system

Abstract

We provide the system. [Solution] Means for collecting user information, A means of learning user preferences based on collected user information, A means of recommending suitable properties to users from real estate information based on learned preferences, A system that includes means for obtaining user feedback and updating learning results.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is very difficult for a user to find a property that meets their desired conditions in the real estate market due to the large amount of information and numerous options. Therefore, there is a need for a means that allows users to efficiently find suitable properties. In addition, conventional systems do not fully consider the individual preferences and lifestyles of users and only provide general information, so they have not led to an improvement in specific user satisfaction.

Means for Solving the Problems

[0005] This invention provides a system that utilizes AI technology to collect user information and learn user preferences based on that information. Furthermore, based on the learning results, it appropriately recommends real estate properties that correspond to the user's lifestyle and past behavioral history, and improves the accuracy of recommendations while obtaining feedback from the user. This system efficiently proposes properties that best suit the user's desired conditions by continuously improving the recommendation results based on the user's preferences and evaluations.

[0006] "User information" refers to all data related to a user, including their behavioral history, search keywords, click data, and data indicating their interests and preferences.

[0007] "Preferences" refer to the personal tastes and tendencies of a user based on specific conditions or values.

[0008] "Means of learning" refers to the process of extracting patterns from collected data and using machine learning or AI technology to analyze and understand user preferences.

[0009] "Real estate information" refers to detailed data about a specific property, including information such as location, price, floor plan, year built, and surrounding facilities.

[0010] "Feedback" refers to information that users provide to the system, such as opinions, ratings, or comments about properties, which helps improve the accuracy of future recommendations.

[0011] "Recommended methods" refer to the process of selecting appropriate real estate properties based on the user's preferences and introducing them to the user. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system that proposes the most suitable real estate property to a user, and its embodiments are described below. The purpose of this system is to recommend a real estate property that suits the user by collecting user information and learning the user's preferences using a generated AI based on that information.

[0034] The server first collects user behavior data when they use the real estate search platform. This includes keywords searched, properties clicked, and viewing time. The server also retrieves real estate information from external property databases and related APIs and updates the system's database. This makes it possible to provide users with the latest market information while maintaining the accuracy of property information.

[0035] Next, the server trains a generative AI model based on the collected data. This process analyzes the user's past preference patterns and behavioral history to predict what types of properties they might be interested in. The AI ​​model learns from this information and forms the basis for future recommendations.

[0036] Based on the learning results, the server generates a customized list of real estate properties for each user. This list is selected based on the user's lifestyle and preferences and is then presented to the user via their device. For example, users who prefer urban living will be given priority recommendations for properties in convenient areas.

[0037] Users view the properties presented through their devices and provide feedback such as "I like it" or "I want to know more details." This feedback information is then collected by the server and used in the next learning process.

[0038] In this way, the AI ​​model can be continuously improved based on user feedback, leading to more accurate recommendations and increased user satisfaction. For example, if a user is identified as having recently searched for many pet-friendly properties, the system will adjust its recommendations to display more pet-friendly properties in the future. As a "form for carrying out the invention," this system is structured to target a segment of the market and effectively generate profits.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server collects user behavior data when users use the real estate search platform. This collected data includes searched keywords, clicked property IDs, viewing time, and access date and time. In addition, the device sends unique user ID information to the server to track user behavior individually.

[0042] Step 2:

[0043] The server periodically retrieves the latest real estate information through real estate databases and external APIs, updating the system's database. This data includes information on property location, price, floor plan, age, and changes in market trends.

[0044] Step 3:

[0045] The server preprocesses the collected user behavior data and uses it as training data for the AI ​​model. It performs data cleansing and feature engineering to convert the data into a format that is easy for machine learning algorithms to learn from.

[0046] Step 4:

[0047] The server uses a machine learning model to analyze user preferences and behavioral patterns. This model considers the user's past choices and interests to predict what should be suggested next. As new feedback is incorporated into the model, the accuracy of recommendations continuously improves.

[0048] Step 5:

[0049] Based on the analysis results, the server selects the most suitable real estate properties for the user's profile. It then generates a personalized recommendation list for the user, which is sent to the terminal.

[0050] Step 6:

[0051] The device displays a list of recommended real estate properties to the user. The property list includes photos, property details, price information, and location. The user can browse the list and click on properties of interest to view more details.

[0052] Step 7:

[0053] Users provide feedback on properties they are interested in. This feedback is entered via their device in specific forms, such as "add to favorites" or "not interested."

[0054] Step 8:

[0055] The server collects user feedback and uses it to retrain the AI ​​model. This feedback data provides information that will be useful for future recommendations and will further improve the accuracy of the system's recommendations.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Traditional real estate recommendation systems had the problem of not being able to adequately reflect the individual preferences of users when recommending properties. Furthermore, the low accuracy of recommendations could lead to low user satisfaction. In addition, it was difficult to reflect the latest market information in real time, making it challenging to provide users with up-to-date and accurate information.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes information processing means for collecting user information, means for using a generative artificial intelligence model that learns user preferences based on the collected user information, and information processing means for acquiring and updating real estate information from an external database. This makes it possible to recommend properties that reflect the individual preferences of the user, and further enhances user satisfaction by providing the latest market information in real time.

[0061] "Information processing means" refers to the means of collecting data from users and appropriately analyzing and managing it within the system.

[0062] A "generative artificial intelligence model" is a model that has algorithms and programs designed to learn user preferences and predict future actions and choices.

[0063] "Information presentation means" refers to the means by which a system presents information adapted to the user in a visual or other way.

[0064] "Information improvement methods" are means of improving the performance and accuracy of a system based on user feedback and other evaluations.

[0065] "Information analysis tools" are means of analyzing input data and feedback in detail to extract new insights and areas for improvement.

[0066] "Information selection methods" refer to the means of selecting the most suitable real estate information based on the user's lifestyle and past behavioral history.

[0067] In order to implement the system according to the present invention, it is necessary for the server, terminal, and user to exchange data with each other. The details are described below.

[0068] The server is responsible for collecting user behavior data for the real estate search platform. This behavior data includes keywords searched by users, properties accessed, and the time spent viewing each property. This data is managed and analyzed within the server using information processing tools. The server also obtains the latest property information via external real estate databases and related APIs, and updates its internal database. This update process ensures that users are always provided with the most up-to-date market information.

[0069] Furthermore, the server uses a generative artificial intelligence model to learn user preferences based on the collected user data. This allows it to predict individual interests based on the user's past behavior history and find real estate properties that match those interests. For example, if a user has a history of searching for "pet-friendly properties," the AI ​​model will take that preference into account and recommend pet-friendly properties.

[0070] The terminal serves to present users with individually customized property lists sent from the server. Users can view property details through the terminal and provide feedback on properties of interest. This feedback is sent to the server and analyzed by information improvement tools, further enhancing the accuracy of the AI ​​model.

[0071] As a concrete example, suppose a user enters the following prompt into the terminal: "I'm currently looking for an apartment where I can live with my pet. Do you have any recommendations?" Based on this prompt, the server prioritizes extracting information on pet-friendly apartments and presents it to the user.

[0072] Thus, the present invention realizes a system that efficiently provides users with optimal real estate information and improves the user experience.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server collects user behavior data from real estate search platforms. Inputs include user search keywords, clicked properties, and viewing time for each property. The server organizes and stores this data within the system using information processing tools. The output is a dataset of user behavior. Specifically, this includes actions such as recording the time a user spends searching for "newly built condominiums" and viewing specific properties.

[0076] Step 2:

[0077] The server retrieves and updates real estate information from external databases and APIs. Input is detailed property information, including location, price, area, and amenities. The retrieved information is compared with existing data, and any changes are saved to the system's database. The output is the latest real estate database. Specific operations include adding newly listed properties and reflecting changes in sales status.

[0078] Step 3:

[0079] The server trains a generative AI model based on collected user information. The input consists of user behavior data and the latest real estate data. The server analyzes this information to extract user preferences and update the AI ​​model. The output is an AI model that reflects the user's preferences. Specifically, it performs a process to infer the user's preferences based on the characteristics of properties they have previously viewed (e.g., location and price range).

[0080] Step 4:

[0081] The server generates a personalized property list for each user using a newly trained AI model. The input consists of the updated AI model and the latest real estate data. The server combines this data to select the property best suited to the user's preferences. The output is a customized property list. Specifically, filtering is performed based on user preferences such as pet-friendly properties and proximity to train stations.

[0082] Step 5:

[0083] The terminal displays a list of properties sent from the server to the user. The input is a customized property list generated by the server. The user reviews the suggested properties through the terminal and clicks on properties of interest to obtain detailed information. The output is a display of property details. Specifically, the property's location, price, floor plan, etc., are displayed on the screen.

[0084] Step 6:

[0085] Users provide feedback on properties through their devices. Input consists of ratings and comments made by the user regarding the presented properties. Users enter feedback such as "I like this property" or "I want more information," and the device sends it to the server. Output is the state in which the feedback has been sent to the server. Specific operations include a function to hide properties that the user "doesn't like" from the list.

[0086] Step 7:

[0087] The server further improves the AI ​​model based on user feedback. The input consists of user feedback and the existing AI model. The server analyzes the feedback information and adjusts the AI ​​model's parameters to improve the accuracy of recommendations. The output is the improved AI model. Specifically, after a sufficient amount of feedback from a large number of users has been accumulated, the model is retrained and the improvements are reflected in the next recommendation.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In food delivery services, it is crucial to suggest optimal menus and facilities based on users' diverse preferences and behavioral history. However, existing systems fail to provide appropriate recommendations to individual users, making it difficult to improve user satisfaction. To solve this problem, it is necessary to learn user preferences using past behavioral data and provide more personalized recommendations.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, and means for recommending user-suitable menus or facilities from food delivery information based on the learned preferences. This makes it possible to recommend menus and facilities that are tailored to the individual preferences of each user.

[0093] "User information" refers to personal information and behavioral data of users related to the food delivery service, including order history, search history, and feedback.

[0094] "Preferences" refer to the inferred preference for a particular menu item or facility based on the user's past tastes and behavioral patterns.

[0095] "Food delivery information" refers to information about menus, facilities, and delivery conditions available to users, and includes information such as the type of food, price, and location of the facilities providing the service.

[0096] "Feedback" refers to the evaluations and opinions that users provide about the menus and facilities presented, and this feedback is used for future recommendations.

[0097] A "generative AI model" refers to an artificial intelligence algorithm that learns user preferences based on past behavioral data and recommends appropriate menus and facilities.

[0098] "Recommendation" refers to the act of presenting menus and facilities that match the user's preferences based on the results of analysis by a generative AI model.

[0099] "Dynamic presentation" refers to a method of displaying appropriate menus and facility information in real time, based on the user's preferences and behavioral history.

[0100] The system that realizes this invention is configured as follows: First, a server collects user information in real time. This information includes the user's order history, search history, and feedback. The information is stored in a database and organized for each user.

[0101] Next, the server uses a generative AI model to learn user preferences based on the collected user information. This process uses machine learning frameworks such as TENSORFLOW® and PyTorch to analyze past behavioral patterns and predict what menus and facilities users will prefer. This allows for the generation of personalized recommendation lists for each user.

[0102] The user's device receives and displays a list of recommendations sent from the server. This list is dynamically updated, suggesting the most suitable menus and establishments based on the user's past search history and preferences when they choose a restaurant.

[0103] Furthermore, user feedback is sent back to the server and used to update the learning model. This allows for continuous improvement of recommendation accuracy and increased user satisfaction.

[0104] For example, if a user has recently ordered a lot of Italian food, the next time they log in, they will be recommended new menu items from Italian restaurants. In this way, recommendations can be tailored to the individual user's preferences.

[0105] An example of a prompt message would be: "Based on past history, suggest the most suitable food delivery menu for this user."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server collects user information. This input includes the user's order history, search history, and feedback. The server collects this information and stores it in a database. During this process, the information is organized by user and assigned to each user.

[0109] Step 2:

[0110] The server learns user preferences based on user information collected using a generative AI model. The input is the user information organized in step 1, and the output is a model of user preferences. The server utilizes TensorFlow and PyTorch to analyze past behavioral patterns and build a predictive model.

[0111] Step 3:

[0112] The server generates user-specific menu and facility recommendation lists based on the learned model. The input is the preference model generated in step 2, and the output is a recommendation list for each user. The server performs real-time data processing and dynamically creates the recommendation lists.

[0113] Step 4:

[0114] The terminal presents the user with a list of recommendations received from the server. The input is the list of recommendations generated in step 3, and the output is the display on the screen. The terminal displays the recommendations appropriately according to the user's current session.

[0115] Step 5:

[0116] Users provide feedback on the presented recommendation list. The input is the display of the recommendation list on the device, and the output is the user's feedback information. Through feedback, users can specifically express their opinions and evaluations.

[0117] Step 6:

[0118] The server collects user feedback again and uses it to update the AI ​​model. The input is the feedback information obtained in step 5, and the output is the updated preference model. The server analyzes the feedback and adjusts the model to improve recommendation accuracy.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention is a technology that combines an emotion engine that recognizes user emotions with a real estate property suggestion system. An embodiment thereof is described below.

[0121] The server first collects behavioral data from users when they use the real estate search platform. This collected data includes search keywords, clicked property listings, viewing time, and access date and time. This information is associated with a user ID based on cookies and session information transmitted via the device.

[0122] The server incorporates an emotion engine that analyzes emotional patterns from user search behavior and feedback information. For example, it uses metrics such as user click speed, page dwell time, and search frequency to infer whether a user is excited or dissatisfied. This information is a crucial element for understanding user preferences with greater accuracy.

[0123] The server uses the above data to train a generative AI model and learn the user's individual preferences. This model optimizes the process of finding real estate properties that match the user's desired conditions based on feedback derived from the user's emotional state.

[0124] Based on the learning results, the server generates a list of recommended properties. Considering the user's emotional data obtained by the emotion engine, the list includes properties that match the user's lifestyle, preferences, and emotions. The list is presented to the user via their device, displaying detailed information.

[0125] Based on user feedback, the server continuously improves its emotion engine and AI models to further enhance personalized recommendations. For example, if emotion data reveals that a user consistently rates high-rise properties highly, the server will proactively present high-rise properties to that user in future recommendations.

[0126] In this way, the present invention can recommend real estate properties desired by users with higher accuracy than conventional systems, improving the user experience while enhancing the system's competitiveness.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server collects real-time behavioral data as users use the real estate search platform. This includes keywords searched, properties viewed, time spent on pages, access date and time, and links clicked. The device sends this data, along with the user ID, to the server, which then stores the history of each individual user.

[0130] Step 2:

[0131] The device optionally sends the user's facial expressions and voice data to the emotion engine. The emotion engine analyzes this data and generates emotion patterns to determine whether the user is interested or dissatisfied. The server also estimates the user's emotional state based on dynamic behavioral data (e.g., quickly navigating between multiple pages).

[0132] Step 3:

[0133] The server uses collected behavioral data and analysis results from the emotion engine to train a generative AI model. The AI ​​model learns to reflect the user's preferences and emotional state, optimizing the next property recommendations. Feedback data based on past search history and trends is also taken into consideration.

[0134] Step 4:

[0135] The server selects suitable properties from the real estate database that match the user's lifestyle and past preferences, based on the predictions of a trained AI model. Depending on the user's current emotional state detected by the emotion engine, specific properties are highlighted or filtered.

[0136] Step 5:

[0137] The device displays a list of recommended properties to the user. Each property on the list includes a detailed description, images, price information, and a sentiment score indicating the user's level of interest. The user can browse the list, select properties that interest them, and view more detailed information.

[0138] Step 6:

[0139] Users provide feedback on recommended properties. This feedback includes emotional responses and specific evaluations. The device aggregates this feedback and sends it to a server for further refinement and learning.

[0140] Step 7:

[0141] The server retrains the AI ​​model based on user feedback and newly acquired sentiment data to improve the accuracy of future recommendations. Model updates that consider both sentiment and preferences continuously improve the individual user experience.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] This addresses the challenge of providing highly accurate information that takes into account users' emotions and individual preferences.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for collecting user behavior data, means for analyzing emotional patterns and recognizing the user's emotions, and means for learning the user's preferences based on the collected data and emotion recognition. This makes it possible to provide optimized information while taking into account the user's emotional state.

[0147] "User behavior data" refers to information that shows the specific actions a user has taken on the platform, and includes data such as search keywords, clicked information, browsing time, and access date and time.

[0148] "Emotional patterns" are data that represents tendencies in emotions such as excitement and dissatisfaction, inferred by analyzing user behavior data.

[0149] "User preferences" refer to information that indicates what conditions and characteristics users prefer in information, and are orientations identified based on past behavior and feedback.

[0150] "Recommended methods" refer to the processes and methods for presenting users with information and options that are appropriate to them, based on the collected data and learning results.

[0151] "Feedback" refers to evaluations and opinions that users provide to the system, and this data is used to improve the accuracy of recommendations in the future.

[0152] "Emotional state" refers to information that indicates the user's current emotional state, obtained through the analysis of emotional patterns.

[0153] This invention is a real estate proposal technology that provides information while taking user emotions into consideration, and includes an emotion engine that collects user behavior data and analyzes emotional patterns. Specific embodiments thereof are described below.

[0154] The server collects user behavior data via communication from the user's device. This behavior data includes search keywords, information viewed, information clicked, time spent on the site, and access date and time. This information is organized based on the user ID associated with cookies and session information collected through the device.

[0155] The server has an emotion engine built in. This engine analyzes user behavior data and uses metrics such as click speed, page dwell time, and search frequency to infer whether the user is excited or dissatisfied. This inferred emotion pattern is used to more accurately understand the user's preferences.

[0156] Next, the server trains a generative AI model based on emotional patterns. This model learns the user's individual preferences and optimizes the process of finding information that matches the user's desired conditions based on feedback derived from the user's emotional state.

[0157] Based on the training results of the optimized model, the server creates a list of recommendations. This list includes information that matches the user's lifestyle, preferences, and emotions, taking into account the user's sentiment data obtained by the sentiment engine. These recommendations are provided to the user through their device, and the user can view detailed information.

[0158] Furthermore, based on user feedback, the server can continuously improve its sentiment engine and AI model to enhance the accuracy of recommendations in the future. For example, if sentiment data reveals that a user tends to prefer a particular type of information, that type of information will be prioritized for their access.

[0159] As a concrete example, one could use text such as, "Based on recent behavioral data, please generate a list of information that is suitable for the user's preferences," as an input prompt to the generative AI model, based on the user's preferences. This prompt would enable the provision of information that reflects the user's emotional state.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server collects user behavior data from the user's device. Specific inputs include search keywords entered by the user on the platform, clicked information, page viewing time, and access date and time. This data is transmitted from the device to the server via communication and associated with a user ID based on cookies and session information. The output is user-specific behavior data.

[0163] Step 2:

[0164] The emotion engine on the server analyzes collected behavioral data to identify the user's emotional patterns. This process involves inputting data such as click speed, page dwell time, and search frequency. By processing this data using these metrics and inferring whether the user is excited or dissatisfied, the emotion pattern is obtained as output.

[0165] Step 3:

[0166] The server trains a generative AI model based on emotional patterns and behavioral data. The emotional patterns and behavioral data obtained in the previous step are used as input. This allows the model to learn individual user preferences and generate an optimized algorithm. The output is an optimized model that receives feedback based on the user's emotional state and efficiently selects information that meets the given conditions.

[0167] Step 4:

[0168] The server generates a list of recommendations using the results of an optimized generative AI model. The trained model and user sentiment data are considered as input to this process. This selects information that matches the user's lifestyle, preferences, and emotions, and the recommendation list is sent to the device as output.

[0169] Step 5:

[0170] Users provide feedback on the recommended list. Feedback is entered from the device and sent to the server. The server receives this information and uses it to improve the emotion engine and AI model. The output is an improved model based on the feedback, resulting in better recommendation accuracy for future uses.

[0171] (Application Example 2)

[0172] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0173] Traditional real estate recommendation systems have struggled to accurately grasp user preferences, particularly in their inability to provide optimal property recommendations that take into account the emotions and interests users experience when they actually visit properties. Therefore, there is a need to effectively utilize emotional data from users visiting showrooms and model rooms to provide optimal property information in real time.

[0174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0175] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, means for recommending user-suitable properties from physical facility information based on the learned preferences, means for obtaining user feedback and updating the learning results, and means for analyzing the user's facial expressions and behavior using a visual information acquisition device and presenting emotion-based information in augmented reality. This makes it possible to immediately utilize emotional data from when the user actually visits a property and present the most appropriate property information in real time.

[0176] "User information" is a general term for information that indicates user behavior and preferences, and mainly includes search keywords, click history, and browsing time.

[0177] "Preferences" are indicators that show a user's tastes, interests, and concerns, and serve as basic data for identifying what kinds of properties and information users find appealing.

[0178] "Physical facility information" refers to all data related to a real estate property, including specific information such as geographical conditions, facilities, and floor plan.

[0179] A "visual information acquisition device" is a device that monitors a user's facial expressions and actions in real time and converts them into digital data; cameras and other photographic equipment fall into this category.

[0180] Augmented reality is a technology that overlays digital information onto the real world, providing users with real-time visual data.

[0181] "Emotion-based information" refers to data generated based on the emotional state analyzed from the user's facial expressions and behavior, and it influences the information suggested.

[0182] This system is designed to provide property recommendations that take into account the user's emotions, such as those used in real estate showrooms. The server, terminal, and user exchange data with each other to process information in real time.

[0183] The server first collects user information. This information includes the user's time spent at the real estate showroom and their level of attention to specific areas. This data is acquired through a visual information acquisition device and analyzed in real time based on the user's facial expressions and behavior.

[0184] The emotion engine analyzes the user's emotions from the acquired visual information. It evaluates facial expressions and dwell time to determine if the user is interested in a particular property or location. Based on this analysis, the server learns the user's preferences more accurately.

[0185] Based on the learning results, the generative AI model selects the most suitable physical facility information for the user and presents that information to the user using augmented reality technology. The presented information allows the user to view property details in real time and visually experience the specific appeal of the facility.

[0186] Furthermore, user feedback is collected through the device. This feedback is sent to the server and used to adjust the parameters of the AI ​​model and emotion engine, thereby improving the accuracy of future suggestions.

[0187] As a concrete example, if a user wearing smart glasses in a showroom shows interest in a kitchen, the server will immediately display detailed information about that kitchen and similar properties on the glasses using augmented reality. An example of a prompt message might be, "You've been in this room for a while and are smiling. To highlight the features of this room, please display detailed information, including related properties, using AR." Through this system, users can have a more fulfilling real estate viewing experience.

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server collects user information at real estate showrooms through a visual information acquisition device. Camera sensors capture users' facial expressions and movements in real time and transmit this data to the processing platform. The visual data, which is the input, consists of user facial expressions and movement information, and this is sent to the server. The output is analyzable user data.

[0191] Step 2:

[0192] The server uses an emotion engine to analyze the user's emotions from the acquired visual information. It evaluates the user's interest and emotional state using indicators such as changes in facial expressions and time spent on the screen (indicated in parentheses). The input is the collected raw visual data, and the output is data points representing the user's emotional state.

[0193] Step 3:

[0194] The server uses a generative AI model based on the acquired sentiment data to learn user preferences. Here, historical data and real-time sentiment analysis results are combined to calculate the optimal physical facility information for each individual user. Based on the sentiment data and past preference history as input, the most suitable property recommendations are generated.

[0195] Step 4:

[0196] The AI-generated model recommends facility information, which is then presented to the user via a terminal. The terminal uses augmented reality technology to display property details and related information within the user's field of view. The input is the generated property information, and the output is a visualized information presentation.

[0197] Step 5:

[0198] The user sends feedback on the presented information to the server via their device. This feedback is recorded as data representing the user's experience and satisfaction. The input is information about the user's reactions and preferences, while the output is data that helps to adjust the parameters of the improved recommendation algorithm.

[0199] Step 6:

[0200] The server analyzes the collected feedback and updates the AI ​​model and the emotion engine's learning algorithms. It then uses the feedback data to further improve the accuracy of future recommendations. The input is user feedback data, and the output is an optimized recommendation system.

[0201] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0202] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0203] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0204] [Second Embodiment]

[0205] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0206] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0207] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0208] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0209] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0210] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0211] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0212] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0213] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0214] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0215] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0216] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0217] This invention is a system that proposes the most suitable real estate property to a user, and its embodiments are described below. The purpose of this system is to recommend a real estate property that suits the user by collecting user information and learning the user's preferences using a generated AI based on that information.

[0218] The server first collects user behavior data when they use the real estate search platform. This includes keywords searched, properties clicked, and viewing time. The server also retrieves real estate information from external property databases and related APIs and updates the system's database. This makes it possible to provide users with the latest market information while maintaining the accuracy of property information.

[0219] Next, the server trains a generative AI model based on the collected data. This process analyzes the user's past preference patterns and behavioral history to predict what types of properties they might be interested in. The AI ​​model learns from this information and forms the basis for future recommendations.

[0220] Based on the learning results, the server generates a customized list of real estate properties for each user. This list is selected based on the user's lifestyle and preferences and is then presented to the user via their device. For example, users who prefer urban living will be given priority recommendations for properties in convenient areas.

[0221] Users view the properties presented through their devices and provide feedback such as "I like it" or "I want to know more details." This feedback information is then collected by the server and used in the next learning process.

[0222] In this way, the AI ​​model can be continuously improved based on user feedback, leading to more accurate recommendations and increased user satisfaction. For example, if a user is identified as having recently searched for many pet-friendly properties, the system will adjust its recommendations to display more pet-friendly properties in the future. As a "form for carrying out the invention," this system is structured to target a segment of the market and effectively generate profits.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The server collects user behavior data when users use the real estate search platform. This collected data includes searched keywords, clicked property IDs, viewing time, and access date and time. In addition, the device sends unique user ID information to the server to track user behavior individually.

[0226] Step 2:

[0227] The server periodically retrieves the latest real estate information through real estate databases and external APIs, updating the system's database. This data includes information on property location, price, floor plan, age, and changes in market trends.

[0228] Step 3:

[0229] The server preprocesses the collected user behavior data and uses it as training data for the AI ​​model. It performs data cleansing and feature engineering to convert the data into a format that is easy for machine learning algorithms to learn from.

[0230] Step 4:

[0231] The server uses a machine learning model to analyze user preferences and behavioral patterns. This model considers the user's past choices and interests to predict what should be suggested next. As new feedback is incorporated into the model, the accuracy of recommendations continuously improves.

[0232] Step 5:

[0233] Based on the analysis results, the server selects the most suitable real estate properties for the user's profile. It then generates a personalized recommendation list for the user, which is sent to the terminal.

[0234] Step 6:

[0235] The device displays a list of recommended real estate properties to the user. The property list includes photos, property details, price information, and location. The user can browse the list and click on properties of interest to view more details.

[0236] Step 7:

[0237] Users provide feedback on properties they are interested in. This feedback is entered via their device in specific forms, such as "add to favorites" or "not interested."

[0238] Step 8:

[0239] The server collects user feedback and uses it to retrain the AI ​​model. This feedback data provides information that will be useful for future recommendations and will further improve the accuracy of the system's recommendations.

[0240] (Example 1)

[0241] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0242] Traditional real estate recommendation systems had the problem of not being able to adequately reflect the individual preferences of users when recommending properties. Furthermore, the low accuracy of recommendations could lead to low user satisfaction. In addition, it was difficult to reflect the latest market information in real time, making it challenging to provide users with up-to-date and accurate information.

[0243] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0244] In this invention, the server includes information processing means for collecting user information, means for using a generative artificial intelligence model that learns user preferences based on the collected user information, and information processing means for acquiring and updating real estate information from an external database. This makes it possible to recommend properties that reflect the individual preferences of the user, and further enhances user satisfaction by providing the latest market information in real time.

[0245] "Information processing means" refers to the means of collecting data from users and appropriately analyzing and managing it within the system.

[0246] A "generative artificial intelligence model" is a model that has algorithms and programs designed to learn user preferences and predict future actions and choices.

[0247] "Information presentation means" refers to the means by which a system presents information adapted to the user in a visual or other way.

[0248] "Information improvement methods" are means of improving the performance and accuracy of a system based on user feedback and other evaluations.

[0249] "Information analysis tools" are means of analyzing input data and feedback in detail to extract new insights and areas for improvement.

[0250] "Information selection methods" refer to the means of selecting the most suitable real estate information based on the user's lifestyle and past behavioral history.

[0251] In order to implement the system according to the present invention, it is necessary for the server, terminal, and user to exchange data with each other. The details are described below.

[0252] The server is responsible for collecting user behavior data for the real estate search platform. This behavior data includes keywords searched by users, properties accessed, and the time spent viewing each property. This data is managed and analyzed within the server using information processing tools. The server also obtains the latest property information via external real estate databases and related APIs, and updates its internal database. This update process ensures that users are always provided with the most up-to-date market information.

[0253] Furthermore, the server uses a generative artificial intelligence model to learn user preferences based on the collected user data. This allows it to predict individual interests based on the user's past behavior history and find real estate properties that match those interests. For example, if a user has a history of searching for "pet-friendly properties," the AI ​​model will take that preference into account and recommend pet-friendly properties.

[0254] The terminal serves to present users with individually customized property lists sent from the server. Users can view property details through the terminal and provide feedback on properties of interest. This feedback is sent to the server and analyzed by information improvement tools, further enhancing the accuracy of the AI ​​model.

[0255] As a concrete example, suppose a user enters the following prompt into the terminal: "I'm currently looking for an apartment where I can live with my pet. Do you have any recommendations?" Based on this prompt, the server prioritizes extracting information on pet-friendly apartments and presents it to the user.

[0256] Thus, the present invention realizes a system that efficiently provides users with optimal real estate information and improves the user experience.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server collects user behavior data from real estate search platforms. Inputs include user search keywords, clicked properties, and viewing time for each property. The server organizes and stores this data within the system using information processing tools. The output is a dataset of user behavior. Specifically, this includes actions such as recording the time a user spends searching for "newly built condominiums" and viewing specific properties.

[0260] Step 2:

[0261] The server retrieves and updates real estate information from external databases and APIs. Input is detailed property information, including location, price, area, and amenities. The retrieved information is compared with existing data, and any changes are saved to the system's database. The output is the latest real estate database. Specific operations include adding newly listed properties and reflecting changes in sales status.

[0262] Step 3:

[0263] The server trains a generative AI model based on collected user information. The input consists of user behavior data and the latest real estate data. The server analyzes this information to extract user preferences and update the AI ​​model. The output is an AI model that reflects the user's preferences. Specifically, it performs a process to infer the user's preferences based on the characteristics of properties they have previously viewed (e.g., location and price range).

[0264] Step 4:

[0265] The server generates a personalized property list for each user using a newly trained AI model. The input consists of the updated AI model and the latest real estate data. The server combines this data to select the property best suited to the user's preferences. The output is a customized property list. Specifically, filtering is performed based on user preferences such as pet-friendly properties and proximity to train stations.

[0266] Step 5:

[0267] The terminal displays a list of properties sent from the server to the user. The input is a customized property list generated by the server. The user reviews the suggested properties through the terminal and clicks on properties of interest to obtain detailed information. The output is a display of property details. Specifically, the property's location, price, floor plan, etc., are displayed on the screen.

[0268] Step 6:

[0269] Users provide feedback on properties through their devices. Input consists of ratings and comments made by the user regarding the presented properties. Users enter feedback such as "I like this property" or "I want more information," and the device sends it to the server. Output is the state in which the feedback has been sent to the server. Specific operations include a function to hide properties that the user "doesn't like" from the list.

[0270] Step 7:

[0271] The server further improves the AI ​​model based on user feedback. The input consists of user feedback and the existing AI model. The server analyzes the feedback information and adjusts the AI ​​model's parameters to improve the accuracy of recommendations. The output is the improved AI model. Specifically, after a sufficient amount of feedback from a large number of users has been accumulated, the model is retrained and the improvements are reflected in the next recommendation.

[0272] (Application Example 1)

[0273] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] In food delivery services, it is crucial to suggest optimal menus and facilities based on users' diverse preferences and behavioral history. However, existing systems fail to provide appropriate recommendations to individual users, making it difficult to improve user satisfaction. To solve this problem, it is necessary to learn user preferences using past behavioral data and provide more personalized recommendations.

[0275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, and means for recommending user-suitable menus or facilities from food delivery information based on the learned preferences. This makes it possible to recommend menus and facilities that are tailored to the individual preferences of each user.

[0277] "User information" refers to personal information and behavioral data of users related to the food delivery service, including order history, search history, and feedback.

[0278] "Preferences" refer to the inferred preference for a particular menu item or facility based on the user's past tastes and behavioral patterns.

[0279] "Food delivery information" refers to information about menus, facilities, and delivery conditions available to users, and includes information such as the type of food, price, and location of the facilities providing the service.

[0280] "Feedback" refers to the evaluations and opinions provided by users regarding the presented menus and facilities, which are used for subsequent recommendations.

[0281] "Generative AI model" refers to an artificial intelligence algorithm that learns user preferences based on the user's past behavior data and recommends appropriate menus and facilities.

[0282] "Recommendation" refers to the act of presenting menus and facilities that match the user's preferences based on the results analyzed by the generative AI model.

[0283] "Dynamically presenting" refers to a method of displaying appropriate menu and facility information in real time according to the user's preferences and behavior history.

[0284] The system that realizes this invention is configured as follows. First, the server collects user information in real time. This information includes the user's order history, search history, and feedback. The information is stored in a database and organized for each user.

[0285] Next, based on the collected user information, the server uses the generative AI model to learn the user's preferences. In this process, machine learning frameworks such as TensorFlow and PyTorch are used to analyze past behavior patterns and predict what menus and facilities the user prefers. As a result, a customized recommendation list can be generated for each user.

[0286] The user's terminal receives and displays the recommendation list sent from the server. This recommendation list is dynamically updated and proposes the most suitable menus and facilities based on the user's past search history and preferences when the user selects a dish.

[0287] Furthermore, the feedback provided by the user is sent back to the server again and used to update the learning model. As a result, the recommendation accuracy can be continuously improved, and the user's satisfaction can be enhanced.

[0288] For example, if a user has recently ordered a lot of Italian food, the next time they log in, they will be recommended new menu items from Italian restaurants. In this way, recommendations can be tailored to the individual user's preferences.

[0289] An example of a prompt message would be: "Based on past history, suggest the most suitable food delivery menu for this user."

[0290] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0291] Step 1:

[0292] The server collects user information. This input includes the user's order history, search history, and feedback. The server collects this information and stores it in a database. During this process, the information is organized by user and assigned to each user.

[0293] Step 2:

[0294] The server learns user preferences based on user information collected using a generative AI model. The input is the user information organized in step 1, and the output is a model of user preferences. The server utilizes TensorFlow and PyTorch to analyze past behavioral patterns and build a predictive model.

[0295] Step 3:

[0296] The server generates user-specific menu and facility recommendation lists based on the learned model. The input is the preference model generated in step 2, and the output is a recommendation list for each user. The server performs real-time data processing and dynamically creates the recommendation lists.

[0297] Step 4:

[0298] The terminal presents the user with a list of recommendations received from the server. The input is the list of recommendations generated in step 3, and the output is the display on the screen. The terminal displays the recommendations appropriately according to the user's current session.

[0299] Step 5:

[0300] Users provide feedback on the presented recommendation list. The input is the display of the recommendation list on the device, and the output is the user's feedback information. Through feedback, users can specifically express their opinions and evaluations.

[0301] Step 6:

[0302] The server collects user feedback again and uses it to update the AI ​​model. The input is the feedback information obtained in step 5, and the output is the updated preference model. The server analyzes the feedback and adjusts the model to improve recommendation accuracy.

[0303] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0304] This invention is a technology that combines an emotion engine that recognizes user emotions with a real estate property suggestion system. An embodiment thereof is described below.

[0305] The server first collects behavioral data from users when they use the real estate search platform. This collected data includes search keywords, clicked property listings, viewing time, and access date and time. This information is associated with a user ID based on cookies and session information transmitted via the device.

[0306] The server incorporates an emotion engine that analyzes emotional patterns from users' search behaviors and feedback information. For example, based on indicators such as the user's click speed, page stay time, and search frequency, it infers whether the user is excited or dissatisfied. This information becomes an important factor for more accurately understanding the user's preferences.

[0307] The server uses the above data to train a generated AI model and learn the user's individual preferences. This model optimizes the process of finding real estate properties that match the conditions desired by the user based on feedback based on the user's emotional state.

[0308] Based on the results of the learning, the server generates a list of recommended properties. Considering the user's emotional data obtained by the emotion engine, properties that match the user's lifestyle, preferences, and emotions are included in the list. The list is presented to the user via the terminal and detailed information is displayed.

[0309] Based on the feedback provided by the user, the server continuously improves the emotion engine and the AI model to further enhance personalized recommendations. As a specific example, if it is read from the emotional data that a certain user always highly evaluates high-rise properties, high-rise properties will be actively presented to that user in the next proposal.

[0310] In this way, the present invention can recommend real estate properties desired by the user with higher accuracy than conventional systems, improve the user experience, and enhance the competitiveness of the system.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The server collects real-time behavioral data as users use the real estate search platform. This includes keywords searched, properties viewed, time spent on pages, access date and time, and links clicked. The device sends this data, along with the user ID, to the server, which then stores the history of each individual user.

[0314] Step 2:

[0315] The device optionally sends the user's facial expressions and voice data to the emotion engine. The emotion engine analyzes this data and generates emotion patterns to determine whether the user is interested or dissatisfied. The server also estimates the user's emotional state based on dynamic behavioral data (e.g., quickly navigating between multiple pages).

[0316] Step 3:

[0317] The server uses collected behavioral data and analysis results from the emotion engine to train a generative AI model. The AI ​​model learns to reflect the user's preferences and emotional state, optimizing the next property recommendations. Feedback data based on past search history and trends is also taken into consideration.

[0318] Step 4:

[0319] The server selects suitable properties from the real estate database that match the user's lifestyle and past preferences, based on the predictions of a trained AI model. Depending on the user's current emotional state detected by the emotion engine, specific properties are highlighted or filtered.

[0320] Step 5:

[0321] The device displays a list of recommended properties to the user. Each property on the list includes a detailed description, images, price information, and a sentiment score indicating the user's level of interest. The user can browse the list, select properties that interest them, and view more detailed information.

[0322] Step 6:

[0323] Users provide feedback on recommended properties. This feedback includes emotional responses and specific evaluations. The device aggregates this feedback and sends it to a server for further refinement and learning.

[0324] Step 7:

[0325] The server retrains the AI ​​model based on user feedback and newly acquired sentiment data to improve the accuracy of future recommendations. Model updates that consider both sentiment and preferences continuously improve the individual user experience.

[0326] (Example 2)

[0327] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0328] This addresses the challenge of providing highly accurate information that takes into account users' emotions and individual preferences.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for collecting user behavior data, means for analyzing emotional patterns and recognizing the user's emotions, and means for learning the user's preferences based on the collected data and emotion recognition. This makes it possible to provide optimized information while taking into account the user's emotional state.

[0331] "User behavior data" refers to information that shows the specific actions a user has taken on the platform, and includes data such as search keywords, clicked information, browsing time, and access date and time.

[0332] "Emotional patterns" are data that represents tendencies in emotions such as excitement and dissatisfaction, inferred by analyzing user behavior data.

[0333] "User preferences" refer to information that indicates what conditions and characteristics users prefer in information, and are orientations identified based on past behavior and feedback.

[0334] "Recommended methods" refer to the processes and methods for presenting users with information and options that are appropriate to them, based on the collected data and learning results.

[0335] "Feedback" refers to evaluations and opinions that users provide to the system, and this data is used to improve the accuracy of recommendations in the future.

[0336] "Emotional state" refers to information that indicates the user's current emotional state, obtained through the analysis of emotional patterns.

[0337] This invention is a real estate proposal technology that provides information while taking user emotions into consideration, and includes an emotion engine that collects user behavior data and analyzes emotional patterns. Specific embodiments thereof are described below.

[0338] The server collects user behavior data via communication from the user's device. This behavior data includes search keywords, information viewed, information clicked, time spent on the site, and access date and time. This information is organized based on the user ID associated with cookies and session information collected through the device.

[0339] The server has an emotion engine built in. This engine analyzes user behavior data and uses metrics such as click speed, page dwell time, and search frequency to infer whether the user is excited or dissatisfied. This inferred emotion pattern is used to more accurately understand the user's preferences.

[0340] Next, the server trains a generative AI model based on emotional patterns. This model learns the user's individual preferences and optimizes the process of finding information that matches the user's desired conditions based on feedback derived from the user's emotional state.

[0341] Based on the training results of the optimized model, the server creates a list of recommendations. This list includes information that matches the user's lifestyle, preferences, and emotions, taking into account the user's sentiment data obtained by the sentiment engine. These recommendations are provided to the user through their device, and the user can view detailed information.

[0342] Furthermore, based on user feedback, the server can continuously improve its sentiment engine and AI model to enhance the accuracy of recommendations in the future. For example, if sentiment data reveals that a user tends to prefer a particular type of information, that type of information will be prioritized for their access.

[0343] As a concrete example, one could use text such as, "Based on recent behavioral data, please generate a list of information that is suitable for the user's preferences," as an input prompt to the generative AI model, based on the user's preferences. This prompt would enable the provision of information that reflects the user's emotional state.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] The server collects user behavior data from the user's device. Specific inputs include search keywords entered by the user on the platform, clicked information, page viewing time, and access date and time. This data is transmitted from the device to the server via communication and associated with a user ID based on cookies and session information. The output is user-specific behavior data.

[0347] Step 2:

[0348] The emotion engine on the server analyzes collected behavioral data to identify the user's emotional patterns. This process involves inputting data such as click speed, page dwell time, and search frequency. By processing this data using these metrics and inferring whether the user is excited or dissatisfied, the emotion pattern is obtained as output.

[0349] Step 3:

[0350] The server trains a generative AI model based on emotional patterns and behavioral data. The emotional patterns and behavioral data obtained in the previous step are used as input. This allows the model to learn individual user preferences and generate an optimized algorithm. The output is an optimized model that receives feedback based on the user's emotional state and efficiently selects information that meets the given conditions.

[0351] Step 4:

[0352] The server generates a list of recommendations using the results of an optimized generative AI model. The trained model and user sentiment data are considered as input to this process. This selects information that matches the user's lifestyle, preferences, and emotions, and the recommendation list is sent to the device as output.

[0353] Step 5:

[0354] Users provide feedback on the recommended list. Feedback is entered from the device and sent to the server. The server receives this information and uses it to improve the emotion engine and AI model. The output is an improved model based on the feedback, resulting in better recommendation accuracy for future uses.

[0355] (Application Example 2)

[0356] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0357] Traditional real estate recommendation systems have struggled to accurately grasp user preferences, particularly in their inability to provide optimal property recommendations that take into account the emotions and interests users experience when they actually visit properties. Therefore, there is a need to effectively utilize emotional data from users visiting showrooms and model rooms to provide optimal property information in real time.

[0358] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0359] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, means for recommending user-suitable properties from physical facility information based on the learned preferences, means for obtaining user feedback and updating the learning results, and means for analyzing the user's facial expressions and behavior using a visual information acquisition device and presenting emotion-based information in augmented reality. This makes it possible to immediately utilize emotional data from when the user actually visits a property and present the most appropriate property information in real time.

[0360] "User information" is a general term for information that indicates user behavior and preferences, and mainly includes search keywords, click history, and browsing time.

[0361] "Preferences" are indicators that show a user's tastes, interests, and concerns, and serve as basic data for identifying what kinds of properties and information users find appealing.

[0362] "Physical facility information" refers to all data related to a real estate property, including specific information such as geographical conditions, facilities, and floor plan.

[0363] A "visual information acquisition device" is a device that monitors a user's facial expressions and actions in real time and converts them into digital data; cameras and other photographic equipment fall into this category.

[0364] Augmented reality is a technology that overlays digital information onto the real world, providing users with real-time visual data.

[0365] "Emotion-based information" refers to data generated based on the emotional state analyzed from the user's facial expressions and behavior, and it influences the information suggested.

[0366] This system is designed to provide property recommendations that take into account the user's emotions, such as those used in real estate showrooms. The server, terminal, and user exchange data with each other to process information in real time.

[0367] The server first collects user information. This information includes the user's time spent at the real estate showroom and their level of attention to specific areas. This data is acquired through a visual information acquisition device and analyzed in real time based on the user's facial expressions and behavior.

[0368] The emotion engine analyzes the user's emotions from the acquired visual information. It evaluates facial expressions and dwell time to determine if the user is interested in a particular property or location. Based on this analysis, the server learns the user's preferences more accurately.

[0369] Based on the learning results, the generative AI model selects the most suitable physical facility information for the user and presents that information to the user using augmented reality technology. The presented information allows the user to view property details in real time and visually experience the specific appeal of the facility.

[0370] Furthermore, user feedback is collected through the device. This feedback is sent to the server and used to adjust the parameters of the AI ​​model and emotion engine, thereby improving the accuracy of future suggestions.

[0371] As a concrete example, if a user wearing smart glasses in a showroom shows interest in a kitchen, the server will immediately display detailed information about that kitchen and similar properties on the glasses using augmented reality. An example of a prompt message might be, "You've been in this room for a while and are smiling. To highlight the features of this room, please display detailed information, including related properties, using AR." Through this system, users can have a more fulfilling real estate viewing experience.

[0372] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0373] Step 1:

[0374] The server collects user information at real estate showrooms through a visual information acquisition device. Camera sensors capture users' facial expressions and movements in real time and transmit this data to the processing platform. The visual data, which is the input, consists of user facial expressions and movement information, and this is sent to the server. The output is analyzable user data.

[0375] Step 2:

[0376] The server uses an emotion engine to analyze the user's emotions from the acquired visual information. It evaluates the user's interest and emotional state using indicators such as changes in facial expressions and time spent on the screen (indicated in parentheses). The input is the collected raw visual data, and the output is data points representing the user's emotional state.

[0377] Step 3:

[0378] The server uses a generative AI model based on the acquired sentiment data to learn user preferences. Here, historical data and real-time sentiment analysis results are combined to calculate the optimal physical facility information for each individual user. Based on the sentiment data and past preference history as input, the most suitable property recommendations are generated.

[0379] Step 4:

[0380] The AI-generated model recommends facility information, which is then presented to the user via a terminal. The terminal uses augmented reality technology to display property details and related information within the user's field of view. The input is the generated property information, and the output is a visualized information presentation.

[0381] Step 5:

[0382] The user sends feedback on the presented information to the server via their device. This feedback is recorded as data representing the user's experience and satisfaction. The input is information about the user's reactions and preferences, while the output is data that helps to adjust the parameters of the improved recommendation algorithm.

[0383] Step 6:

[0384] The server analyzes the collected feedback and updates the AI ​​model and the emotion engine's learning algorithms. It then uses the feedback data to further improve the accuracy of future recommendations. The input is user feedback data, and the output is an optimized recommendation system.

[0385] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0386] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0387] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0388] [Third Embodiment]

[0389] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0390] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0391] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0392] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0393] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0394] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0395] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0396] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0397] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0398] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0399] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0400] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0401] This invention is a system that proposes the most suitable real estate property to a user, and its embodiments are described below. The purpose of this system is to recommend a real estate property that suits the user by collecting user information and learning the user's preferences using a generated AI based on that information.

[0402] The server first collects user behavior data when they use the real estate search platform. This includes keywords searched, properties clicked, and viewing time. The server also retrieves real estate information from external property databases and related APIs and updates the system's database. This makes it possible to provide users with the latest market information while maintaining the accuracy of property information.

[0403] Next, the server trains a generative AI model based on the collected data. This process analyzes the user's past preference patterns and behavioral history to predict what types of properties they might be interested in. The AI ​​model learns from this information and forms the basis for future recommendations.

[0404] Based on the learning results, the server generates a customized list of real estate properties for each user. This list is selected based on the user's lifestyle and preferences and is then presented to the user via their device. For example, users who prefer urban living will be given priority recommendations for properties in convenient areas.

[0405] Users view the properties presented through their devices and provide feedback such as "I like it" or "I want to know more details." This feedback information is then collected by the server and used in the next learning process.

[0406] In this way, the AI ​​model can be continuously improved based on user feedback, leading to more accurate recommendations and increased user satisfaction. For example, if a user is identified as having recently searched for many pet-friendly properties, the system will adjust its recommendations to display more pet-friendly properties in the future. As a "form for carrying out the invention," this system is structured to target a segment of the market and effectively generate profits.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The server collects user behavior data when users use the real estate search platform. This collected data includes searched keywords, clicked property IDs, viewing time, and access date and time. In addition, the device sends unique user ID information to the server to track user behavior individually.

[0410] Step 2:

[0411] The server periodically retrieves the latest real estate information through real estate databases and external APIs, updating the system's database. This data includes information on property location, price, floor plan, age, and changes in market trends.

[0412] Step 3:

[0413] The server preprocesses the collected user behavior data and uses it as training data for the AI ​​model. It performs data cleansing and feature engineering to convert the data into a format that is easy for machine learning algorithms to learn from.

[0414] Step 4:

[0415] The server uses a machine learning model to analyze user preferences and behavioral patterns. This model considers the user's past choices and interests to predict what should be suggested next. As new feedback is incorporated into the model, the accuracy of recommendations continuously improves.

[0416] Step 5:

[0417] Based on the analysis results, the server selects the most suitable real estate properties for the user's profile. It then generates a personalized recommendation list for the user, which is sent to the terminal.

[0418] Step 6:

[0419] The device displays a list of recommended real estate properties to the user. The property list includes photos, property details, price information, and location. The user can browse the list and click on properties of interest to view more details.

[0420] Step 7:

[0421] Users provide feedback on properties they are interested in. This feedback is entered via their device in specific forms, such as "add to favorites" or "not interested."

[0422] Step 8:

[0423] The server collects user feedback and uses it to retrain the AI ​​model. This feedback data provides information that will be useful for future recommendations and will further improve the accuracy of the system's recommendations.

[0424] (Example 1)

[0425] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0426] Traditional real estate recommendation systems had the problem of not being able to adequately reflect the individual preferences of users when recommending properties. Furthermore, the low accuracy of recommendations could lead to low user satisfaction. In addition, it was difficult to reflect the latest market information in real time, making it challenging to provide users with up-to-date and accurate information.

[0427] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0428] In this invention, the server includes information processing means for collecting user information, means for using a generative artificial intelligence model that learns user preferences based on the collected user information, and information processing means for acquiring and updating real estate information from an external database. This makes it possible to recommend properties that reflect the individual preferences of the user, and further enhances user satisfaction by providing the latest market information in real time.

[0429] "Information processing means" refers to the means of collecting data from users and appropriately analyzing and managing it within the system.

[0430] A "generative artificial intelligence model" is a model that has algorithms and programs designed to learn user preferences and predict future actions and choices.

[0431] "Information presentation means" refers to the means by which a system presents information adapted to the user in a visual or other way.

[0432] "Information improvement methods" are means of improving the performance and accuracy of a system based on user feedback and other evaluations.

[0433] "Information analysis tools" are means of analyzing input data and feedback in detail to extract new insights and areas for improvement.

[0434] "Information selection methods" refer to the means of selecting the most suitable real estate information based on the user's lifestyle and past behavioral history.

[0435] In order to implement the system according to the present invention, it is necessary for the server, terminal, and user to exchange data with each other. The details are described below.

[0436] The server is responsible for collecting user behavior data for the real estate search platform. This behavior data includes keywords searched by users, properties accessed, and the time spent viewing each property. This data is managed and analyzed within the server using information processing tools. The server also obtains the latest property information via external real estate databases and related APIs, and updates its internal database. This update process ensures that users are always provided with the most up-to-date market information.

[0437] Furthermore, the server uses a generative artificial intelligence model to learn user preferences based on the collected user data. This allows it to predict individual interests based on the user's past behavior history and find real estate properties that match those interests. For example, if a user has a history of searching for "pet-friendly properties," the AI ​​model will take that preference into account and recommend pet-friendly properties.

[0438] The terminal serves to present users with individually customized property lists sent from the server. Users can view property details through the terminal and provide feedback on properties of interest. This feedback is sent to the server and analyzed by information improvement tools, further enhancing the accuracy of the AI ​​model.

[0439] As a concrete example, suppose a user enters the following prompt into the terminal: "I'm currently looking for an apartment where I can live with my pet. Do you have any recommendations?" Based on this prompt, the server prioritizes extracting information on pet-friendly apartments and presents it to the user.

[0440] Thus, the present invention realizes a system that efficiently provides users with optimal real estate information and improves the user experience.

[0441] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0442] Step 1:

[0443] The server collects user behavior data from real estate search platforms. Inputs include user search keywords, clicked properties, and viewing time for each property. The server organizes and stores this data within the system using information processing tools. The output is a dataset of user behavior. Specifically, this includes actions such as recording the time a user spends searching for "newly built condominiums" and viewing specific properties.

[0444] Step 2:

[0445] The server retrieves and updates real estate information from external databases and APIs. Input is detailed property information, including location, price, area, and amenities. The retrieved information is compared with existing data, and any changes are saved to the system's database. The output is the latest real estate database. Specific operations include adding newly listed properties and reflecting changes in sales status.

[0446] Step 3:

[0447] The server trains a generative AI model based on collected user information. The input consists of user behavior data and the latest real estate data. The server analyzes this information to extract user preferences and update the AI ​​model. The output is an AI model that reflects the user's preferences. Specifically, it performs a process to infer the user's preferences based on the characteristics of properties they have previously viewed (e.g., location and price range).

[0448] Step 4:

[0449] The server generates a personalized property list for each user using a newly trained AI model. The input consists of the updated AI model and the latest real estate data. The server combines this data to select the property best suited to the user's preferences. The output is a customized property list. Specifically, filtering is performed based on user preferences such as pet-friendly properties and proximity to train stations.

[0450] Step 5:

[0451] The terminal displays a list of properties sent from the server to the user. The input is a customized property list generated by the server. The user reviews the suggested properties through the terminal and clicks on properties of interest to obtain detailed information. The output is a display of property details. Specifically, the property's location, price, floor plan, etc., are displayed on the screen.

[0452] Step 6:

[0453] Users provide feedback on properties through their devices. Input consists of ratings and comments made by the user regarding the presented properties. Users enter feedback such as "I like this property" or "I want more information," and the device sends it to the server. Output is the state in which the feedback has been sent to the server. Specific operations include a function to hide properties that the user "doesn't like" from the list.

[0454] Step 7:

[0455] The server further improves the AI ​​model based on user feedback. The input consists of user feedback and the existing AI model. The server analyzes the feedback information and adjusts the AI ​​model's parameters to improve the accuracy of recommendations. The output is the improved AI model. Specifically, after a sufficient amount of feedback from a large number of users has been accumulated, the model is retrained and the improvements are reflected in the next recommendation.

[0456] (Application Example 1)

[0457] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] In food delivery services, it is crucial to suggest optimal menus and facilities based on users' diverse preferences and behavioral history. However, existing systems fail to provide appropriate recommendations to individual users, making it difficult to improve user satisfaction. To solve this problem, it is necessary to learn user preferences using past behavioral data and provide more personalized recommendations.

[0459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0460] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, and means for recommending user-suitable menus or facilities from food delivery information based on the learned preferences. This makes it possible to recommend menus and facilities that are tailored to the individual preferences of each user.

[0461] "User information" refers to personal information and behavioral data of users related to the food delivery service, including order history, search history, and feedback.

[0462] "Preferences" refer to the inferred preference for a particular menu item or facility based on the user's past tastes and behavioral patterns.

[0463] "Food delivery information" refers to information about menus, facilities, and delivery conditions available to users, and includes information such as the type of food, price, and location of the facilities providing the service.

[0464] "Feedback" refers to the evaluations and opinions that users provide about the menus and facilities presented, and this feedback is used for future recommendations.

[0465] A "generative AI model" refers to an artificial intelligence algorithm that learns user preferences based on past behavioral data and recommends appropriate menus and facilities.

[0466] "Recommendation" refers to the act of presenting menus and facilities that match the user's preferences based on the results of analysis by a generative AI model.

[0467] "Dynamic presentation" refers to a method of displaying appropriate menus and facility information in real time, based on the user's preferences and behavioral history.

[0468] The system that realizes this invention is configured as follows: First, a server collects user information in real time. This information includes the user's order history, search history, and feedback. The information is stored in a database and organized for each user.

[0469] Next, the server uses a generative AI model to learn user preferences based on the collected user information. This process uses machine learning frameworks such as TensorFlow and PyTorch to analyze past behavioral patterns and predict what menus and facilities users will prefer. This allows for the generation of personalized recommendation lists for each user.

[0470] The user's device receives and displays a list of recommendations sent from the server. This list is dynamically updated, suggesting the most suitable menus and establishments based on the user's past search history and preferences when they choose a restaurant.

[0471] Furthermore, user feedback is sent back to the server and used to update the learning model. This allows for continuous improvement of recommendation accuracy and increased user satisfaction.

[0472] For example, if a user has recently ordered a lot of Italian food, the next time they log in, they will be recommended new menu items from Italian restaurants. In this way, recommendations can be tailored to the individual user's preferences.

[0473] An example of a prompt message would be: "Based on past history, suggest the most suitable food delivery menu for this user."

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The server collects user information. This input includes the user's order history, search history, and feedback. The server collects this information and stores it in a database. During this process, the information is organized by user and assigned to each user.

[0477] Step 2:

[0478] The server learns user preferences based on user information collected using a generative AI model. The input is the user information organized in step 1, and the output is a model of user preferences. The server utilizes TensorFlow and PyTorch to analyze past behavioral patterns and build a predictive model.

[0479] Step 3:

[0480] The server generates user-specific menu and facility recommendation lists based on the learned model. The input is the preference model generated in step 2, and the output is a recommendation list for each user. The server performs real-time data processing and dynamically creates the recommendation lists.

[0481] Step 4:

[0482] The terminal presents the user with a list of recommendations received from the server. The input is the list of recommendations generated in step 3, and the output is the display on the screen. The terminal displays the recommendations appropriately according to the user's current session.

[0483] Step 5:

[0484] Users provide feedback on the presented recommendation list. The input is the display of the recommendation list on the device, and the output is the user's feedback information. Through feedback, users can specifically express their opinions and evaluations.

[0485] Step 6:

[0486] The server collects user feedback again and uses it to update the AI ​​model. The input is the feedback information obtained in step 5, and the output is the updated preference model. The server analyzes the feedback and adjusts the model to improve recommendation accuracy.

[0487] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0488] This invention is a technology that combines an emotion engine that recognizes user emotions with a real estate property suggestion system. An embodiment thereof is described below.

[0489] The server first collects behavioral data from users when they use the real estate search platform. This collected data includes search keywords, clicked property listings, viewing time, and access date and time. This information is associated with a user ID based on cookies and session information transmitted via the device.

[0490] The server incorporates an emotion engine that analyzes emotional patterns from user search behavior and feedback information. For example, it uses metrics such as user click speed, page dwell time, and search frequency to infer whether a user is excited or dissatisfied. This information is a crucial element for understanding user preferences with greater accuracy.

[0491] The server uses the above data to train a generative AI model and learn the user's individual preferences. This model optimizes the process of finding real estate properties that match the user's desired conditions based on feedback derived from the user's emotional state.

[0492] Based on the learning results, the server generates a list of recommended properties. Considering the user's emotional data obtained by the emotion engine, the list includes properties that match the user's lifestyle, preferences, and emotions. The list is presented to the user via their device, displaying detailed information.

[0493] Based on user feedback, the server continuously improves its emotion engine and AI models to further enhance personalized recommendations. For example, if emotion data reveals that a user consistently rates high-rise properties highly, the server will proactively present high-rise properties to that user in future recommendations.

[0494] In this way, the present invention can recommend real estate properties desired by users with higher accuracy than conventional systems, improving the user experience while enhancing the system's competitiveness.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] The server collects real-time behavioral data as users use the real estate search platform. This includes keywords searched, properties viewed, time spent on pages, access date and time, and links clicked. The device sends this data, along with the user ID, to the server, which then stores the history of each individual user.

[0498] Step 2:

[0499] The device optionally sends the user's facial expressions and voice data to the emotion engine. The emotion engine analyzes this data and generates emotion patterns to determine whether the user is interested or dissatisfied. The server also estimates the user's emotional state based on dynamic behavioral data (e.g., quickly navigating between multiple pages).

[0500] Step 3:

[0501] The server uses collected behavioral data and analysis results from the emotion engine to train a generative AI model. The AI ​​model learns to reflect the user's preferences and emotional state, optimizing the next property recommendations. Feedback data based on past search history and trends is also taken into consideration.

[0502] Step 4:

[0503] The server selects suitable properties from the real estate database that match the user's lifestyle and past preferences, based on the predictions of a trained AI model. Depending on the user's current emotional state detected by the emotion engine, specific properties are highlighted or filtered.

[0504] Step 5:

[0505] The device displays a list of recommended properties to the user. Each property on the list includes a detailed description, images, price information, and a sentiment score indicating the user's level of interest. The user can browse the list, select properties that interest them, and view more detailed information.

[0506] Step 6:

[0507] Users provide feedback on recommended properties. This feedback includes emotional responses and specific evaluations. The device aggregates this feedback and sends it to a server for further refinement and learning.

[0508] Step 7:

[0509] The server retrains the AI ​​model based on user feedback and newly acquired sentiment data to improve the accuracy of future recommendations. Model updates that consider both sentiment and preferences continuously improve the individual user experience.

[0510] (Example 2)

[0511] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0512] This addresses the challenge of providing highly accurate information that takes into account users' emotions and individual preferences.

[0513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0514] In this invention, the server includes means for collecting user behavior data, means for analyzing emotional patterns and recognizing the user's emotions, and means for learning the user's preferences based on the collected data and emotion recognition. This makes it possible to provide optimized information while taking into account the user's emotional state.

[0515] "User behavior data" refers to information that shows the specific actions a user has taken on the platform, and includes data such as search keywords, clicked information, browsing time, and access date and time.

[0516] "Emotional patterns" are data that represents tendencies in emotions such as excitement and dissatisfaction, inferred by analyzing user behavior data.

[0517] "User preferences" refer to information that indicates what conditions and characteristics users prefer in information, and are orientations identified based on past behavior and feedback.

[0518] "Recommended methods" refer to the processes and methods for presenting users with information and options that are appropriate to them, based on the collected data and learning results.

[0519] "Feedback" refers to evaluations and opinions that users provide to the system, and this data is used to improve the accuracy of recommendations in the future.

[0520] "Emotional state" refers to information that indicates the user's current emotional state, obtained through the analysis of emotional patterns.

[0521] This invention is a real estate proposal technology that provides information while taking user emotions into consideration, and includes an emotion engine that collects user behavior data and analyzes emotional patterns. Specific embodiments thereof are described below.

[0522] The server collects user behavior data via communication from the user's device. This behavior data includes search keywords, information viewed, information clicked, time spent on the site, and access date and time. This information is organized based on the user ID associated with cookies and session information collected through the device.

[0523] The server has an emotion engine built in. This engine analyzes user behavior data and uses metrics such as click speed, page dwell time, and search frequency to infer whether the user is excited or dissatisfied. This inferred emotion pattern is used to more accurately understand the user's preferences.

[0524] Next, the server trains a generative AI model based on emotional patterns. This model learns the user's individual preferences and optimizes the process of finding information that matches the user's desired conditions based on feedback derived from the user's emotional state.

[0525] Based on the training results of the optimized model, the server creates a list of recommendations. This list includes information that matches the user's lifestyle, preferences, and emotions, taking into account the user's sentiment data obtained by the sentiment engine. These recommendations are provided to the user through their device, and the user can view detailed information.

[0526] Furthermore, based on user feedback, the server can continuously improve its sentiment engine and AI model to enhance the accuracy of recommendations in the future. For example, if sentiment data reveals that a user tends to prefer a particular type of information, that type of information will be prioritized for their access.

[0527] As a concrete example, one could use text such as, "Based on recent behavioral data, please generate a list of information that is suitable for the user's preferences," as an input prompt to the generative AI model, based on the user's preferences. This prompt would enable the provision of information that reflects the user's emotional state.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] The server collects user behavior data from the user's device. Specific inputs include search keywords entered by the user on the platform, clicked information, page viewing time, and access date and time. This data is transmitted from the device to the server via communication and associated with a user ID based on cookies and session information. The output is user-specific behavior data.

[0531] Step 2:

[0532] The emotion engine on the server analyzes collected behavioral data to identify the user's emotional patterns. This process involves inputting data such as click speed, page dwell time, and search frequency. By processing this data using these metrics and inferring whether the user is excited or dissatisfied, the emotion pattern is obtained as output.

[0533] Step 3:

[0534] The server trains a generative AI model based on emotional patterns and behavioral data. The emotional patterns and behavioral data obtained in the previous step are used as input. This allows the model to learn individual user preferences and generate an optimized algorithm. The output is an optimized model that receives feedback based on the user's emotional state and efficiently selects information that meets the given conditions.

[0535] Step 4:

[0536] The server generates a list of recommendations using the results of an optimized generative AI model. The trained model and user sentiment data are considered as input to this process. This selects information that matches the user's lifestyle, preferences, and emotions, and the recommendation list is sent to the device as output.

[0537] Step 5:

[0538] Users provide feedback on the recommended list. Feedback is entered from the device and sent to the server. The server receives this information and uses it to improve the emotion engine and AI model. The output is an improved model based on the feedback, resulting in better recommendation accuracy for future uses.

[0539] (Application Example 2)

[0540] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0541] Traditional real estate recommendation systems have struggled to accurately grasp user preferences, particularly in their inability to provide optimal property recommendations that take into account the emotions and interests users experience when they actually visit properties. Therefore, there is a need to effectively utilize emotional data from users visiting showrooms and model rooms to provide optimal property information in real time.

[0542] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0543] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, means for recommending user-suitable properties from physical facility information based on the learned preferences, means for obtaining user feedback and updating the learning results, and means for analyzing the user's facial expressions and behavior using a visual information acquisition device and presenting emotion-based information in augmented reality. This makes it possible to immediately utilize emotional data from when the user actually visits a property and present the most appropriate property information in real time.

[0544] "User information" is a general term for information that indicates user behavior and preferences, and mainly includes search keywords, click history, and browsing time.

[0545] "Preferences" are indicators that show a user's tastes, interests, and concerns, and serve as basic data for identifying what kinds of properties and information users find appealing.

[0546] "Physical facility information" refers to all data related to a real estate property, including specific information such as geographical conditions, facilities, and floor plan.

[0547] A "visual information acquisition device" is a device that monitors a user's facial expressions and actions in real time and converts them into digital data; cameras and other photographic equipment fall into this category.

[0548] Augmented reality is a technology that overlays digital information onto the real world, providing users with real-time visual data.

[0549] "Emotion-based information" refers to data generated based on the emotional state analyzed from the user's facial expressions and behavior, and it influences the information suggested.

[0550] This system is designed to provide property recommendations that take into account the user's emotions, such as those used in real estate showrooms. The server, terminal, and user exchange data with each other to process information in real time.

[0551] The server first collects user information. This information includes the user's time spent at the real estate showroom and their level of attention to specific areas. This data is acquired through a visual information acquisition device and analyzed in real time based on the user's facial expressions and behavior.

[0552] The emotion engine analyzes the user's emotions from the acquired visual information. It evaluates facial expressions and dwell time to determine if the user is interested in a particular property or location. Based on this analysis, the server learns the user's preferences more accurately.

[0553] Based on the learning results, the generative AI model selects the most suitable physical facility information for the user and presents that information to the user using augmented reality technology. The presented information allows the user to view property details in real time and visually experience the specific appeal of the facility.

[0554] Furthermore, user feedback is collected through the device. This feedback is sent to the server and used to adjust the parameters of the AI ​​model and emotion engine, thereby improving the accuracy of future suggestions.

[0555] As a concrete example, if a user wearing smart glasses in a showroom shows interest in a kitchen, the server will immediately display detailed information about that kitchen and similar properties on the glasses using augmented reality. An example of a prompt message might be, "You've been in this room for a while and are smiling. To highlight the features of this room, please display detailed information, including related properties, using AR." Through this system, users can have a more fulfilling real estate viewing experience.

[0556] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0557] Step 1:

[0558] The server collects user information at real estate showrooms through a visual information acquisition device. Camera sensors capture users' facial expressions and movements in real time and transmit this data to the processing platform. The visual data, which is the input, consists of user facial expressions and movement information, and this is sent to the server. The output is analyzable user data.

[0559] Step 2:

[0560] The server uses an emotion engine to analyze the user's emotions from the acquired visual information. It evaluates the user's interest and emotional state using indicators such as changes in facial expressions and time spent on the screen (indicated in parentheses). The input is the collected raw visual data, and the output is data points representing the user's emotional state.

[0561] Step 3:

[0562] The server uses a generative AI model based on the acquired sentiment data to learn user preferences. Here, historical data and real-time sentiment analysis results are combined to calculate the optimal physical facility information for each individual user. Based on the sentiment data and past preference history as input, the most suitable property recommendations are generated.

[0563] Step 4:

[0564] The AI-generated model recommends facility information, which is then presented to the user via a terminal. The terminal uses augmented reality technology to display property details and related information within the user's field of view. The input is the generated property information, and the output is a visualized information presentation.

[0565] Step 5:

[0566] The user sends feedback on the presented information to the server via their device. This feedback is recorded as data representing the user's experience and satisfaction. The input is information about the user's reactions and preferences, while the output is data that helps to adjust the parameters of the improved recommendation algorithm.

[0567] Step 6:

[0568] The server analyzes the collected feedback and updates the AI ​​model and the emotion engine's learning algorithms. It then uses the feedback data to further improve the accuracy of future recommendations. The input is user feedback data, and the output is an optimized recommendation system.

[0569] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0570] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0571] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0572] [Fourth Embodiment]

[0573] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0574] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0575] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0576] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0577] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0578] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0579] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0580] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0581] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0582] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0583] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0584] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0585] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0586] This invention is a system that proposes the most suitable real estate property to a user, and its embodiments are described below. The purpose of this system is to recommend a real estate property that suits the user by collecting user information and learning the user's preferences using a generated AI based on that information.

[0587] The server first collects user behavior data when they use the real estate search platform. This includes keywords searched, properties clicked, and viewing time. The server also retrieves real estate information from external property databases and related APIs and updates the system's database. This makes it possible to provide users with the latest market information while maintaining the accuracy of property information.

[0588] Next, the server trains a generative AI model based on the collected data. This process analyzes the user's past preference patterns and behavioral history to predict what types of properties they might be interested in. The AI ​​model learns from this information and forms the basis for future recommendations.

[0589] Based on the learning results, the server generates a customized list of real estate properties for each user. This list is selected based on the user's lifestyle and preferences and is then presented to the user via their device. For example, users who prefer urban living will be given priority recommendations for properties in convenient areas.

[0590] Users view the properties presented through their devices and provide feedback such as "I like it" or "I want to know more details." This feedback information is then collected by the server and used in the next learning process.

[0591] In this way, the AI ​​model can be continuously improved based on user feedback, leading to more accurate recommendations and increased user satisfaction. For example, if a user is identified as having recently searched for many pet-friendly properties, the system will adjust its recommendations to display more pet-friendly properties in the future. As a "form for carrying out the invention," this system is structured to target a segment of the market and effectively generate profits.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] The server collects user behavior data when users use the real estate search platform. This collected data includes searched keywords, clicked property IDs, viewing time, and access date and time. In addition, the device sends unique user ID information to the server to track user behavior individually.

[0595] Step 2:

[0596] The server periodically retrieves the latest real estate information through real estate databases and external APIs, updating the system's database. This data includes information on property location, price, floor plan, age, and changes in market trends.

[0597] Step 3:

[0598] The server preprocesses the collected user behavior data and uses it as training data for the AI ​​model. It performs data cleansing and feature engineering to convert the data into a format that is easy for machine learning algorithms to learn from.

[0599] Step 4:

[0600] The server uses a machine learning model to analyze user preferences and behavioral patterns. This model considers the user's past choices and interests to predict what should be suggested next. As new feedback is incorporated into the model, the accuracy of recommendations continuously improves.

[0601] Step 5:

[0602] Based on the analysis results, the server selects the most suitable real estate properties for the user's profile. It then generates a personalized recommendation list for the user, which is sent to the terminal.

[0603] Step 6:

[0604] The device displays a list of recommended real estate properties to the user. The property list includes photos, property details, price information, and location. The user can browse the list and click on properties of interest to view more details.

[0605] Step 7:

[0606] Users provide feedback on properties they are interested in. This feedback is entered via their device in specific forms, such as "add to favorites" or "not interested."

[0607] Step 8:

[0608] The server collects user feedback and uses it to retrain the AI ​​model. This feedback data provides information that will be useful for future recommendations and will further improve the accuracy of the system's recommendations.

[0609] (Example 1)

[0610] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0611] Traditional real estate recommendation systems had the problem of not being able to adequately reflect the individual preferences of users when recommending properties. Furthermore, the low accuracy of recommendations could lead to low user satisfaction. In addition, it was difficult to reflect the latest market information in real time, making it challenging to provide users with up-to-date and accurate information.

[0612] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0613] In this invention, the server includes information processing means for collecting user information, means for using a generative artificial intelligence model that learns user preferences based on the collected user information, and information processing means for acquiring and updating real estate information from an external database. This makes it possible to recommend properties that reflect the individual preferences of the user, and further enhances user satisfaction by providing the latest market information in real time.

[0614] "Information processing means" refers to the means of collecting data from users and appropriately analyzing and managing it within the system.

[0615] A "generative artificial intelligence model" is a model that has algorithms and programs designed to learn user preferences and predict future actions and choices.

[0616] "Information presentation means" refers to the means by which a system presents information adapted to the user in a visual or other way.

[0617] "Information improvement methods" are means of improving the performance and accuracy of a system based on user feedback and other evaluations.

[0618] "Information analysis tools" are means of analyzing input data and feedback in detail to extract new insights and areas for improvement.

[0619] "Information selection methods" refer to the means of selecting the most suitable real estate information based on the user's lifestyle and past behavioral history.

[0620] In order to implement the system according to the present invention, it is necessary for the server, terminal, and user to exchange data with each other. The details are described below.

[0621] The server is responsible for collecting user behavior data for the real estate search platform. This behavior data includes keywords searched by users, properties accessed, and the time spent viewing each property. This data is managed and analyzed within the server using information processing tools. The server also obtains the latest property information via external real estate databases and related APIs, and updates its internal database. This update process ensures that users are always provided with the most up-to-date market information.

[0622] Furthermore, the server uses a generative artificial intelligence model to learn user preferences based on the collected user data. This allows it to predict individual interests based on the user's past behavior history and find real estate properties that match those interests. For example, if a user has a history of searching for "pet-friendly properties," the AI ​​model will take that preference into account and recommend pet-friendly properties.

[0623] The terminal serves to present users with individually customized property lists sent from the server. Users can view property details through the terminal and provide feedback on properties of interest. This feedback is sent to the server and analyzed by information improvement tools, further enhancing the accuracy of the AI ​​model.

[0624] As a concrete example, suppose a user enters the following prompt into the terminal: "I'm currently looking for an apartment where I can live with my pet. Do you have any recommendations?" Based on this prompt, the server prioritizes extracting information on pet-friendly apartments and presents it to the user.

[0625] Thus, the present invention realizes a system that efficiently provides users with optimal real estate information and improves the user experience.

[0626] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0627] Step 1:

[0628] The server collects user behavior data from real estate search platforms. Inputs include user search keywords, clicked properties, and viewing time for each property. The server organizes and stores this data within the system using information processing tools. The output is a dataset of user behavior. Specifically, this includes actions such as recording the time a user spends searching for "newly built condominiums" and viewing specific properties.

[0629] Step 2:

[0630] The server retrieves and updates real estate information from external databases and APIs. Input is detailed property information, including location, price, area, and amenities. The retrieved information is compared with existing data, and any changes are saved to the system's database. The output is the latest real estate database. Specific operations include adding newly listed properties and reflecting changes in sales status.

[0631] Step 3:

[0632] The server trains a generative AI model based on collected user information. The input consists of user behavior data and the latest real estate data. The server analyzes this information to extract user preferences and update the AI ​​model. The output is an AI model that reflects the user's preferences. Specifically, it performs a process to infer the user's preferences based on the characteristics of properties they have previously viewed (e.g., location and price range).

[0633] Step 4:

[0634] The server generates a personalized property list for each user using a newly trained AI model. The input consists of the updated AI model and the latest real estate data. The server combines this data to select the property best suited to the user's preferences. The output is a customized property list. Specifically, filtering is performed based on user preferences such as pet-friendly properties and proximity to train stations.

[0635] Step 5:

[0636] The terminal displays a list of properties sent from the server to the user. The input is a customized property list generated by the server. The user reviews the suggested properties through the terminal and clicks on properties of interest to obtain detailed information. The output is a display of property details. Specifically, the property's location, price, floor plan, etc., are displayed on the screen.

[0637] Step 6:

[0638] Users provide feedback on properties through their devices. Input consists of ratings and comments made by the user regarding the presented properties. Users enter feedback such as "I like this property" or "I want more information," and the device sends it to the server. Output is the state in which the feedback has been sent to the server. Specific operations include a function to hide properties that the user "doesn't like" from the list.

[0639] Step 7:

[0640] The server further improves the AI ​​model based on user feedback. The input consists of user feedback and the existing AI model. The server analyzes the feedback information and adjusts the AI ​​model's parameters to improve the accuracy of recommendations. The output is the improved AI model. Specifically, after a sufficient amount of feedback from a large number of users has been accumulated, the model is retrained and the improvements are reflected in the next recommendation.

[0641] (Application Example 1)

[0642] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] In food delivery services, it is crucial to suggest optimal menus and facilities based on users' diverse preferences and behavioral history. However, existing systems fail to provide appropriate recommendations to individual users, making it difficult to improve user satisfaction. To solve this problem, it is necessary to learn user preferences using past behavioral data and provide more personalized recommendations.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0645] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, and means for recommending user-suitable menus or facilities from food delivery information based on the learned preferences. This makes it possible to recommend menus and facilities that are tailored to the individual preferences of each user.

[0646] "User information" refers to personal information and behavioral data of users related to the food delivery service, including order history, search history, and feedback.

[0647] "Preferences" refer to the inferred preference for a particular menu item or facility based on the user's past tastes and behavioral patterns.

[0648] "Food delivery information" refers to information about menus, facilities, and delivery conditions available to users, and includes information such as the type of food, price, and location of the facilities providing the service.

[0649] "Feedback" refers to the evaluations and opinions that users provide about the menus and facilities presented, and this feedback is used for future recommendations.

[0650] A "generative AI model" refers to an artificial intelligence algorithm that learns user preferences based on past behavioral data and recommends appropriate menus and facilities.

[0651] "Recommendation" refers to the act of presenting menus and facilities that match the user's preferences based on the results of analysis by a generative AI model.

[0652] "Dynamic presentation" refers to a method of displaying appropriate menus and facility information in real time, based on the user's preferences and behavioral history.

[0653] The system that realizes this invention is configured as follows: First, a server collects user information in real time. This information includes the user's order history, search history, and feedback. The information is stored in a database and organized for each user.

[0654] Next, the server uses a generative AI model to learn user preferences based on the collected user information. This process uses machine learning frameworks such as TensorFlow and PyTorch to analyze past behavioral patterns and predict what menus and facilities users will prefer. This allows for the generation of personalized recommendation lists for each user.

[0655] The user's device receives and displays a list of recommendations sent from the server. This list is dynamically updated, suggesting the most suitable menus and establishments based on the user's past search history and preferences when they choose a restaurant.

[0656] Furthermore, user feedback is sent back to the server and used to update the learning model. This allows for continuous improvement of recommendation accuracy and increased user satisfaction.

[0657] For example, if a user has recently ordered a lot of Italian food, the next time they log in, they will be recommended new menu items from Italian restaurants. In this way, recommendations can be tailored to the individual user's preferences.

[0658] An example of a prompt message would be: "Based on past history, suggest the most suitable food delivery menu for this user."

[0659] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0660] Step 1:

[0661] The server collects user information. This input includes the user's order history, search history, and feedback. The server collects this information and stores it in a database. During this process, the information is organized by user and assigned to each user.

[0662] Step 2:

[0663] The server learns user preferences based on user information collected using a generative AI model. The input is the user information organized in step 1, and the output is a model of user preferences. The server utilizes TensorFlow and PyTorch to analyze past behavioral patterns and build a predictive model.

[0664] Step 3:

[0665] The server generates user-specific menu and facility recommendation lists based on the learned model. The input is the preference model generated in step 2, and the output is a recommendation list for each user. The server performs real-time data processing and dynamically creates the recommendation lists.

[0666] Step 4:

[0667] The terminal presents the user with a list of recommendations received from the server. The input is the list of recommendations generated in step 3, and the output is the display on the screen. The terminal displays the recommendations appropriately according to the user's current session.

[0668] Step 5:

[0669] Users provide feedback on the presented recommendation list. The input is the display of the recommendation list on the device, and the output is the user's feedback information. Through feedback, users can specifically express their opinions and evaluations.

[0670] Step 6:

[0671] The server collects user feedback again and uses it to update the AI ​​model. The input is the feedback information obtained in step 5, and the output is the updated preference model. The server analyzes the feedback and adjusts the model to improve recommendation accuracy.

[0672] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0673] This invention is a technology that combines an emotion engine that recognizes user emotions with a real estate property suggestion system. An embodiment thereof is described below.

[0674] The server first collects behavioral data from users when they use the real estate search platform. This collected data includes search keywords, clicked property listings, viewing time, and access date and time. This information is associated with a user ID based on cookies and session information transmitted via the device.

[0675] The server incorporates an emotion engine that analyzes emotional patterns from user search behavior and feedback information. For example, it uses metrics such as user click speed, page dwell time, and search frequency to infer whether a user is excited or dissatisfied. This information is a crucial element for understanding user preferences with greater accuracy.

[0676] The server uses the above data to train a generative AI model and learn the user's individual preferences. This model optimizes the process of finding real estate properties that match the user's desired conditions based on feedback derived from the user's emotional state.

[0677] Based on the learning results, the server generates a list of recommended properties. Considering the user's emotional data obtained by the emotion engine, the list includes properties that match the user's lifestyle, preferences, and emotions. The list is presented to the user via their device, displaying detailed information.

[0678] Based on user feedback, the server continuously improves its emotion engine and AI models to further enhance personalized recommendations. For example, if emotion data reveals that a user consistently rates high-rise properties highly, the server will proactively present high-rise properties to that user in future recommendations.

[0679] In this way, the present invention can recommend real estate properties desired by users with higher accuracy than conventional systems, improving the user experience while enhancing the system's competitiveness.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The server collects real-time behavioral data as users use the real estate search platform. This includes keywords searched, properties viewed, time spent on pages, access date and time, and links clicked. The device sends this data, along with the user ID, to the server, which then stores the history of each individual user.

[0683] Step 2:

[0684] The device optionally sends the user's facial expressions and voice data to the emotion engine. The emotion engine analyzes this data and generates emotion patterns to determine whether the user is interested or dissatisfied. The server also estimates the user's emotional state based on dynamic behavioral data (e.g., quickly navigating between multiple pages).

[0685] Step 3:

[0686] The server uses collected behavioral data and analysis results from the emotion engine to train a generative AI model. The AI ​​model learns to reflect the user's preferences and emotional state, optimizing the next property recommendations. Feedback data based on past search history and trends is also taken into consideration.

[0687] Step 4:

[0688] The server selects suitable properties from the real estate database that match the user's lifestyle and past preferences, based on the predictions of a trained AI model. Depending on the user's current emotional state detected by the emotion engine, specific properties are highlighted or filtered.

[0689] Step 5:

[0690] The device displays a list of recommended properties to the user. Each property on the list includes a detailed description, images, price information, and a sentiment score indicating the user's level of interest. The user can browse the list, select properties that interest them, and view more detailed information.

[0691] Step 6:

[0692] Users provide feedback on recommended properties. This feedback includes emotional responses and specific evaluations. The device aggregates this feedback and sends it to a server for further refinement and learning.

[0693] Step 7:

[0694] The server retrains the AI ​​model based on user feedback and newly acquired sentiment data to improve the accuracy of future recommendations. Model updates that consider both sentiment and preferences continuously improve the individual user experience.

[0695] (Example 2)

[0696] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] This addresses the challenge of providing highly accurate information that takes into account users' emotions and individual preferences.

[0698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0699] In this invention, the server includes means for collecting user behavior data, means for analyzing emotional patterns and recognizing the user's emotions, and means for learning the user's preferences based on the collected data and emotion recognition. This makes it possible to provide optimized information while taking into account the user's emotional state.

[0700] "User behavior data" refers to information that shows the specific actions a user has taken on the platform, and includes data such as search keywords, clicked information, browsing time, and access date and time.

[0701] "Emotional patterns" are data that represents tendencies in emotions such as excitement and dissatisfaction, inferred by analyzing user behavior data.

[0702] "User preferences" refer to information that indicates what conditions and characteristics users prefer in information, and are orientations identified based on past behavior and feedback.

[0703] "Recommended methods" refer to the processes and methods for presenting users with information and options that are appropriate to them, based on the collected data and learning results.

[0704] "Feedback" refers to evaluations and opinions that users provide to the system, and this data is used to improve the accuracy of recommendations in the future.

[0705] "Emotional state" refers to information that indicates the user's current emotional state, obtained through the analysis of emotional patterns.

[0706] This invention is a real estate proposal technology that provides information while taking user emotions into consideration, and includes an emotion engine that collects user behavior data and analyzes emotional patterns. Specific embodiments thereof are described below.

[0707] The server collects user behavior data via communication from the user's device. This behavior data includes search keywords, information viewed, information clicked, time spent on the site, and access date and time. This information is organized based on the user ID associated with cookies and session information collected through the device.

[0708] The server has an emotion engine built in. This engine analyzes user behavior data and uses metrics such as click speed, page dwell time, and search frequency to infer whether the user is excited or dissatisfied. This inferred emotion pattern is used to more accurately understand the user's preferences.

[0709] Next, the server trains a generative AI model based on emotional patterns. This model learns the user's individual preferences and optimizes the process of finding information that matches the user's desired conditions based on feedback derived from the user's emotional state.

[0710] Based on the training results of the optimized model, the server creates a list of recommendations. This list includes information that matches the user's lifestyle, preferences, and emotions, taking into account the user's sentiment data obtained by the sentiment engine. These recommendations are provided to the user through their device, and the user can view detailed information.

[0711] Furthermore, based on user feedback, the server can continuously improve its sentiment engine and AI model to enhance the accuracy of recommendations in the future. For example, if sentiment data reveals that a user tends to prefer a particular type of information, that type of information will be prioritized for their access.

[0712] As a concrete example, one could use text such as, "Based on recent behavioral data, please generate a list of information that is suitable for the user's preferences," as an input prompt to the generative AI model, based on the user's preferences. This prompt would enable the provision of information that reflects the user's emotional state.

[0713] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0714] Step 1:

[0715] The server collects user behavior data from the user's device. Specific inputs include search keywords entered by the user on the platform, clicked information, page viewing time, and access date and time. This data is transmitted from the device to the server via communication and associated with a user ID based on cookies and session information. The output is user-specific behavior data.

[0716] Step 2:

[0717] The emotion engine on the server analyzes collected behavioral data to identify the user's emotional patterns. This process involves inputting data such as click speed, page dwell time, and search frequency. By processing this data using these metrics and inferring whether the user is excited or dissatisfied, the emotion pattern is obtained as output.

[0718] Step 3:

[0719] The server trains a generative AI model based on emotional patterns and behavioral data. The emotional patterns and behavioral data obtained in the previous step are used as input. This allows the model to learn individual user preferences and generate an optimized algorithm. The output is an optimized model that receives feedback based on the user's emotional state and efficiently selects information that meets the given conditions.

[0720] Step 4:

[0721] The server generates a list of recommendations using the results of an optimized generative AI model. The trained model and user sentiment data are considered as input to this process. This selects information that matches the user's lifestyle, preferences, and emotions, and the recommendation list is sent to the device as output.

[0722] Step 5:

[0723] Users provide feedback on the recommended list. Feedback is entered from the device and sent to the server. The server receives this information and uses it to improve the emotion engine and AI model. The output is an improved model based on the feedback, resulting in better recommendation accuracy for future uses.

[0724] (Application Example 2)

[0725] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0726] Traditional real estate recommendation systems have struggled to accurately grasp user preferences, particularly in their inability to provide optimal property recommendations that take into account the emotions and interests users experience when they actually visit properties. Therefore, there is a need to effectively utilize emotional data from users visiting showrooms and model rooms to provide optimal property information in real time.

[0727] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0728] In this invention, the server includes means for collecting user information, means for learning user preferences based on the collected user information, means for recommending user-suitable properties from physical facility information based on the learned preferences, means for obtaining user feedback and updating the learning results, and means for analyzing the user's facial expressions and behavior using a visual information acquisition device and presenting emotion-based information in augmented reality. This makes it possible to immediately utilize emotional data from when the user actually visits a property and present the most appropriate property information in real time.

[0729] "User information" is a general term for information that indicates user behavior and preferences, and mainly includes search keywords, click history, and browsing time.

[0730] "Preferences" are indicators that show a user's tastes, interests, and concerns, and serve as basic data for identifying what kinds of properties and information users find appealing.

[0731] "Physical facility information" refers to all data related to a real estate property, including specific information such as geographical conditions, facilities, and floor plan.

[0732] A "visual information acquisition device" is a device that monitors a user's facial expressions and actions in real time and converts them into digital data; cameras and other photographic equipment fall into this category.

[0733] Augmented reality is a technology that overlays digital information onto the real world, providing users with real-time visual data.

[0734] "Emotion-based information" refers to data generated based on the emotional state analyzed from the user's facial expressions and behavior, and it influences the information suggested.

[0735] This system is designed to provide property recommendations that take into account the user's emotions, such as those used in real estate showrooms. The server, terminal, and user exchange data with each other to process information in real time.

[0736] The server first collects user information. This information includes the user's time spent at the real estate showroom and their level of attention to specific areas. This data is acquired through a visual information acquisition device and analyzed in real time based on the user's facial expressions and behavior.

[0737] The emotion engine analyzes the user's emotions from the acquired visual information. It evaluates facial expressions and dwell time to determine if the user is interested in a particular property or location. Based on this analysis, the server learns the user's preferences more accurately.

[0738] Based on the learning results, the generative AI model selects the most suitable physical facility information for the user and presents that information to the user using augmented reality technology. The presented information allows the user to view property details in real time and visually experience the specific appeal of the facility.

[0739] Furthermore, user feedback is collected through the device. This feedback is sent to the server and used to adjust the parameters of the AI ​​model and emotion engine, thereby improving the accuracy of future suggestions.

[0740] As a concrete example, if a user wearing smart glasses in a showroom shows interest in a kitchen, the server will immediately display detailed information about that kitchen and similar properties on the glasses using augmented reality. An example of a prompt message might be, "You've been in this room for a while and are smiling. To highlight the features of this room, please display detailed information, including related properties, using AR." Through this system, users can have a more fulfilling real estate viewing experience.

[0741] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0742] Step 1:

[0743] The server collects user information at real estate showrooms through a visual information acquisition device. Camera sensors capture users' facial expressions and movements in real time and transmit this data to the processing platform. The visual data, which is the input, consists of user facial expressions and movement information, and this is sent to the server. The output is analyzable user data.

[0744] Step 2:

[0745] The server uses an emotion engine to analyze the user's emotions from the acquired visual information. It evaluates the user's interest and emotional state using indicators such as changes in facial expressions and time spent on the screen (indicated in parentheses). The input is the collected raw visual data, and the output is data points representing the user's emotional state.

[0746] Step 3:

[0747] The server uses a generative AI model based on the acquired sentiment data to learn user preferences. Here, historical data and real-time sentiment analysis results are combined to calculate the optimal physical facility information for each individual user. Based on the sentiment data and past preference history as input, the most suitable property recommendations are generated.

[0748] Step 4:

[0749] The AI-generated model recommends facility information, which is then presented to the user via a terminal. The terminal uses augmented reality technology to display property details and related information within the user's field of view. The input is the generated property information, and the output is a visualized information presentation.

[0750] Step 5:

[0751] The user sends feedback on the presented information to the server via their device. This feedback is recorded as data representing the user's experience and satisfaction. The input is information about the user's reactions and preferences, while the output is data that helps to adjust the parameters of the improved recommendation algorithm.

[0752] Step 6:

[0753] The server analyzes the collected feedback and updates the AI ​​model and the emotion engine's learning algorithms. It then uses the feedback data to further improve the accuracy of future recommendations. The input is user feedback data, and the output is an optimized recommendation system.

[0754] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0755] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0756] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0757] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0758] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0759] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0760] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0761] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0762] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0763] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0764] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0765] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0766] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0767] 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.

[0768] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0769] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0770] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0771] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0772] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0773] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0774] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0775] The following is further disclosed regarding the embodiments described above.

[0776] (Claim 1)

[0777] Means for collecting user information,

[0778] A means of learning user preferences based on collected user information,

[0779] A means of recommending suitable properties to users from real estate information based on learned preferences,

[0780] A system that includes means for obtaining user feedback and updating learning results.

[0781] (Claim 2)

[0782] The system according to claim 1, comprising means for analyzing user feedback and improving the accuracy of future recommendations.

[0783] (Claim 3)

[0784] The system according to claim 1, comprising means for selecting recommended real estate information based on the user's lifestyle and past behavioral history.

[0785] "Example 1"

[0786] (Claim 1)

[0787] Information processing means for collecting user information,

[0788] A method using a generative artificial intelligence model that learns user preferences based on collected user information,

[0789] An information processing means for acquiring and updating real estate information from an external database,

[0790] An information presentation method that recommends user-suitable properties from a database based on learned preferences,

[0791] A means of improving information by obtaining user feedback, analyzing that feedback, and updating the learning results,

[0792] A system including information processing means to improve recommendation accuracy based on improved learning results.

[0793] (Claim 2)

[0794] The system according to claim 1, comprising information analysis means for analyzing feedback obtained from users and improving the accuracy of the generated artificial intelligence model.

[0795] (Claim 3)

[0796] The system according to claim 1, comprising an information selection means for selecting recommended real estate information based on the user's lifestyle and past behavioral history.

[0797] "Application Example 1"

[0798] (Claim 1)

[0799] Means of collecting user information,

[0800] A means of learning user preferences based on collected user information,

[0801] A means of recommending user-suitable menus or facilities from food delivery information based on learned preferences,

[0802] A means of obtaining feedback from users and updating learning results,

[0803] Recommended food delivery information is selected based on the user's preferences and past usage history.

[0804] A system that includes means for dynamically presenting food delivery information based on user preferences.

[0805] (Claim 2)

[0806] The system according to claim 1, comprising means for analyzing feedback obtained from users and improving the accuracy of future recommendations.

[0807] (Claim 3)

[0808] The system according to claim 1, wherein the recommended food delivery information includes means of analyzing the user's past behavioral patterns using a generating AI model and suggesting the optimal menu or facility.

[0809] "Example 2 of combining an emotion engine"

[0810] (Claim 1)

[0811] Means of collecting user behavior data,

[0812] A means of analyzing emotional patterns and recognizing the user's emotions,

[0813] A means of learning user preferences based on collected data and emotion recognition,

[0814] A means of recommending user-suitable information from information provision based on learned preferences,

[0815] A means of obtaining user feedback and updating learning results,

[0816] A system that includes means for optimizing recommendation information by taking into account the user's emotional state.

[0817] (Claim 2)

[0818] The system according to claim 1, comprising means for analyzing user feedback and improving the accuracy of future recommendations.

[0819] (Claim 3)

[0820] The system according to claim 1, comprising means for selecting recommended information based on the user's lifestyle, past behavioral history, and emotional data.

[0821] "Application example 2 when combining with an emotional engine"

[0822] (Claim 1)

[0823] Means for collecting user information,

[0824] A means of learning user preferences based on collected user information,

[0825] A means of recommending user-suitable properties based on learned preferences and physical facility information,

[0826] A means of obtaining user feedback and updating learning results,

[0827] A means of analyzing a user's facial expressions and behavior using a visual information acquisition device and presenting emotion-based information in augmented reality,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, comprising means for analyzing user feedback and improving the accuracy of future recommendations.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for selecting recommended physical facility information based on the user's lifestyle and past behavioral history. [Explanation of symbols]

[0833] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting user information, A means of learning user preferences based on collected user information, A means of recommending suitable properties to users from real estate information based on learned preferences, A system that includes means for obtaining user feedback and updating learning results.

2. The system according to claim 1, comprising means for analyzing feedback obtained from users and improving the accuracy of future recommendations.

3. The system according to claim 1, comprising means for selecting recommended real estate information based on the user's lifestyle and past behavioral history.

Images