (registered trademark) devices), head-mounted displays (e.g., Oculus Quest 2)

[0452] Software: Sentiment analysis engine, machine learning model (e.g., TENSORFLOW (registered trademark)), database (e.g., MySQL (registered trademark)), application server (e.g., Node.js)

[0453] Processing flow

[0454] 1. The user terminal provides an interface for inputting user data. The user inputs details such as dietary habits, favorite foods, allergy information, and their emotional state at the time.

[0455] 2. The terminal sends the entered data to the server.

[0456] 3. The server receives the data and performs preprocessing such as unifying the data format and filling in missing values. The emotion analysis engine also analyzes the user's emotional state in real time.

[0457] 4. The server uses machine learning models to generate a personality profile of the user and recommends optimal food delivery options based on that profile and emotional state.

[0458] 5. The server generates a recommendation list and sends detailed information to the user terminal.

[0459] 6. The user device displays a recommendation list from which the user can make a selection.

[0460] 7. The user enters feedback on the recommendation, and the device sends the feedback and emotion data to the server.

[0461] 8. The server analyzes the feedback and sentiment data to improve the algorithm and re-evaluate the user profile.

[0462] Specific examples

[0463] For example, if a user is tired and wants to order a light meal, they can enter their user data and emotional state as follows:

[0464] Diet: Vegetable-based

[0465] Favorite food: Japanese food

[0466] Allergies: None

[0467] Emotional state: Tired

[0468] Example prompts to give to a generative AI model:

[0469] "The user is currently tired and has a preference for Japanese food based on their past ordering history. Please recommend the best light Japanese delivery options for the user."

[0470] Based on this prompt, the generative AI model recommends suitable food delivery options for the user and displays the results in real time, allowing users to easily find the best food delivery options that match their emotional state.

[0471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0472] Step 1:

[0473] The user terminal provides an interface for inputting user data. The user inputs information about their diet, favorite foods, allergies, and current emotional state. This input data is used as the initial input for the system.

[0474] Step 2:

[0475] The device transmits the input data to the server, which includes lifestyle information, favorite foods, and emotional state.

[0476] Step 3:

[0477] The server receives user data and performs preprocessing such as standardizing the data format and filling in missing values. Specifically, it predicts and fills in missing data and prepares the data format for analysis.

[0478] Step 4:

[0479] The emotion analysis engine analyzes the user's emotional state in real time. The input is the raw data of the emotional state, and the output is the analyzed emotional evaluation result.

[0480] Step 5:

[0481] The server uses a machine learning model to generate a personality profile for the user. The input data is preprocessed user data and sentiment analysis results, and the output data is a combination of the personality profile and sentiment assessment.

[0482] Step 6:

[0483] The server generates prompts to recommend optimal food delivery options based on the generated personality profile and emotional state. The prompts are used as instructions for the generative AI model, and the output is a list of optimal delivery options.

[0484] Step 7:

[0485] The server generates a recommendation list and sends the details to the user's device, including specific information about each delivery option (menu, price, ratings, etc.).

[0486] Step 8:

[0487] The user terminal displays the recommendation list, allowing the user to check the recommendations.

[0488] Step 9:

[0489] Users enter feedback on the recommendations, including ratings and impressions of the selected options.

[0490] Step 10:

[0491] The terminal again transmits the feedback data and emotion data to the server.

[0492] Step 11:

[0493] The server analyzes the feedback and emotion data to improve existing recommendation algorithms and also reassess the user's personality profile based on the analysis results to improve the accuracy of future recommendations.

[0494] This series of steps allows users to receive the best food delivery recommendations that suit their emotional state at any given time.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 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.

[0501] 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).

[0502] 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.

[0503] 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.

[0504] 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).

[0505] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] 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.

[0510] 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."

[0511] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0512] Program processing flow

[0513] Data Entry

[0514] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[0515] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, and desired residential conditions (e.g., transportation access, medical facilities, educational institutions, and recreational facilities).

[0516] 3. The device sends these input data to the server.

[0517] Data preprocessing and analysis

[0518] 1. The server receives the received user data, completes missing values, and standardizes the format of the data.

[0519] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[0520] 3. The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[0521] Recommendation generation and display

[0522] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0523] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[0524] 3. The device displays the recommendation list to the user, allowing the user to review it.

[0525] Collecting and analyzing feedback

[0526] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[0527] 2. The terminal transmits the user's feedback data to the server.

[0528] 3. The server analyzes the received feedback data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[0529] Specific examples

[0530] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[0531] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[0532] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[0533] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[0534] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[0535] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[0536] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[0537] Thus, the present invention provides a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing their growth and happiness. This system effectively functions using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[0538] The processing flow will be explained below.

[0539] Step 1:

[0540] A user logs in to the system by entering their user ID and password on the login screen and clicking the login button.

[0541] Step 2:

[0542] The device sends the login information to the server, which authenticates the login information and returns a success message to the user.

[0543] Step 3:

[0544] The user displays a data entry screen for a residential search, which allows the user to specify a desired location for a job transfer or relocation.

[0545] Step 4:

[0546] Users input their lifestyle (hobbies, work style, sleeping habits, diet, etc.) and desired conditions (transportation access, medical facilities, educational institutions, entertainment facilities, etc.).

[0547] Step 5:

[0548] The terminal transmits the input user data to the server, which then retrieves the user's lifestyle information.

[0549] Step 6:

[0550] The server preprocesses the data it receives, standardizing the data format and filling in missing values. It also detects and removes outliers in the data.

[0551] Step 7:

[0552] The server inputs the pre-processed data into a machine learning model to generate a personality profile of the user, which includes the user's personality traits and lifestyle patterns.

[0553] Step 8:

[0554] The server compares the generated personality profile with the smart city database, evaluates multiple residential candidate locations, and calculates an evaluation score.

[0555] Step 9:

[0556] The server generates a list of potential residential locations, including detailed information about each location (e.g., accessibility, amenities, and environmental safety).

[0557] Step 10:

[0558] The server sends the recommendation list to the terminal.

[0559] Step 11:

[0560] The device displays a list of recommendations to the user, who can then view detailed information about each location and make the best choice.

[0561] Step 12:

[0562] Users enter feedback on the recommendations, including location ratings and additional preferences.

[0563] Step 13:

[0564] The terminal sends the user's feedback to the server.

[0565] Step 14:

[0566] The server receives and analyzes the feedback. The feedback data is used to improve the recommendation algorithm.

[0567] Step 15:

[0568] The server uses the improved algorithm to improve the accuracy of future recommendations, and the user's profile is also re-evaluated.

[0569] In this way, users can find the place to live that best suits their individual lifestyle and personality. The entire system is designed to work together and function effectively.

[0570] Example 1

[0571] 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."

[0572] In modern society, users face difficulties in finding a place to live that best suits their lifestyle and personality. Conventional residential search systems often fail to provide satisfactory results because they make recommendations based only on general criteria, without considering the user's detailed personality and lifestyle. Furthermore, they lack mechanisms for improving the accuracy of recommendations based on user feedback.

[0573] 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.

[0574] In this invention, the server includes means for generating a user's lifestyle and personality profile using a machine learning model, means for generating residential property recommendations based on user data and a city database, and means for improving the algorithm and increasing the accuracy of the recommendations in response to user feedback. This allows users to receive recommendations for optimal residential properties based on their detailed lifestyle and personality, and by incorporating the feedback, more accurate recommendations can be provided to each individual user.

[0575] A "user terminal" is a computing device or communication device used by a user.

[0576] "User data" is information provided by a user, including lifestyle, personality information, and desired conditions.

[0577] A "server" is a central computing device that receives and analyzes user data and generates recommendations.

[0578] The "pre-processing means for received data" is a processing means for complementing missing values ​​and standardizing the format of user data received by the server.

[0579] The "means for analyzing received data" refers to the means by which the server analyzes the pre-processed data and generates a profile of the user.

[0580] A "personality profile" is information that describes a user's lifestyle and personality traits, generated using a machine learning model.

[0581] "Possible residence locations" is a list of residence locations suitable for the user, recommended by the server.

[0582] A "recommendation" is a proposal for the optimal place to live generated by the server based on the user's lifestyle and desired conditions.

[0583] The "means for displaying a list of recommendations" is a means for the user terminal to display a list of candidate housing locations to the user.

[0584] The "feedback collection means" is a means for collecting opinions and evaluations of the recommendations from users.

[0585] The "means for analyzing feedback and improving algorithms" refers to the means by which the server analyzes feedback from users and improves the recommendation algorithm based on the analysis.

[0586] A "machine learning model" is an algorithm and its implementation that learns from data and makes predictions and classifications.

[0587] The "urban database" is a database containing information on potential residential locations, and evaluation criteria include transportation access, the availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0588] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0589] Hardware and Software Use

[0590] The system implementation uses the following hardware and software:

[0591] User terminal: A device used by a user to input data, such as a smartphone or computer.

[0592] Server: A high-performance computing device that preprocesses, analyzes, and generates recommendations from received data.

[0593] Machine learning model: Uses Python's Scikit-learn library to generate a user's lifestyle and personality profile.

[0594] Database: A smart city database will be used to manage information such as transportation access, medical facilities, educational institutions, the availability of entertainment facilities, and safety.

[0595] Communication protocol: HTTPS is used to securely transmit data between the user terminal and the server.

[0596] System operation explanation

[0597] 1. When a user logs in to the system, a data entry screen for residential searches is displayed on the terminal. To log in, the user uses their user ID and password.

[0598] 2. Users input their lifestyle (e.g., "active" or "indoor"), hobbies (e.g., "running" or "reading"), work style (e.g., "remote work" or "office work"), sleep habits (e.g., "night owl" or "early to bed, early to rise"), and diet (e.g., "vegetarian" or "gourmet"), and also select the conditions for their desired place of residence (e.g., transportation access, availability of medical facilities, educational institutions, entertainment facilities, safety, etc.).

[0599] 3. The device sends these input data to the server in real time using HTTPS, which encrypts the data.

[0600] 4. The server receives the received user data and performs data imputation and formatting. For example, if there are missing values, it imputes them using the mean or median. It also standardizes the data format (for example, converting "yes / no" to "1 / 0").

[0601] 5. The server generates a lifestyle and personality profile of the user based on the preprocessed data, which is implemented using a machine learning library such as Scikit-learn in Python.

[0602] 6. The server uses the user's personality profile to run a recommendation algorithm, specifically a recommender system (e.g., collaborative filtering or content-based filtering) to determine the appropriate action.

[0603] 7. The server compares the user profile with the smart city database and generates a list of residential options that best suit the user. For example, it selects areas such as "Toyosu," "Shinagawa," and "Shibuya" from the Tokyo database.

[0604] 8. The server creates a list containing detailed information about the recommended housing candidates (e.g., location of the housing, surrounding facilities, environment, rent, etc.) and sends it to the terminal.

[0605] 9. The device displays this list to the user, allowing them to view more information, for example by displaying a map using the Google Maps API.

[0606] 10. The user enters feedback on the recommendation through the system. For example, they can enter a rating such as "The Toyosu area is very convenient" or additional preferences such as "I would prefer a place with a little more nature."

[0607] 11. The device transmits these feedback data to the server in real time using a secure communication channel.

[0608] 12. The server analyzes the received feedback data and improves the algorithm based on the analysis results. For example, by analyzing the text data of the feedback using natural language processing (NLP) technology, new user needs can be discovered. Based on the feedback, the server also reevaluates the user's personality profile and improves the accuracy of the system's recommendations.

[0609] Specific examples

[0610] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[0611] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[0612] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[0613] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[0614] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[0615] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[0616] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[0617] Thus, the present invention is a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing the user's growth and happiness. This system functions effectively using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[0618] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0619] Step 1:

[0620] The user logs into the system and displays a data entry screen for a residence search on the terminal.

[0621] Input: User ID and password

[0622] Output: Data entry screen

[0623] Specific operation: The user launches a browser or app and enters their user ID and password into the login form. The device receives this and sends it to the authentication server. After successful authentication, a data entry screen for a home search is displayed.

[0624] Step 2:

[0625] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, eating habits, and desired place of residence.

[0626] Input: Lifestyle, hobbies, work style, sleeping habits, diet, desired conditions

[0627] Output: Input data

[0628] Specific operation: The user enters information into each field on the data entry screen (e.g., "Lifestyle: Active," "Hobbies: Running," "Work Style: Remote Work," etc.) and presses the "Send" button. The device then compiles this input data and sends it to the server.

[0629] Step 3:

[0630] The terminal transmits these input data to the server.

[0631] Input: User-entered data

[0632] Output: Data sent to the server

[0633] How it works: The device temporarily stores the data entered by the user and then transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[0634] Step 4:

[0635] The server receives the received user data, completes missing values ​​in the data, and standardizes the format.

[0636] Input: Received data

[0637] Output: Preprocessed data

[0638] Specific operation: The server validates the received data and fills in any missing values ​​with the mean or median. It also performs processing such as converting "yes / no" to "1 / 0" to unify the data format.

[0639] Step 5:

[0640] The server generates a lifestyle and personality profile of the user based on the pre-processed data.

[0641] Input: Preprocessed data

[0642] Output: Personality profile

[0643] How it works: The server uses machine learning models to analyze the pre-processed data and generate a profile that characterizes the user's lifestyle and personality.

[0644] Step 6:

[0645] The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[0646] Enter: personality profile

[0647] Output: Recommendation data

[0648] Specific operation: Based on the personality profile, the server runs a recommender system (e.g., collaborative filtering or content-based filtering) to create a list of optimal housing candidates.

[0649] Step 7:

[0650] The server compares the user's personality profile with a smart city database and generates a list of suitable housing options for the user.

[0651] Input: personality profile, smart city database

[0652] Output: List of potential housing locations

[0653] How it works: The server compares the smart city database with the user's personality profile, evaluating factors such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety. Based on this, it generates a list of recommended housing options.

[0654] Step 8:

[0655] The server creates detailed information about the recommended housing candidate locations and sends it to the terminal.

[0656] Input: List of potential housing locations

[0657] Output: A list of recommendations with detailed information

[0658] Specific operation: The server adds detailed information about the potential residence (e.g., location of the residence, surrounding facilities, environment, rent, etc.) to a recommendation list and sends it to the terminal.

[0659] Step 9:

[0660] The terminal displays the recommendation list to the user, allowing the user to check it.

[0661] Input: A list of recommendations with detailed information

[0662] Output: Displayed recommendation list

[0663] Specific operation: The device displays the received recommendation list in GUI format, allowing the user to view detailed information, and displays a map using the Google Maps API if necessary.

[0664] Step 10:

[0665] The user inputs feedback on the recommendation through the terminal.

[0666] Input: Feedback (ratings and desired conditions)

[0667] Output: Feedback data

[0668] Specific operation: After checking the recommendation list, the user inputs their own rating and any additional desired conditions, and presses the "Submit" button. The device then sends this feedback data to the server.

[0669] Step 11:

[0670] The terminal transmits the user feedback data to the server.

[0671] Input: Feedback data

[0672] Output: Data sent to the server

[0673] How it works: The device temporarily stores the user's feedback data and transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[0674] Step 12:

[0675] The server analyzes the received feedback data and uses it to improve existing algorithms, as well as reassess the user's personality profile to improve the accuracy of future recommendations.

[0676] Input: Feedback data

[0677] Output: Improved algorithm, updated personality profile

[0678] How it works: The server analyzes the feedback data using natural language processing (NLP) techniques, improves the recommendation algorithm based on the analysis results, and re-evaluates the user's personality profile based on the feedback to improve the accuracy of future recommendations.

[0679] (Application example 1)

[0680] 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."

[0681] In modern urban life, it is extremely difficult for an individual user to find a residential location that best suits their lifestyle and personality. Furthermore, simply displaying a list or providing text information does not allow the user to fully understand the actual environment of each candidate location, resulting in a decrease in the accuracy of property selection. Furthermore, it is difficult for users to provide detailed feedback on recommended candidate locations, which means the system cannot always reflect the user's latest needs. A system that solves these issues is needed.

[0682] 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.

[0683] In this invention, the server includes means for displaying detailed information about potential housing sites in the form of a virtual tour on a user terminal using augmented reality or virtual reality technology based on the user's lifestyle and personality profile, means for collecting and analyzing user feedback, and means for improving the algorithm based on the feedback. This allows users to check detailed environmental information about the recommended housing sites through the virtual tour before actually visiting them, allowing them to select a home that suits them with greater accuracy. Furthermore, the system can always provide optimal recommendations based on user feedback.

[0684] A "user terminal" is an electronic device used by a user to input data, display and provide feedback.

[0685] "User data" is a collection of information entered by a user based on their lifestyle and personality characteristics.

[0686] A "server" is a computer system that receives user data, performs pre-processing and analysis, generates recommendations, and processes feedback.

[0687] "Preprocessing of received data" refers to data cleaning work performed by the server, such as filling in missing values ​​and standardizing the format of the received data.

[0688] "Analysis of received data" is the process by which the server analyzes user data and generates a personality profile.

[0689] A "personality profile" is profile information that includes characteristics such as a user's lifestyle, hobbies, and work style.

[0690] "Evaluation of potential residential locations" is the process of evaluating conditions such as convenience and environment of selected potential locations by comparing them with a personality profile.

[0691] "Recommendation generation" is the process of suggesting the best possible housing locations based on the analyzed personality profile.

[0692] "Displaying a list of recommendations" means displaying a list of recommended housing candidates on the user terminal.

[0693] "Feedback" refers to the input of a user's opinion on the recommendation results, additional desired conditions, and the like.

[0694] "Feedback collection" is the process of collecting feedback information input by users from their terminals to the server.

[0695] "Algorithm improvement" is the process of updating recommendation algorithms and improving their accuracy based on collected feedback.

[0696] "Augmented reality" is a technology that overlays digital information onto the real world.

[0697] "Virtual reality" is a technology that allows users to experience a three-dimensional virtual environment generated by a computer.

[0698] A "virtual tour" is a feature that uses augmented reality or virtual reality to allow users to explore a location in a virtual space without actually visiting the location.

[0699] In one embodiment of the present invention, a system is used that combines a user terminal, a server, and augmented reality (AR) or virtual reality (VR) technology. The user terminal may be a smartphone, smart glasses, or a head-mounted display.

[0700] 1. Data Entry

[0701] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and recreational facilities). This data is then sent from the device to a server.

[0702] 2. Data Preprocessing and Analysis

[0703] The server receives the data from the user, fills in missing values, and standardizes the format. Once the data is cleaned, a machine learning model is used to generate a personality profile for the user. Pandas and Scikit-learn are used as data analysis tools to generate this profile.

[0704] 3. Recommendation Generation

[0705] The server compares the generated user's personality profile with the smart city database to create a list of recommendations for optimal housing options, including evaluation criteria such as transportation access, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0706] 4. Displaying Recommendations

[0707] The user device not only displays the recommendation list, but also uses augmented reality or virtual reality technology to display detailed information about the recommended housing candidate sites in the form of a virtual tour. This virtual tour allows users to see the interior and surrounding environment of the property without actually visiting it. This is done using development platforms such as ARKit (Apple) and ARCore (Google).

[0708] 5. Feedback collection and analysis

[0709] Users input feedback based on the recommendation results. This feedback includes ratings and additional preferences. The feedback data is sent from the device to the server, which analyzes it and uses it to improve the algorithm. Based on the analysis results, the user's personality profile and the accuracy of the recommendations are improved.

[0710] Specific examples

[0711] If a user plans to relocate to Tokyo, they log in to the system and enter "Tokyo" as the city they will be relocated to. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and pet type (e.g., "dog"). The device sends this information to the server, which preprocesses the data and then uses a machine learning model to generate a personality profile. A recommendation list is created, suggesting potential housing locations such as "Minami-Aoyama" and "Meguro." The user can then put on the smart glasses and experience a virtual tour of these potential locations in augmented reality.

[0712] Example prompts for generative AI models

[0713] "I love reading, I work remotely, and I have a cat. Please recommend the best place to live that meets these criteria."

[0714] As described above, the present invention allows users to efficiently go through the process of finding the home that best suits them.

[0715] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0716] Program processing flow

[0717] Step 1: Data entry

[0718] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and entertainment facilities). This data is then sent from the device to a server.

[0719] Input: Hobbies, work style, whether you have pets, desired location

[0720] Output: User data is sent to the server

[0721] Step 2: Preprocessing the data

[0722] The server performs missing value imputation and format unification on the data received from the user. Here, Pandas is used to clean the data.

[0723] Input: User data

[0724] Output: Preprocessed data

[0725] Specific operation: Impute missing values ​​and unify data formats

[0726] Step 3: Generate a personality profile

[0727] The server uses a machine learning model, in this case Scikit-learn, to generate a user personality profile from the preprocessed data.

[0728] Input: Preprocessed data

[0729] Output: Personality profile

[0730] What happens: Feed data into a machine learning model to build a personality profile

[0731] Step 4: Recommendation Generation

[0732] The server compares the generated personality profile with the smart city database to create a list of recommendations for optimal housing options, based on evaluation criteria such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety.

[0733] Input: Personality profile, Smart City database

[0734] Output: Recommendation list

[0735] Specific operation: Match the profile with the database and evaluate the candidate site based on each evaluation item.

[0736] Step 5: View recommendations

[0737] The user terminal displays the recommendation list and also displays detailed information about the recommended housing candidates in the form of a virtual tour using augmented reality (AR) or virtual reality (VR) technology.

[0738] Input: Recommendation list

[0739] Output: Detailed information displayed in a virtual tour format

[0740] What it does: Uses ARKit or ARCore to display detailed information in a virtual tour format.

[0741] Step 6: Gather feedback

[0742] The user inputs feedback on the recommendation results, including ratings and additional desired conditions, and the feedback data is sent from the terminal to the server.

[0743] Input: Feedback (rating, additional requirements, etc.)

[0744] Output: Feedback data sent to the server

[0745] What it does: Collects input from users through a feedback form

[0746] Step 7: Analyzing feedback and improving the algorithm

[0747] The server analyzes the collected feedback to improve the recommendation algorithm, which includes the process of optimizing the parameters of the algorithm based on the collected feedback data.

[0748] Input: Feedback data

[0749] Output: An improved recommendation algorithm

[0750] Specific behavior: Analyze feedback data and optimize parameters of recommendation algorithms

[0751] 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.

[0752] This invention combines a system that recommends optimal residential locations based on a user's lifestyle and personality with an emotion engine that recognizes the user's emotions. This system inputs user data and emotion data via the user's terminal, analyzes and processes the data on the server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0753] Program processing flow

[0754] Data Entry

[0755] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[0756] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (e.g., access to transportation, medical facilities, educational institutions, and recreational facilities).

[0757] 3. The device sends these input data to the server.

[0758] Data preprocessing and analysis

[0759] 1. The server receives the user data. It fills in missing values ​​and standardizes the format of the data. The emotion engine also analyzes the user's emotional state.

[0760] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[0761] 3. The emotion engine monitors the user's emotional state in real time and generates analytical results.

[0762] 4. The server applies an algorithm to make optimal recommendations based on the user's personality profile and emotional state.

[0763] Recommendation generation and display

[0764] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0765] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[0766] 3. The device displays the recommendation list to the user, allowing the user to review it.

[0767] Collecting and analyzing feedback

[0768] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[0769] 2. The device sends the user's feedback and emotion data to the server.

[0770] 3. The server analyzes the received feedback and sentiment data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[0771] Specific examples

[0772] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[0773] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), sleep habits (e.g., "night owl"), etc. They also enter their emotional state at the time (e.g., "feeling stressed").

[0774] 2. The device sends this information to the server, which preprocesses the data and analyzes it using machine learning models and an emotion engine.

[0775] 3. The server uses the user's input data and emotional data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[0776] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[0777] 5. The user enters feedback based on their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the device sends this to the server. The emotion engine also analyzes the user's emotional state.

[0778] 6. The server analyzes the feedback and sentiment data to help improve the algorithm and reassess the user's profile to improve future recommendations.

[0779] Thus, the present invention provides a system that recommends optimal residential locations by taking into account the user's lifestyle, personality, and emotional state. This system effectively functions using a user device, a server that performs data preprocessing and analysis, recommendation generation, feedback collection and analysis, and an emotion engine.

[0780] The processing flow will be explained below.

[0781] Step 1:

[0782] The user logs in to the system and the data entry screen for the residence search is displayed on the terminal. The user ID and password are used to log in.

[0783] Step 2:

[0784] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (such as access to transportation, medical facilities, educational institutions, and recreational facilities).

[0785] Step 3:

[0786] The terminal transmits these input data to the server.

[0787] Step 4:

[0788] The server retrieves the user data received, fills in missing values, standardizes the format, and performs data cleansing.

[0789] Step 5:

[0790] The server uses the pre-processed data to feed it into a machine learning model to generate a lifestyle and personality profile of the user.

[0791] Step 6:

[0792] The emotion engine analyzes the user's emotional state from input data, and performs emotion recognition through text and voice analysis.

[0793] Step 7:

[0794] The server integrates the emotion data obtained from the emotion engine with the personality profile to generate a comprehensive profile of the user.

[0795] Step 8:

[0796] The server compares the user's profile with the smart city database and performs an evaluation to recommend the most suitable place to live.

[0797] Step 9:

[0798] The server calculates the evaluation score of each residential location and generates a list of suitable residential locations for the user, including detailed information about each location (such as transportation access, availability of facilities, and environmental safety).

[0799] Step 10:

[0800] The server sends the recommendation list and detailed information to the terminal.

[0801] Step 11:

[0802] The device displays a recommendation list to the user, who can then browse the list and view detailed information about the potential residences.

[0803] Step 12:

[0804] The user selects the best place to live based on the recommendations and then enters the results and feedback, including the location's rating and emotional state.

[0805] Step 13:

[0806] The device sends the user's feedback and emotion data to the server.

[0807] Step 14:

[0808] The server analyzes the received feedback and sentiment data. The feedback data is used to analyze and improve the recommendation algorithm.

[0809] Step 15:

[0810] The server updates the algorithm based on the feedback analysis results that reflect the emotional data, improving the accuracy of future recommendations. It also reevaluates the user's profile and generates a new one.

[0811] In this way, users can find the place to live that best suits their individual lifestyle, personality, and even emotional state. The entire system is designed to work together to maximize the user's growth and happiness.

[0812] Example 2

[0813] 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."

[0814] There is a need for a system that can recommend optimal residential locations by taking into account users' diverse lifestyles, personalities, and emotional states. Conventional systems are based on fixed information about users and have the problem of being unable to respond to emotions or real-time changes in the situation. Therefore, it is necessary to provide more accurate recommendations that also take into account the user's emotional state.

[0815] 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.

[0816] In this invention, the server includes means for receiving user data, means for preprocessing the received data, means for analyzing the received data, means for generating a user's personality profile, means for evaluating potential housing sites and generating recommendations, means for analyzing feedback and improving algorithms, means for receiving and analyzing emotional data, and means for optimizing recommendations based on the emotional state, thereby enabling highly accurate residential site recommendations that reflect the user's emotional state in addition to their lifestyle and personality.

[0817] "User data" refers to information such as the user's lifestyle, personality information, emotional state, and desired conditions regarding the place of residence.

[0818] A "user terminal" is a device that a user uses to input data and check recommendations, and includes smartphones, personal computers, etc.

[0819] "Server" means the computer system that operates centrally to analyze and process data received from Users and generate recommendations.

[0820] "Means for preprocessing received data" refers to a process for standardizing user data, complementing missing values, and standardizing formats.

[0821] "Analysis Means" means the methods and techniques used to analyze and interpret the received data and generate a lifestyle and personality profile of the User.

[0822] A "personality profile" is a profile of personal characteristics generated based on a user's lifestyle, hobbies, and behavioral patterns.

[0823] The "recommendation generation means" is a process that selects and lists the most suitable housing candidates based on the user's profile.

[0824] "Emotion data" is information that indicates the user's current emotional state, and includes stress, happiness, satisfaction, and the like.

[0825] The "emotion engine" is a system that analyzes the user's emotional state from input data and monitors changes in emotions in real time.

[0826] "Feedback collection means" is the process of collecting user-entered ratings and additional requests for recommendations.

[0827] "Algorithm improvement" is the process of analyzing collected feedback and sentiment data to improve the recommendation algorithm.

[0828] An "optimizer" is a method that takes into account the user's emotional state to adjust recommendations and suggest the most suitable place to live for the user.

[0829] A "collaborative filtering algorithm" is a method for comparing data from multiple users and making recommendations based on similarities.

[0830] MODE FOR CARRYING OUT THE INVENTION

[0831] The present invention is a system that recommends optimal residential locations by taking into consideration not only the user's lifestyle and personality, but also the user's emotional state. This system is composed of hardware and software, such as a user terminal, a server, and an emotion engine.

[0832] Overall structure

[0833] First, a user accesses the system through a user terminal and inputs the necessary data, including their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired residential location. This data is then sent from the user terminal to the server.

[0834] The server preprocesses the data received from users, filling in missing values ​​and standardizing formats. It then uses machine learning models to analyze the data and generate personality profiles. It also uses an emotion engine to analyze users' emotional data and monitor their emotional state in real time.

[0835] The server then applies a recommendation algorithm based on the user's generated personality profile and emotional state to generate a list of optimal residential location recommendations, including detailed information on potential locations based on evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety.

[0836] Next, the device displays a list of recommended housing options to the user. The user can review the options and view detailed information. For example, a recommendation could include information such as, "I'm planning to be transferred to Tokyo, my hobby is running, I often work remotely, I'm a night owl, and I feel stressed."

[0837] Users can provide feedback on the recommendations, and the feedback and emotional data are sent back to the server, which can then use this feedback to improve existing algorithms and reassess the user's personality profile to improve the accuracy of future recommendations.

[0838] Hardware and software used

[0839] User device: A device such as a smartphone or PC is used to input user data and display a list of recommendations.

[0840] Server: A computer system that performs central data analysis and recommendation generation.

[0841] Emotion Engine: A software module for recognizing and analyzing a user's emotional state. It uses natural language processing techniques to extract emotions from text.

[0842] Machine learning models: Generate user profiles using techniques such as k-nearest neighbors and decision trees, and generate recommendations using collaborative filtering algorithms.

[0843] Specific examples

[0844] For example, if a user enters "I'm planning to transfer to Tokyo, I mostly work remotely, my hobby is running, I'm a night owl, and I've been feeling stressed lately," the system will act as follows:

[0845] 1. The user enters the necessary information on the user terminal and sends it to the server.

[0846] 2. The server preprocesses the received data and analyzes it using machine learning models and an emotion engine.

[0847] 3. The server generates a list of recommended housing candidates and sends it to the device.

[0848] 4. The device displays the recommendation list to the user, and the user checks the details.

[0849] 5. The user enters feedback on the recommendation and sends it to the server via the device.

[0850] 6. The server analyzes the feedback data to improve the algorithm and re-evaluate the user profile.

[0851] This method makes it possible to provide highly accurate recommendations that reflect the user's lifestyle and emotional state.

[0852] Prompt Sentence Examples

[0853] "I'm planning to be transferred to Tokyo. I do a lot of remote work at work, and my hobby is running. I'm a night owl, and I've been feeling stressed lately. Could you please tell me the best place to live?"

[0854] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0855] Step 1:

[0856] A user logs into the system using a terminal. The user enters a username and password and is authenticated. If the login is successful, a data entry screen for a residence search is displayed on the terminal.

[0857] Input: Username, Password

[0858] Output: Display of data entry screen

[0859] Step 2:

[0860] Users enter information such as their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired place of residence into a data entry screen. Specifically, they enter information such as "running," "remote work," "night owl," "feeling stressed," and "Tokyo."

[0861] Input: Lifestyle, hobbies, work style, sleep habits, diet, emotional state, desired location

[0862] Output: Prepare input data for sending

[0863] Step 3:

[0864] The device sends this input data to the server, where it is encrypted and securely delivered to the server.

[0865] Input: Input data

[0866] Output: Data sent to the server

[0867] Step 4:

[0868] The server preprocesses the user data it receives. This involves filling in missing values ​​and standardizing data formats. For example, if there is missing information in the input data, it is filled in based on past data or statistical models.

[0869] Input: User data

[0870] Output: Preprocessed data

[0871] Step 5:

[0872] The server analyzes the pre-processed data and uses machine learning models to generate a lifestyle and personality profile of the user. Models used include k-nearest neighbors and decision trees.

[0873] Input: Preprocessed data

[0874] Output: Personality profile

[0875] Step 6:

[0876] The emotion engine monitors the user's emotional state in real time and generates analytical results. It uses natural language processing technology to extract emotions from the user's text input.

[0877] Input: User emotion data

[0878] Output: Emotion analysis results

[0879] Step 7:

[0880] The server applies a recommendation algorithm based on the user's personality profile and emotional state, and uses a collaborative filtering algorithm to recommend the best place to live.

[0881] Input: Personality profile, emotion analysis results

[0882] Output: Recommendation list

[0883] Step 8:

[0884] The server generates a recommendation list and sends it to the device. The list includes detailed information about potential housing locations, including evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety. For example, the list includes candidate locations such as "Toyosu," "Shinagawa," and "Shibuya."

[0885] Input: Recommendation list

[0886] Output: List sent to terminal

[0887] Step 9:

[0888] The device displays a list of recommendations to the user, who can then browse detailed information and select a location that best suits their needs.

[0889] Input: Recommendation list

[0890] Output: The list displayed to the user

[0891] Step 10:

[0892] The user enters feedback on the recommendation. The feedback includes an evaluation of the place of residence and any additional desired conditions. For example, the user can enter content such as "I am very satisfied with the convenience of Toyosu."

[0893] Input: Feedback

[0894] Output: Feedback ready to be sent

[0895] Step 11:

[0896] The device sends the user's feedback and emotional data to the server, where it is again encrypted and transmitted securely.

[0897] Input: Feedback, emotion data

[0898] Output: Feedback and emotion data sent to the server

[0899] Step 12:

[0900] The server analyzes the feedback and sentiment data, improving existing algorithms and reassessing the user's personality profile to improve the accuracy of future recommendations.

[0901] Input: Feedback, emotion data

[0902] Output: Improved algorithm and re-evaluated profile

[0903] (Application example 2)

[0904] 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."

[0905] Conventional food delivery recommendation systems make recommendations based on a user's eating habits and preferences, but they are unable to make recommendations that take into account the user's real-time emotional state. This makes it difficult for users to select the optimal food delivery service that matches their emotional state at any given time. Furthermore, the lack of monitoring and analysis of the user's real-time emotional state makes it difficult to provide more personalized recommendations.

[0906] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0907] In this invention, the server includes means for real-time monitoring of the user's emotional state using an emotion analysis engine, and means for the server to generate food delivery options based on the user's personality profile and emotional state, thereby enabling personalized food delivery recommendations that take into account the user's real-time emotional state.

[0908] A "user terminal" is an electronic device that allows a user to access the system and input and display data.

[0909] "User data" refers to data that includes information about a user's lifestyle, personality, diet, emotional state, and so on.

[0910] A "server" is a computer system for receiving, preprocessing, and analyzing user data, and for generating and displaying recommendations.

[0911] The "receiving means" is a function for the server to receive data sent from the user terminal.

[0912] The "preprocessing means" is a function that complements missing values ​​and standardizes the format of received data.

[0913] The "analysis means" is a function that analyzes the pre-processed data and generates a personality profile and emotional state of the user.

[0914] A "personality profile" is a profile generated based on a user's lifestyle and personality characteristics.

[0915] An "emotion analysis engine" is an algorithm and software for analyzing a user's real-time emotional state.

[0916] A "recommendation" is a list of best candidates provided to a user.

[0917] "Feedback" refers to collected data of users' ratings and opinions on recommendations.

[0918] "Means for improving algorithms" is a function for improving existing algorithms based on feedback data.

[0919] "Food delivery options" are the food and meal options available for delivery to a user.

[0920] The invention is a system that recommends food delivery options based on a user's lifestyle, personality information, and real-time emotional state. Specifically, the system is implemented as follows.

[0921] Overall system configuration

[0922] The system includes a user terminal, a server, a sentiment analysis engine, and a machine learning model. The user terminal is responsible for inputting user data and displaying recommendations, while the server performs data preprocessing, analysis, recommendation generation, feedback collection, and algorithm improvement. The sentiment analysis engine monitors and analyzes the user's emotional state in real time.

[0923] Hardware and software used

[0924] Hardware: Smartphones (e.g., iPhone, Android devices), head-mounted displays (e.g., Oculus Quest 2)

[0925] Software: Sentiment analysis engine, machine learning model (e.g., TensorFlow), database (e.g., MySQL), application server (e.g., Node.js)

[0926] Processing flow

[0927] 1. The user terminal provides an interface for inputting user data. The user inputs details such as dietary habits, favorite foods, allergy information, and their emotional state at the time.

[0928] 2. The terminal sends the entered data to the server.

[0929] 3. The server receives the data and performs preprocessing such as unifying the data format and filling in missing values. The emotion analysis engine also analyzes the user's emotional state in real time.

[0930] 4. The server uses machine learning models to generate a personality profile of the user and recommends optimal food delivery options based on that profile and emotional state.

[0931] 5. The server generates a recommendation list and sends detailed information to the user terminal.

[0932] 6. The user device displays a recommendation list from which the user can make a selection.

[0933] 7. The user enters feedback on the recommendation, and the device sends the feedback and emotion data to the server.

[0934] 8. The server analyzes the feedback and sentiment data to improve the algorithm and re-evaluate the user profile.

[0935] Specific examples

[0936] For example, if a user is tired and wants to order a light meal, they can enter their user data and emotional state as follows:

[0937] Diet: Vegetable-based

[0938] Favorite food: Japanese food

[0939] Allergies: None

[0940] Emotional state: Tired

[0941] Example prompts to give to a generative AI model:

[0942] "The user is currently tired and has a preference for Japanese food based on their past ordering history. Please recommend the best light Japanese delivery options for the user."

[0943] Based on this prompt, the generative AI model recommends suitable food delivery options for the user and displays the results in real time, allowing users to easily find the best food delivery options that match their emotional state.

[0944] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0945] Step 1:

[0946] The user terminal provides an interface for inputting user data. The user inputs information about their diet, favorite foods, allergies, and current emotional state. This input data is used as the initial input for the system.

[0947] Step 2:

[0948] The device transmits the input data to the server, which includes lifestyle information, favorite foods, and emotional state.

[0949] Step 3:

[0950] The server receives user data and performs preprocessing such as standardizing the data format and filling in missing values. Specifically, it predicts and fills in missing data and prepares the data format for analysis.

[0951] Step 4:

[0952] The emotion analysis engine analyzes the user's emotional state in real time. The input is the raw data of the emotional state, and the output is the analyzed emotional evaluation result.

[0953] Step 5:

[0954] The server uses a machine learning model to generate a personality profile for the user. The input data is preprocessed user data and sentiment analysis results, and the output data is a combination of the personality profile and sentiment assessment.

[0955] Step 6:

[0956] The server generates prompts to recommend optimal food delivery options based on the generated personality profile and emotional state. The prompts are used as instructions for the generative AI model, and the output is a list of optimal delivery options.

[0957] Step 7:

[0958] The server generates a recommendation list and sends the details to the user's device, including specific information about each delivery option (menu, price, ratings, etc.).

[0959] Step 8:

[0960] The user terminal displays the recommendation list, allowing the user to check the recommendations.

[0961] Step 9:

[0962] Users enter feedback on the recommendations, including ratings and impressions of the selected options.

[0963] Step 10:

[0964] The terminal again transmits the feedback data and emotion data to the server.

[0965] Step 11:

[0966] The server analyzes the feedback and emotion data to improve existing recommendation algorithms and also reassess the user's personality profile based on the analysis results to improve the accuracy of future recommendations.

[0967] This series of steps allows users to receive the best food delivery recommendations that suit their emotional state at any given time.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] [Third embodiment]

[0972] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0973] 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.

[0974] 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).

[0975] 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.

[0976] 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.

[0977] 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).

[0978] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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."

[0984] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[0985] Program processing flow

[0986] Data Entry

[0987] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[0988] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, and desired residential conditions (e.g., transportation access, medical facilities, educational institutions, and recreational facilities).

[0989] 3. The device sends these input data to the server.

[0990] Data preprocessing and analysis

[0991] 1. The server receives the received user data, completes missing values, and standardizes the format of the data.

[0992] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[0993] 3. The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[0994] Recommendation generation and display

[0995] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[0996] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[0997] 3. The device displays the recommendation list to the user, allowing the user to review it.

[0998] Collecting and analyzing feedback

[0999] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[1000] 2. The terminal transmits the user's feedback data to the server.

[1001] 3. The server analyzes the received feedback data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[1002] Specific examples

[1003] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[1004] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[1005] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[1006] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[1007] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[1008] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[1009] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[1010] Thus, the present invention provides a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing their growth and happiness. This system effectively functions using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[1011] The processing flow will be explained below.

[1012] Step 1:

[1013] A user logs in to the system by entering their user ID and password on the login screen and clicking the login button.

[1014] Step 2:

[1015] The device sends the login information to the server, which authenticates the login information and returns a success message to the user.

[1016] Step 3:

[1017] The user displays a data entry screen for a residential search, which allows the user to specify a desired location for a job transfer or relocation.

[1018] Step 4:

[1019] Users input their lifestyle (hobbies, work style, sleeping habits, diet, etc.) and desired conditions (transportation access, medical facilities, educational institutions, entertainment facilities, etc.).

[1020] Step 5:

[1021] The terminal transmits the input user data to the server, which then retrieves the user's lifestyle information.

[1022] Step 6:

[1023] The server preprocesses the data it receives, standardizing the data format and filling in missing values. It also detects and removes outliers in the data.

[1024] Step 7:

[1025] The server inputs the pre-processed data into a machine learning model to generate a personality profile of the user, which includes the user's personality traits and lifestyle patterns.

[1026] Step 8:

[1027] The server compares the generated personality profile with the smart city database, evaluates multiple residential candidate locations, and calculates an evaluation score.

[1028] Step 9:

[1029] The server generates a list of potential residential locations, including detailed information about each location (e.g., accessibility, amenities, and environmental safety).

[1030] Step 10:

[1031] The server sends the recommendation list to the terminal.

[1032] Step 11:

[1033] The device displays a list of recommendations to the user, who can then view detailed information about each location and make the best choice.

[1034] Step 12:

[1035] Users enter feedback on the recommendations, including location ratings and additional preferences.

[1036] Step 13:

[1037] The terminal sends the user's feedback to the server.

[1038] Step 14:

[1039] The server receives and analyzes the feedback. The feedback data is used to improve the recommendation algorithm.

[1040] Step 15:

[1041] The server uses the improved algorithm to improve the accuracy of future recommendations, and the user's profile is also re-evaluated.

[1042] In this way, users can find the place to live that best suits their individual lifestyle and personality. The entire system is designed to work together and function effectively.

[1043] Example 1

[1044] 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."

[1045] In modern society, users face difficulties in finding a place to live that best suits their lifestyle and personality. Conventional residential search systems often fail to provide satisfactory results because they make recommendations based only on general criteria, without considering the user's detailed personality and lifestyle. Furthermore, they lack mechanisms for improving the accuracy of recommendations based on user feedback.

[1046] 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.

[1047] In this invention, the server includes means for generating a user's lifestyle and personality profile using a machine learning model, means for generating residential property recommendations based on user data and a city database, and means for improving the algorithm and increasing the accuracy of the recommendations in response to user feedback. This allows users to receive recommendations for optimal residential properties based on their detailed lifestyle and personality, and by incorporating the feedback, more accurate recommendations can be provided to each individual user.

[1048] A "user terminal" is a computing device or communication device used by a user.

[1049] "User data" is information provided by a user, including lifestyle, personality information, and desired conditions.

[1050] A "server" is a central computing device that receives and analyzes user data and generates recommendations.

[1051] The "pre-processing means for received data" is a processing means for complementing missing values ​​and standardizing the format of user data received by the server.

[1052] The "means for analyzing received data" refers to the means by which the server analyzes the pre-processed data and generates a profile of the user.

[1053] A "personality profile" is information that describes a user's lifestyle and personality traits, generated using a machine learning model.

[1054] "Possible residence locations" is a list of residence locations suitable for the user, recommended by the server.

[1055] A "recommendation" is a proposal for the optimal place to live generated by the server based on the user's lifestyle and desired conditions.

[1056] The "means for displaying a list of recommendations" is a means for the user terminal to display a list of candidate housing locations to the user.

[1057] The "feedback collection means" is a means for collecting opinions and evaluations of the recommendations from users.

[1058] The "means for analyzing feedback and improving algorithms" refers to the means by which the server analyzes feedback from users and improves the recommendation algorithm based on the analysis.

[1059] A "machine learning model" is an algorithm and its implementation that learns from data and makes predictions and classifications.

[1060] The "urban database" is a database containing information on potential residential locations, and evaluation criteria include transportation access, the availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1061] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[1062] Hardware and Software Use

[1063] The system implementation uses the following hardware and software:

[1064] User terminal: A device used by a user to input data, such as a smartphone or computer.

[1065] Server: A high-performance computing device that preprocesses, analyzes, and generates recommendations from received data.

[1066] Machine learning model: Uses Python's Scikit-learn library to generate a user's lifestyle and personality profile.

[1067] Database: A smart city database will be used to manage information such as transportation access, medical facilities, educational institutions, the availability of entertainment facilities, and safety.

[1068] Communication protocol: HTTPS is used to securely transmit data between the user terminal and the server.

[1069] System operation explanation

[1070] 1. When a user logs in to the system, a data entry screen for residential searches is displayed on the terminal. To log in, the user uses their user ID and password.

[1071] 2. Users input their lifestyle (e.g., "active" or "indoor"), hobbies (e.g., "running" or "reading"), work style (e.g., "remote work" or "office work"), sleep habits (e.g., "night owl" or "early to bed, early to rise"), and diet (e.g., "vegetarian" or "gourmet"), and also select the conditions for their desired place of residence (e.g., transportation access, availability of medical facilities, educational institutions, entertainment facilities, safety, etc.).

[1072] 3. The device sends these input data to the server in real time using HTTPS, which encrypts the data.

[1073] 4. The server receives the received user data and performs data imputation and formatting. For example, if there are missing values, it imputes them using the mean or median. It also standardizes the data format (for example, converting "yes / no" to "1 / 0").

[1074] 5. The server generates a lifestyle and personality profile of the user based on the preprocessed data, which is implemented using a machine learning library such as Scikit-learn in Python.

[1075] 6. The server uses the user's personality profile to run a recommendation algorithm, specifically a recommender system (e.g., collaborative filtering or content-based filtering) to determine the appropriate action.

[1076] 7. The server compares the user profile with the smart city database and generates a list of residential options that best suit the user. For example, it selects areas such as "Toyosu," "Shinagawa," and "Shibuya" from the Tokyo database.

[1077] 8. The server creates a list containing detailed information about the recommended housing candidates (e.g., location of the housing, surrounding facilities, environment, rent, etc.) and sends it to the terminal.

[1078] 9. The device displays this list to the user, allowing them to view more information, for example by displaying a map using the Google Maps API.

[1079] 10. The user enters feedback on the recommendation through the system. For example, they can enter a rating such as "The Toyosu area is very convenient" or additional preferences such as "I would prefer a place with a little more nature."

[1080] 11. The device transmits these feedback data to the server in real time using a secure communication channel.

[1081] 12. The server analyzes the received feedback data and improves the algorithm based on the analysis results. For example, by analyzing the text data of the feedback using natural language processing (NLP) technology, new user needs can be discovered. Based on the feedback, the server also reevaluates the user's personality profile and improves the accuracy of the system's recommendations.

[1082] Specific examples

[1083] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[1084] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[1085] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[1086] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[1087] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[1088] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[1089] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[1090] Thus, the present invention is a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing the user's growth and happiness. This system functions effectively using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[1091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1092] Step 1:

[1093] The user logs into the system and displays a data entry screen for a residence search on the terminal.

[1094] Input: User ID and password

[1095] Output: Data entry screen

[1096] Specific operation: The user launches a browser or app and enters their user ID and password into the login form. The device receives this and sends it to the authentication server. After successful authentication, a data entry screen for a home search is displayed.

[1097] Step 2:

[1098] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, eating habits, and desired place of residence.

[1099] Input: Lifestyle, hobbies, work style, sleeping habits, diet, desired conditions

[1100] Output: Input data

[1101] Specific operation: The user enters information into each field on the data entry screen (e.g., "Lifestyle: Active," "Hobbies: Running," "Work Style: Remote Work," etc.) and presses the "Send" button. The device then compiles this input data and sends it to the server.

[1102] Step 3:

[1103] The terminal transmits these input data to the server.

[1104] Input: User-entered data

[1105] Output: Data sent to the server

[1106] How it works: The device temporarily stores the data entered by the user and then transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[1107] Step 4:

[1108] The server receives the received user data, completes missing values ​​in the data, and standardizes the format.

[1109] Input: Received data

[1110] Output: Preprocessed data

[1111] Specific operation: The server validates the received data and fills in any missing values ​​with the mean or median. It also performs processing such as converting "yes / no" to "1 / 0" to unify the data format.

[1112] Step 5:

[1113] The server generates a lifestyle and personality profile of the user based on the pre-processed data.

[1114] Input: Preprocessed data

[1115] Output: Personality profile

[1116] How it works: The server uses machine learning models to analyze the pre-processed data and generate a profile that characterizes the user's lifestyle and personality.

[1117] Step 6:

[1118] The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[1119] Enter: personality profile

[1120] Output: Recommendation data

[1121] Specific operation: Based on the personality profile, the server runs a recommender system (e.g., collaborative filtering or content-based filtering) to create a list of optimal housing candidates.

[1122] Step 7:

[1123] The server compares the user's personality profile with a smart city database and generates a list of suitable housing options for the user.

[1124] Input: personality profile, smart city database

[1125] Output: List of potential housing locations

[1126] How it works: The server compares the smart city database with the user's personality profile, evaluating factors such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety. Based on this, it generates a list of recommended housing options.

[1127] Step 8:

[1128] The server creates detailed information about the recommended housing candidate locations and sends it to the terminal.

[1129] Input: List of potential housing locations

[1130] Output: A list of recommendations with detailed information

[1131] Specific operation: The server adds detailed information about the potential residence (e.g., location of the residence, surrounding facilities, environment, rent, etc.) to a recommendation list and sends it to the terminal.

[1132] Step 9:

[1133] The terminal displays the recommendation list to the user, allowing the user to check it.

[1134] Input: A list of recommendations with detailed information

[1135] Output: Displayed recommendation list

[1136] Specific operation: The device displays the received recommendation list in GUI format, allowing the user to view detailed information, and displays a map using the Google Maps API if necessary.

[1137] Step 10:

[1138] The user inputs feedback on the recommendation through the terminal.

[1139] Input: Feedback (ratings and desired conditions)

[1140] Output: Feedback data

[1141] Specific operation: After checking the recommendation list, the user inputs their own rating and any additional desired conditions, and presses the "Submit" button. The device then sends this feedback data to the server.

[1142] Step 11:

[1143] The terminal transmits the user feedback data to the server.

[1144] Input: Feedback data

[1145] Output: Data sent to the server

[1146] How it works: The device temporarily stores the user's feedback data and transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[1147] Step 12:

[1148] The server analyzes the received feedback data and uses it to improve existing algorithms, as well as reassess the user's personality profile to improve the accuracy of future recommendations.

[1149] Input: Feedback data

[1150] Output: Improved algorithm, updated personality profile

[1151] How it works: The server analyzes the feedback data using natural language processing (NLP) techniques, improves the recommendation algorithm based on the analysis results, and re-evaluates the user's personality profile based on the feedback to improve the accuracy of future recommendations.

[1152] (Application example 1)

[1153] 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."

[1154] In modern urban life, it is extremely difficult for an individual user to find a residential location that best suits their lifestyle and personality. Furthermore, simply displaying a list or providing text information does not allow the user to fully understand the actual environment of each candidate location, resulting in a decrease in the accuracy of property selection. Furthermore, it is difficult for users to provide detailed feedback on recommended candidate locations, which means the system cannot always reflect the user's latest needs. A system that solves these issues is needed.

[1155] 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.

[1156] In this invention, the server includes means for displaying detailed information about potential housing sites in the form of a virtual tour on a user terminal using augmented reality or virtual reality technology based on the user's lifestyle and personality profile, means for collecting and analyzing user feedback, and means for improving the algorithm based on the feedback. This allows users to check detailed environmental information about the recommended housing sites through the virtual tour before actually visiting them, allowing them to select a home that suits them with greater accuracy. Furthermore, the system can always provide optimal recommendations based on user feedback.

[1157] A "user terminal" is an electronic device used by a user to input data, display and provide feedback.

[1158] "User data" is a collection of information entered by a user based on their lifestyle and personality characteristics.

[1159] A "server" is a computer system that receives user data, performs pre-processing and analysis, generates recommendations, and processes feedback.

[1160] "Preprocessing of received data" refers to data cleaning work performed by the server, such as filling in missing values ​​and standardizing the format of the received data.

[1161] "Analysis of received data" is the process by which the server analyzes user data and generates a personality profile.

[1162] A "personality profile" is profile information that includes characteristics such as a user's lifestyle, hobbies, and work style.

[1163] "Evaluation of potential residential locations" is the process of evaluating conditions such as convenience and environment of selected potential locations by comparing them with a personality profile.

[1164] "Recommendation generation" is the process of suggesting the best possible housing locations based on the analyzed personality profile.

[1165] "Displaying a list of recommendations" means displaying a list of recommended housing candidates on the user terminal.

[1166] "Feedback" refers to the input of a user's opinion on the recommendation results, additional desired conditions, and the like.

[1167] "Feedback collection" is the process of collecting feedback information input by users from their terminals to the server.

[1168] "Algorithm improvement" is the process of updating recommendation algorithms and improving their accuracy based on collected feedback.

[1169] "Augmented reality" is a technology that overlays digital information onto the real world.

[1170] "Virtual reality" is a technology that allows users to experience a three-dimensional virtual environment generated by a computer.

[1171] A "virtual tour" is a feature that uses augmented reality or virtual reality to allow users to explore a location in a virtual space without actually visiting the location.

[1172] In one embodiment of the present invention, a system is used that combines a user terminal, a server, and augmented reality (AR) or virtual reality (VR) technology. The user terminal may be a smartphone, smart glasses, or a head-mounted display.

[1173] 1. Data Entry

[1174] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and recreational facilities). This data is then sent from the device to a server.

[1175] 2. Data Preprocessing and Analysis

[1176] The server receives the data from the user, fills in missing values, and standardizes the format. Once the data is cleaned, a machine learning model is used to generate a personality profile for the user. Pandas and Scikit-learn are used as data analysis tools to generate this profile.

[1177] 3. Recommendation Generation

[1178] The server compares the generated user's personality profile with the smart city database to create a list of recommendations for optimal housing options, including evaluation criteria such as transportation access, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1179] 4. Displaying Recommendations

[1180] The user device not only displays the recommendation list, but also uses augmented reality or virtual reality technology to display detailed information about the recommended housing candidate sites in the form of a virtual tour. This virtual tour allows users to see the interior and surrounding environment of the property without actually visiting it. This is done using development platforms such as ARKit (Apple) and ARCore (Google).

[1181] 5. Feedback collection and analysis

[1182] Users input feedback based on the recommendation results. This feedback includes ratings and additional preferences. The feedback data is sent from the device to the server, which analyzes it and uses it to improve the algorithm. Based on the analysis results, the user's personality profile and the accuracy of the recommendations are improved.

[1183] Specific examples

[1184] If a user plans to relocate to Tokyo, they log in to the system and enter "Tokyo" as the city they will be relocated to. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and pet type (e.g., "dog"). The device sends this information to the server, which preprocesses the data and then uses a machine learning model to generate a personality profile. A recommendation list is created, suggesting potential housing locations such as "Minami-Aoyama" and "Meguro." The user can then put on the smart glasses and experience a virtual tour of these potential locations in augmented reality.

[1185] Example prompts for generative AI models

[1186] "I love reading, I work remotely, and I have a cat. Please recommend the best place to live that meets these criteria."

[1187] As described above, the present invention allows users to efficiently go through the process of finding the home that best suits them.

[1188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1189] Program processing flow

[1190] Step 1: Data entry

[1191] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and entertainment facilities). This data is then sent from the device to a server.

[1192] Input: Hobbies, work style, whether you have pets, desired location

[1193] Output: User data is sent to the server

[1194] Step 2: Preprocessing the data

[1195] The server performs missing value imputation and format unification on the data received from the user. Here, Pandas is used to clean the data.

[1196] Input: User data

[1197] Output: Preprocessed data

[1198] Specific operation: Impute missing values ​​and unify data formats

[1199] Step 3: Generate a personality profile

[1200] The server uses a machine learning model, in this case Scikit-learn, to generate a user personality profile from the preprocessed data.

[1201] Input: Preprocessed data

[1202] Output: Personality profile

[1203] What happens: Feed data into a machine learning model to build a personality profile

[1204] Step 4: Recommendation Generation

[1205] The server compares the generated personality profile with the smart city database to create a list of recommendations for optimal housing options, based on evaluation criteria such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety.

[1206] Input: Personality profile, Smart City database

[1207] Output: Recommendation list

[1208] Specific operation: Match the profile with the database and evaluate the candidate site based on each evaluation item.

[1209] Step 5: View recommendations

[1210] The user terminal displays the recommendation list and also displays detailed information about the recommended housing candidates in the form of a virtual tour using augmented reality (AR) or virtual reality (VR) technology.

[1211] Input: Recommendation list

[1212] Output: Detailed information displayed in a virtual tour format

[1213] What it does: Uses ARKit or ARCore to display detailed information in a virtual tour format.

[1214] Step 6: Gather feedback

[1215] The user inputs feedback on the recommendation results, including ratings and additional desired conditions, and the feedback data is sent from the terminal to the server.

[1216] Input: Feedback (rating, additional requirements, etc.)

[1217] Output: Feedback data sent to the server

[1218] What it does: Collects input from users through a feedback form

[1219] Step 7: Analyzing feedback and improving the algorithm

[1220] The server analyzes the collected feedback to improve the recommendation algorithm, which includes the process of optimizing the parameters of the algorithm based on the collected feedback data.

[1221] Input: Feedback data

[1222] Output: An improved recommendation algorithm

[1223] Specific behavior: Analyze feedback data and optimize parameters of recommendation algorithms

[1224] 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.

[1225] This invention combines a system that recommends optimal residential locations based on a user's lifestyle and personality with an emotion engine that recognizes the user's emotions. This system inputs user data and emotion data via the user's terminal, analyzes and processes the data on the server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[1226] Program processing flow

[1227] Data Entry

[1228] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[1229] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (e.g., access to transportation, medical facilities, educational institutions, and recreational facilities).

[1230] 3. The device sends these input data to the server.

[1231] Data preprocessing and analysis

[1232] 1. The server receives the user data. It fills in missing values ​​and standardizes the format of the data. The emotion engine also analyzes the user's emotional state.

[1233] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[1234] 3. The emotion engine monitors the user's emotional state in real time and generates analytical results.

[1235] 4. The server applies an algorithm to make optimal recommendations based on the user's personality profile and emotional state.

[1236] Recommendation generation and display

[1237] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1238] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[1239] 3. The device displays the recommendation list to the user, allowing the user to review it.

[1240] Collecting and analyzing feedback

[1241] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[1242] 2. The device sends the user's feedback and emotion data to the server.

[1243] 3. The server analyzes the received feedback and sentiment data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[1244] Specific examples

[1245] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[1246] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), sleep habits (e.g., "night owl"), etc. They also enter their emotional state at the time (e.g., "feeling stressed").

[1247] 2. The device sends this information to the server, which preprocesses the data and analyzes it using machine learning models and an emotion engine.

[1248] 3. The server uses the user's input data and emotional data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[1249] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[1250] 5. The user enters feedback based on their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the device sends this to the server. The emotion engine also analyzes the user's emotional state.

[1251] 6. The server analyzes the feedback and sentiment data to help improve the algorithm and reassess the user's profile to improve future recommendations.

[1252] Thus, the present invention provides a system that recommends optimal residential locations by taking into account the user's lifestyle, personality, and emotional state. This system effectively functions using a user device, a server that performs data preprocessing and analysis, recommendation generation, feedback collection and analysis, and an emotion engine.

[1253] The processing flow will be explained below.

[1254] Step 1:

[1255] The user logs in to the system and the data entry screen for the residence search is displayed on the terminal. The user ID and password are used to log in.

[1256] Step 2:

[1257] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (such as access to transportation, medical facilities, educational institutions, and recreational facilities).

[1258] Step 3:

[1259] The terminal transmits these input data to the server.

[1260] Step 4:

[1261] The server retrieves the user data received, fills in missing values, standardizes the format, and performs data cleansing.

[1262] Step 5:

[1263] The server uses the pre-processed data to feed it into a machine learning model to generate a lifestyle and personality profile of the user.

[1264] Step 6:

[1265] The emotion engine analyzes the user's emotional state from input data, and performs emotion recognition through text and voice analysis.

[1266] Step 7:

[1267] The server integrates the emotion data obtained from the emotion engine with the personality profile to generate a comprehensive profile of the user.

[1268] Step 8:

[1269] The server compares the user's profile with the smart city database and performs an evaluation to recommend the most suitable place to live.

[1270] Step 9:

[1271] The server calculates the evaluation score of each residential location and generates a list of suitable residential locations for the user, including detailed information about each location (such as transportation access, availability of facilities, and environmental safety).

[1272] Step 10:

[1273] The server sends the recommendation list and detailed information to the terminal.

[1274] Step 11:

[1275] The device displays a recommendation list to the user, who can then browse the list and view detailed information about the potential residences.

[1276] Step 12:

[1277] The user selects the best place to live based on the recommendations and then enters the results and feedback, including the location's rating and emotional state.

[1278] Step 13:

[1279] The device sends the user's feedback and emotion data to the server.

[1280] Step 14:

[1281] The server analyzes the received feedback and sentiment data. The feedback data is used to analyze and improve the recommendation algorithm.

[1282] Step 15:

[1283] The server updates the algorithm based on the feedback analysis results that reflect the emotional data, improving the accuracy of future recommendations. It also reevaluates the user's profile and generates a new one.

[1284] In this way, users can find the place to live that best suits their individual lifestyle, personality, and even emotional state. The entire system is designed to work together to maximize the user's growth and happiness.

[1285] Example 2

[1286] 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."

[1287] There is a need for a system that can recommend optimal residential locations by taking into account users' diverse lifestyles, personalities, and emotional states. Conventional systems are based on fixed information about users and have the problem of being unable to respond to emotions or real-time changes in the situation. Therefore, it is necessary to provide more accurate recommendations that also take into account the user's emotional state.

[1288] 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.

[1289] In this invention, the server includes means for receiving user data, means for preprocessing the received data, means for analyzing the received data, means for generating a user's personality profile, means for evaluating potential housing sites and generating recommendations, means for analyzing feedback and improving algorithms, means for receiving and analyzing emotional data, and means for optimizing recommendations based on the emotional state, thereby enabling highly accurate residential site recommendations that reflect the user's emotional state in addition to their lifestyle and personality.

[1290] "User data" refers to information such as the user's lifestyle, personality information, emotional state, and desired conditions regarding the place of residence.

[1291] A "user terminal" is a device that a user uses to input data and check recommendations, and includes smartphones, personal computers, etc.

[1292] "Server" means the computer system that operates centrally to analyze and process data received from Users and generate recommendations.

[1293] "Means for preprocessing received data" refers to a process for standardizing user data, complementing missing values, and standardizing formats.

[1294] "Analysis Means" means the methods and techniques used to analyze and interpret the received data and generate a lifestyle and personality profile of the User.

[1295] A "personality profile" is a profile of personal characteristics generated based on a user's lifestyle, hobbies, and behavioral patterns.

[1296] The "recommendation generation means" is a process that selects and lists the most suitable housing candidates based on the user's profile.

[1297] "Emotion data" is information that indicates the user's current emotional state, and includes stress, happiness, satisfaction, and the like.

[1298] The "emotion engine" is a system that analyzes the user's emotional state from input data and monitors changes in emotions in real time.

[1299] "Feedback collection means" is the process of collecting user-entered ratings and additional requests for recommendations.

[1300] "Algorithm improvement" is the process of analyzing collected feedback and sentiment data to improve the recommendation algorithm.

[1301] An "optimizer" is a method that takes into account the user's emotional state to adjust recommendations and suggest the most suitable place to live for the user.

[1302] A "collaborative filtering algorithm" is a method for comparing data from multiple users and making recommendations based on similarities.

[1303] MODE FOR CARRYING OUT THE INVENTION

[1304] The present invention is a system that recommends optimal residential locations by taking into consideration not only the user's lifestyle and personality, but also the user's emotional state. This system is composed of hardware and software, such as a user terminal, a server, and an emotion engine.

[1305] Overall structure

[1306] First, a user accesses the system through a user terminal and inputs the necessary data, including their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired residential location. This data is then sent from the user terminal to the server.

[1307] The server preprocesses the data received from users, filling in missing values ​​and standardizing formats. It then uses machine learning models to analyze the data and generate personality profiles. It also uses an emotion engine to analyze users' emotional data and monitor their emotional state in real time.

[1308] The server then applies a recommendation algorithm based on the user's generated personality profile and emotional state to generate a list of optimal residential location recommendations, including detailed information on potential locations based on evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety.

[1309] Next, the device displays a list of recommended housing options to the user. The user can review the options and view detailed information. For example, a recommendation could include information such as, "I'm planning to be transferred to Tokyo, my hobby is running, I often work remotely, I'm a night owl, and I feel stressed."

[1310] Users can provide feedback on the recommendations, and the feedback and emotional data are sent back to the server, which can then use this feedback to improve existing algorithms and reassess the user's personality profile to improve the accuracy of future recommendations.

[1311] Hardware and software used

[1312] User device: A device such as a smartphone or PC is used to input user data and display a list of recommendations.

[1313] Server: A computer system that performs central data analysis and recommendation generation.

[1314] Emotion Engine: A software module for recognizing and analyzing a user's emotional state. It uses natural language processing techniques to extract emotions from text.

[1315] Machine learning models: Generate user profiles using techniques such as k-nearest neighbors and decision trees, and generate recommendations using collaborative filtering algorithms.

[1316] Specific examples

[1317] For example, if a user enters "I'm planning to transfer to Tokyo, I mostly work remotely, my hobby is running, I'm a night owl, and I've been feeling stressed lately," the system will act as follows:

[1318] 1. The user enters the necessary information on the user terminal and sends it to the server.

[1319] 2. The server preprocesses the received data and analyzes it using machine learning models and an emotion engine.

[1320] 3. The server generates a list of recommended housing candidates and sends it to the device.

[1321] 4. The device displays the recommendation list to the user, and the user checks the details.

[1322] 5. The user enters feedback on the recommendation and sends it to the server via the device.

[1323] 6. The server analyzes the feedback data to improve the algorithm and re-evaluate the user profile.

[1324] This method makes it possible to provide highly accurate recommendations that reflect the user's lifestyle and emotional state.

[1325] Prompt Sentence Examples

[1326] "I'm planning to be transferred to Tokyo. I do a lot of remote work at work, and my hobby is running. I'm a night owl, and I've been feeling stressed lately. Could you please tell me the best place to live?"

[1327] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1328] Step 1:

[1329] A user logs into the system using a terminal. The user enters a username and password and is authenticated. If the login is successful, a data entry screen for a residence search is displayed on the terminal.

[1330] Input: Username, Password

[1331] Output: Display of data entry screen

[1332] Step 2:

[1333] Users enter information such as their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired place of residence into a data entry screen. Specifically, they enter information such as "running," "remote work," "night owl," "feeling stressed," and "Tokyo."

[1334] Input: Lifestyle, hobbies, work style, sleep habits, diet, emotional state, desired location

[1335] Output: Prepare input data for sending

[1336] Step 3:

[1337] The device sends this input data to the server, where it is encrypted and securely delivered to the server.

[1338] Input: Input data

[1339] Output: Data sent to the server

[1340] Step 4:

[1341] The server preprocesses the user data it receives. This involves filling in missing values ​​and standardizing data formats. For example, if there is missing information in the input data, it is filled in based on past data or statistical models.

[1342] Input: User data

[1343] Output: Preprocessed data

[1344] Step 5:

[1345] The server analyzes the pre-processed data and uses machine learning models to generate a lifestyle and personality profile of the user. Models used include k-nearest neighbors and decision trees.

[1346] Input: Preprocessed data

[1347] Output: Personality profile

[1348] Step 6:

[1349] The emotion engine monitors the user's emotional state in real time and generates analytical results. It uses natural language processing technology to extract emotions from the user's text input.

[1350] Input: User emotion data

[1351] Output: Emotion analysis results

[1352] Step 7:

[1353] The server applies a recommendation algorithm based on the user's personality profile and emotional state, and uses a collaborative filtering algorithm to recommend the best place to live.

[1354] Input: Personality profile, emotion analysis results

[1355] Output: Recommendation list

[1356] Step 8:

[1357] The server generates a recommendation list and sends it to the device. The list includes detailed information about potential housing locations, including evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety. For example, the list includes candidate locations such as "Toyosu," "Shinagawa," and "Shibuya."

[1358] Input: Recommendation list

[1359] Output: List sent to terminal

[1360] Step 9:

[1361] The device displays a list of recommendations to the user, who can then browse detailed information and select a location that best suits their needs.

[1362] Input: Recommendation list

[1363] Output: The list displayed to the user

[1364] Step 10:

[1365] The user enters feedback on the recommendation. The feedback includes an evaluation of the place of residence and any additional desired conditions. For example, the user can enter content such as "I am very satisfied with the convenience of Toyosu."

[1366] Input: Feedback

[1367] Output: Feedback ready to be sent

[1368] Step 11:

[1369] The device sends the user's feedback and emotional data to the server, where it is again encrypted and transmitted securely.

[1370] Input: Feedback, emotion data

[1371] Output: Feedback and emotion data sent to the server

[1372] Step 12:

[1373] The server analyzes the feedback and sentiment data, improving existing algorithms and reassessing the user's personality profile to improve the accuracy of future recommendations.

[1374] Input: Feedback, emotion data

[1375] Output: Improved algorithm and re-evaluated profile

[1376] (Application example 2)

[1377] 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."

[1378] Conventional food delivery recommendation systems make recommendations based on a user's eating habits and preferences, but they are unable to make recommendations that take into account the user's real-time emotional state. This makes it difficult for users to select the optimal food delivery service that matches their emotional state at any given time. Furthermore, the lack of monitoring and analysis of the user's real-time emotional state makes it difficult to provide more personalized recommendations.

[1379] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1380] In this invention, the server includes means for real-time monitoring of the user's emotional state using an emotion analysis engine, and means for the server to generate food delivery options based on the user's personality profile and emotional state, thereby enabling personalized food delivery recommendations that take into account the user's real-time emotional state.

[1381] A "user terminal" is an electronic device that allows a user to access the system and input and display data.

[1382] "User data" refers to data that includes information about a user's lifestyle, personality, diet, emotional state, and so on.

[1383] A "server" is a computer system for receiving, preprocessing, and analyzing user data, and for generating and displaying recommendations.

[1384] The "receiving means" is a function for the server to receive data sent from the user terminal.

[1385] The "preprocessing means" is a function that complements missing values ​​and standardizes the format of received data.

[1386] The "analysis means" is a function that analyzes the pre-processed data and generates a personality profile and emotional state of the user.

[1387] A "personality profile" is a profile generated based on a user's lifestyle and personality characteristics.

[1388] An "emotion analysis engine" is an algorithm and software for analyzing a user's real-time emotional state.

[1389] A "recommendation" is a list of best candidates provided to a user.

[1390] "Feedback" refers to collected data of users' ratings and opinions on recommendations.

[1391] "Means for improving algorithms" is a function for improving existing algorithms based on feedback data.

[1392] "Food delivery options" are the food and meal options available for delivery to a user.

[1393] The invention is a system that recommends food delivery options based on a user's lifestyle, personality information, and real-time emotional state. Specifically, the system is implemented as follows.

[1394] Overall system configuration

[1395] The system includes a user terminal, a server, a sentiment analysis engine, and a machine learning model. The user terminal is responsible for inputting user data and displaying recommendations, while the server performs data preprocessing, analysis, recommendation generation, feedback collection, and algorithm improvement. The sentiment analysis engine monitors and analyzes the user's emotional state in real time.

[1396] Hardware and software used

[1397] Hardware: Smartphones (e.g., iPhone, Android devices), head-mounted displays (e.g., Oculus Quest 2)

[1398] Software: Sentiment analysis engine, machine learning model (e.g., TensorFlow), database (e.g., MySQL), application server (e.g., Node.js)

[1399] Processing flow

[1400] 1. The user terminal provides an interface for inputting user data. The user inputs details such as dietary habits, favorite foods, allergy information, and their emotional state at the time.

[1401] 2. The terminal sends the entered data to the server.

[1402] 3. The server receives the data and performs preprocessing such as unifying the data format and filling in missing values. The emotion analysis engine also analyzes the user's emotional state in real time.

[1403] 4. The server uses machine learning models to generate a personality profile of the user and recommends optimal food delivery options based on that profile and emotional state.

[1404] 5. The server generates a recommendation list and sends detailed information to the user terminal.

[1405] 6. The user device displays a recommendation list from which the user can make a selection.

[1406] 7. The user enters feedback on the recommendation, and the device sends the feedback and emotion data to the server.

[1407] 8. The server analyzes the feedback and sentiment data to improve the algorithm and re-evaluate the user profile.

[1408] Specific examples

[1409] For example, if a user is tired and wants to order a light meal, they can enter their user data and emotional state as follows:

[1410] Diet: Vegetable-based

[1411] Favorite food: Japanese food

[1412] Allergies: None

[1413] Emotional state: Tired

[1414] Example prompts to give to a generative AI model:

[1415] "The user is currently tired and has a preference for Japanese food based on their past ordering history. Please recommend the best light Japanese delivery options for the user."

[1416] Based on this prompt, the generative AI model recommends suitable food delivery options for the user and displays the results in real time, allowing users to easily find the best food delivery options that match their emotional state.

[1417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1418] Step 1:

[1419] The user terminal provides an interface for inputting user data. The user inputs information about their diet, favorite foods, allergies, and current emotional state. This input data is used as the initial input for the system.

[1420] Step 2:

[1421] The device transmits the input data to the server, which includes lifestyle information, favorite foods, and emotional state.

[1422] Step 3:

[1423] The server receives user data and performs preprocessing such as standardizing the data format and filling in missing values. Specifically, it predicts and fills in missing data and prepares the data format for analysis.

[1424] Step 4:

[1425] The emotion analysis engine analyzes the user's emotional state in real time. The input is the raw data of the emotional state, and the output is the analyzed emotional evaluation result.

[1426] Step 5:

[1427] The server uses a machine learning model to generate a personality profile for the user. The input data is preprocessed user data and sentiment analysis results, and the output data is a combination of the personality profile and sentiment assessment.

[1428] Step 6:

[1429] The server generates prompts to recommend optimal food delivery options based on the generated personality profile and emotional state. The prompts are used as instructions for the generative AI model, and the output is a list of optimal delivery options.

[1430] Step 7:

[1431] The server generates a recommendation list and sends the details to the user's device, including specific information about each delivery option (menu, price, ratings, etc.).

[1432] Step 8:

[1433] The user terminal displays the recommendation list, allowing the user to check the recommendations.

[1434] Step 9:

[1435] Users enter feedback on the recommendations, including ratings and impressions of the selected options.

[1436] Step 10:

[1437] The terminal again transmits the feedback data and emotion data to the server.

[1438] Step 11:

[1439] The server analyzes the feedback and emotion data to improve existing recommendation algorithms and also reassess the user's personality profile based on the analysis results to improve the accuracy of future recommendations.

[1440] This series of steps allows users to receive the best food delivery recommendations that suit their emotional state at any given time.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] [Fourth embodiment]

[1445] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1446] 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.

[1447] 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).

[1448] 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.

[1449] 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.

[1450] 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).

[1451] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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."

[1458] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[1459] Program processing flow

[1460] Data Entry

[1461] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[1462] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, and desired residential conditions (e.g., transportation access, medical facilities, educational institutions, and recreational facilities).

[1463] 3. The device sends these input data to the server.

[1464] Data preprocessing and analysis

[1465] 1. The server receives the received user data, completes missing values, and standardizes the format of the data.

[1466] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[1467] 3. The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[1468] Recommendation generation and display

[1469] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1470] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[1471] 3. The device displays the recommendation list to the user, allowing the user to review it.

[1472] Collecting and analyzing feedback

[1473] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[1474] 2. The terminal transmits the user's feedback data to the server.

[1475] 3. The server analyzes the received feedback data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[1476] Specific examples

[1477] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[1478] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[1479] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[1480] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[1481] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[1482] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[1483] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[1484] Thus, the present invention provides a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing their growth and happiness. This system effectively functions using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[1485] The processing flow will be explained below.

[1486] Step 1:

[1487] A user logs in to the system by entering their user ID and password on the login screen and clicking the login button.

[1488] Step 2:

[1489] The device sends the login information to the server, which authenticates the login information and returns a success message to the user.

[1490] Step 3:

[1491] The user displays a data entry screen for a residential search, which allows the user to specify a desired location for a job transfer or relocation.

[1492] Step 4:

[1493] Users input their lifestyle (hobbies, work style, sleeping habits, diet, etc.) and desired conditions (transportation access, medical facilities, educational institutions, entertainment facilities, etc.).

[1494] Step 5:

[1495] The terminal transmits the input user data to the server, which then retrieves the user's lifestyle information.

[1496] Step 6:

[1497] The server preprocesses the data it receives, standardizing the data format and filling in missing values. It also detects and removes outliers in the data.

[1498] Step 7:

[1499] The server inputs the pre-processed data into a machine learning model to generate a personality profile of the user, which includes the user's personality traits and lifestyle patterns.

[1500] Step 8:

[1501] The server compares the generated personality profile with the smart city database, evaluates multiple residential candidate locations, and calculates an evaluation score.

[1502] Step 9:

[1503] The server generates a list of potential residential locations, including detailed information about each location (e.g., accessibility, amenities, and environmental safety).

[1504] Step 10:

[1505] The server sends the recommendation list to the terminal.

[1506] Step 11:

[1507] The device displays a list of recommendations to the user, who can then view detailed information about each location and make the best choice.

[1508] Step 12:

[1509] Users enter feedback on the recommendations, including location ratings and additional preferences.

[1510] Step 13:

[1511] The terminal sends the user's feedback to the server.

[1512] Step 14:

[1513] The server receives and analyzes the feedback. The feedback data is used to improve the recommendation algorithm.

[1514] Step 15:

[1515] The server uses the improved algorithm to improve the accuracy of future recommendations, and the user's profile is also re-evaluated.

[1516] In this way, users can find the place to live that best suits their individual lifestyle and personality. The entire system is designed to work together and function effectively.

[1517] Example 1

[1518] 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."

[1519] In modern society, users face difficulties in finding a place to live that best suits their lifestyle and personality. Conventional residential search systems often fail to provide satisfactory results because they make recommendations based only on general criteria, without considering the user's detailed personality and lifestyle. Furthermore, they lack mechanisms for improving the accuracy of recommendations based on user feedback.

[1520] 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.

[1521] In this invention, the server includes means for generating a user's lifestyle and personality profile using a machine learning model, means for generating residential property recommendations based on user data and a city database, and means for improving the algorithm and increasing the accuracy of the recommendations in response to user feedback. This allows users to receive recommendations for optimal residential properties based on their detailed lifestyle and personality, and by incorporating the feedback, more accurate recommendations can be provided to each individual user.

[1522] A "user terminal" is a computing device or communication device used by a user.

[1523] "User data" is information provided by a user, including lifestyle, personality information, and desired conditions.

[1524] A "server" is a central computing device that receives and analyzes user data and generates recommendations.

[1525] The "pre-processing means for received data" is a processing means for complementing missing values ​​and standardizing the format of user data received by the server.

[1526] The "means for analyzing received data" refers to the means by which the server analyzes the pre-processed data and generates a profile of the user.

[1527] A "personality profile" is information that describes a user's lifestyle and personality traits, generated using a machine learning model.

[1528] "Possible residence locations" is a list of residence locations suitable for the user, recommended by the server.

[1529] A "recommendation" is a proposal for the optimal place to live generated by the server based on the user's lifestyle and desired conditions.

[1530] The "means for displaying a list of recommendations" is a means for the user terminal to display a list of candidate housing locations to the user.

[1531] The "feedback collection means" is a means for collecting opinions and evaluations of the recommendations from users.

[1532] The "means for analyzing feedback and improving algorithms" refers to the means by which the server analyzes feedback from users and improves the recommendation algorithm based on the analysis.

[1533] A "machine learning model" is an algorithm and its implementation that learns from data and makes predictions and classifications.

[1534] The "urban database" is a database containing information on potential residential locations, and evaluation criteria include transportation access, the availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1535] This invention relates to a system that recommends optimal residential locations based on the user's lifestyle and personality. This system inputs user data via the user's terminal, analyzes and processes the data on a server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[1536] Hardware and Software Use

[1537] The system implementation uses the following hardware and software:

[1538] User terminal: A device used by a user to input data, such as a smartphone or computer.

[1539] Server: A high-performance computing device that preprocesses, analyzes, and generates recommendations from received data.

[1540] Machine learning model: Uses Python's Scikit-learn library to generate a user's lifestyle and personality profile.

[1541] Database: A smart city database will be used to manage information such as transportation access, medical facilities, educational institutions, the availability of entertainment facilities, and safety.

[1542] Communication protocol: HTTPS is used to securely transmit data between the user terminal and the server.

[1543] System operation explanation

[1544] 1. When a user logs in to the system, a data entry screen for residential searches is displayed on the terminal. To log in, the user uses their user ID and password.

[1545] 2. Users input their lifestyle (e.g., "active" or "indoor"), hobbies (e.g., "running" or "reading"), work style (e.g., "remote work" or "office work"), sleep habits (e.g., "night owl" or "early to bed, early to rise"), and diet (e.g., "vegetarian" or "gourmet"), and also select the conditions for their desired place of residence (e.g., transportation access, availability of medical facilities, educational institutions, entertainment facilities, safety, etc.).

[1546] 3. The device sends these input data to the server in real time using HTTPS, which encrypts the data.

[1547] 4. The server receives the received user data and performs data imputation and formatting. For example, if there are missing values, it imputes them using the mean or median. It also standardizes the data format (for example, converting "yes / no" to "1 / 0").

[1548] 5. The server generates a lifestyle and personality profile of the user based on the preprocessed data, which is implemented using a machine learning library such as Scikit-learn in Python.

[1549] 6. The server uses the user's personality profile to run a recommendation algorithm, specifically a recommender system (e.g., collaborative filtering or content-based filtering) to determine the appropriate action.

[1550] 7. The server compares the user profile with the smart city database and generates a list of residential options that best suit the user. For example, it selects areas such as "Toyosu," "Shinagawa," and "Shibuya" from the Tokyo database.

[1551] 8. The server creates a list containing detailed information about the recommended housing candidates (e.g., location of the housing, surrounding facilities, environment, rent, etc.) and sends it to the terminal.

[1552] 9. The device displays this list to the user, allowing them to view more information, for example by displaying a map using the Google Maps API.

[1553] 10. The user enters feedback on the recommendation through the system. For example, they can enter a rating such as "The Toyosu area is very convenient" or additional preferences such as "I would prefer a place with a little more nature."

[1554] 11. The device transmits these feedback data to the server in real time using a secure communication channel.

[1555] 12. The server analyzes the received feedback data and improves the algorithm based on the analysis results. For example, by analyzing the text data of the feedback using natural language processing (NLP) technology, new user needs can be discovered. Based on the feedback, the server also reevaluates the user's personality profile and improves the accuracy of the system's recommendations.

[1556] Specific examples

[1557] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[1558] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and sleeping habits (e.g., "night owl").

[1559] 2. The device sends this information to the server, which then preprocesses the data and analyzes it using a machine learning model.

[1560] 3. The server uses the user's input data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[1561] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[1562] 5. The user enters feedback based on the results of their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the terminal sends this to the server.

[1563] 6. The server analyzes the feedback to help improve the algorithm and re-evaluate the user's profile to improve future recommendations.

[1564] Thus, the present invention is a system that recommends optimal residential locations based on a user's lifestyle and personality, maximizing the user's growth and happiness. This system functions effectively using user devices and a server that performs data preprocessing and analysis, recommendation generation, and feedback collection and analysis.

[1565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1566] Step 1:

[1567] The user logs into the system and displays a data entry screen for a residence search on the terminal.

[1568] Input: User ID and password

[1569] Output: Data entry screen

[1570] Specific operation: The user launches a browser or app and enters their user ID and password into the login form. The device receives this and sends it to the authentication server. After successful authentication, a data entry screen for a home search is displayed.

[1571] Step 2:

[1572] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, eating habits, and desired place of residence.

[1573] Input: Lifestyle, hobbies, work style, sleeping habits, diet, desired conditions

[1574] Output: Input data

[1575] Specific operation: The user enters information into each field on the data entry screen (e.g., "Lifestyle: Active," "Hobbies: Running," "Work Style: Remote Work," etc.) and presses the "Send" button. The device then compiles this input data and sends it to the server.

[1576] Step 3:

[1577] The terminal transmits these input data to the server.

[1578] Input: User-entered data

[1579] Output: Data sent to the server

[1580] How it works: The device temporarily stores the data entered by the user and then transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[1581] Step 4:

[1582] The server receives the received user data, completes missing values ​​in the data, and standardizes the format.

[1583] Input: Received data

[1584] Output: Preprocessed data

[1585] Specific operation: The server validates the received data and fills in any missing values ​​with the mean or median. It also performs processing such as converting "yes / no" to "1 / 0" to unify the data format.

[1586] Step 5:

[1587] The server generates a lifestyle and personality profile of the user based on the pre-processed data.

[1588] Input: Preprocessed data

[1589] Output: Personality profile

[1590] How it works: The server uses machine learning models to analyze the pre-processed data and generate a profile that characterizes the user's lifestyle and personality.

[1591] Step 6:

[1592] The server applies an algorithm to make optimal recommendations based on the generated personality profile.

[1593] Enter: personality profile

[1594] Output: Recommendation data

[1595] Specific operation: Based on the personality profile, the server runs a recommender system (e.g., collaborative filtering or content-based filtering) to create a list of optimal housing candidates.

[1596] Step 7:

[1597] The server compares the user's personality profile with a smart city database and generates a list of suitable housing options for the user.

[1598] Input: personality profile, smart city database

[1599] Output: List of potential housing locations

[1600] How it works: The server compares the smart city database with the user's personality profile, evaluating factors such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety. Based on this, it generates a list of recommended housing options.

[1601] Step 8:

[1602] The server creates detailed information about the recommended housing candidate locations and sends it to the terminal.

[1603] Input: List of potential housing locations

[1604] Output: A list of recommendations with detailed information

[1605] Specific operation: The server adds detailed information about the potential residence (e.g., location of the residence, surrounding facilities, environment, rent, etc.) to a recommendation list and sends it to the terminal.

[1606] Step 9:

[1607] The terminal displays the recommendation list to the user, allowing the user to check it.

[1608] Input: A list of recommendations with detailed information

[1609] Output: Displayed recommendation list

[1610] Specific operation: The device displays the received recommendation list in GUI format, allowing the user to view detailed information, and displays a map using the Google Maps API if necessary.

[1611] Step 10:

[1612] The user inputs feedback on the recommendation through the terminal.

[1613] Input: Feedback (ratings and desired conditions)

[1614] Output: Feedback data

[1615] Specific operation: After checking the recommendation list, the user inputs their own rating and any additional desired conditions, and presses the "Submit" button. The device then sends this feedback data to the server.

[1616] Step 11:

[1617] The terminal transmits the user feedback data to the server.

[1618] Input: Feedback data

[1619] Output: Data sent to the server

[1620] How it works: The device temporarily stores the user's feedback data and transmits it to the server using the HTTPS protocol. The communication is encrypted and takes place in real time.

[1621] Step 12:

[1622] The server analyzes the received feedback data and uses it to improve existing algorithms, as well as reassess the user's personality profile to improve the accuracy of future recommendations.

[1623] Input: Feedback data

[1624] Output: Improved algorithm, updated personality profile

[1625] How it works: The server analyzes the feedback data using natural language processing (NLP) techniques, improves the recommendation algorithm based on the analysis results, and re-evaluates the user's personality profile based on the feedback to improve the accuracy of future recommendations.

[1626] (Application example 1)

[1627] 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."

[1628] In modern urban life, it is extremely difficult for an individual user to find a residential location that best suits their lifestyle and personality. Furthermore, simply displaying a list or providing text information does not allow the user to fully understand the actual environment of each candidate location, resulting in a decrease in the accuracy of property selection. Furthermore, it is difficult for users to provide detailed feedback on recommended candidate locations, which means the system cannot always reflect the user's latest needs. A system that solves these issues is needed.

[1629] 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.

[1630] In this invention, the server includes means for displaying detailed information about potential housing sites in the form of a virtual tour on a user terminal using augmented reality or virtual reality technology based on the user's lifestyle and personality profile, means for collecting and analyzing user feedback, and means for improving the algorithm based on the feedback. This allows users to check detailed environmental information about the recommended housing sites through the virtual tour before actually visiting them, allowing them to select a home that suits them with greater accuracy. Furthermore, the system can always provide optimal recommendations based on user feedback.

[1631] A "user terminal" is an electronic device used by a user to input data, display and provide feedback.

[1632] "User data" is a collection of information entered by a user based on their lifestyle and personality characteristics.

[1633] A "server" is a computer system that receives user data, performs pre-processing and analysis, generates recommendations, and processes feedback.

[1634] "Preprocessing of received data" refers to data cleaning work performed by the server, such as filling in missing values ​​and standardizing the format of the received data.

[1635] "Analysis of received data" is the process by which the server analyzes user data and generates a personality profile.

[1636] A "personality profile" is profile information that includes characteristics such as a user's lifestyle, hobbies, and work style.

[1637] "Evaluation of potential residential locations" is the process of evaluating conditions such as convenience and environment of selected potential locations by comparing them with a personality profile.

[1638] "Recommendation generation" is the process of suggesting the best possible housing locations based on the analyzed personality profile.

[1639] "Displaying a list of recommendations" means displaying a list of recommended housing candidates on the user terminal.

[1640] "Feedback" refers to the input of a user's opinion on the recommendation results, additional desired conditions, and the like.

[1641] "Feedback collection" is the process of collecting feedback information input by users from their terminals to the server.

[1642] "Algorithm improvement" is the process of updating recommendation algorithms and improving their accuracy based on collected feedback.

[1643] "Augmented reality" is a technology that overlays digital information onto the real world.

[1644] "Virtual reality" is a technology that allows users to experience a three-dimensional virtual environment generated by a computer.

[1645] A "virtual tour" is a feature that uses augmented reality or virtual reality to allow users to explore a location in a virtual space without actually visiting the location.

[1646] In one embodiment of the present invention, a system is used that combines a user terminal, a server, and augmented reality (AR) or virtual reality (VR) technology. The user terminal may be a smartphone, smart glasses, or a head-mounted display.

[1647] 1. Data Entry

[1648] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and recreational facilities). This data is then sent from the device to a server.

[1649] 2. Data Preprocessing and Analysis

[1650] The server receives the data from the user, fills in missing values, and standardizes the format. Once the data is cleaned, a machine learning model is used to generate a personality profile for the user. Pandas and Scikit-learn are used as data analysis tools to generate this profile.

[1651] 3. Recommendation Generation

[1652] The server compares the generated user's personality profile with the smart city database to create a list of recommendations for optimal housing options, including evaluation criteria such as transportation access, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1653] 4. Displaying Recommendations

[1654] The user device not only displays the recommendation list, but also uses augmented reality or virtual reality technology to display detailed information about the recommended housing candidate sites in the form of a virtual tour. This virtual tour allows users to see the interior and surrounding environment of the property without actually visiting it. This is done using development platforms such as ARKit (Apple) and ARCore (Google).

[1655] 5. Feedback collection and analysis

[1656] Users input feedback based on the recommendation results. This feedback includes ratings and additional preferences. The feedback data is sent from the device to the server, which analyzes it and uses it to improve the algorithm. Based on the analysis results, the user's personality profile and the accuracy of the recommendations are improved.

[1657] Specific examples

[1658] If a user plans to relocate to Tokyo, they log in to the system and enter "Tokyo" as the city they will be relocated to. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), and pet type (e.g., "dog"). The device sends this information to the server, which preprocesses the data and then uses a machine learning model to generate a personality profile. A recommendation list is created, suggesting potential housing locations such as "Minami-Aoyama" and "Meguro." The user can then put on the smart glasses and experience a virtual tour of these potential locations in augmented reality.

[1659] Example prompts for generative AI models

[1660] "I love reading, I work remotely, and I have a cat. Please recommend the best place to live that meets these criteria."

[1661] As described above, the present invention allows users to efficiently go through the process of finding the home that best suits them.

[1662] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1663] Program processing flow

[1664] Step 1: Data entry

[1665] Users use devices such as smartphones or smart glasses to input data related to their lifestyle and personality. Specifically, they input information such as hobbies, work style, whether they have pets, and the desired conditions for their place of residence (e.g., transportation access, availability of medical facilities, educational institutions, and entertainment facilities). This data is then sent from the device to a server.

[1666] Input: Hobbies, work style, whether you have pets, desired location

[1667] Output: User data is sent to the server

[1668] Step 2: Preprocessing the data

[1669] The server performs missing value imputation and format unification on the data received from the user. Here, Pandas is used to clean the data.

[1670] Input: User data

[1671] Output: Preprocessed data

[1672] Specific operation: Impute missing values ​​and unify data formats

[1673] Step 3: Generate a personality profile

[1674] The server uses a machine learning model, in this case Scikit-learn, to generate a user personality profile from the preprocessed data.

[1675] Input: Preprocessed data

[1676] Output: Personality profile

[1677] What happens: Feed data into a machine learning model to build a personality profile

[1678] Step 4: Recommendation Generation

[1679] The server compares the generated personality profile with the smart city database to create a list of recommendations for optimal housing options, based on evaluation criteria such as access to transportation, medical facilities, educational institutions, recreational facilities, and safety.

[1680] Input: Personality profile, Smart City database

[1681] Output: Recommendation list

[1682] Specific operation: Match the profile with the database and evaluate the candidate site based on each evaluation item.

[1683] Step 5: View recommendations

[1684] The user terminal displays the recommendation list and also displays detailed information about the recommended housing candidates in the form of a virtual tour using augmented reality (AR) or virtual reality (VR) technology.

[1685] Input: Recommendation list

[1686] Output: Detailed information displayed in a virtual tour format

[1687] What it does: Uses ARKit or ARCore to display detailed information in a virtual tour format.

[1688] Step 6: Gather feedback

[1689] The user inputs feedback on the recommendation results, including ratings and additional desired conditions, and the feedback data is sent from the terminal to the server.

[1690] Input: Feedback (rating, additional requirements, etc.)

[1691] Output: Feedback data sent to the server

[1692] What it does: Collects input from users through a feedback form

[1693] Step 7: Analyzing feedback and improving the algorithm

[1694] The server analyzes the collected feedback to improve the recommendation algorithm, which includes the process of optimizing the parameters of the algorithm based on the collected feedback data.

[1695] Input: Feedback data

[1696] Output: An improved recommendation algorithm

[1697] Specific behavior: Analyze feedback data and optimize parameters of recommendation algorithms

[1698] 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.

[1699] This invention combines a system that recommends optimal residential locations based on a user's lifestyle and personality with an emotion engine that recognizes the user's emotions. This system inputs user data and emotion data via the user's terminal, analyzes and processes the data on the server to generate recommendations, displays them on the user's terminal, and collects and analyzes feedback.

[1700] Program processing flow

[1701] Data Entry

[1702] 1. The user logs in to the system and displays the data entry screen for a residential search on the terminal.

[1703] 2. The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (e.g., access to transportation, medical facilities, educational institutions, and recreational facilities).

[1704] 3. The device sends these input data to the server.

[1705] Data preprocessing and analysis

[1706] 1. The server receives the user data. It fills in missing values ​​and standardizes the format of the data. The emotion engine also analyzes the user's emotional state.

[1707] 2. The server uses the pre-processed data to generate a lifestyle and personality profile of the user, using machine learning models.

[1708] 3. The emotion engine monitors the user's emotional state in real time and generates analytical results.

[1709] 4. The server applies an algorithm to make optimal recommendations based on the user's personality profile and emotional state.

[1710] Recommendation generation and display

[1711] 1. The server compares the user's personality profile with the smart city database to generate a list of suitable housing options for the user, including factors such as access to transportation, availability of medical facilities, educational institutions, and recreational facilities, and safety.

[1712] 2. The server creates a list containing detailed information about the recommended housing candidates (e.g., the location of the housing, surrounding facilities, environment, etc.) and sends it to the terminal.

[1713] 3. The device displays the recommendation list to the user, allowing the user to review it.

[1714] Collecting and analyzing feedback

[1715] 1. The user inputs feedback on the recommendation via the terminal, including the rating of the residence and any additional desired conditions.

[1716] 2. The device sends the user's feedback and emotion data to the server.

[1717] 3. The server analyzes the received feedback and sentiment data and uses it to improve existing algorithms. It also uses the results of this analysis to reassess the user's personality profile and improve the accuracy of future recommendations.

[1718] Specific examples

[1719] For example, if a user plans to relocate to Tokyo, they would take the following steps:

[1720] 1. A user logs in to the system and enters "Tokyo" as the city to which they will be transferred. They also enter their hobbies (e.g., "running"), work style (e.g., "remote work"), sleep habits (e.g., "night owl"), etc. They also enter their emotional state at the time (e.g., "feeling stressed").

[1721] 2. The device sends this information to the server, which preprocesses the data and analyzes it using machine learning models and an emotion engine.

[1722] 3. The server uses the user's input data and emotional data to generate a personality profile and create a list of recommended housing locations, such as "Toyosu, Shinagawa, Shibuya."

[1723] 4. The device displays this recommendation list to the user, who then browses through the detailed information and selects "Toyosu."

[1724] 5. The user enters feedback based on their selection (for example, "Toyosu is very convenient and I'm satisfied"), and the device sends this to the server. The emotion engine also analyzes the user's emotional state.

[1725] 6. The server analyzes the feedback and sentiment data to help improve the algorithm and reassess the user's profile to improve future recommendations.

[1726] Thus, the present invention provides a system that recommends optimal residential locations by taking into account the user's lifestyle, personality, and emotional state. This system effectively functions using a user device, a server that performs data preprocessing and analysis, recommendation generation, feedback collection and analysis, and an emotion engine.

[1727] The processing flow will be explained below.

[1728] Step 1:

[1729] The user logs in to the system and the data entry screen for the residence search is displayed on the terminal. The user ID and password are used to log in.

[1730] Step 2:

[1731] The user inputs information about their lifestyle, hobbies, work style, sleeping habits, diet, emotional state, and desired residential conditions (such as access to transportation, medical facilities, educational institutions, and recreational facilities).

[1732] Step 3:

[1733] The terminal transmits these input data to the server.

[1734] Step 4:

[1735] The server retrieves the user data received, fills in missing values, standardizes the format, and performs data cleansing.

[1736] Step 5:

[1737] The server uses the pre-processed data to feed it into a machine learning model to generate a lifestyle and personality profile of the user.

[1738] Step 6:

[1739] The emotion engine analyzes the user's emotional state from input data, and performs emotion recognition through text and voice analysis.

[1740] Step 7:

[1741] The server integrates the emotion data obtained from the emotion engine with the personality profile to generate a comprehensive profile of the user.

[1742] Step 8:

[1743] The server compares the user's profile with the smart city database and performs an evaluation to recommend the most suitable place to live.

[1744] Step 9:

[1745] The server calculates the evaluation score of each residential location and generates a list of suitable residential locations for the user, including detailed information about each location (such as transportation access, availability of facilities, and environmental safety).

[1746] Step 10:

[1747] The server sends the recommendation list and detailed information to the terminal.

[1748] Step 11:

[1749] The device displays a recommendation list to the user, who can then browse the list and view detailed information about the potential residences.

[1750] Step 12:

[1751] The user selects the best place to live based on the recommendations and then enters the results and feedback, including the location's rating and emotional state.

[1752] Step 13:

[1753] The device sends the user's feedback and emotion data to the server.

[1754] Step 14:

[1755] The server analyzes the received feedback and sentiment data. The feedback data is used to analyze and improve the recommendation algorithm.

[1756] Step 15:

[1757] The server updates the algorithm based on the feedback analysis results that reflect the emotional data, improving the accuracy of future recommendations. It also reevaluates the user's profile and generates a new one.

[1758] In this way, users can find the place to live that best suits their individual lifestyle, personality, and even emotional state. The entire system is designed to work together to maximize the user's growth and happiness.

[1759] Example 2

[1760] 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."

[1761] There is a need for a system that can recommend optimal residential locations by taking into account users' diverse lifestyles, personalities, and emotional states. Conventional systems are based on fixed information about users and have the problem of being unable to respond to emotions or real-time changes in the situation. Therefore, it is necessary to provide more accurate recommendations that also take into account the user's emotional state.

[1762] 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.

[1763] In this invention, the server includes means for receiving user data, means for preprocessing the received data, means for analyzing the received data, means for generating a user's personality profile, means for evaluating potential housing sites and generating recommendations, means for analyzing feedback and improving algorithms, means for receiving and analyzing emotional data, and means for optimizing recommendations based on the emotional state, thereby enabling highly accurate residential site recommendations that reflect the user's emotional state in addition to their lifestyle and personality.

[1764] "User data" refers to information such as the user's lifestyle, personality information, emotional state, and desired conditions regarding the place of residence.

[1765] A "user terminal" is a device that a user uses to input data and check recommendations, and includes smartphones, personal computers, etc.

[1766] "Server" means the computer system that operates centrally to analyze and process data received from Users and generate recommendations.

[1767] "Means for preprocessing received data" refers to a process for standardizing user data, complementing missing values, and standardizing formats.

[1768] "Analysis Means" means the methods and techniques used to analyze and interpret the received data and generate a lifestyle and personality profile of the User.

[1769] A "personality profile" is a profile of personal characteristics generated based on a user's lifestyle, hobbies, and behavioral patterns.

[1770] The "recommendation generation means" is a process that selects and lists the most suitable housing candidates based on the user's profile.

[1771] "Emotion data" is information that indicates the user's current emotional state, and includes stress, happiness, satisfaction, and the like.

[1772] The "emotion engine" is a system that analyzes the user's emotional state from input data and monitors changes in emotions in real time.

[1773] "Feedback collection means" is the process of collecting user-entered ratings and additional requests for recommendations.

[1774] "Algorithm improvement" is the process of analyzing collected feedback and sentiment data to improve the recommendation algorithm.

[1775] An "optimizer" is a method that takes into account the user's emotional state to adjust recommendations and suggest the most suitable place to live for the user.

[1776] A "collaborative filtering algorithm" is a method for comparing data from multiple users and making recommendations based on similarities.

[1777] MODE FOR CARRYING OUT THE INVENTION

[1778] The present invention is a system that recommends optimal residential locations by taking into consideration not only the user's lifestyle and personality, but also the user's emotional state. This system is composed of hardware and software, such as a user terminal, a server, and an emotion engine.

[1779] Overall structure

[1780] First, a user accesses the system through a user terminal and inputs the necessary data, including their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired residential location. This data is then sent from the user terminal to the server.

[1781] The server preprocesses the data received from users, filling in missing values ​​and standardizing formats. It then uses machine learning models to analyze the data and generate personality profiles. It also uses an emotion engine to analyze users' emotional data and monitor their emotional state in real time.

[1782] The server then applies a recommendation algorithm based on the user's generated personality profile and emotional state to generate a list of optimal residential location recommendations, including detailed information on potential locations based on evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety.

[1783] Next, the device displays a list of recommended housing options to the user. The user can review the options and view detailed information. For example, a recommendation could include information such as, "I'm planning to be transferred to Tokyo, my hobby is running, I often work remotely, I'm a night owl, and I feel stressed."

[1784] Users can provide feedback on the recommendations, and the feedback and emotional data are sent back to the server, which can then use this feedback to improve existing algorithms and reassess the user's personality profile to improve the accuracy of future recommendations.

[1785] Hardware and software used

[1786] User device: A device such as a smartphone or PC is used to input user data and display a list of recommendations.

[1787] Server: A computer system that performs central data analysis and recommendation generation.

[1788] Emotion Engine: A software module for recognizing and analyzing a user's emotional state. It uses natural language processing techniques to extract emotions from text.

[1789] Machine learning models: Generate user profiles using techniques such as k-nearest neighbors and decision trees, and generate recommendations using collaborative filtering algorithms.

[1790] Specific examples

[1791] For example, if a user enters "I'm planning to transfer to Tokyo, I mostly work remotely, my hobby is running, I'm a night owl, and I've been feeling stressed lately," the system will act as follows:

[1792] 1. The user enters the necessary information on the user terminal and sends it to the server.

[1793] 2. The server preprocesses the received data and analyzes it using machine learning models and an emotion engine.

[1794] 3. The server generates a list of recommended housing candidates and sends it to the device.

[1795] 4. The device displays the recommendation list to the user, and the user checks the details.

[1796] 5. The user enters feedback on the recommendation and sends it to the server via the device.

[1797] 6. The server analyzes the feedback data to improve the algorithm and re-evaluate the user profile.

[1798] This method makes it possible to provide highly accurate recommendations that reflect the user's lifestyle and emotional state.

[1799] Prompt Sentence Examples

[1800] "I'm planning to be transferred to Tokyo. I do a lot of remote work at work, and my hobby is running. I'm a night owl, and I've been feeling stressed lately. Could you please tell me the best place to live?"

[1801] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1802] Step 1:

[1803] A user logs into the system using a terminal. The user enters a username and password and is authenticated. If the login is successful, a data entry screen for a residence search is displayed on the terminal.

[1804] Input: Username, Password

[1805] Output: Display of data entry screen

[1806] Step 2:

[1807] Users enter information such as their lifestyle, hobbies, work style, sleep habits, diet, emotional state, and desired place of residence into a data entry screen. Specifically, they enter information such as "running," "remote work," "night owl," "feeling stressed," and "Tokyo."

[1808] Input: Lifestyle, hobbies, work style, sleep habits, diet, emotional state, desired location

[1809] Output: Prepare input data for sending

[1810] Step 3:

[1811] The device sends this input data to the server, where it is encrypted and securely delivered to the server.

[1812] Input: Input data

[1813] Output: Data sent to the server

[1814] Step 4:

[1815] The server preprocesses the user data it receives. This involves filling in missing values ​​and standardizing data formats. For example, if there is missing information in the input data, it is filled in based on past data or statistical models.

[1816] Input: User data

[1817] Output: Preprocessed data

[1818] Step 5:

[1819] The server analyzes the pre-processed data and uses machine learning models to generate a lifestyle and personality profile of the user. Models used include k-nearest neighbors and decision trees.

[1820] Input: Preprocessed data

[1821] Output: Personality profile

[1822] Step 6:

[1823] The emotion engine monitors the user's emotional state in real time and generates analytical results. It uses natural language processing technology to extract emotions from the user's text input.

[1824] Input: User emotion data

[1825] Output: Emotion analysis results

[1826] Step 7:

[1827] The server applies a recommendation algorithm based on the user's personality profile and emotional state, and uses a collaborative filtering algorithm to recommend the best place to live.

[1828] Input: Personality profile, emotion analysis results

[1829] Output: Recommendation list

[1830] Step 8:

[1831] The server generates a recommendation list and sends it to the device. The list includes detailed information about potential housing locations, including evaluation criteria such as transportation access, medical facilities, educational institutions, entertainment facilities, and safety. For example, the list includes candidate locations such as "Toyosu," "Shinagawa," and "Shibuya."

[1832] Input: Recommendation list

[1833] Output: List sent to terminal

[1834] Step 9:

[1835] The device displays a list of recommendations to the user, who can then browse detailed information and select a location that best suits their needs.

[1836] Input: Recommendation list

[1837] Output: The list displayed to the user

[1838] Step 10:

[1839] The user enters feedback on the recommendation. The feedback includes an evaluation of the place of residence and any additional desired conditions. For example, the user can enter content such as "I am very satisfied with the convenience of Toyosu."

[1840] Input: Feedback

[1841] Output: Feedback ready to be sent

[1842] Step 11:

[1843] The device sends the user's feedback and emotional data to the server, where it is again encrypted and transmitted securely.

[1844] Input: Feedback, emotion data

[1845] Output: Feedback and emotion data sent to the server

[1846] Step 12:

[1847] The server analyzes the feedback and sentiment data, improving existing algorithms and reassessing the user's personality profile to improve the accuracy of future recommendations.

[1848] Input: Feedback, emotion data

[1849] Output: Improved algorithm and re-evaluated profile

[1850] (Application example 2)

[1851] 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."

[1852] Conventional food delivery recommendation systems make recommendations based on a user's eating habits and preferences, but they are unable to make recommendations that take into account the user's real-time emotional state. This makes it difficult for users to select the optimal food delivery service that matches their emotional state at any given time. Furthermore, the lack of monitoring and analysis of the user's real-time emotional state makes it difficult to provide more personalized recommendations.

[1853] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1854] In this invention, the server includes means for real-time monitoring of the user's emotional state using an emotion analysis engine, and means for the server to generate food delivery options based on the user's personality profile and emotional state, thereby enabling personalized food delivery recommendations that take into account the user's real-time emotional state.

[1855] A "user terminal" is an electronic device that allows a user to access the system and input and display data.

[1856] "User data" refers to data that includes information about a user's lifestyle, personality, diet, emotional state, and so on.

[1857] A "server" is a computer system for receiving, preprocessing, and analyzing user data, and for generating and displaying recommendations.

[1858] The "receiving means" is a function for the server to receive data sent from the user terminal.

[1859] The "preprocessing means" is a function that complements missing values ​​and standardizes the format of received data.

[1860] The "analysis means" is a function that analyzes the pre-processed data and generates a personality profile and emotional state of the user.

[1861] A "personality profile" is a profile generated based on a user's lifestyle and personality characteristics.

[1862] An "emotion analysis engine" is an algorithm and software for analyzing a user's real-time emotional state.

[1863] A "recommendation" is a list of best candidates provided to a user.

[1864] "Feedback" refers to collected data of users' ratings and opinions on recommendations.

[1865] "Means for improving algorithms" is a function for improving existing algorithms based on feedback data.

[1866] "Food delivery options" are the food and meal options available for delivery to a user.

[1867] The invention is a system that recommends food delivery options based on a user's lifestyle, personality information, and real-time emotional state. Specifically, the system is implemented as follows.

[1868] Overall system configuration

[1869] The system includes a user terminal, a server, a sentiment analysis engine, and a machine learning model. The user terminal is responsible for inputting user data and displaying recommendations, while the server performs data preprocessing, analysis, recommendation generation, feedback collection, and algorithm improvement. The sentiment analysis engine monitors and analyzes the user's emotional state in real time.

[1870] Hardware and software used

[1871] Hardware: Smartphones (e.g., iPhone, Android devices), head-mounted displays (e.g., Oculus Quest 2)

[1872] Software: Sentiment analysis engine, machine learning model (e.g., TensorFlow), database (e.g., MySQL), application server (e.g., Node.js)

[1873] Processing flow

[1874] 1. The user terminal provides an interface for inputting user data. The user inputs details such as dietary habits, favorite foods, allergy information, and their emotional state at the time.

[1875] 2. The terminal sends the entered data to the server.

[1876] 3. The server receives the data and performs preprocessing such as unifying the data format and filling in missing values. The emotion analysis engine also analyzes the user's emotional state in real time.

[1877] 4. The server uses machine learning models to generate a personality profile of the user and recommends optimal food delivery options based on that profile and emotional state.

[1878] 5. The server generates a recommendation list and sends detailed information to the user terminal.

[1879] 6. The user device displays a recommendation list from which the user can make a selection.

[1880] 7. The user enters feedback on the recommendation, and the device sends the feedback and emotion data to the server.

[1881] 8. The server analyzes the feedback and sentiment data to improve the algorithm and re-evaluate the user profile.

[1882] Specific examples

[1883] For example, if a user is tired and wants to order a light meal, they can enter their user data and emotional state as follows:

[1884] Diet: Vegetable-based

[1885] Favorite food: Japanese food

[1886] Allergies: None

[1887] Emotional state: Tired

[1888] Example prompts to give to a generative AI model:

[1889] "The user is currently tired and has a preference for Japanese food based on their past ordering history. Please recommend the best light Japanese delivery options for the user."

[1890] Based on this prompt, the generative AI model recommends suitable food delivery options for the user and displays the results in real time, allowing users to easily find the best food delivery options that match their emotional state.

[1891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1892] Step 1:

[1893] The user terminal provides an interface for inputting user data. The user inputs information about their diet, favorite foods, allergies, and current emotional state. This input data is used as the initial input for the system.

[1894] Step 2:

[1895] The device transmits the input data to the server, which includes lifestyle information, favorite foods, and emotional state.

[1896] Step 3:

[1897] The server receives user data and performs preprocessing such as standardizing the data format and filling in missing values. Specifically, it predicts and fills in missing data and prepares the data format for analysis.

[1898] Step 4:

[1899] The emotion analysis engine analyzes the user's emotional state in real time. The input is the raw data of the emotional state, and the output is the analyzed emotional evaluation result.

[1900] Step 5:

[1901] The server uses a machine learning model to generate a personality profile for the user. The input data is preprocessed user data and sentiment analysis results, and the output data is a combination of the personality profile and sentiment assessment.

[1902] Step 6:

[1903] The server generates prompts to recommend optimal food delivery options based on the generated personality profile and emotional state. The prompts are used as instructions for the generative AI model, and the output is a list of optimal delivery options.

[1904] Step 7:

[1905] The server generates a recommendation list and sends the details to the user's device, including specific information about each delivery option (menu, price, ratings, etc.).

[1906] Step 8:

[1907] The user terminal displays the recommendation list, allowing the user to check the recommendations.

[1908] Step 9:

[1909] Users enter feedback on the recommendations, including ratings and impressions of the selected options.

[1910] Step 10:

[1911] The terminal again transmits the feedback data and emotion data to the server.

[1912] Step 11:

[1913] The server analyzes the feedback and emotion data to improve existing recommendation algorithms and also reassess the user's personality profile based on the analysis results to improve the accuracy of future recommendations.

[1914] This series of steps allows users to receive the best food delivery recommendations that suit their emotional state at any given time.

[1915] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1916] 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.

[1917] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1918] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1919] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1920] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1921] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1922] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1923] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1924] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1925] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1926] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1927] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1928] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1929] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1930] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1931] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1932] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1933] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1934] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1935] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1936] The following is further disclosed regarding the above embodiment.

[1937] (Claim 1)

[1938] A means for inputting user data using a user terminal;

[1939] A means for receiving user data by a server;

[1940] A means for preprocessing received data by the server;

[1941] A means for analyzing received data by the server;

[1942] means for generating a personality profile of the user by the server;

[1943] A server-based means for evaluating potential housing sites and generating recommendations;

[1944] A means for displaying a list of recommendations on a user terminal;

[1945] A means for collecting feedback on the recommendations by the user terminal;

[1946] a means by which the server analyzes the feedback and improves the algorithm;

[1947] A system including:

[1948] (Claim 2)

[1949] 10. The system of claim 1, wherein the user data includes lifestyle and personality information.

[1950] (Claim 3)

[1951] 10. The system of claim 1, wherein the means for analyzing the user data uses a machine learning model.

[1952] "Example 1"

[1953] (Claim 1)

[1954] A means for inputting user data using a user terminal;

[1955] A means for receiving user data by a server;

[1956] A means for preprocessing received data by the server;

[1957] A means for analyzing received data by the server;

[1958] means for generating a personality profile of the user by the server;

[1959] A server-based means for evaluating potential housing sites and generating recommendations;

[1960] A means for displaying a list of recommendations on a user terminal;

[1961] A means for collecting feedback on the recommendations by the user terminal;

[1962] a means by which the server analyzes the feedback and improves the algorithm;

[1963] A means for generating a lifestyle and personality profile of a user using a machine learning model;

[1964] means for generating recommendations for potential housing locations based on user data and a city database;

[1965] A means to improve the algorithm in response to user feedback and increase the accuracy of recommendations;

[1966] A system including:

[1967] (Claim 2)

[1968] 10. The system of claim 1, wherein the user data includes lifestyle and personality information.

[1969] (Claim 3)

[1970] 10. The system of claim 1, wherein the means for analyzing the user data uses a machine learning model.

[1971] "Application Example 1"

[1972] (Claim 1)

[1973] A means for inputting user data using a user terminal;

[1974] A means for receiving user data by a server;

[1975] A means for preprocessing received data by the server;

[1976] A means for analyzing received data by the server;

[1977] means for generating a personality profile of the user by the server;

[1978] A server-based means for evaluating potential housing sites and generating recommendations;

[1979] A means for displaying a list of recommendations on a user terminal;

[1980] A means for collecting feedback on the recommendations by the user terminal;

[1981] a means by which the server analyzes the feedback and improves the algorithm;

[1982] a means for displaying detailed information of the recommended housing candidate sites in a virtual tour format on a user terminal using augmented reality or virtual reality technology;

[1983] A system including:

[1984] (Claim 2)

[1985] 10. The system of claim 1, wherein the user data includes lifestyle and personality information.

[1986] (Claim 3)

[1987] 10. The system of claim 1, wherein the means for analyzing the user data uses a machine learning model.

[1988] "Example 2: Combining Emotion Engines"

[1989] (Claim 1)

[1990] A means for inputting user data using a user terminal;

[1991] A means for receiving user data by a server;

[1992] A means for preprocessing received data by the server;

[1993] A means for analyzing received data by the server;

[1994] means for generating a personality profile of the user by the server;

[1995] A server-based means for evaluating potential housing sites and generating recommendations;

[1996] A means for displaying a list of recommendations on a user terminal;

[1997] A means for collecting feedback on the recommendations by the user terminal;

[1998] a means by which the server analyzes the feedback and improves the algorithm;

[1999] A server receives and analyzes emotion data;

[2000] means for analyzing the emotional state of a user by an emotion engine;

[2001] A server-based method for optimizing recommendations based on emotional states;

[2002] A system including:

[2003] (Claim 2)

[2004] 10. The system of claim 1, wherein the user data includes lifestyle, personality information, and emotional state.

[2005] (Claim 3)

[2006] 10. The system of claim 1, wherein the means for analyzing the user data uses a machine learning model.

[2007] (Claim 4)

[2008] 10. The system of claim 1, wherein the recommendation optimizer uses a collaborative filtering algorithm.

[2009] "Application example 2 when combining emotion engines"

[2010] (Claim 1)

[2011] A means for inputting user data using a user terminal;

[2012] A means for receiving user data by a server;

[2013] A means for preprocessing received data by the server;

[2014] A means for analyzing received data by the server;

[2015] means for generating a personality profile of the user by the server;

[2016] A means for the server to evaluate the candidate list and generate recommendations;

[2017] A means for displaying a list of recommendations on a user terminal;

[2018] A means for collecting feedback on the recommendations by the user terminal;

[2019] a means by which the server analyzes the feedback and improves the algorithm;

[2020] a means for real-time monitoring of a user's emotional state using an emotion analysis engine;

[2021] means for generating food delivery options based on the user's personality profile and emotional state by the server;

[2022] A system including:

[2023] (Claim 2)

[2024] 10. The system of claim 1, wherein the user data includes lifestyle, personality information, and dietary information.

[2025] (Claim 3)

[2026] 10. The system of claim 1, wherein the means for analyzing the user data uses a machine learning model. [Explanation of symbols]

[2027] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for inputting user data using a user terminal; A means for receiving user data by a server; A means for preprocessing received data by the server; A means for analyzing received data by the server; means for generating a personality profile of the user by the server; A server-based means for evaluating potential housing sites and generating recommendations; A means for displaying a list of recommendations on a user terminal; A means for collecting feedback on the recommendations by the user terminal; a means by which the server analyzes the feedback and improves the algorithm; A system including:

2. The system of claim 1 , wherein the user data includes lifestyle and personality information.

3. The system of claim 1 , wherein the means for analyzing the user data uses a machine learning model.

Images