system

Abstract

Provide a system. 【Solution means】 Means for automatically collecting information related to the environment from an information source, Means for integrating the collected environmental information and storing it in a data storage device, Means for obtaining desired conditions from a user, Means for selecting the environmental information stored based on the desired conditions, Means for analyzing the selected information and calculating an evaluation score, Means for analyzing requirements and evaluating risks, Means for presenting the evaluated score to the user, A system including the above.

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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern real estate market, when looking for a rental property, multiple complex factors are intertwined, such as the reasonableness of rent and initial costs, the location and grade of the property, and the understanding of the contract terms. Therefore, it is difficult for users to make reasonable and accurate judgments, and as a result, inappropriate contracts and unexpected troubles may occur. In particular, since information is dispersed on the Internet and it takes time and effort to manually aggregate and judge it, obtaining reliable real estate information efficiently is a major issue.

Means for Solving the Problems

[0005] To address this challenge, we provide a system that automatically collects real estate information from various sources, integrates it into a database, and stores it. This system automatically filters property information based on the user's desired conditions and analyzes the reasonableness of rent and the risks of contract terms. The analysis results are displayed to the user in a scored format, allowing them to easily make rational decisions. Furthermore, by collecting feedback after property selection and using it as training data for the system, its performance can be continuously improved.

[0006] "Information sources" refer to various platforms such as websites and social media that provide real estate information.

[0007] "Real estate information" refers to basic data related to a property, such as rent, location, facilities, and contract terms.

[0008] "Automatically collecting" refers to the process of obtaining information without manual intervention, using crawlers or APIs.

[0009] A "database" refers to a system or platform for organizing and storing collected real estate information.

[0010] A "user" refers to an individual or legal entity that is searching for and selecting a rental property.

[0011] "Desired conditions" refer to specific requirements that users have for rental properties, such as rent, location, and facilities.

[0012] "Filtering" refers to the process of selecting collected real estate information based on the user's desired criteria.

[0013] The "rent appropriateness score" refers to an index that indicates whether the rent of a property is appropriate compared to the market average.

[0014] Evaluating "contractual risks" refers to the process of analyzing the terms of a contract to identify potential disadvantages or problems.

[0015] "Scored form" refers to a state where the analysis results are digitized and presented in a comparable format.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map where multiple emotions are mapped. [Figure 10] It shows an emotion map where multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of a data processing system in Embodiment 2 when a sentiment engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. **Modes for Carrying Out the Invention**

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered 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.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered 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, and the like.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system that automatically collects real estate information and analyzes and selects it based on the user's preferences. This system operates with a server and terminal working in conjunction to provide the user with guidance on choosing rental properties.

[0038] First, the server automatically collects real estate information from source websites and social media. Using crawlers and APIs, this information is retrieved in real time and organized and stored in a database. This database contains a variety of information, including property rent, location, facilities, and contract terms.

[0039] Next, the terminal interacts with the user and provides an interface for collecting the desired property criteria. When the user enters their maximum rent, desired area, and required amenities, these criteria are sent to the server.

[0040] The server filters the property information in the database based on the received request criteria. Using an AI model, it calculates a rent reasonableness score for the filtered results. Furthermore, it analyzes the contract terms and assesses the risks associated with each property.

[0041] The analysis results are presented on the device in a scored format. Users can select from the presented property list and view detailed information. For example, a user looking for a property in Shinjuku Ward with a monthly rent of 100,000 yen or less and free internet access will be presented with the most suitable properties. This display includes a rent appropriateness score and contract risk points for each property.

[0042] Furthermore, after the user selects a property and makes a final decision, a screen for collecting feedback is displayed on the terminal. The server analyzes this feedback and uses it to improve the system. In this way, the system continuously improves its accuracy and supports more reliable property selection.

[0043] By implementing this invention, users will be able to compare a large amount of information in a short time and make rational decisions. This will help prevent inappropriate contracts and unexpected problems.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects property information from multiple websites and social media sources. It uses a crawler to automatically retrieve the latest real estate information and saves it to a database.

[0047] Step 2:

[0048] The terminal displays an interface to the user, prompting them to enter their desired conditions. The user enters their desired rent, location requirements, necessary amenities, etc., and this information is sent directly from the terminal to the server.

[0049] Step 3:

[0050] The server filters the property information in the database based on the user's criteria. This filtering ensures that only properties matching the user's conditions are displayed.

[0051] Step 4:

[0052] The server uses an AI model to calculate a rent justification score for filtered properties. It compares the rent to market trends and evaluates the relative value of each property.

[0053] Step 5:

[0054] The server analyzes the contract terms of the filtered properties and assesses the risks. In particular, it identifies clauses that pose hidden risks within the contract and pinpoints points that users should pay attention to.

[0055] Step 6:

[0056] The server comprehensively evaluates the calculated rent reasonableness score and contract risk, and organizes this into a ranking. The ranking results are sent to the terminal and displayed in a way that the user can visually understand.

[0057] Step 7:

[0058] The user reviews the presented rankings and selects detailed information about properties that interest them. The device then displays more in-depth information in response to that request.

[0059] Step 8:

[0060] After the user completes their property selection, a feedback screen will appear on their device. The user enters feedback based on their experience and sends it from their device to the server.

[0061] Step 9:

[0062] The server analyzes the collected feedback and uses it to improve the AI ​​model and system. The system is then adjusted to provide more accurate information to future users.

[0063] (Example 1)

[0064] 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."

[0065] Data collection, selection, and indicator calculation can be time-consuming and labor-intensive. In particular, providing users with information that meets their specific requirements quickly and accurately is difficult, placing a significant burden on them. Furthermore, there is a lack of support to enable users to effectively utilize the provided information and make optimal choices.

[0066] 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.

[0067] In this invention, the server includes means for automatically collecting data from information sources, means for integrating the collected data and storing it in a storage device, and means for obtaining desired conditions from the user. This reduces the burden on the user and makes it possible to provide the desired information quickly and efficiently.

[0068] "Information source" refers to websites or social networking platforms where content exists for obtaining data.

[0069] "Data" refers to real estate information and related numerical and textual information collected from various sources.

[0070] A "storage device" refers to an internal or external storage system of a computer used to integrate and store collected data.

[0071] "User" refers to an individual or legal entity that operates this system and acquires or selects information.

[0072] "Desired conditions" refer to specific conditions or specifications that users specify for the data, and serve as the basis for data filtering.

[0073] "Selection" refers to the process of extracting and narrowing down only the relevant data from a database based on desired conditions.

[0074] An "indicator" is a numerical result evaluated through analysis, and refers to an indicator used to show the validity of data and risk assessment.

[0075] "Contract terms" refers to information that outlines the legal and operational requirements and arrangements related to specific data.

[0076] "Risk" refers to the analysis of potential uncertainties and negative impacts related to the terms and conditions of a contract.

[0077] "Presentation" refers to the process of visually or descriptively displaying the results of selection or analysis to the user.

[0078] This invention describes embodiments for carrying out this invention. The system consists of three main components: data collection, automated data analysis, and interface provision. The server and terminal work together to support users in efficiently accessing data and making decisions.

[0079] The server plays the role of collecting data from websites and social networks on the internet as information sources. Specifically, it uses crawlers and APIs to obtain the necessary information. This allows for real-time aggregation of information. The collected data is integrated and stored in a database on the server. A database management system (DBMS) is used to organize and deduplication the data.

[0080] The terminal provides an interface with the user and has a means of inputting desired conditions. The terminal works by allowing the user to input conditions into fields, thereby giving instructions to the system. The user interface is intuitive and easy to operate, supporting efficient user input.

[0081] When a user enters conditions into their device, that information is sent to the server. The server searches and filters the information in the database based on these conditions. SQL queries are used to quickly extract data that matches the conditions. Then, a generative AI model is used to perform more detailed analysis on the extracted data. Specifically, this includes calculating a score to evaluate the reasonableness of the rent and conducting a risk assessment based on the contract terms.

[0082] These analysis results are presented to the user via the terminal. For example, a user looking for a rental property in Shinjuku Ward with a monthly fee of 100,000 yen or less and free internet access can be presented with suitable candidates along with a validity score and risk assessment score.

[0083] An example of a prompt message is: "I'm looking for a rental property in Shinjuku Ward with a monthly rent of 100,000 yen or less, free internet, and at least two rooms (2DK). Please recommend properties with low risk in the contract terms and a high rent reasonableness score." By using this prompt message, the system is able to provide the user with the most suitable property.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server automatically collects data from source websites and social networks. A crawler periodically visits web pages and parses HTML data. Reliable information can also be obtained through APIs. Input is the URL of the source or API key, and output is the parsed raw data.

[0087] Step 2:

[0088] The server organizes and stores the collected raw data in a database. A database management system is used to store the data, and cleanup is performed to check for duplicates and missing data. The input is raw data, and the output is organized database entries.

[0089] Step 3:

[0090] The terminal provides the user with an interface to input their desired property criteria. The input form includes fields for rent limit, desired area, and required amenities. Information is collected as the user enters these criteria. The input consists of user-specified conditions, and the output is a search request incorporating those conditions.

[0091] Step 4:

[0092] The server filters candidate data from the database based on the user's specified criteria. It uses SQL queries to extract data that matches the criteria. The input is the user's search request, and the output is the filtered property information.

[0093] Step 5:

[0094] The server uses a generative AI model to perform analysis based on filtered property information. It evaluates rent reasonableness scores and risks derived from contract terms. The input is filtered property information, and the output is analysis scores and risk assessments.

[0095] Step 6:

[0096] The terminal presents the analysis results to the user. It visually displays a scored property list, indicating the priority and details of the information. The input is the analysis score and risk assessment, and the output is a user-friendly results display.

[0097] Step 7:

[0098] Users select from the presented properties and make a final choice. The user's selection is input to the system as feedback. The input is the user's selection result, and the output is data for continuous system improvement.

[0099] Step 8:

[0100] The server collects user feedback and analyzes it to help improve the system. This enables further system improvements tailored to user needs. The input is feedback data, and the output is the improved system functionality.

[0101] (Application Example 1)

[0102] 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."

[0103] For autonomous vehicles, efficiently finding the optimal parking space near the destination is a crucial challenge in minimizing wasted time and energy. It is essential to collect the latest parking information from multiple sources and quickly analyze and evaluate it according to the user's preferences to support the selection of the best parking spot.

[0104] 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.

[0105] In this invention, the server includes means for automatically collecting environment-related information from information sources, means for integrating the collected environment information and storing it in a data storage device, and means for obtaining desired conditions from the user. This enables the user to quickly select the optimal parking space closest to their destination.

[0106] A "source" refers to an external data provider, such as a website or database, that provides data for a specific purpose.

[0107] "Environmental information" refers to various data related to location and conditions, including, for example, the location, fees, and availability of parking lots.

[0108] A "data storage device" is hardware or software used to store and manage data within a computer system.

[0109] A "user" is an individual who operates the system to receive information and services.

[0110] "Desired conditions" refer to the specific conditions or requirements that a user seeks regarding a particular service or information.

[0111] "Selection" is the process of classifying stored information based on specified criteria and selecting the appropriate results.

[0112] "Analysis" is the act of performing evaluations and calculations on data to extract important information and insights.

[0113] An "evaluation score" is the result of an evaluation that quantifies information or conditions based on specific criteria.

[0114] "Requirements" refer to the conditions or standards that information or a service must meet.

[0115] "Risk" refers to the potential for unfavorable consequences or costs associated with a particular action or piece of information.

[0116] "Feedback" refers to information based on opinions and experiences obtained from system users, and is used to improve the system.

[0117] This invention is a system that suggests the optimal parking space around a destination to an autonomous vehicle, and is realized by collecting, storing, and analyzing environmental information.

[0118] The server automatically collects environmental information related to parking lots from multiple sources, integrates it, and stores it in a data storage device. Specifically, it uses an API to retrieve data in real time, creating a dataset that includes parking lot locations, fees, and availability. This dataset is managed in a database on the computer system.

[0119] Users input their desired conditions through the terminal interface. These conditions include parking fees, distance, available hours, and whether or not there is a roof. These conditions are sent to the server, which then filters the stored data. The filtered information is then evaluated using an AI model to calculate a score. This model is implemented using machine learning libraries such as Scikit-learn and TENSORFLOW®.

[0120] The terminal presents the user with the most suitable parking options based on their evaluation score. This allows users to quickly find a parking space that meets their needs upon arriving at their destination.

[0121] As a concrete example, when a user heads to a shopping mall, they can enter conditions such as "close to the entrance, free for under an hour" into a terminal. The server will then select the most suitable parking lot based on those conditions, score it, and present a list.

[0122] Examples of prompts to input into a generative AI model:

[0123] "Design a system that collects real-time parking information around a destination and suggests the best parking option based on the user's preferences. The criteria should include price, distance, and whether or not the parking area is covered."

[0124] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0125] Step 1:

[0126] The server collects environmental information related to parking lots from multiple sources via an API. This input data includes parking lot location, fees, and availability. The server retrieves this data in real time and stores it in a database. The data is formatted and standardized and organized to improve usability.

[0127] Step 2:

[0128] The user enters their desired parking conditions via a terminal. These conditions may include a maximum parking fee, shortest distance, and required parking time. The system supports input via a multi-touch display or voice command interface. The terminal then sends these conditions to the server.

[0129] Step 3:

[0130] The server filters relevant information from the database based on the user's preferences. Based on the entered preferences, parking information that meets the criteria is selected from the stored dataset. This creates a list of parking lots that match the specified conditions.

[0131] Step 4:

[0132] The server uses a generative AI model to calculate an evaluation score for the selected parking lot information. This process uses Scikit-learn and TensorFlow to comprehensively evaluate multiple factors such as parking fees and accessibility, and quantifies the degree of optimality. This evaluation score is output, and the parking lots are sorted in descending order of score.

[0133] Step 5:

[0134] The terminal displays evaluation scores received from the server to the user. The screen shows a list of suggestions, including the location, fee, and scoring result of the parking lot. Based on this information, the user can select the best parking space. This allows for quick finding of suitable parking spaces near the destination.

[0135] 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.

[0136] This invention is a system that incorporates an emotion engine into a conventional rental property search system, recognizing the user's emotions in real time and optimizing the information presented accordingly. The system, through the interaction of the server, terminal, and emotion engine, makes the user's property selection more accurate and user-friendly.

[0137] First, the server automatically collects real estate information from sources and stores it in a database. This process uses crawlers and APIs. The stored data includes basic information such as property rent, location, and amenities. This information is then filtered based on the user's desired criteria.

[0138] Next, the terminal prompts the user to input their desired conditions for a property using an interface. The user's entered preferences are immediately sent to the server, and the filtering process begins.

[0139] The emotion engine is installed in the device and analyzes the user's emotions from their facial expressions and voice. This allows the system to capture the user's emotional state when they are viewing property information. For example, emotions such as indifference, interest, and aversion can be recognized in real time.

[0140] The server presents property information filtered based on the user's preferences, scoring it based on factors such as rent reasonableness and contract risk. It can dynamically adjust the presentation method, incorporating feedback from the emotion engine to prioritize properties the user has shown interest in.

[0141] Through the emotion engine, users can obtain more interesting and relevant property information, facilitating a smoother property selection process. Furthermore, user emotion data is collected on the server and analyzed for use in future visits. This process improves system performance to provide information more optimized for the user.

[0142] As a concrete example, let's say a user is looking for a property in Shinjuku Ward with free internet access and a budget of under 100,000 yen. If the user shows interest when viewing property A, the emotion engine detects this, and the server prioritizes displaying similar properties. In this way, the user can quickly access the property information they are looking for and make a satisfying property choice.

[0143] In this way, this system, which incorporates an emotion engine, can provide more accurate information than before and significantly improve the user experience.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The server automatically collects real estate information from websites and social media sources. It uses a crawler to retrieve the latest property information in real time and saves it to a database.

[0147] Step 2:

[0148] The terminal displays an interface to the user, prompting them to input their desired property criteria. The user enters their desired rent, location, amenities, and other conditions, and the terminal sends this information to the server.

[0149] Step 3:

[0150] The server filters property information in the database based on the user's desired criteria. It generates a list of properties that match the criteria and passes the result to the next process.

[0151] Step 4:

[0152] The emotion engine analyzes the user's facial expressions and voice on the device, obtaining the user's emotional state in real time while they are viewing property information. This information is then sent to the server.

[0153] Step 5:

[0154] The server scores the reasonableness of the rent and the risk of the contract for the filtered properties. These scores are considered in combination with sentiment data from the sentiment engine.

[0155] Step 6:

[0156] The server dynamically adjusts how information is presented based on the user's emotional state. For example, it optimizes the display by prioritizing properties the user has shown interest in, or hiding properties they have not shown interest in.

[0157] Step 7:

[0158] The terminal displays optimized property information from the server to the user. The user selects properties of interest based on the provided information and checks the details.

[0159] Step 8:

[0160] After the user completes their property selection, the device displays a feedback screen. The user enters their thoughts and experiences, and then sends them from the device to the server.

[0161] Step 9:

[0162] The server analyzes the feedback and sentiment data it collects to help improve the system. The system is then adjusted to provide better information in subsequent user sessions.

[0163] (Example 2)

[0164] 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".

[0165] Conventional information retrieval systems have a problem in that they do not present information while considering the user's feelings, making it difficult to provide the most suitable information for the user. In particular, with real estate information, it is difficult to find the right property from a large number of options, and accurately understanding the user's intentions is required.

[0166] 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.

[0167] In this invention, the server includes means for automatically collecting information from information sources, means for integrating the collected information and storing it in a memory unit, and means for analyzing the user's emotions. This enables dynamic information presentation that takes the user's emotions into consideration.

[0168] "Information source" refers to an external data provider service or database used to obtain data or information.

[0169] A "storage unit" refers to a recording device or memory device used to store data or information for long-term or short-term storage.

[0170] "User" refers to a person or system that operates the system to obtain information or input conditions.

[0171] "Conditions" refer to information used to define the user's preferences and constraints.

[0172] "Selection" refers to the process of selecting relevant information and data based on user criteria and indicators.

[0173] A "validity indicator" refers to a numerical value or evaluation score that assesses the appropriateness of information against specific conditions or criteria.

[0174] "Emotions" refer to the mental or sensory states expressed by users while using the system.

[0175] "Dynamic information presentation" refers to a presentation technique that adjusts the way information is displayed in real time according to the user's situation and emotions.

[0176] This invention is a system designed to enable users to efficiently obtain the information they desire. Specifically, a server, terminal, and sentiment analysis engine work together. The server is responsible for data collection and storage, automatically gathering necessary information from external sources. This is done using technologies such as crawlers and APIs. The collected information is stored in a memory unit, ready for subsequent processing.

[0177] The terminal's role is to receive user preferences through an interface. These preferences include specific requests such as price range, location, and the availability of certain equipment. This data is immediately sent to the server, where the necessary information is filtered.

[0178] The emotion analysis engine is installed in the device and analyzes the user's emotions in real time from their facial expressions and voice. This analysis captures the user's feelings and reactions when viewing information and sends it to the server. This data is used to adjust the display results.

[0179] As a concrete example, let's consider a scenario where a user is searching for real estate information. If the user wants a property in Shinjuku Ward with a budget of 100,000 yen or less and free internet access, the device sends these conditions to the server. At the same time, if the sentiment analysis engine recognizes the user's facial expression indicating interest while viewing property A, the server uses this information to prioritize displaying similar properties. In this way, the user can quickly access property information that interests them.

[0180] An example of a prompt is, "Describe a system that uses facial recognition to prioritize displaying rental properties that the user has shown interest in." This prompt helps the generative AI model provide information relevant to the user. Throughout the entire system, users will be able to gather information more intuitively and quickly, improving the user experience.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The server begins collecting data from information sources. Specifically, it uses crawlers and APIs to retrieve real estate information from external sources. This information includes property rent, location, and amenities. The input is the target information sources, and the output is integrated real estate data. The collected information is automatically stored in memory and used for subsequent filtering processes.

[0184] Step 2:

[0185] The terminal accepts the user's desired conditions. The user explicitly inputs conditions such as budget, region, and equipment using the interface. The input consists of the conditions specified by the user, and the output is a record of these conditions. This information is sent to the server and used as a filtering criterion.

[0186] Step 3:

[0187] The emotion analysis engine installed in the terminal analyzes the user's emotions. This process captures the user's facial expressions and voice as input while they view property information. This analysis outputs an emotional state, such as interest or indifference. This output is then sent to the server as feedback.

[0188] Step 4:

[0189] The server selects relevant properties from its stored data based on the received conditions and sentiment data. The input consists of desired conditions and sentiment data sent from the terminal, and the output is filtered property information. In parallel, the server also performs a process to score the reasonableness of the rent and the risk of the contract.

[0190] Step 5:

[0191] The server presents property information optimized for the user based on the obtained scoring results and analysis data. Specifically, based on the sentiment analysis results, it dynamically adjusts the display so that properties that the user has shown interest in are prioritized. The input consists of filtering results and scoring data, and the output is optimized information presentation.

[0192] Step 6:

[0193] The user reviews the presented options and selects the properties they are interested in. The selected information is recorded on the device, and this data will be used for future reference. The input is the presented property information, and the output is the user's selection result.

[0194] Step 7:

[0195] The server collects and analyzes user choices and emotional feedback. This data is used to improve future operations, modifying and enhancing system performance to better satisfy users. Input is user reactions and selection history, and output is adjustment data for performance improvement.

[0196] (Application Example 2)

[0197] 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".

[0198] Traditional e-commerce systems present product information without considering user emotions, making personalization that reflects user interests and preferences difficult. Furthermore, they cannot immediately grasp product information that users are interested in and recommend products based on that information, posing a challenge to improving the user experience.

[0199] 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.

[0200] In this invention, the server includes means for automatically collecting product information from information sources, means for integrating the collected product information and storing it in a database, and means for analyzing the user's emotions. This enables the presentation of relevant products in real time according to the user's emotions, resulting in a more personalized shopping experience.

[0201] "Information sources" refer to a general term for external data provision systems such as online databases and websites used to obtain product information.

[0202] "Product information" refers to data that includes detailed product features, price, stock availability, reviews, and other related information.

[0203] A "database" is an organized collection of information within a system for efficiently storing and managing product information.

[0204] A "user" is someone who uses a system to search for, view, and consider purchasing product information.

[0205] "Desired conditions" refer to the specific requirements or criteria that a user prioritizes when selecting a product.

[0206] "Emotional analysis methods" refer to technologies and software that analyze data such as a user's facial expressions and voice to recognize the user's emotional state.

[0207] "Filtering" is the process of selecting data based on specific criteria, and it is the process of choosing product information that matches the user's desired conditions.

[0208] A "recommendation score" is an evaluation value used by the system to recommend a specific product, based on the results of user sentiment analysis and past behavioral history.

[0209] A system implementing this invention consists of a network-based platform including a terminal used by the user, emotion analysis means for performing emotion analysis, and a server for managing product information.

[0210] The terminal receives the user's facial expressions and voice as input and analyzes the user's emotional state in real time through emotion analysis tools. Emotion recognition libraries such as EmotionML and OpenCV are used in this process. The terminal also obtains the user's desired conditions through an interface and sends them to the server.

[0211] The server automatically collects product information from various sources using APIs and web crawlers and stores it in a database. The database contains product details, pricing, and inventory information. The server filters the stored product information based on the user's preferences, analyzes the results, and calculates a recommendation score. Furthermore, based on input from sentiment analysis tools, it prioritizes listing products the user has shown interest in. This information presentation optimization is achieved using the Django framework.

[0212] As a concrete example, when a user uses smart glasses to shop in real time and shows interest in a particular product, related items (such as related accessories or clothing) are immediately displayed on the screen. This process allows users to efficiently discover products that match their emotions and preferences.

[0213] An example of a prompt message is: "Propose an application that uses an emotion analysis engine for a product recommendation system to detect the emotions a user expresses towards a product and then lists related products based on those emotions."

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The device receives user facial expressions and voice data as input. This data is processed in real time using emotion analysis tools such as EmotionML and OpenCV libraries to identify the user's emotional state. In this process, the input is raw data acquired through the camera and microphone, and the output is an emotion label such as "interest" or "surprise."

[0217] Step 2:

[0218] The user enters their desired search criteria for products through the terminal interface. This information is sent to the server in text format and used as the basis for filtering. The input consists of user-specified conditions (e.g., price range or category), and the output is a set of conditions for the filtering process.

[0219] Step 3:

[0220] The server collects product information from sources and stores the collected data in a database. Product information includes product name, price, ratings, and availability. The server retrieves this information using APIs and web crawlers. Input is product data retrieved online, and output is information in a format integrated into the database.

[0221] Step 4:

[0222] The server filters product information stored in the database based on the user's desired criteria. SQL queries are used for filtering to select products that match the specified conditions. The input consists of all product information retrieved from the database and the user's desired criteria, while the output is a set of product information that meets those criteria.

[0223] Step 5:

[0224] The server calculates a recommendation score for the filtered product information. It adjusts the score and determines priority based on the sentiment analysis results (the level of interest indicated by the user). The input is the filtered data and sentiment analysis results, and the output is a scored product list.

[0225] Step 6:

[0226] The server displays products highly relevant to the user on their device based on a calculated score. This information presentation includes dynamic UI changes, such as displaying products with higher priority based on sentiment analysis at the top of the list. The input is information about products with high recommendation scores, and the output is a list of information presented to the user.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] This invention is a system that automatically collects real estate information and analyzes and selects it based on the user's preferences. This system operates with a server and terminal working in conjunction to provide the user with guidance on choosing rental properties.

[0244] First, the server automatically collects real estate information from source websites and social media. Using crawlers and APIs, this information is retrieved in real time and organized and stored in a database. This database contains a variety of information, including property rent, location, facilities, and contract terms.

[0245] Next, the terminal interacts with the user and provides an interface for collecting the desired property criteria. When the user enters their maximum rent, desired area, and required amenities, these criteria are sent to the server.

[0246] The server filters the property information in the database based on the received request criteria. Using an AI model, it calculates a rent reasonableness score for the filtered results. Furthermore, it analyzes the contract terms and assesses the risks associated with each property.

[0247] The analysis results are presented on the device in a scored format. Users can select from the presented property list and view detailed information. For example, a user looking for a property in Shinjuku Ward with a monthly rent of 100,000 yen or less and free internet access will be presented with the most suitable properties. This display includes a rent appropriateness score and contract risk points for each property.

[0248] Furthermore, after the user selects a property and makes a final decision, a screen for collecting feedback is displayed on the terminal. The server analyzes this feedback and uses it to improve the system. In this way, the system continuously improves its accuracy and supports more reliable property selection.

[0249] By implementing this invention, users will be able to compare a large amount of information in a short time and make rational decisions. This will help prevent inappropriate contracts and unexpected problems.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The server collects property information from multiple websites and social media sources. It uses a crawler to automatically retrieve the latest real estate information and saves it to a database.

[0253] Step 2:

[0254] The terminal displays an interface to the user, prompting them to enter their desired conditions. The user enters their desired rent, location requirements, necessary amenities, etc., and this information is sent directly from the terminal to the server.

[0255] Step 3:

[0256] The server filters the property information in the database based on the user's criteria. This filtering ensures that only properties matching the user's conditions are displayed.

[0257] Step 4:

[0258] The server uses an AI model to calculate a rent justification score for filtered properties. It compares the rent to market trends and evaluates the relative value of each property.

[0259] Step 5:

[0260] The server analyzes the contract terms of the filtered properties and assesses the risks. In particular, it identifies clauses that pose hidden risks within the contract and pinpoints points that users should pay attention to.

[0261] Step 6:

[0262] The server comprehensively evaluates the calculated rent reasonableness score and contract risk, and organizes this into a ranking. The ranking results are sent to the terminal and displayed in a way that the user can visually understand.

[0263] Step 7:

[0264] The user reviews the presented rankings and selects detailed information about properties that interest them. The device then displays more in-depth information in response to that request.

[0265] Step 8:

[0266] After the user completes their property selection, a feedback screen will appear on their device. The user enters feedback based on their experience and sends it from their device to the server.

[0267] Step 9:

[0268] The server analyzes the collected feedback and uses it to improve the AI ​​model and system. The system is then adjusted to provide more accurate information to future users.

[0269] (Example 1)

[0270] 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."

[0271] Data collection, selection, and indicator calculation can be time-consuming and labor-intensive. In particular, providing users with information that meets their specific requirements quickly and accurately is difficult, placing a significant burden on them. Furthermore, there is a lack of support to enable users to effectively utilize the provided information and make optimal choices.

[0272] 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.

[0273] In this invention, the server includes means for automatically collecting data from information sources, means for integrating the collected data and storing it in a storage device, and means for obtaining desired conditions from the user. This reduces the burden on the user and makes it possible to provide the desired information quickly and efficiently.

[0274] "Information source" refers to websites or social networking platforms where content exists for obtaining data.

[0275] "Data" refers to real estate information collected from information sources and related numerical and text-based information.

[0276] "Memory device" refers to an internal or external storage system of a computer for integrating and storing the collected data.

[0277] "User" refers to an individual or legal entity that operates this system to obtain and select information.

[0278] "Desired conditions" are the specific conditions and specifications required by the user for the data, and refer to the criteria for data filtering.

[0279] "Selection" refers to the process of extracting and narrowing down only the relevant data from the database based on the desired conditions.

[0280] "Indicator" is a numerical result evaluated through analysis, and refers to an indicator for indicating the validity and risk assessment of the data.

[0281] "Contract conditions" refer to information indicating legal and business requirements and agreements related to specific data.

[0282] "Risk" refers to the analysis of possible uncertainties and negative impacts related to the contract conditions.

[0283] "Presentation" refers to the process of visually or descriptively presenting the selected or analyzed results to the user.

[0284] The embodiments for implementing this invention will be described. This system is composed by combining three main components: data collection, automated data analysis, and interface provision. The server and the terminal operate in cooperation to provide support for the user to efficiently access the data and make decisions.

[0285] The server serves as an information source, collecting data from websites and social networks on the Internet. Specifically, it uses crawlers and APIs to obtain the necessary information. As a result, information is aggregated in real time. The collected data is integrated and stored in the database on the server. Using a database management system (DBMS), data sorting and duplicate elimination are carried out.

[0286] The terminal provides an interface with the user and has a means for inputting desired conditions. In the terminal, when the user inputs conditions into the fields, it is a mechanism for giving instructions to the system. The user interface is intuitive and easily operable, assisting the user in efficient input.

[0287] When the user inputs conditions into the terminal, the information is sent to the server. The server searches for information in the database based on these conditions and performs filtering. Using SQL queries, data that meets the conditions is quickly extracted. Then, the generated AI model is utilized to conduct further detailed analysis on the extracted data. Specifically, calculations of scores for evaluating the validity of rent and risk assessments based on contract conditions are carried out.

[0288] These analysis results are presented to the user through the terminal. For example, for a user searching for a rental property within 100,000 yen per month in Shinjuku Ward with free Internet, appropriate candidates can be presented along with the numerical values of the validity score and risk assessment.

[0289] An example of a prompt sentence is "I am looking for a rental property in Shinjuku Ward within 100,000 yen per month, with free Internet, and 2DK or more. Please recommend properties with low contract risk and high rent validity scores." By using this prompt sentence, the system can provide the user with the optimal property.

[0290] The flow of the specific process in Example 1 will be described using FIG. 11.

[0291] Step 1:

[0292] The server automatically collects data from source websites and social networks. A crawler periodically visits web pages and parses HTML data. Reliable information can also be obtained through APIs. Input is the URL of the source or API key, and output is the parsed raw data.

[0293] Step 2:

[0294] The server organizes and stores the collected raw data in a database. A database management system is used to store the data, and cleanup is performed to check for duplicates and missing data. The input is raw data, and the output is organized database entries.

[0295] Step 3:

[0296] The terminal provides the user with an interface to input their desired property criteria. The input form includes fields for rent limit, desired area, and required amenities. Information is collected as the user enters these criteria. The input consists of user-specified conditions, and the output is a search request incorporating those conditions.

[0297] Step 4:

[0298] The server filters candidate data from the database based on the user's specified criteria. It uses SQL queries to extract data that matches the criteria. The input is the user's search request, and the output is the filtered property information.

[0299] Step 5:

[0300] The server uses a generative AI model to perform analysis based on filtered property information. It evaluates rent reasonableness scores and risks derived from contract terms. The input is filtered property information, and the output is analysis scores and risk assessments.

[0301] Step 6:

[0302] The terminal presents the analysis results to the user. It visually displays the scored property list, indicating the priority and details of the information. The input is the analysis score and risk assessment, and the output is a result display that is easy for the user to view.

[0303] Step 7:

[0304] The user makes a selection from the presented properties and makes a final choice. The user's selection is input to the system as feedback. The input is the user's selection result, and the output is data for continuous system improvement.

[0305] Step 8:

[0306] The server collects the user's feedback and performs analysis to use it for system improvement. As a result, further system improvements suitable for user needs are realized. The input is feedback data, and the output is improved system functions.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] In an autonomous vehicle, efficiently finding the optimal parking space around the destination is an important issue for suppressing waste of time and energy. It is required to support an optimal parking selection by collecting the latest parking lot information from many information sources and quickly analyzing and evaluating according to the user's desired conditions.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0311] In this invention, the server includes means for automatically collecting environment-related information from information sources, means for integrating the collected environment information and storing it in a data storage device, and means for obtaining desired conditions from the user. This enables the user to quickly select the optimal parking space closest to their destination.

[0312] A "source" refers to an external data provider, such as a website or database, that provides data for a specific purpose.

[0313] "Environmental information" refers to various data related to location and conditions, including, for example, the location, fees, and availability of parking lots.

[0314] A "data storage device" is hardware or software used to store and manage data within a computer system.

[0315] A "user" is an individual who operates the system to receive information and services.

[0316] "Desired conditions" refer to the specific conditions or requirements that a user seeks regarding a particular service or information.

[0317] "Selection" is the process of classifying stored information based on specified criteria and selecting the appropriate results.

[0318] "Analysis" is the act of performing evaluations and calculations on data to extract important information and insights.

[0319] An "evaluation score" is the result of an evaluation that quantifies information or conditions based on specific criteria.

[0320] "Requirements" refer to the conditions or standards that information or a service must meet.

[0321] "Risk" refers to the potential for unfavorable consequences or costs associated with a particular action or piece of information.

[0322] "Feedback" refers to information based on opinions and experiences obtained from system users, and is used to improve the system.

[0323] This invention is a system that suggests the optimal parking space around a destination to an autonomous vehicle, and is realized by collecting, storing, and analyzing environmental information.

[0324] The server automatically collects environmental information related to parking lots from multiple sources, integrates it, and stores it in a data storage device. Specifically, it uses an API to retrieve data in real time, creating a dataset that includes parking lot locations, fees, and availability. This dataset is managed in a database on the computer system.

[0325] Users input their desired conditions through the terminal interface. These conditions include parking fees, distance, available hours, and whether or not there is a roof. These conditions are sent to the server, which then filters the stored data. The filtered information is then evaluated using an AI model to calculate a score. This model is implemented using machine learning libraries such as Scikit-learn and TensorFlow.

[0326] The terminal presents the user with the most suitable parking options based on their evaluation score. This allows users to quickly find a parking space that meets their needs upon arriving at their destination.

[0327] As a concrete example, when a user heads to a shopping mall, they can enter conditions such as "close to the entrance, free for under an hour" into a terminal. The server will then select the most suitable parking lot based on those conditions, score it, and present a list.

[0328] Examples of prompts to input into a generative AI model:

[0329] "Design a system that collects real-time parking information around a destination and suggests the best parking option based on the user's preferences. The criteria should include price, distance, and whether or not the parking area is covered."

[0330] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0331] Step 1:

[0332] The server collects environmental information related to parking lots from multiple sources via an API. This input data includes parking lot location, fees, and availability. The server retrieves this data in real time and stores it in a database. The data is formatted and standardized and organized to improve usability.

[0333] Step 2:

[0334] The user enters their desired parking conditions via a terminal. These conditions may include a maximum parking fee, shortest distance, and required parking time. The system supports input via a multi-touch display or voice command interface. The terminal then sends these conditions to the server.

[0335] Step 3:

[0336] The server filters relevant information from the database based on the user's preferences. Based on the entered preferences, parking information that meets the criteria is selected from the stored dataset. This creates a list of parking lots that match the specified conditions.

[0337] Step 4:

[0338] The server uses a generative AI model to calculate an evaluation score for the selected parking lot information. This process uses Scikit-learn and TensorFlow to comprehensively evaluate multiple factors such as parking fees and accessibility, and quantifies the degree of optimality. This evaluation score is output, and the parking lots are sorted in descending order of score.

[0339] Step 5:

[0340] The terminal displays evaluation scores received from the server to the user. The screen shows a list of suggestions, including the location, fee, and scoring result of the parking lot. Based on this information, the user can select the best parking space. This allows for quick finding of suitable parking spaces near the destination.

[0341] 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.

[0342] This invention is a system that incorporates an emotion engine into a conventional rental property search system, recognizing the user's emotions in real time and optimizing the information presented accordingly. The system, through the interaction of the server, terminal, and emotion engine, makes the user's property selection more accurate and user-friendly.

[0343] First, the server automatically collects real estate information from sources and stores it in a database. This process uses crawlers and APIs. The stored data includes basic information such as property rent, location, and amenities. This information is then filtered based on the user's desired criteria.

[0344] Next, the terminal prompts the user to input their desired conditions for a property using an interface. The user's entered preferences are immediately sent to the server, and the filtering process begins.

[0345] The emotion engine is installed in the device and analyzes the user's emotions from their facial expressions and voice. This allows the system to capture the user's emotional state when they are viewing property information. For example, emotions such as indifference, interest, and aversion can be recognized in real time.

[0346] The server presents property information filtered based on the user's preferences, scoring it based on factors such as rent reasonableness and contract risk. It can dynamically adjust the presentation method, incorporating feedback from the emotion engine to prioritize properties the user has shown interest in.

[0347] Through the emotion engine, users can obtain more interesting and relevant property information, facilitating a smoother property selection process. Furthermore, user emotion data is collected on the server and analyzed for use in future visits. This process improves system performance to provide information more optimized for the user.

[0348] As a concrete example, let's say a user is looking for a property in Shinjuku Ward with free internet access and a budget of under 100,000 yen. If the user shows interest when viewing property A, the emotion engine detects this, and the server prioritizes displaying similar properties. In this way, the user can quickly access the property information they are looking for and make a satisfying property choice.

[0349] In this way, this system, which incorporates an emotion engine, can provide more accurate information than before and significantly improve the user experience.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The server automatically collects real estate information from websites and social media sources. It uses a crawler to retrieve the latest property information in real time and saves it to a database.

[0353] Step 2:

[0354] The terminal displays an interface to the user, prompting them to input their desired property criteria. The user enters their desired rent, location, amenities, and other conditions, and the terminal sends this information to the server.

[0355] Step 3:

[0356] The server filters property information in the database based on the user's desired criteria. It generates a list of properties that match the criteria and passes the result to the next process.

[0357] Step 4:

[0358] The emotion engine analyzes the user's facial expressions and voice on the device, obtaining the user's emotional state in real time while they are viewing property information. This information is then sent to the server.

[0359] Step 5:

[0360] The server scores the reasonableness of the rent and the risk of the contract for the filtered properties. These scores are considered in combination with sentiment data from the sentiment engine.

[0361] Step 6:

[0362] The server dynamically adjusts how information is presented based on the user's emotional state. For example, it optimizes the display by prioritizing properties the user has shown interest in, or hiding properties they have not shown interest in.

[0363] Step 7:

[0364] The terminal displays optimized property information from the server to the user. The user selects properties of interest based on the provided information and checks the details.

[0365] Step 8:

[0366] After the user completes their property selection, the device displays a feedback screen. The user enters their thoughts and experiences, and then sends them from the device to the server.

[0367] Step 9:

[0368] The server analyzes the feedback and sentiment data it collects to help improve the system. The system is then adjusted to provide better information in subsequent user sessions.

[0369] (Example 2)

[0370] 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".

[0371] Conventional information retrieval systems have a problem in that they do not present information while considering the user's feelings, making it difficult to provide the most suitable information for the user. In particular, with real estate information, it is difficult to find the right property from a large number of options, and accurately understanding the user's intentions is required.

[0372] 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.

[0373] In this invention, the server includes means for automatically collecting information from information sources, means for integrating the collected information and storing it in a memory unit, and means for analyzing the user's emotions. This enables dynamic information presentation that takes the user's emotions into consideration.

[0374] "Information source" refers to an external data provider service or database used to obtain data or information.

[0375] A "storage unit" refers to a recording device or memory device used to store data or information for long-term or short-term storage.

[0376] "User" refers to a person or system that operates the system to obtain information or input conditions.

[0377] "Conditions" refer to information used to define the user's preferences and constraints.

[0378] "Selection" refers to the process of selecting relevant information and data based on user criteria and indicators.

[0379] A "validity indicator" refers to a numerical value or evaluation score that assesses the appropriateness of information against specific conditions or criteria.

[0380] "Emotions" refer to the mental or sensory states expressed by users while using the system.

[0381] "Dynamic information presentation" refers to a presentation technique that adjusts the way information is displayed in real time according to the user's situation and emotions.

[0382] This invention is a system designed to enable users to efficiently obtain the information they desire. Specifically, a server, terminal, and sentiment analysis engine work together. The server is responsible for data collection and storage, automatically gathering necessary information from external sources. This is done using technologies such as crawlers and APIs. The collected information is stored in a memory unit, ready for subsequent processing.

[0383] The terminal's role is to receive user preferences through an interface. These preferences include specific requests such as price range, location, and the availability of certain equipment. This data is immediately sent to the server, where the necessary information is filtered.

[0384] The emotion analysis engine is installed in the device and analyzes the user's emotions in real time from their facial expressions and voice. This analysis captures the user's feelings and reactions when viewing information and sends it to the server. This data is used to adjust the display results.

[0385] As a concrete example, let's consider a scenario where a user is searching for real estate information. If the user wants a property in Shinjuku Ward with a budget of 100,000 yen or less and free internet access, the device sends these conditions to the server. At the same time, if the sentiment analysis engine recognizes the user's facial expression indicating interest while viewing property A, the server uses this information to prioritize displaying similar properties. In this way, the user can quickly access property information that interests them.

[0386] An example of a prompt is, "Describe a system that uses facial recognition to prioritize displaying rental properties that the user has shown interest in." This prompt helps the generative AI model provide information relevant to the user. Throughout the entire system, users will be able to gather information more intuitively and quickly, improving the user experience.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] The server begins collecting data from information sources. Specifically, it uses crawlers and APIs to retrieve real estate information from external sources. This information includes property rent, location, and amenities. The input is the target information sources, and the output is integrated real estate data. The collected information is automatically stored in memory and used for subsequent filtering processes.

[0390] Step 2:

[0391] The terminal accepts the user's desired conditions. The user explicitly inputs conditions such as budget, region, and equipment using the interface. The input consists of the conditions specified by the user, and the output is a record of these conditions. This information is sent to the server and used as a filtering criterion.

[0392] Step 3:

[0393] The emotion analysis engine installed in the terminal analyzes the user's emotions. This process captures the user's facial expressions and voice as input while they view property information. This analysis outputs an emotional state, such as interest or indifference. This output is then sent to the server as feedback.

[0394] Step 4:

[0395] The server selects relevant properties from its stored data based on the received conditions and sentiment data. The input consists of desired conditions and sentiment data sent from the terminal, and the output is filtered property information. In parallel, the server also performs a process to score the reasonableness of the rent and the risk of the contract.

[0396] Step 5:

[0397] The server presents property information optimized for the user based on the obtained scoring results and analysis data. Specifically, based on the sentiment analysis results, it dynamically adjusts the display so that properties that the user has shown interest in are prioritized. The input consists of filtering results and scoring data, and the output is optimized information presentation.

[0398] Step 6:

[0399] The user reviews the presented options and selects the properties they are interested in. The selected information is recorded on the device, and this data will be used for future reference. The input is the presented property information, and the output is the user's selection result.

[0400] Step 7:

[0401] The server collects and analyzes user choices and emotional feedback. This data is used to improve future operations, modifying and enhancing system performance to better satisfy users. Input is user reactions and selection history, and output is adjustment data for performance improvement.

[0402] (Application Example 2)

[0403] 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 as the "terminal".

[0404] Traditional e-commerce systems present product information without considering user emotions, making personalization that reflects user interests and preferences difficult. Furthermore, they cannot immediately grasp product information that users are interested in and recommend products based on that information, posing a challenge to improving the user experience.

[0405] 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.

[0406] In this invention, the server includes means for automatically collecting product information from information sources, means for integrating the collected product information and storing it in a database, and means for analyzing the user's emotions. This enables the presentation of relevant products in real time according to the user's emotions, resulting in a more personalized shopping experience.

[0407] "Information sources" refer to a general term for external data provision systems such as online databases and websites used to obtain product information.

[0408] "Product information" refers to data that includes detailed product features, price, stock availability, reviews, and other related information.

[0409] A "database" is an organized collection of information within a system for efficiently storing and managing product information.

[0410] A "user" is someone who uses a system to search for, view, and consider purchasing product information.

[0411] "Desired conditions" refer to the specific requirements or criteria that a user prioritizes when selecting a product.

[0412] "Emotional analysis methods" refer to technologies and software that analyze data such as a user's facial expressions and voice to recognize the user's emotional state.

[0413] "Filtering" is the process of selecting data based on specific criteria, and it is the process of choosing product information that matches the user's desired conditions.

[0414] A "recommendation score" is an evaluation value used by the system to recommend a specific product, based on the results of user sentiment analysis and past behavioral history.

[0415] A system implementing this invention consists of a network-based platform including a terminal used by the user, emotion analysis means for performing emotion analysis, and a server for managing product information.

[0416] The terminal receives the user's facial expressions and voice as input and analyzes the user's emotional state in real time through emotion analysis tools. Emotion recognition libraries such as EmotionML and OpenCV are used in this process. The terminal also obtains the user's desired conditions through an interface and sends them to the server.

[0417] The server automatically collects product information from various sources using APIs and web crawlers and stores it in a database. The database contains product details, pricing, and inventory information. The server filters the stored product information based on the user's preferences, analyzes the results, and calculates a recommendation score. Furthermore, based on input from sentiment analysis tools, it prioritizes listing products the user has shown interest in. This information presentation optimization is achieved using the Django framework.

[0418] As a concrete example, when a user uses smart glasses to shop in real time and shows interest in a particular product, related items (such as related accessories or clothing) are immediately displayed on the screen. This process allows users to efficiently discover products that match their emotions and preferences.

[0419] An example of a prompt message is: "Propose an application that uses an emotion analysis engine for a product recommendation system to detect the emotions a user expresses towards a product and then lists related products based on those emotions."

[0420] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0421] Step 1:

[0422] The device receives user facial expressions and voice data as input. This data is processed in real time using emotion analysis tools such as EmotionML and OpenCV libraries to identify the user's emotional state. In this process, the input is raw data acquired through the camera and microphone, and the output is an emotion label such as "interest" or "surprise."

[0423] Step 2:

[0424] The user enters their desired search criteria for products through the terminal interface. This information is sent to the server in text format and used as the basis for filtering. The input consists of user-specified conditions (e.g., price range or category), and the output is a set of conditions for the filtering process.

[0425] Step 3:

[0426] The server collects product information from sources and stores the collected data in a database. Product information includes product name, price, ratings, and availability. The server retrieves this information using APIs and web crawlers. Input is product data retrieved online, and output is information in a format integrated into the database.

[0427] Step 4:

[0428] The server filters product information stored in the database based on the user's desired criteria. SQL queries are used for filtering to select products that match the specified conditions. The input consists of all product information retrieved from the database and the user's desired criteria, while the output is a set of product information that meets those criteria.

[0429] Step 5:

[0430] The server calculates a recommendation score for the filtered product information. It adjusts the score and determines priority based on the sentiment analysis results (the level of interest indicated by the user). The input is the filtered data and sentiment analysis results, and the output is a scored product list.

[0431] Step 6:

[0432] The server displays products highly relevant to the user on their device based on a calculated score. This information presentation includes dynamic UI changes, such as displaying products with higher priority based on sentiment analysis at the top of the list. The input is information about products with high recommendation scores, and the output is a list of information presented to the user.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] [Third Embodiment]

[0437] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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".

[0449] This invention is a system that automatically collects real estate information and analyzes and selects it based on the user's preferences. This system operates with a server and terminal working in conjunction to provide the user with guidance on choosing rental properties.

[0450] First, the server automatically collects real estate information from source websites and social media. Using crawlers and APIs, this information is retrieved in real time and organized and stored in a database. This database contains a variety of information, including property rent, location, facilities, and contract terms.

[0451] Next, the terminal interacts with the user and provides an interface for collecting the desired property criteria. When the user enters their maximum rent, desired area, and required amenities, these criteria are sent to the server.

[0452] The server filters the property information in the database based on the received request criteria. Using an AI model, it calculates a rent reasonableness score for the filtered results. Furthermore, it analyzes the contract terms and assesses the risks associated with each property.

[0453] The analysis results are presented on the device in a scored format. Users can select from the presented property list and view detailed information. For example, a user looking for a property in Shinjuku Ward with a monthly rent of 100,000 yen or less and free internet access will be presented with the most suitable properties. This display includes a rent appropriateness score and contract risk points for each property.

[0454] Furthermore, after the user selects a property and makes a final decision, a screen for collecting feedback is displayed on the terminal. The server analyzes this feedback and uses it to improve the system. In this way, the system continuously improves its accuracy and supports more reliable property selection.

[0455] By implementing this invention, users will be able to compare a large amount of information in a short time and make rational decisions. This will help prevent inappropriate contracts and unexpected problems.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The server collects property information from multiple websites and social media sources. It uses a crawler to automatically retrieve the latest real estate information and saves it to a database.

[0459] Step 2:

[0460] The terminal displays an interface to the user, prompting them to enter their desired conditions. The user enters their desired rent, location requirements, necessary amenities, etc., and this information is sent directly from the terminal to the server.

[0461] Step 3:

[0462] The server filters the property information in the database based on the user's criteria. This filtering ensures that only properties matching the user's conditions are displayed.

[0463] Step 4:

[0464] The server uses an AI model to calculate a rent justification score for filtered properties. It compares the rent to market trends and evaluates the relative value of each property.

[0465] Step 5:

[0466] The server analyzes the contract terms of the filtered properties and assesses the risks. In particular, it identifies clauses that pose hidden risks within the contract and pinpoints points that users should pay attention to.

[0467] Step 6:

[0468] The server comprehensively evaluates the calculated rent reasonableness score and contract risk, and organizes this into a ranking. The ranking results are sent to the terminal and displayed in a way that the user can visually understand.

[0469] Step 7:

[0470] The user reviews the presented rankings and selects detailed information about properties that interest them. The device then displays more in-depth information in response to that request.

[0471] Step 8:

[0472] After the user completes their property selection, a feedback screen will appear on their device. The user enters feedback based on their experience and sends it from their device to the server.

[0473] Step 9:

[0474] The server analyzes the collected feedback and uses it to improve the AI ​​model and system. The system is then adjusted to provide more accurate information to future users.

[0475] (Example 1)

[0476] 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."

[0477] Data collection, selection, and indicator calculation can be time-consuming and labor-intensive. In particular, providing users with information that meets their specific requirements quickly and accurately is difficult, placing a significant burden on them. Furthermore, there is a lack of support to enable users to effectively utilize the provided information and make optimal choices.

[0478] 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.

[0479] In this invention, the server includes means for automatically collecting data from information sources, means for integrating the collected data and storing it in a storage device, and means for obtaining desired conditions from the user. This reduces the burden on the user and makes it possible to provide the desired information quickly and efficiently.

[0480] "Information source" refers to websites or social networking platforms where content exists for obtaining data.

[0481] "Data" refers to real estate information and related numerical and textual information collected from various sources.

[0482] A "storage device" refers to an internal or external storage system of a computer used to integrate and store collected data.

[0483] "User" refers to an individual or legal entity that operates this system and acquires or selects information.

[0484] "Desired conditions" refer to specific conditions or specifications that users specify for the data, and serve as the basis for data filtering.

[0485] "Selection" refers to the process of extracting and narrowing down only the relevant data from a database based on desired conditions.

[0486] An "indicator" is a numerical result evaluated through analysis, and refers to an indicator used to show the validity of data and risk assessment.

[0487] "Contract terms" refers to information that outlines the legal and operational requirements and arrangements related to specific data.

[0488] "Risk" refers to the analysis of potential uncertainties and negative impacts related to the terms and conditions of a contract.

[0489] "Presentation" refers to the process of visually or descriptively displaying the results of selection or analysis to the user.

[0490] This invention describes embodiments for carrying out this invention. The system consists of three main components: data collection, automated data analysis, and interface provision. The server and terminal work together to support users in efficiently accessing data and making decisions.

[0491] The server plays the role of collecting data from websites and social networks on the internet as information sources. Specifically, it uses crawlers and APIs to obtain the necessary information. This allows for real-time aggregation of information. The collected data is integrated and stored in a database on the server. A database management system (DBMS) is used to organize and deduplication the data.

[0492] The terminal provides an interface with the user and has a means of inputting desired conditions. The terminal works by allowing the user to input conditions into fields, thereby giving instructions to the system. The user interface is intuitive and easy to operate, supporting efficient user input.

[0493] When a user enters conditions into their device, that information is sent to the server. The server searches and filters the information in the database based on these conditions. SQL queries are used to quickly extract data that matches the conditions. Then, a generative AI model is used to perform more detailed analysis on the extracted data. Specifically, this includes calculating a score to evaluate the reasonableness of the rent and conducting a risk assessment based on the contract terms.

[0494] These analysis results are presented to the user via the terminal. For example, a user looking for a rental property in Shinjuku Ward with a monthly fee of 100,000 yen or less and free internet access can be presented with suitable candidates along with a validity score and risk assessment score.

[0495] An example of a prompt message is: "I'm looking for a rental property in Shinjuku Ward with a monthly rent of 100,000 yen or less, free internet, and at least two rooms (2DK). Please recommend properties with low risk in the contract terms and a high rent reasonableness score." By using this prompt message, the system is able to provide the user with the most suitable property.

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] The server automatically collects data from source websites and social networks. A crawler periodically visits web pages and parses HTML data. Reliable information can also be obtained through APIs. Input is the URL of the source or API key, and output is the parsed raw data.

[0499] Step 2:

[0500] The server organizes and stores the collected raw data in a database. A database management system is used to store the data, and cleanup is performed to check for duplicates and missing data. The input is raw data, and the output is organized database entries.

[0501] Step 3:

[0502] The terminal provides the user with an interface to input their desired property criteria. The input form includes fields for rent limit, desired area, and required amenities. Information is collected as the user enters these criteria. The input consists of user-specified conditions, and the output is a search request incorporating those conditions.

[0503] Step 4:

[0504] The server filters candidate data from the database based on the user's specified criteria. It uses SQL queries to extract data that matches the criteria. The input is the user's search request, and the output is the filtered property information.

[0505] Step 5:

[0506] The server uses a generative AI model to perform analysis based on filtered property information. It evaluates rent reasonableness scores and risks derived from contract terms. The input is filtered property information, and the output is analysis scores and risk assessments.

[0507] Step 6:

[0508] The terminal presents the analysis results to the user. It visually displays a scored property list, indicating the priority and details of the information. The input is the analysis score and risk assessment, and the output is a user-friendly results display.

[0509] Step 7:

[0510] Users select from the presented properties and make a final choice. The user's selection is input to the system as feedback. The input is the user's selection result, and the output is data for continuous system improvement.

[0511] Step 8:

[0512] The server collects user feedback and analyzes it to help improve the system. This enables further system improvements tailored to user needs. The input is feedback data, and the output is the improved system functionality.

[0513] (Application Example 1)

[0514] 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."

[0515] For autonomous vehicles, efficiently finding the optimal parking space near the destination is a crucial challenge in minimizing wasted time and energy. It is essential to collect the latest parking information from multiple sources and quickly analyze and evaluate it according to the user's preferences to support the selection of the best parking spot.

[0516] 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.

[0517] In this invention, the server includes means for automatically collecting environment-related information from information sources, means for integrating the collected environment information and storing it in a data storage device, and means for obtaining desired conditions from the user. This enables the user to quickly select the optimal parking space closest to their destination.

[0518] A "source" refers to an external data provider, such as a website or database, that provides data for a specific purpose.

[0519] "Environmental information" refers to various data related to location and conditions, including, for example, the location, fees, and availability of parking lots.

[0520] A "data storage device" is hardware or software used to store and manage data within a computer system.

[0521] A "user" is an individual who operates the system to receive information and services.

[0522] "Desired conditions" refer to the specific conditions or requirements that a user seeks regarding a particular service or information.

[0523] "Selection" is the process of classifying stored information based on specified criteria and selecting the appropriate results.

[0524] "Analysis" is the act of performing evaluations and calculations on data to extract important information and insights.

[0525] An "evaluation score" is the result of an evaluation that quantifies information or conditions based on specific criteria.

[0526] "Requirements" refer to the conditions or standards that information or a service must meet.

[0527] "Risk" refers to the potential for unfavorable consequences or costs associated with a particular action or piece of information.

[0528] "Feedback" refers to information based on opinions and experiences obtained from system users, and is used to improve the system.

[0529] This invention is a system that suggests the optimal parking space around a destination to an autonomous vehicle, and is realized by collecting, storing, and analyzing environmental information.

[0530] The server automatically collects environmental information related to parking lots from multiple sources, integrates it, and stores it in a data storage device. Specifically, it uses an API to retrieve data in real time, creating a dataset that includes parking lot locations, fees, and availability. This dataset is managed in a database on the computer system.

[0531] Users input their desired conditions through the terminal interface. These conditions include parking fees, distance, available hours, and whether or not there is a roof. These conditions are sent to the server, which then filters the stored data. The filtered information is then evaluated using an AI model to calculate a score. This model is implemented using machine learning libraries such as Scikit-learn and TensorFlow.

[0532] The terminal presents the user with the most suitable parking options based on their evaluation score. This allows users to quickly find a parking space that meets their needs upon arriving at their destination.

[0533] As a concrete example, when a user heads to a shopping mall, they can enter conditions such as "close to the entrance, free for under an hour" into a terminal. The server will then select the most suitable parking lot based on those conditions, score it, and present a list.

[0534] Examples of prompts to input into a generative AI model:

[0535] "Design a system that collects real-time parking information around a destination and suggests the best parking option based on the user's preferences. The criteria should include price, distance, and whether or not the parking area is covered."

[0536] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0537] Step 1:

[0538] The server collects environmental information related to parking lots from multiple sources via an API. This input data includes parking lot location, fees, and availability. The server retrieves this data in real time and stores it in a database. The data is formatted and standardized and organized to improve usability.

[0539] Step 2:

[0540] The user enters their desired parking conditions via a terminal. These conditions may include a maximum parking fee, shortest distance, and required parking time. The system supports input via a multi-touch display or voice command interface. The terminal then sends these conditions to the server.

[0541] Step 3:

[0542] The server filters relevant information from the database based on the user's preferences. Based on the entered preferences, parking information that meets the criteria is selected from the stored dataset. This creates a list of parking lots that match the specified conditions.

[0543] Step 4:

[0544] The server uses a generative AI model to calculate an evaluation score for the selected parking lot information. This process uses Scikit-learn and TensorFlow to comprehensively evaluate multiple factors such as parking fees and accessibility, and quantifies the degree of optimality. This evaluation score is output, and the parking lots are sorted in descending order of score.

[0545] Step 5:

[0546] The terminal displays evaluation scores received from the server to the user. The screen shows a list of suggestions, including the location, fee, and scoring result of the parking lot. Based on this information, the user can select the best parking space. This allows for quick finding of suitable parking spaces near the destination.

[0547] 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.

[0548] This invention is a system that incorporates an emotion engine into a conventional rental property search system, recognizing the user's emotions in real time and optimizing the information presented accordingly. The system, through the interaction of the server, terminal, and emotion engine, makes the user's property selection more accurate and user-friendly.

[0549] First, the server automatically collects real estate information from sources and stores it in a database. This process uses crawlers and APIs. The stored data includes basic information such as property rent, location, and amenities. This information is then filtered based on the user's desired criteria.

[0550] Next, the terminal prompts the user to input their desired conditions for a property using an interface. The user's entered preferences are immediately sent to the server, and the filtering process begins.

[0551] The emotion engine is installed in the device and analyzes the user's emotions from their facial expressions and voice. This allows the system to capture the user's emotional state when they are viewing property information. For example, emotions such as indifference, interest, and aversion can be recognized in real time.

[0552] The server presents property information filtered based on the user's preferences, scoring it based on factors such as rent reasonableness and contract risk. It can dynamically adjust the presentation method, incorporating feedback from the emotion engine to prioritize properties the user has shown interest in.

[0553] Through the emotion engine, users can obtain more interesting and relevant property information, facilitating a smoother property selection process. Furthermore, user emotion data is collected on the server and analyzed for use in future visits. This process improves system performance to provide information more optimized for the user.

[0554] As a concrete example, let's say a user is looking for a property in Shinjuku Ward with free internet access and a budget of under 100,000 yen. If the user shows interest when viewing property A, the emotion engine detects this, and the server prioritizes displaying similar properties. In this way, the user can quickly access the property information they are looking for and make a satisfying property choice.

[0555] In this way, this system, which incorporates an emotion engine, can provide more accurate information than before and significantly improve the user experience.

[0556] The following describes the processing flow.

[0557] Step 1:

[0558] The server automatically collects real estate information from websites and social media sources. It uses a crawler to retrieve the latest property information in real time and saves it to a database.

[0559] Step 2:

[0560] The terminal displays an interface to the user, prompting them to input their desired property criteria. The user enters their desired rent, location, amenities, and other conditions, and the terminal sends this information to the server.

[0561] Step 3:

[0562] The server filters property information in the database based on the user's desired criteria. It generates a list of properties that match the criteria and passes the result to the next process.

[0563] Step 4:

[0564] The emotion engine analyzes the user's facial expressions and voice on the device, obtaining the user's emotional state in real time while they are viewing property information. This information is then sent to the server.

[0565] Step 5:

[0566] The server scores the reasonableness of the rent and the risk of the contract for the filtered properties. These scores are considered in combination with sentiment data from the sentiment engine.

[0567] Step 6:

[0568] The server dynamically adjusts how information is presented based on the user's emotional state. For example, it optimizes the display by prioritizing properties the user has shown interest in, or hiding properties they have not shown interest in.

[0569] Step 7:

[0570] The terminal displays optimized property information from the server to the user. The user selects properties of interest based on the provided information and checks the details.

[0571] Step 8:

[0572] After the user completes their property selection, the device displays a feedback screen. The user enters their thoughts and experiences, and then sends them from the device to the server.

[0573] Step 9:

[0574] The server analyzes the feedback and sentiment data it collects to help improve the system. The system is then adjusted to provide better information in subsequent user sessions.

[0575] (Example 2)

[0576] 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."

[0577] Conventional information retrieval systems have a problem in that they do not present information while considering the user's feelings, making it difficult to provide the most suitable information for the user. In particular, with real estate information, it is difficult to find the right property from a large number of options, and accurately understanding the user's intentions is required.

[0578] 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.

[0579] In this invention, the server includes means for automatically collecting information from information sources, means for integrating the collected information and storing it in a memory unit, and means for analyzing the user's emotions. This enables dynamic information presentation that takes the user's emotions into consideration.

[0580] "Information source" refers to an external data provider service or database used to obtain data or information.

[0581] A "storage unit" refers to a recording device or memory device used to store data or information for long-term or short-term storage.

[0582] "User" refers to a person or system that operates the system to obtain information or input conditions.

[0583] "Conditions" refer to information used to define the user's preferences and constraints.

[0584] "Selection" refers to the process of selecting relevant information and data based on user criteria and indicators.

[0585] A "validity indicator" refers to a numerical value or evaluation score that assesses the appropriateness of information against specific conditions or criteria.

[0586] "Emotions" refer to the mental or sensory states expressed by users while using the system.

[0587] "Dynamic information presentation" refers to a presentation technique that adjusts the way information is displayed in real time according to the user's situation and emotions.

[0588] This invention is a system designed to enable users to efficiently obtain the information they desire. Specifically, a server, terminal, and sentiment analysis engine work together. The server is responsible for data collection and storage, automatically gathering necessary information from external sources. This is done using technologies such as crawlers and APIs. The collected information is stored in a memory unit, ready for subsequent processing.

[0589] The terminal's role is to receive user preferences through an interface. These preferences include specific requests such as price range, location, and the availability of certain equipment. This data is immediately sent to the server, where the necessary information is filtered.

[0590] The emotion analysis engine is installed in the device and analyzes the user's emotions in real time from their facial expressions and voice. This analysis captures the user's feelings and reactions when viewing information and sends it to the server. This data is used to adjust the display results.

[0591] As a concrete example, let's consider a scenario where a user is searching for real estate information. If the user wants a property in Shinjuku Ward with a budget of 100,000 yen or less and free internet access, the device sends these conditions to the server. At the same time, if the sentiment analysis engine recognizes the user's facial expression indicating interest while viewing property A, the server uses this information to prioritize displaying similar properties. In this way, the user can quickly access property information that interests them.

[0592] An example of a prompt is, "Describe a system that uses facial recognition to prioritize displaying rental properties that the user has shown interest in." This prompt helps the generative AI model provide information relevant to the user. Throughout the entire system, users will be able to gather information more intuitively and quickly, improving the user experience.

[0593] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0594] Step 1:

[0595] The server begins collecting data from information sources. Specifically, it uses crawlers and APIs to retrieve real estate information from external sources. This information includes property rent, location, and amenities. The input is the target information sources, and the output is integrated real estate data. The collected information is automatically stored in memory and used for subsequent filtering processes.

[0596] Step 2:

[0597] The terminal accepts the user's desired conditions. The user explicitly inputs conditions such as budget, region, and equipment using the interface. The input consists of the conditions specified by the user, and the output is a record of these conditions. This information is sent to the server and used as a filtering criterion.

[0598] Step 3:

[0599] The emotion analysis engine installed in the terminal analyzes the user's emotions. This process captures the user's facial expressions and voice as input while they view property information. This analysis outputs an emotional state, such as interest or indifference. This output is then sent to the server as feedback.

[0600] Step 4:

[0601] The server selects relevant properties from its stored data based on the received conditions and sentiment data. The input consists of desired conditions and sentiment data sent from the terminal, and the output is filtered property information. In parallel, the server also performs a process to score the reasonableness of the rent and the risk of the contract.

[0602] Step 5:

[0603] The server presents property information optimized for the user based on the obtained scoring results and analysis data. Specifically, based on the sentiment analysis results, it dynamically adjusts the display so that properties that the user has shown interest in are prioritized. The input consists of filtering results and scoring data, and the output is optimized information presentation.

[0604] Step 6:

[0605] The user reviews the presented options and selects the properties they are interested in. The selected information is recorded on the device, and this data will be used for future reference. The input is the presented property information, and the output is the user's selection result.

[0606] Step 7:

[0607] The server collects and analyzes user choices and emotional feedback. This data is used to improve future operations, modifying and enhancing system performance to better satisfy users. Input is user reactions and selection history, and output is adjustment data for performance improvement.

[0608] (Application Example 2)

[0609] 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."

[0610] Traditional e-commerce systems present product information without considering user emotions, making personalization that reflects user interests and preferences difficult. Furthermore, they cannot immediately grasp product information that users are interested in and recommend products based on that information, posing a challenge to improving the user experience.

[0611] 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.

[0612] In this invention, the server includes means for automatically collecting product information from information sources, means for integrating the collected product information and storing it in a database, and means for analyzing the user's emotions. This enables the presentation of relevant products in real time according to the user's emotions, resulting in a more personalized shopping experience.

[0613] "Information sources" refer to a general term for external data provision systems such as online databases and websites used to obtain product information.

[0614] "Product information" refers to data that includes detailed product features, price, stock availability, reviews, and other related information.

[0615] A "database" is an organized collection of information within a system for efficiently storing and managing product information.

[0616] A "user" is someone who uses a system to search for, view, and consider purchasing product information.

[0617] "Desired conditions" refer to the specific requirements or criteria that a user prioritizes when selecting a product.

[0618] "Emotional analysis methods" refer to technologies and software that analyze data such as a user's facial expressions and voice to recognize the user's emotional state.

[0619] "Filtering" is the process of selecting data based on specific criteria, and it is the process of choosing product information that matches the user's desired conditions.

[0620] A "recommendation score" is an evaluation value used by the system to recommend a specific product, based on the results of user sentiment analysis and past behavioral history.

[0621] A system implementing this invention consists of a network-based platform including a terminal used by the user, emotion analysis means for performing emotion analysis, and a server for managing product information.

[0622] The terminal receives the user's facial expressions and voice as input and analyzes the user's emotional state in real time through emotion analysis tools. Emotion recognition libraries such as EmotionML and OpenCV are used in this process. The terminal also obtains the user's desired conditions through an interface and sends them to the server.

[0623] The server automatically collects product information from various sources using APIs and web crawlers and stores it in a database. The database contains product details, pricing, and inventory information. The server filters the stored product information based on the user's preferences, analyzes the results, and calculates a recommendation score. Furthermore, based on input from sentiment analysis tools, it prioritizes listing products the user has shown interest in. This information presentation optimization is achieved using the Django framework.

[0624] As a concrete example, when a user uses smart glasses to shop in real time and shows interest in a particular product, related items (such as related accessories or clothing) are immediately displayed on the screen. This process allows users to efficiently discover products that match their emotions and preferences.

[0625] An example of a prompt message is: "Propose an application that uses an emotion analysis engine for a product recommendation system to detect the emotions a user expresses towards a product and then lists related products based on those emotions."

[0626] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0627] Step 1:

[0628] The device receives user facial expressions and voice data as input. This data is processed in real time using emotion analysis tools such as EmotionML and OpenCV libraries to identify the user's emotional state. In this process, the input is raw data acquired through the camera and microphone, and the output is an emotion label such as "interest" or "surprise."

[0629] Step 2:

[0630] The user enters their desired search criteria for products through the terminal interface. This information is sent to the server in text format and used as the basis for filtering. The input consists of user-specified conditions (e.g., price range or category), and the output is a set of conditions for the filtering process.

[0631] Step 3:

[0632] The server collects product information from sources and stores the collected data in a database. Product information includes product name, price, ratings, and availability. The server retrieves this information using APIs and web crawlers. Input is product data retrieved online, and output is information in a format integrated into the database.

[0633] Step 4:

[0634] The server filters product information stored in the database based on the user's desired criteria. SQL queries are used for filtering to select products that match the specified conditions. The input consists of all product information retrieved from the database and the user's desired criteria, while the output is a set of product information that meets those criteria.

[0635] Step 5:

[0636] The server calculates a recommendation score for the filtered product information. It adjusts the score and determines priority based on the sentiment analysis results (the level of interest indicated by the user). The input is the filtered data and sentiment analysis results, and the output is a scored product list.

[0637] Step 6:

[0638] The server displays products highly relevant to the user on their device based on a calculated score. This information presentation includes dynamic UI changes, such as displaying products with higher priority based on sentiment analysis at the top of the list. The input is information about products with high recommendation scores, and the output is a list of information presented to the user.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] [Fourth Embodiment]

[0643] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0644] 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.

[0645] 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).

[0646] 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.

[0647] 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.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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".

[0656] This invention is a system that automatically collects real estate information and analyzes and selects it based on the user's preferences. This system operates with a server and terminal working in conjunction to provide the user with guidance on choosing rental properties.

[0657] First, the server automatically collects real estate information from source websites and social media. Using crawlers and APIs, this information is retrieved in real time and organized and stored in a database. This database contains a variety of information, including property rent, location, facilities, and contract terms.

[0658] Next, the terminal interacts with the user and provides an interface for collecting the desired property criteria. When the user enters their maximum rent, desired area, and required amenities, these criteria are sent to the server.

[0659] The server filters the property information in the database based on the received request criteria. Using an AI model, it calculates a rent reasonableness score for the filtered results. Furthermore, it analyzes the contract terms and assesses the risks associated with each property.

[0660] The analysis results are presented on the device in a scored format. Users can select from the presented property list and view detailed information. For example, a user looking for a property in Shinjuku Ward with a monthly rent of 100,000 yen or less and free internet access will be presented with the most suitable properties. This display includes a rent appropriateness score and contract risk points for each property.

[0661] Furthermore, after the user selects a property and makes a final decision, a screen for collecting feedback is displayed on the terminal. The server analyzes this feedback and uses it to improve the system. In this way, the system continuously improves its accuracy and supports more reliable property selection.

[0662] By implementing this invention, users will be able to compare a large amount of information in a short time and make rational decisions. This will help prevent inappropriate contracts and unexpected problems.

[0663] The following describes the processing flow.

[0664] Step 1:

[0665] The server collects property information from multiple websites and social media sources. It uses a crawler to automatically retrieve the latest real estate information and saves it to a database.

[0666] Step 2:

[0667] The terminal displays an interface to the user, prompting them to enter their desired conditions. The user enters their desired rent, location requirements, necessary amenities, etc., and this information is sent directly from the terminal to the server.

[0668] Step 3:

[0669] The server filters the property information in the database based on the user's criteria. This filtering ensures that only properties matching the user's conditions are displayed.

[0670] Step 4:

[0671] The server uses an AI model to calculate a rent justification score for filtered properties. It compares the rent to market trends and evaluates the relative value of each property.

[0672] Step 5:

[0673] The server analyzes the contract terms of the filtered properties and assesses the risks. In particular, it identifies clauses that pose hidden risks within the contract and pinpoints points that users should pay attention to.

[0674] Step 6:

[0675] The server comprehensively evaluates the calculated rent reasonableness score and contract risk, and organizes this into a ranking. The ranking results are sent to the terminal and displayed in a way that the user can visually understand.

[0676] Step 7:

[0677] The user reviews the presented rankings and selects detailed information about properties that interest them. The device then displays more in-depth information in response to that request.

[0678] Step 8:

[0679] After the user completes their property selection, a feedback screen will appear on their device. The user enters feedback based on their experience and sends it from their device to the server.

[0680] Step 9:

[0681] The server analyzes the collected feedback and uses it to improve the AI ​​model and system. The system is then adjusted to provide more accurate information to future users.

[0682] (Example 1)

[0683] 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".

[0684] Data collection, selection, and indicator calculation can be time-consuming and labor-intensive. In particular, providing users with information that meets their specific requirements quickly and accurately is difficult, placing a significant burden on them. Furthermore, there is a lack of support to enable users to effectively utilize the provided information and make optimal choices.

[0685] 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.

[0686] In this invention, the server includes means for automatically collecting data from information sources, means for integrating the collected data and storing it in a storage device, and means for obtaining desired conditions from the user. This reduces the burden on the user and makes it possible to provide the desired information quickly and efficiently.

[0687] "Information source" refers to websites or social networking platforms where content exists for obtaining data.

[0688] "Data" refers to real estate information and related numerical and textual information collected from various sources.

[0689] A "storage device" refers to an internal or external storage system of a computer used to integrate and store collected data.

[0690] "User" refers to an individual or legal entity that operates this system and acquires or selects information.

[0691] "Desired conditions" refer to specific conditions or specifications that users specify for the data, and serve as the basis for data filtering.

[0692] "Selection" refers to the process of extracting and narrowing down only the relevant data from a database based on desired conditions.

[0693] An "indicator" is a numerical result evaluated through analysis, and refers to an indicator used to show the validity of data and risk assessment.

[0694] "Contract terms" refers to information that outlines the legal and operational requirements and arrangements related to specific data.

[0695] "Risk" refers to the analysis of potential uncertainties and negative impacts related to the terms and conditions of a contract.

[0696] "Presentation" refers to the process of visually or descriptively displaying the results of selection or analysis to the user.

[0697] This invention describes embodiments for carrying out this invention. The system consists of three main components: data collection, automated data analysis, and interface provision. The server and terminal work together to support users in efficiently accessing data and making decisions.

[0698] The server plays the role of collecting data from websites and social networks on the internet as information sources. Specifically, it uses crawlers and APIs to obtain the necessary information. This allows for real-time aggregation of information. The collected data is integrated and stored in a database on the server. A database management system (DBMS) is used to organize and deduplication the data.

[0699] The terminal provides an interface with the user and has a means of inputting desired conditions. The terminal works by allowing the user to input conditions into fields, thereby giving instructions to the system. The user interface is intuitive and easy to operate, supporting efficient user input.

[0700] When a user enters conditions into their device, that information is sent to the server. The server searches and filters the information in the database based on these conditions. SQL queries are used to quickly extract data that matches the conditions. Then, a generative AI model is used to perform more detailed analysis on the extracted data. Specifically, this includes calculating a score to evaluate the reasonableness of the rent and conducting a risk assessment based on the contract terms.

[0701] These analysis results are presented to the user via the terminal. For example, a user looking for a rental property in Shinjuku Ward with a monthly fee of 100,000 yen or less and free internet access can be presented with suitable candidates along with a validity score and risk assessment score.

[0702] An example of a prompt message is: "I'm looking for a rental property in Shinjuku Ward with a monthly rent of 100,000 yen or less, free internet, and at least two rooms (2DK). Please recommend properties with low risk in the contract terms and a high rent reasonableness score." By using this prompt message, the system is able to provide the user with the most suitable property.

[0703] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0704] Step 1:

[0705] The server automatically collects data from source websites and social networks. A crawler periodically visits web pages and parses HTML data. Reliable information can also be obtained through APIs. Input is the URL of the source or API key, and output is the parsed raw data.

[0706] Step 2:

[0707] The server organizes and stores the collected raw data in a database. A database management system is used to store the data, and cleanup is performed to check for duplicates and missing data. The input is raw data, and the output is organized database entries.

[0708] Step 3:

[0709] The terminal provides the user with an interface to input their desired property criteria. The input form includes fields for rent limit, desired area, and required amenities. Information is collected as the user enters these criteria. The input consists of user-specified conditions, and the output is a search request incorporating those conditions.

[0710] Step 4:

[0711] The server filters candidate data from the database based on the user's specified criteria. It uses SQL queries to extract data that matches the criteria. The input is the user's search request, and the output is the filtered property information.

[0712] Step 5:

[0713] The server uses a generative AI model to perform analysis based on filtered property information. It evaluates rent reasonableness scores and risks derived from contract terms. The input is filtered property information, and the output is analysis scores and risk assessments.

[0714] Step 6:

[0715] The terminal presents the analysis results to the user. It visually displays a scored property list, indicating the priority and details of the information. The input is the analysis score and risk assessment, and the output is a user-friendly results display.

[0716] Step 7:

[0717] Users select from the presented properties and make a final choice. The user's selection is input to the system as feedback. The input is the user's selection result, and the output is data for continuous system improvement.

[0718] Step 8:

[0719] The server collects user feedback and analyzes it to help improve the system. This enables further system improvements tailored to user needs. The input is feedback data, and the output is the improved system functionality.

[0720] (Application Example 1)

[0721] 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".

[0722] For autonomous vehicles, efficiently finding the optimal parking space near the destination is a crucial challenge in minimizing wasted time and energy. It is essential to collect the latest parking information from multiple sources and quickly analyze and evaluate it according to the user's preferences to support the selection of the best parking spot.

[0723] 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.

[0724] In this invention, the server includes means for automatically collecting environment-related information from information sources, means for integrating the collected environment information and storing it in a data storage device, and means for obtaining desired conditions from the user. This enables the user to quickly select the optimal parking space closest to their destination.

[0725] A "source" refers to an external data provider, such as a website or database, that provides data for a specific purpose.

[0726] "Environmental information" refers to various data related to location and conditions, including, for example, the location, fees, and availability of parking lots.

[0727] A "data storage device" is hardware or software used to store and manage data within a computer system.

[0728] A "user" is an individual who operates the system to receive information and services.

[0729] "Desired conditions" refer to the specific conditions or requirements that a user seeks regarding a particular service or information.

[0730] "Selection" is the process of classifying stored information based on specified criteria and selecting the appropriate results.

[0731] "Analysis" is the act of performing evaluations and calculations on data to extract important information and insights.

[0732] An "evaluation score" is the result of an evaluation that quantifies information or conditions based on specific criteria.

[0733] "Requirements" refer to the conditions or standards that information or a service must meet.

[0734] "Risk" refers to the potential for unfavorable consequences or costs associated with a particular action or piece of information.

[0735] "Feedback" refers to information based on opinions and experiences obtained from system users, and is used to improve the system.

[0736] This invention is a system that suggests the optimal parking space around a destination to an autonomous vehicle, and is realized by collecting, storing, and analyzing environmental information.

[0737] The server automatically collects environmental information related to parking lots from multiple sources, integrates it, and stores it in a data storage device. Specifically, it uses an API to retrieve data in real time, creating a dataset that includes parking lot locations, fees, and availability. This dataset is managed in a database on the computer system.

[0738] Users input their desired conditions through the terminal interface. These conditions include parking fees, distance, available hours, and whether or not there is a roof. These conditions are sent to the server, which then filters the stored data. The filtered information is then evaluated using an AI model to calculate a score. This model is implemented using machine learning libraries such as Scikit-learn and TensorFlow.

[0739] The terminal presents the user with the most suitable parking options based on their evaluation score. This allows users to quickly find a parking space that meets their needs upon arriving at their destination.

[0740] As a concrete example, when a user heads to a shopping mall, they can enter conditions such as "close to the entrance, free for under an hour" into a terminal. The server will then select the most suitable parking lot based on those conditions, score it, and present a list.

[0741] Examples of prompts to input into a generative AI model:

[0742] "Design a system that collects real-time parking information around a destination and suggests the best parking option based on the user's preferences. The criteria should include price, distance, and whether or not the parking area is covered."

[0743] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0744] Step 1:

[0745] The server collects environmental information related to parking lots from multiple sources via an API. This input data includes parking lot location, fees, and availability. The server retrieves this data in real time and stores it in a database. The data is formatted and standardized and organized to improve usability.

[0746] Step 2:

[0747] The user enters their desired parking conditions via a terminal. These conditions may include a maximum parking fee, shortest distance, and required parking time. The system supports input via a multi-touch display or voice command interface. The terminal then sends these conditions to the server.

[0748] Step 3:

[0749] The server filters relevant information from the database based on the user's preferences. Based on the entered preferences, parking information that meets the criteria is selected from the stored dataset. This creates a list of parking lots that match the specified conditions.

[0750] Step 4:

[0751] The server uses a generative AI model to calculate an evaluation score for the selected parking lot information. This process uses Scikit-learn and TensorFlow to comprehensively evaluate multiple factors such as parking fees and accessibility, and quantifies the degree of optimality. This evaluation score is output, and the parking lots are sorted in descending order of score.

[0752] Step 5:

[0753] The terminal displays evaluation scores received from the server to the user. The screen shows a list of suggestions, including the location, fee, and scoring result of the parking lot. Based on this information, the user can select the best parking space. This allows for quick finding of suitable parking spaces near the destination.

[0754] 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.

[0755] This invention is a system that incorporates an emotion engine into a conventional rental property search system, recognizing the user's emotions in real time and optimizing the information presented accordingly. The system, through the interaction of the server, terminal, and emotion engine, makes the user's property selection more accurate and user-friendly.

[0756] First, the server automatically collects real estate information from sources and stores it in a database. This process uses crawlers and APIs. The stored data includes basic information such as property rent, location, and amenities. This information is then filtered based on the user's desired criteria.

[0757] Next, the terminal prompts the user to input their desired conditions for a property using an interface. The user's entered preferences are immediately sent to the server, and the filtering process begins.

[0758] The emotion engine is installed in the device and analyzes the user's emotions from their facial expressions and voice. This allows the system to capture the user's emotional state when they are viewing property information. For example, emotions such as indifference, interest, and aversion can be recognized in real time.

[0759] The server presents property information filtered based on the user's preferences, scoring it based on factors such as rent reasonableness and contract risk. It can dynamically adjust the presentation method, incorporating feedback from the emotion engine to prioritize properties the user has shown interest in.

[0760] Through the emotion engine, users can obtain more interesting and relevant property information, facilitating a smoother property selection process. Furthermore, user emotion data is collected on the server and analyzed for use in future visits. This process improves system performance to provide information more optimized for the user.

[0761] As a concrete example, let's say a user is looking for a property in Shinjuku Ward with free internet access and a budget of under 100,000 yen. If the user shows interest when viewing property A, the emotion engine detects this, and the server prioritizes displaying similar properties. In this way, the user can quickly access the property information they are looking for and make a satisfying property choice.

[0762] In this way, this system, which incorporates an emotion engine, can provide more accurate information than before and significantly improve the user experience.

[0763] The following describes the processing flow.

[0764] Step 1:

[0765] The server automatically collects real estate information from websites and social media sources. It uses a crawler to retrieve the latest property information in real time and saves it to a database.

[0766] Step 2:

[0767] The terminal displays an interface to the user, prompting them to input their desired property criteria. The user enters their desired rent, location, amenities, and other conditions, and the terminal sends this information to the server.

[0768] Step 3:

[0769] The server filters property information in the database based on the user's desired criteria. It generates a list of properties that match the criteria and passes the result to the next process.

[0770] Step 4:

[0771] The emotion engine analyzes the user's facial expressions and voice on the device, obtaining the user's emotional state in real time while they are viewing property information. This information is then sent to the server.

[0772] Step 5:

[0773] The server scores the reasonableness of the rent and the risk of the contract for the filtered properties. These scores are considered in combination with sentiment data from the sentiment engine.

[0774] Step 6:

[0775] The server dynamically adjusts how information is presented based on the user's emotional state. For example, it optimizes the display by prioritizing properties the user has shown interest in, or hiding properties they have not shown interest in.

[0776] Step 7:

[0777] The terminal displays optimized property information from the server to the user. The user selects properties of interest based on the provided information and checks the details.

[0778] Step 8:

[0779] After the user completes their property selection, the device displays a feedback screen. The user enters their thoughts and experiences, and then sends them from the device to the server.

[0780] Step 9:

[0781] The server analyzes the feedback and sentiment data it collects to help improve the system. The system is then adjusted to provide better information in subsequent user sessions.

[0782] (Example 2)

[0783] 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".

[0784] Conventional information retrieval systems have a problem in that they do not present information while considering the user's feelings, making it difficult to provide the most suitable information for the user. In particular, with real estate information, it is difficult to find the right property from a large number of options, and accurately understanding the user's intentions is required.

[0785] 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.

[0786] In this invention, the server includes means for automatically collecting information from information sources, means for integrating the collected information and storing it in a memory unit, and means for analyzing the user's emotions. This enables dynamic information presentation that takes the user's emotions into consideration.

[0787] "Information source" refers to an external data provider service or database used to obtain data or information.

[0788] A "storage unit" refers to a recording device or memory device used to store data or information for long-term or short-term storage.

[0789] "User" refers to a person or system that operates the system to obtain information or input conditions.

[0790] "Conditions" refer to information used to define the user's preferences and constraints.

[0791] "Selection" refers to the process of selecting relevant information and data based on user criteria and indicators.

[0792] A "validity indicator" refers to a numerical value or evaluation score that assesses the appropriateness of information against specific conditions or criteria.

[0793] "Emotions" refer to the mental or sensory states expressed by users while using the system.

[0794] "Dynamic information presentation" refers to a presentation technique that adjusts the way information is displayed in real time according to the user's situation and emotions.

[0795] This invention is a system designed to enable users to efficiently obtain the information they desire. Specifically, a server, terminal, and sentiment analysis engine work together. The server is responsible for data collection and storage, automatically gathering necessary information from external sources. This is done using technologies such as crawlers and APIs. The collected information is stored in a memory unit, ready for subsequent processing.

[0796] The terminal's role is to receive user preferences through an interface. These preferences include specific requests such as price range, location, and the availability of certain equipment. This data is immediately sent to the server, where the necessary information is filtered.

[0797] The emotion analysis engine is installed in the device and analyzes the user's emotions in real time from their facial expressions and voice. This analysis captures the user's feelings and reactions when viewing information and sends it to the server. This data is used to adjust the display results.

[0798] As a concrete example, let's consider a scenario where a user is searching for real estate information. If the user wants a property in Shinjuku Ward with a budget of 100,000 yen or less and free internet access, the device sends these conditions to the server. At the same time, if the sentiment analysis engine recognizes the user's facial expression indicating interest while viewing property A, the server uses this information to prioritize displaying similar properties. In this way, the user can quickly access property information that interests them.

[0799] An example of a prompt is, "Describe a system that uses facial recognition to prioritize displaying rental properties that the user has shown interest in." This prompt helps the generative AI model provide information relevant to the user. Throughout the entire system, users will be able to gather information more intuitively and quickly, improving the user experience.

[0800] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0801] Step 1:

[0802] The server begins collecting data from information sources. Specifically, it uses crawlers and APIs to retrieve real estate information from external sources. This information includes property rent, location, and amenities. The input is the target information sources, and the output is integrated real estate data. The collected information is automatically stored in memory and used for subsequent filtering processes.

[0803] Step 2:

[0804] The terminal accepts the user's desired conditions. The user explicitly inputs conditions such as budget, region, and equipment using the interface. The input consists of the conditions specified by the user, and the output is a record of these conditions. This information is sent to the server and used as a filtering criterion.

[0805] Step 3:

[0806] The emotion analysis engine installed in the terminal analyzes the user's emotions. This process captures the user's facial expressions and voice as input while they view property information. This analysis outputs an emotional state, such as interest or indifference. This output is then sent to the server as feedback.

[0807] Step 4:

[0808] The server selects relevant properties from its stored data based on the received conditions and sentiment data. The input consists of desired conditions and sentiment data sent from the terminal, and the output is filtered property information. In parallel, the server also performs a process to score the reasonableness of the rent and the risk of the contract.

[0809] Step 5:

[0810] The server presents property information optimized for the user based on the obtained scoring results and analysis data. Specifically, based on the sentiment analysis results, it dynamically adjusts the display so that properties that the user has shown interest in are prioritized. The input consists of filtering results and scoring data, and the output is optimized information presentation.

[0811] Step 6:

[0812] The user reviews the presented options and selects the properties they are interested in. The selected information is recorded on the device, and this data will be used for future reference. The input is the presented property information, and the output is the user's selection result.

[0813] Step 7:

[0814] The server collects and analyzes user choices and emotional feedback. This data is used to improve future operations, modifying and enhancing system performance to better satisfy users. Input is user reactions and selection history, and output is adjustment data for performance improvement.

[0815] (Application Example 2)

[0816] 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".

[0817] Traditional e-commerce systems present product information without considering user emotions, making personalization that reflects user interests and preferences difficult. Furthermore, they cannot immediately grasp product information that users are interested in and recommend products based on that information, posing a challenge to improving the user experience.

[0818] 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.

[0819] In this invention, the server includes means for automatically collecting product information from information sources, means for integrating the collected product information and storing it in a database, and means for analyzing the user's emotions. This enables the presentation of relevant products in real time according to the user's emotions, resulting in a more personalized shopping experience.

[0820] "Information sources" refer to a general term for external data provision systems such as online databases and websites used to obtain product information.

[0821] "Product information" refers to data that includes detailed product features, price, stock availability, reviews, and other related information.

[0822] A "database" is an organized collection of information within a system for efficiently storing and managing product information.

[0823] A "user" is someone who uses a system to search for, view, and consider purchasing product information.

[0824] "Desired conditions" refer to the specific requirements or criteria that a user prioritizes when selecting a product.

[0825] "Emotional analysis methods" refer to technologies and software that analyze data such as a user's facial expressions and voice to recognize the user's emotional state.

[0826] "Filtering" is the process of selecting data based on specific criteria, and it is the process of choosing product information that matches the user's desired conditions.

[0827] A "recommendation score" is an evaluation value used by the system to recommend a specific product, based on the results of user sentiment analysis and past behavioral history.

[0828] A system implementing this invention consists of a network-based platform including a terminal used by the user, emotion analysis means for performing emotion analysis, and a server for managing product information.

[0829] The terminal receives the user's facial expressions and voice as input and analyzes the user's emotional state in real time through emotion analysis tools. Emotion recognition libraries such as EmotionML and OpenCV are used in this process. The terminal also obtains the user's desired conditions through an interface and sends them to the server.

[0830] The server automatically collects product information from various sources using APIs and web crawlers and stores it in a database. The database contains product details, pricing, and inventory information. The server filters the stored product information based on the user's preferences, analyzes the results, and calculates a recommendation score. Furthermore, based on input from sentiment analysis tools, it prioritizes listing products the user has shown interest in. This information presentation optimization is achieved using the Django framework.

[0831] As a concrete example, when a user uses smart glasses to shop in real time and shows interest in a particular product, related items (such as related accessories or clothing) are immediately displayed on the screen. This process allows users to efficiently discover products that match their emotions and preferences.

[0832] An example of a prompt message is: "Propose an application that uses an emotion analysis engine for a product recommendation system to detect the emotions a user expresses towards a product and then lists related products based on those emotions."

[0833] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0834] Step 1:

[0835] The device receives user facial expressions and voice data as input. This data is processed in real time using emotion analysis tools such as EmotionML and OpenCV libraries to identify the user's emotional state. In this process, the input is raw data acquired through the camera and microphone, and the output is an emotion label such as "interest" or "surprise."

[0836] Step 2:

[0837] The user enters their desired search criteria for products through the terminal interface. This information is sent to the server in text format and used as the basis for filtering. The input consists of user-specified conditions (e.g., price range or category), and the output is a set of conditions for the filtering process.

[0838] Step 3:

[0839] The server collects product information from sources and stores the collected data in a database. Product information includes product name, price, ratings, and availability. The server retrieves this information using APIs and web crawlers. Input is product data retrieved online, and output is information in a format integrated into the database.

[0840] Step 4:

[0841] The server filters product information stored in the database based on the user's desired criteria. SQL queries are used for filtering to select products that match the specified conditions. The input consists of all product information retrieved from the database and the user's desired criteria, while the output is a set of product information that meets those criteria.

[0842] Step 5:

[0843] The server calculates a recommendation score for the filtered product information. It adjusts the score and determines priority based on the sentiment analysis results (the level of interest indicated by the user). The input is the filtered data and sentiment analysis results, and the output is a scored product list.

[0844] Step 6:

[0845] The server displays products highly relevant to the user on their device based on a calculated score. This information presentation includes dynamic UI changes, such as displaying products with higher priority based on sentiment analysis at the top of the list. The input is information about products with high recommendation scores, and the output is a list of information presented to the user.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] A means of automatically collecting real estate information from information sources,

[0870] A means of integrating the collected real estate information and storing it in a database,

[0871] A means of obtaining desired conditions from the user,

[0872] A means of filtering real estate information saved based on desired conditions,

[0873] A method for analyzing filtered property information to calculate a rent justification score,

[0874] A means of analyzing contract terms and assessing risk,

[0875] A means of presenting the evaluated score to the user,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, further comprising means for accepting a user's selection based on presented real estate information.

[0879] (Claim 3)

[0880] Means for collecting and analyzing user feedback,

[0881] The system according to claim 1, further comprising means for improving the system's performance using collected feedback.

[0882] "Example 1"

[0883] (Claim 1)

[0884] Means for automatically collecting data from information sources,

[0885] A means of integrating the collected data and storing it in a storage device,

[0886] A means of obtaining desired conditions from users,

[0887] A means of selecting data stored based on desired conditions,

[0888] A means of analyzing selected data and calculating indicators,

[0889] A means of analyzing contract terms and assessing risks,

[0890] A means of presenting the evaluated metrics to the user,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising means for accepting user selections based on presented data.

[0894] (Claim 3)

[0895] A means of collecting and analyzing user feedback,

[0896] The system according to claim 1, further comprising means for improving the system's performance using collected feedback.

[0897] "Application Example 1"

[0898] (Claim 1)

[0899] A means of automatically collecting environmentally relevant information from information sources,

[0900] A means for integrating the collected environmental information and storing it in a data storage device,

[0901] A means of obtaining desired conditions from the user,

[0902] A means of selecting environmental information stored based on desired conditions,

[0903] A means of analyzing selected information and calculating an evaluation score,

[0904] A means of analyzing requirements and assessing risks,

[0905] A means of presenting the evaluated score to the user,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, further comprising means for accepting a user's selection based on presented environmental information.

[0909] (Claim 3)

[0910] A means of collecting and analyzing user feedback,

[0911] The system according to claim 1, further comprising means for improving the system's performance using collected feedback.

[0912] "Example 2 of combining an emotion engine"

[0913] (Claim 1)

[0914] Means for automatically collecting information from sources,

[0915] A means of integrating the collected information and storing it in the memory unit,

[0916] Means of obtaining conditions from users,

[0917] A means for selecting stored information based on acquired conditions,

[0918] A means of analyzing selected item information to calculate a validity index,

[0919] A means of analyzing conditions and evaluating risk,

[0920] A means of presenting the evaluated metrics to the user,

[0921] A means of analyzing user emotions,

[0922] A means for dynamically adjusting the way information is presented based on the analysis results,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, further comprising means for accepting user selections based on presented information.

[0926] (Claim 3)

[0927] A means of collecting and analyzing user feedback,

[0928] The system according to claim 1, further comprising means for improving the system's performance using collected feedback.

[0929] "Application example 2 when combining with an emotional engine"

[0930] (Claim 1)

[0931] A means of automatically collecting product information from information sources,

[0932] A means of integrating the collected product information and storing it in a database,

[0933] A means of obtaining desired conditions from the user,

[0934] A means of filtering product information saved based on desired conditions,

[0935] A means of analyzing user emotions,

[0936] A means of prioritizing the display of products that the user has shown interest in, using emotion analysis tools,

[0937] A method for analyzing filtered product information to calculate a recommendation score,

[0938] A means of presenting the score to the user,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, further comprising means for accepting a user's selection based on presented product information.

[0942] (Claim 3)

[0943] Means for collecting and analyzing user feedback,

[0944] The system according to claim 1, further comprising means for improving the system's performance using collected feedback. [Explanation of Symbols]

[0945] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically collecting environmentally relevant information from information sources, A means for integrating the collected environmental information and storing it in a data storage device, A means of obtaining desired conditions from the user, A means of selecting environmental information stored based on desired conditions, A means of analyzing selected information and calculating an evaluation score, A means of analyzing requirements and assessing risks, A means of presenting the evaluated score to the user, A system that includes this.

2. The system according to claim 1, further comprising means for accepting a user's selection based on presented environmental information.

3. A means of collecting and analyzing user feedback, The system according to claim 1, further comprising means for improving the system's performance using collected feedback.

Images