System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting basic building information, maintenance history, and building material characteristics; means for analyzing the collected information by extracting features using a generative AI model; means for creating an optimum maintenance schedule based on the analysis result and notifying a user of the maintenance schedule; and means for collecting feedback information from the user who has received the notification and updating the database.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Because creating a home maintenance plan is extremely complex and time-consuming, many homeowners and managers are unable to perform appropriate maintenance. It is particularly difficult to perform appropriate maintenance according to the characteristics of building materials and the environment in which they are used, which is likely to have a negative impact on the safety and lifespan of the building. Furthermore, manually managing maintenance history is inefficient and carries the risk of making decisions based on incomplete information. The purpose of the present invention is to solve these problems and ensure the safety and long lifespan of homes. [Means for solving the problem]

[0005] The present invention supports the planning and implementation of appropriate home maintenance through a system that includes: a means for collecting basic information about a home, its maintenance history, and building material characteristic data; a means for a generative AI model to extract and analyze features based on the collected data; a means for creating an optimal maintenance schedule based on the analysis results and notifying the user; and a means for collecting feedback data from users who have received the notification and updating the database. The generative AI model can predict the home's deterioration pattern and lifespan and identify the optimal maintenance period. Furthermore, if the collected data is insufficient or contains abnormal values, the system can detect this and notify the user, allowing the missing data or abnormal values ​​to be filled in. This allows users to efficiently obtain an accurate maintenance schedule and ensure the safety and long lifespan of their home.

[0006] "Basic information about a house" refers to basic information about the house, such as the building's location, year of construction, structure, blueprints, number of residents, and purpose of use.

[0007] "Maintenance history" refers to past records of home repairs and maintenance management, and specifically includes information on the date of maintenance, the work performed, the building materials used, and the contractor in charge.

[0008] "Building material characteristic data" is detailed information about the type, manufacturer, model number, quality, strength, durability, resistance to environmental conditions, and maintenance needs of materials used in the construction of a home.

[0009] A "generative AI model" is an algorithm or learning model that applies artificial intelligence technology to optimize home maintenance plans.

[0010] "Means for extracting and analyzing features" refers to identifying important features from the basic information about the house, maintenance history, and characteristic data of building materials stored in the database, and then conducting data analysis based on these.

[0011] "Means for creating an optimal maintenance schedule" means designing a schedule that includes the appropriate maintenance timing and content for each part of the house based on the analysis results of the generative AI model.

[0012] "Means of notifying users" refers to the method used to communicate the created maintenance schedule to users, specifically using communication methods such as email, in-app messages, and SMS.

[0013] The "means for collecting feedback data and updating the database" refers to receiving maintenance results and new information from users and reflecting them in the database to keep it up to date.

[0014] "Deterioration patterns and lifespan predictions" are the results of analysis that predict the future progression of deterioration and when repairs will be required based on the usage and environmental conditions of building materials and structures. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notification.

[0037] 1. Data collection and capture

[0038] server

[0039] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This can be a web app or a mobile app. The server provides forms and options for users to enter this information and stores the entered data in a database. The stored data is pre-processed to ensure standardization and consistency.

[0040] User

[0041] The user enters basic information about the house (year of construction, address, structure, etc.) and past maintenance history (date, time, contents, materials used, etc.) into the system. The user also enters characteristic data of the building materials used (manufacturer, model number, quality, etc.). The data entered by the user is sent to the server.

[0042] 2. Analyzing the data and applying the model

[0043] server

[0044] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[0045] 3. Creating a proposal and notifying users

[0046] server

[0047] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The created schedule is notified to the user. Notification methods include email, in-app message, and SMS.

[0048] User

[0049] The user can check the notified maintenance schedule and prepare for the next maintenance to be performed. Based on the schedule, they can gather the necessary tools and materials or call in a specialist. They can also provide feedback and new information to the server, which allows the system to reanalyze and update the database based on the latest information.

[0050] 4. Regular follow-up

[0051] server

[0052] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at the appropriate time. Based on the periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0053] Specific examples

[0054] Example 1: Collecting Data

[0055] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[0056] Example 2: Analyzing Data

[0057] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[0058] Example 3: Notifications and feedback

[0059] The server notifies Yamada of the next scheduled maintenance date: "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system.

[0060] In this way, collaboration between the server, generating AI, and user can assist in creating optimal maintenance plans for homes, ensuring their safety and long lifespan.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The server provides an interface for collecting information about the home, allowing users to enter the information through a web app or mobile app.

[0064] Step 2:

[0065] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[0066] Step 3:

[0067] The server receives the data entered by the user and stores it in a database, where it is pre-processed to ensure standardization and consistency.

[0068] Step 4:

[0069] The server feeds the collected data into the generative AI model, cleaning and formatting the data to check for missing data or outliers.

[0070] Step 5:

[0071] The generative AI extracts features based on the data provided and analyzes the home's deterioration patterns and lifespan predictions.

[0072] Step 6:

[0073] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[0074] Step 7:

[0075] The server notifies the user of the created maintenance schedule via email, in-app message, SMS, etc.

[0076] Step 8:

[0077] The user checks the received maintenance schedule and prepares for the next maintenance, and if necessary, sends questions or feedback to the server through the interface.

[0078] Step 9:

[0079] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[0080] Step 10:

[0081] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at an appropriate time.

[0082] Step 11:

[0083] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] In home maintenance and management, it is difficult to determine the appropriate timing for maintenance, and neglecting it leads to further deterioration of the home and higher repair costs. Furthermore, if maintenance history and data on building material characteristics are insufficient, it is difficult to accurately predict deterioration and create a maintenance schedule. This presents a challenge in ensuring the safety and long life of homes.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes means for collecting basic information about the home, maintenance history, and property data of building materials, means for saving the data entered by the user in a database, and means for standardizing and preprocessing the saved data, thereby maintaining the consistency of the collected data and enabling accurate deterioration prediction and the creation of an optimal maintenance schedule.

[0089] "Basic information about the home" refers to basic data such as the year the home was built, its address, and its structure.

[0090] "Maintenance history" refers to records of past repairs and maintenance carried out on a home, including the date, time, details, and materials used.

[0091] "Building material characteristic data" refers to information such as the manufacturer, model number, and material of the building materials used in the home.

[0092] A "generative AI model" refers to an artificial intelligence model that extracts features from collected data and performs analysis.

[0093] "Means for feature extraction and analysis" refers to the process of using generative AI models to extract useful information from collected data and then analyzing that information.

[0094] "Means for creating an optimal maintenance schedule and notifying the user" refers to the process of creating a maintenance plan based on the analysis results and notifying the user of the plan.

[0095] "Means for collecting feedback data and updating the database" refers to the process of collecting user opinions and new data and reflecting them in the database.

[0096] "Means for determining deterioration patterns and predictions" refers to the process of predicting the degree of deterioration of a home based on collected data and identifying when future maintenance will be required.

[0097] "Means for detecting missing data or abnormal values ​​and notifying users to supplement the missing data or abnormal values" refers to the process of informing users when there are gaps or abnormalities in the collected data and having the users provide additional data.

[0098] "Means for sending periodic reminders" refers to a process for sending notifications to users when the next maintenance date and time is approaching.

[0099] "Means for updating the generative AI model" refers to the process of retraining the generative AI model based on feedback data to improve its analytical accuracy.

[0100] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. The system is composed mainly of a server, terminals, and users, and their cooperation ensures the safety and long life of the home.

[0101] Data collection and ingestion

[0102] server

[0103] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. Specifically, it will have web and mobile apps developed using React Native and Flutter. Forms and drop-down menus will be included to make it easy for users to enter information.

[0104] User

[0105] Using a web or mobile app, users input basic information about their home (year of construction, address, structure, etc.), maintenance history (date, time, details, materials used, etc.), and building material characteristics data (manufacturer, model number, material, etc.). This data is then sent from the device to the server.

[0106] server

[0107] The server stores the transmitted data in a database using an RDBMS such as MySQL or PostgreSQL. The stored data is standardized using tools such as Pandas.

[0108] Analyzing the data and applying the model

[0109] server

[0110] The server applies a generative AI model, built with TensorFlow or PyTorch, to the collected data, cleaning and shaping the data, and detecting missing values ​​and outliers.

[0111] Generative AI Models

[0112] The generative AI model predicts the deterioration patterns and lifespan of a home. For example, it analyzes the deterioration pattern of a roof based on past maintenance history and predicts when the next maintenance is due.

[0113] server

[0114] The server stores the analysis results in a database, and if missing data or abnormal values ​​are detected, the server notifies the user.

[0115] Creating proposals and notifying users

[0116] server

[0117] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model, which includes specific maintenance items and their recommended timing.

[0118] server

[0119] The server allows the user to select a notification method (email, in-app message, SMS, etc.) and notifies the user of the maintenance schedule based on the selection.

[0120] Regular follow-up

[0121] server

[0122] The server periodically sends reminders to users of upcoming maintenance, allowing them to perform the maintenance at the appropriate time.

[0123] server

[0124] The server collects feedback data from users and updates the database. Based on the feedback data, the generative AI model is updated to improve analysis accuracy.

[0125] Specific examples

[0126] Example 1: Collecting Data

[0127] Users access the app using their smartphones and enter basic information about their home (year built: 2010, location: urban area, structure: wooden). They also enter that the roof was repaired in 2016. This information is sent to the server and stored in a database.

[0128] Example 2: Analyzing Data

[0129] The server runs a generative AI model based on the user's home data. The generative AI analyzes the roof's deterioration pattern and predicts that the next repair will be required in June 2023.

[0130] Example 3: Notifications and feedback

[0131] The server sends a notification to the user stating, "We recommend that the next roof inspection and repair be performed in June 2023." The user receives this notification, prepares for the maintenance, and after actually performing the maintenance, feeds the results back into the system. The system then reanalyzes the feedback and updates the database with the latest information.

[0132] Prompt Sentence Examples

[0133] "You enter your home's building materials and past maintenance history. We then run a generative AI model to analyze your home's deterioration patterns and identify predicted maintenance needs."

[0134] By implementing this invention, the maintenance and management of a house can be carried out efficiently, and its safety and long life can be ensured.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1: Collect and ingest data

[0137] In step 1, the server provides a web app or mobile app for collecting housing information. The user enters basic information about the house (year of construction, address, structure, etc.), maintenance history (date and time, contents, materials used, etc.), and building material characteristic data (manufacturer, model number, quality, etc.) into these interfaces. The entered data is sent from the terminal to the server. The server saves the sent data in a database. The saved data is standardized using tools such as Pandas. The input is the house information, maintenance history, and building material characteristic data from the user, and the output is the data saved in the database after standardization processing.

[0138] Step 2: Analyze the data and apply the model

[0139] In step 2, the server applies the generative AI model to the collected data. The generative AI model estimates the deterioration pattern and predicts the lifespan. The server cleans the data and removes missing values ​​and outliers. Based on this, the generative AI model estimates the deterioration pattern of the house and makes a prediction. These analysis results are then saved back into the database. The inputs are the collected data and the generative AI model, and the output is the analysis results.

[0140] Step 3: Create a proposal and notify users

[0141] In step 3, the server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and recommended times. Next, the server sends a prompt to the user to select a notification method. After the user selects a notification method (email, in-app message, SMS, etc.), the server notifies the user of the maintenance schedule based on this selection. The input is the analysis results and the user's selection of the notification method, and the output is a notification of the maintenance schedule.

[0142] Step 4: Regular follow-up

[0143] In step 4, the server periodically sends the user a reminder for the next maintenance. It collects feedback data from users and updates the database. The generative AI model retrains based on this feedback data to improve its analysis accuracy. The inputs are the output results of the generative AI model and feedback data from users, and the outputs are an updated database and the latest maintenance schedule.

[0144] Through the above processing steps, the server, terminals, and users work together to realize a system that supports optimal home maintenance planning and ensures the safety and long life of homes.

[0145] (Application example 1)

[0146] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0147] Homes and factory facilities are used for long periods of time, but their upkeep and maintenance take time and effort, requiring efficient schedule management. Furthermore, if maintenance is not performed at the appropriate time, it can lead to a decrease in safety and a shortened lifespan. However, current maintenance management systems have difficulty collecting and analyzing data individually, requiring a great deal of effort. Furthermore, incompleteness in the collected data and the presence of abnormal values ​​can reduce the reliability of the system. To solve these issues, there is a need for technology that can comprehensively manage basic information, maintenance history, and characteristic data for homes and factory facilities, and efficiently generate maintenance schedules.

[0148] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0149] In this invention, the server includes means for collecting basic information, maintenance history, and property data of building materials for homes, means for collecting basic information, maintenance history, and property data of factory equipment, means for a generative AI model to extract and analyze features based on the collected data, means for creating an optimal maintenance schedule based on the analysis results and notifying the user, and means for collecting feedback data from users who have received the notification and updating the database. This enables efficient and accurate maintenance schedule management for homes and factory equipment.

[0150] A "house" is a building constructed using building materials for human habitation.

[0151] "Basic information" refers to basic data such as the structure of the object, the year of installation, the address, and the materials used.

[0152] "Maintenance history" refers to data on the date, time, and content of past repairs and maintenance work, as well as the materials used.

[0153] "Characteristic data" refers to detailed data such as the manufacturer, model number, and material of the building materials and equipment used.

[0154] "Factory equipment" is a general term for machines and devices installed for manufacturing and production activities.

[0155] A "data collection means" is a method or system for inputting, recording, or obtaining information about an object.

[0156] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and perform tasks such as prediction and classification.

[0157] "Means for extracting features and performing analysis" refers to methods or systems that efficiently find relevant information and patterns from collected data and perform analysis based on them.

[0158] The "optimal maintenance period" refers to the most appropriate time to perform maintenance depending on the condition of the equipment and building materials.

[0159] "Feedback data" refers to data provided by the user regarding the results of the performed maintenance and new information.

[0160] A "means for updating a database" is a method or system for adding or modifying new collected data to an existing database.

[0161] A "means for notifying" is a method or system for conveying information to a user.

[0162] This invention relates to a system for generating optimal maintenance schedules for residential and factory facilities. Servers, terminals, and users work together to collect, analyze, and notify data, thereby achieving efficient maintenance management.

[0163] Hardware and Software Configuration

[0164] Hardware

[0165] Server: A server for hosting the database and generative AI model. Examples include AWS EC2 and Google Cloud.

[0166] Client Device: Smartphone, tablet, or head-mounted display (HMD) used for data collection and notification. Examples include iPhone, Android devices, and Microsoft HoloLens.

[0167] software

[0168] Data collection interface: A web or mobile app that allows users to enter basic information about home and industrial facilities, maintenance history, and characteristics of building materials and equipment.

[0169] Generative AI model: An AI model implemented using TensorFlow or PyTorch that analyzes data and predicts maintenance times.

[0170] Notification system: A notification system using a microservices architecture that notifies users about scheduled maintenance via email, SMS, or in-app messages.

[0171] System operation explanation

[0172] 1. Data collection

[0173] The server collects basic information about the home and factory facilities provided by the user, maintenance history, and characteristic data of building materials and equipment. The user enters this data through the application form and sends it to the server.

[0174] 2. Data Analysis

[0175] The server uses generative AI models to extract features and analyze the collected data, cleaning and pre-processing the data, and notifying the user if missing data or outliers are detected.

[0176] 3. Generate a maintenance schedule

[0177] The generative AI model predicts the optimal maintenance period based on the collected data. The server generates a maintenance schedule based on the analysis results and notifies each user.

[0178] 4. Notifying users and gathering feedback

[0179] The server notifies users of the scheduled maintenance. Users receive the notification and prepare for the next maintenance based on the notification. After the actual maintenance is performed, users input their feedback into the system, and the database is updated.

[0180] Specific examples

[0181] For example, a factory manager can collect maintenance data for equipment in a factory and use an AI model to predict when the next maintenance will be required. The AI ​​model analyzes the deterioration pattern of the equipment based on past maintenance history and equipment characteristic data, and determines the optimal maintenance timing. As a result, the factory manager will be notified via a notification system with a specific date and time, such as "The next maintenance for equipment ID: 001 is December 15, 2023."

[0182] Prompt Sentence Examples

[0183] Equipment ID: 001

[0184] Last maintenance date: 2022-06-10

[0185] Materials used: bearings, lubricants

[0186] Current status: Driving

[0187] In this way, an embodiment of a system that realizes efficient and highly accurate maintenance management is constructed.

[0188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0189] Step 1:

[0190] The user inputs basic information about the home or factory facility, maintenance history, and characteristic data of building materials and equipment.

[0191] Input: Basic information about the home or factory facilities, maintenance history, and characteristic data of building materials and equipment

[0192] Specific operation: A user enters information about a home or factory facility into a form via a smartphone or tablet application, such as the year of construction or details of past maintenance work.

[0193] Output: The input data is sent to the server.

[0194] Step 2:

[0195] The server stores the received data in a database.

[0196] Input: Basic information sent by the user, maintenance history, property data of building materials and equipment

[0197] What happens: The server receives the data and stores it in a consistent format in the database. Data normalization and preprocessing are also performed at this stage.

[0198] Output: Saved data

[0199] Step 3:

[0200] The server begins analysis based on the stored data.

[0201] Input: Basic information stored in the database, maintenance history, property data of building materials and equipment

[0202] Data processing: Preprocessing involves cleaning the data and detecting missing data and outliers.

[0203] What it does: The server performs data cleaning to detect missing data and outliers, notifies the user of any detected missing data or outliers, collects user feedback if necessary, and updates the database.

[0204] Output: Cleaned data

[0205] Step 4:

[0206] Analysis is performed using a generative AI model.

[0207] Input: Basic information on cleaning, maintenance history, property data of building materials and equipment

[0208] Data computation: Generative AI models extract features and predict degradation patterns and lifespan.

[0209] How it works: The server analyzes the data using a generative AI model built using TensorFlow and PyTorch. The generative AI model extracts features based on each data point and predicts degradation patterns and lifespan.

[0210] Output: Analysis results (next maintenance time and recommendations)

[0211] Step 5:

[0212] The server creates an optimal maintenance schedule based on the analysis results and notifies the user.

[0213] Input: Analysis results of the generative AI model

[0214] How it works: The server receives the analysis results and creates an optimal maintenance schedule for each facility or home, then notifies the user via email, SMS, or in-app message.

[0215] Output: Maintenance schedule notification sent to user

[0216] Step 6:

[0217] The user receives the notification and enters the feedback data.

[0218] Input: Maintenance schedule notification, feedback data

[0219] Specific operation: The user confirms the notification and starts preparations for the next maintenance. After the actual maintenance is completed, the results are entered as feedback data through the application and sent to the server.

[0220] Output: Feedback data is sent to the server

[0221] Step 7:

[0222] The server updates the database based on the received feedback data.

[0223] Input: Feedback data

[0224] What happens: The server receives the feedback data and updates the database, ensuring that the next analysis is based on the most up-to-date information.

[0225] Output: Updated database

[0226] This enables users, servers, and generative AI models to work together to efficiently manage the maintenance of residential and factory facilities.

[0227] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0228] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and building material characteristics data to generate an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notifications. Furthermore, by combining it with an emotion engine, the system recognizes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[0229] 1. Data collection and capture

[0230] server

[0231] The server provides an interface for collecting information about homes. Users can enter the information through a web app or mobile app. The server receives the basic information about the home (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[0232] User

[0233] The user inputs basic information about the house, its maintenance history, and the characteristics of the building materials through the interface, and the data entered by the user is sent to the server.

[0234] 2. Analyzing the data and applying the model

[0235] server

[0236] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[0237] 3. Creating a proposal and notifying users

[0238] server

[0239] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended times. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, notifies the user with the optimal timing and content. Notification methods include email, in-app messages, and SMS.

[0240] User

[0241] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[0242] 4. Regular follow-up

[0243] server

[0244] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0245] Specific examples

[0246] Example 1: Collecting Data

[0247] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[0248] Example 2: Analyzing Data

[0249] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[0250] Example 3: Notifications and feedback

[0251] The server notifies Yamada of the next scheduled maintenance. "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system. The emotion engine analyzes Yamada's feedback data and recognizes his emotional state. The next notification and advice will be given taking the results into account.

[0252] In this way, collaboration between the server, generative AI, emotion engine, and user can assist in optimal home maintenance planning, ensuring the safety and longevity of the home.

[0253] The processing flow will be explained below.

[0254] Step 1:

[0255] The server provides an interface for collecting housing information, allowing users to enter the information through a web app or mobile app.

[0256] Step 2:

[0257] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[0258] Step 3:

[0259] The server receives the data entered by the user and stores it in a database, where it is standardized and pre-processed for consistency.

[0260] Step 4:

[0261] The server feeds the collected data into a generative AI model, which cleans and shapes the data to detect missing data and outliers.

[0262] Step 5:

[0263] The generative AI extracts features from the data provided, analyzes the deterioration pattern of the home, and predicts its lifespan, predicting the progress of deterioration and when the next maintenance will be required.

[0264] Step 6:

[0265] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[0266] Step 7:

[0267] The server will notify the user of the optimal maintenance schedule via email, in-app message, SMS, etc.

[0268] Step 8:

[0269] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, the user can send questions or feedback to the server through the interface.

[0270] Step 9:

[0271] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[0272] Step 10:

[0273] The server runs an emotion engine that recognizes emotions from user input and feedback data, analyzes the user's emotional state, and adjusts advice and reminders accordingly.

[0274] Step 11:

[0275] The server sends users advice and reminders based on their emotional state, which are tailored to improve their motivation.

[0276] Step 12:

[0277] The server periodically sends reminders to users for the next maintenance appointment, and the emotion engine adjusts the timing and content of the reminders based on the user's latest emotional state.

[0278] Step 13:

[0279] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[0280] Example 2

[0281] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0282] Home maintenance typically requires users to understand the home's past history and current condition, and then perform the maintenance at the appropriate time and with the appropriate content based on that information. However, many homeowners find it difficult to manage this properly, and as a result, maintenance is often neglected. This problem accelerates the deterioration of the home, ultimately leading to the need for serious repairs and shortening the home's lifespan. Furthermore, existing systems have difficulty providing appropriate notifications and feedback that take the user's emotional state into account, which can lead to issues such as reduced user satisfaction and reduced system usage efficiency.

[0283] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the home, maintenance history, and property data of building materials; means for cleaning and shaping the collected data and detecting missing data and outliers; means for applying a generative AI model to the shaped data to extract and analyze features; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state from feedback data and input data using an emotion engine and adjusting the timing and content of the notification; means for collecting feedback data from the user who received the notification and updating the database; and means for periodically sending a reminder for the next maintenance and performing a new analysis using the generative AI model. This enables efficient maintenance that takes the user's emotional state into consideration while ensuring the safety and long life of the home.

[0284] "Basic information about the house" refers to basic data about the house itself, such as the year it was built, its address, and its structure.

[0285] "Maintenance history" is a record of the date, time, content, materials used, etc. of past maintenance work.

[0286] "Characteristic data of building materials" is data that indicates characteristics such as the manufacturer, model number, and material of the building materials used in the house.

[0287] "Means of collection" refers to the mechanism by which a user inputs information through an interface, the server receives it, and stores it in a database.

[0288] A "generative AI model" is an artificial intelligence model that extracts features based on input data and performs analysis.

[0289] "Cleaning and shaping" refers to the process of detecting missing or outliers in data and correcting or modifying them.

[0290] "Means for analysis" refers to the mechanism for extracting and analyzing the characteristics of collected data using a generative AI model.

[0291] The "optimal maintenance schedule" is a schedule that includes specific maintenance items and their recommended timing, proposed based on deterioration patterns and lifespan predictions.

[0292] "Means of notification" refers to the method of communicating the maintenance schedule to users, including email, in-app messages, SMS, etc.

[0293] "Emotion engine" refers to technology that analyzes a user's emotional state from feedback data and input data, and adjusts the timing and content of notifications based on that.

[0294] "Feedback data" refers to data including results reports and opinions provided by users after maintenance has been performed.

[0295] "Means for updating the database" refers to a mechanism for adding or amending collected feedback data to an existing database.

[0296] A "reminder" is a periodic message that notifies the user again of the next scheduled maintenance.

[0297] "New analysis" means that the generative AI model uses regularly collected feedback data to conduct the latest analysis and reflect the results.

[0298] This invention relates to a system that collects information about a home and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging information between a server, terminals, and users, and by analyzing and notifying them. Furthermore, it uses an emotion engine to recognize the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[0299] The server first provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This interface is implemented as a web app or mobile app, through which users can input data. Specifically, the server receives the basic information (year built, address, structure, etc.), maintenance history (date, time, content, materials used, etc.), and the characteristics of building materials (manufacturer, model number, material, etc.) and stores them in a database.

[0300] The collected data is cleaned and shaped by the server. If missing data or outliers are detected, the server automatically sends a notification to the user requesting them to complete or correct them. After cleaning and shaping, the data is applied to the generative AI model.

[0301] The generative AI model uses the formatted data to predict the home's deterioration patterns and lifespan. The model identifies the optimal maintenance period and content for the home and stores the analysis results in a database. Based on the analysis results, the server creates an optimal maintenance schedule and notifies the user. This notification is sent via email, in-app messages, SMS, etc.

[0302] Furthermore, the emotion engine analyzes the user's emotional state from feedback data and input data, and adjusts the timing and content of notifications. This helps users to carry out maintenance at the appropriate time. The user checks the notified schedule and carries out the maintenance. After carrying out the maintenance, the results can be fed back to the system. The server collects this feedback data and updates the database.

[0303] The server also periodically sends reminders to users for upcoming maintenance. The emotion engine adjusts the timing and content of the reminders, allowing users to appropriately prepare for the next maintenance. Based on the periodically collected feedback data, the generative AI model performs new analysis and updates the maintenance schedule accordingly.

[0304] As a concrete example, the following prompt sentences are used when the user inputs house data:

[0305] Prompt Sentence Examples

[0306] Generate a deterioration prediction and an optimal maintenance schedule for a home based on basic information, maintenance history, and building material characteristics data entered by the user. Below are some examples of specific data.

[0307] basic information:

[0308] Construction year: 2010

[0309] Address: Shinjuku-ku, Tokyo

[0310] Structure: wooden

[0311] Maintenance history:

[0312] Date: March 2016

[0313] Content: Roof repair

[0314] Materials used: Material A

[0315] Building material property data:

[0316] Manufacturer: Manufacturer X

[0317] Model number: YZ123

[0318] Material: Cement

[0319] Predict the optimal maintenance timing and content.

[0320] As described above, collaboration between the server, generative AI model, emotion engine, and user can efficiently support home maintenance planning and ensure the safety and long life of homes.

[0321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0322] Step 1:

[0323] User

[0324] Users enter basic information about the home, maintenance history, and characteristic data of building materials using input forms in the web app or mobile app. The data entered includes the year of construction, address, structure, past maintenance dates and times, details, materials used, manufacturer, model number, and quality of building materials. This information is sent to the server by the user manually entering it and pressing the send button. Input: Basic information about the home, maintenance history, characteristic data of building materials. Output: Data sent to the server.

[0325] Step 2:

[0326] server

[0327] The server receives data sent by the user and saves it in the database in real time. Processing performed here includes format checks for input data, confirmation of required fields, and detection of missing data. For example, if the address or year of construction is not entered, an error message is generated. Input: Data sent by the user. Output: Data saved in the database, error message (if necessary).

[0328] Step 3:

[0329] server

[0330] The server cleans and formats the stored data. It detects missing data and outliers and sends a completion request to the user accordingly. For example, if there is missing data, it automatically sends a completion request email saying, "The construction year has not been entered. Please enter it." Input: Stored data. Output: Cleaned and formatted data, completion request email.

[0331] Step 4:

[0332] server

[0333] The server inputs the cleaned and formatted data into a generative AI model, which extracts and analyzes features. The generative AI model predicts the deterioration pattern and lifespan of the home, and identifies the optimal maintenance timing and content. For example, it may predict that "roof repairs will be required in June 2023." Input: Cleaned and formatted data. Output: Deterioration pattern, lifespan prediction, optimal maintenance timing.

[0334] Step 5:

[0335] server

[0336] The server automatically creates an optimal maintenance schedule based on the analysis results of the generative AI model. This schedule includes specific maintenance items and their recommended timing. For example, it may include the content, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Analysis results of the generative AI model. Output: Optimal maintenance schedule.

[0337] Step 6:

[0338] server

[0339] The server uses an emotion engine to analyze the user's emotional state from their feedback data and input data. Based on these results, it adjusts the timing and content of notifications. For example, if past feedback indicates that the user is feeling stressed, it sends a message that takes this into consideration. Input: Feedback data, input data. Output: Emotional state analysis results, adjusted notification content.

[0340] Step 7:

[0341] server

[0342] The server notifies the user of the optimal maintenance schedule via email, in-app message, SMS, etc. For example, it sends a message saying, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Optimal maintenance schedule, adjusted notification content. Output: Notification to the user.

[0343] Step 8:

[0344] User

[0345] The user receives a notification from the server and prepares for maintenance. The user carries out the maintenance according to the notification and feeds back the results to the server through the interface. For example, the user can enter and send information such as "The roof was inspected and repaired in June 2023." Input: Feedback data. Output: Sending results to the server.

[0346] Step 9:

[0347] server

[0348] The server receives feedback data from users and updates the database. The updated data is used for the next analysis and to generate maintenance schedules. Input: Feedback data from users. Output: Updated database.

[0349] Step 10:

[0350] server

[0351] The server periodically sends reminders to users about upcoming maintenance. The timing and content of these reminders are adjusted by the emotion engine. For example, a reminder such as "Don't forget to come for your next scheduled inspection" can be sent. Input: Next maintenance information based on the database. Output: Reminder notification.

[0352] Step 11:

[0353] server

[0354] The server runs the generative AI model again based on the feedback data collected periodically, and performs a new analysis. Based on the analysis results, the maintenance schedule is updated as appropriate. Input: Feedback data. Output: Updated analysis results and maintenance schedule.

[0355] Through the above steps, this system can efficiently support users in planning their home maintenance, ensuring the safety and longevity of their homes.

[0356] (Application example 2)

[0357] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] In recent years, physical store operators have been required to ensure operational efficiency and safety by properly maintaining their store buildings. However, determining the appropriate timing and content of maintenance is difficult, and maintenance work is often postponed depending on the operator's busy schedule or mood. This problem can lead to further deterioration of the building, resulting in large repair costs. There is also a risk that overlooking maintenance could compromise the safety of the store. Therefore, a system that allows physical store operators to plan and carry out maintenance at the appropriate time is needed.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the building, maintenance history, and characteristic data of building materials; means for a generative AI model to extract and analyze features based on the collected data; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state using an emotion engine and providing notifications and advice at appropriate times and with appropriate content; and means for collecting feedback data from users who have received the notifications and updating the database. This enables operators of physical stores to plan and implement optimal maintenance at appropriate times, ensuring the safety and long life of the store.

[0360] "Basic building information" refers to data including basic attributes and information of a building, such as the year of construction, address, and construction structure of the building.

[0361] "Maintenance history" is data that shows records of the date, time, content, materials used, etc. of maintenance work that has been carried out on a building in the past.

[0362] "Building material characteristic data" is data that includes detailed attribute information such as the manufacturer, model number, and quality of various building materials used in a building.

[0363] A "generative AI model" is an artificial intelligence model that extracts features from collected data and predicts building deterioration patterns and lifespans.

[0364] The "emotion engine" is a system that analyzes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content based on that analysis.

[0365] "User" means the person or entity that is the owner or manager of the building and uses the maintenance management system.

[0366] "Database" means an electronic record system for storing collected basic building information, maintenance history, building material characteristic data, and feedback data.

[0367] "Feedback data" refers to information including the results and impressions of the maintenance carried out based on the maintenance schedule notified to the user.

[0368] A "maintenance schedule" is a plan created by a generative AI model that indicates the optimal time and content of building maintenance work.

[0369] "Notification" is a means of communicating generated maintenance schedules and other important information to users.

[0370] This invention relates to a system that collects and analyzes basic information about brick-and-mortar store buildings, maintenance history, and building material characteristic data to generate an optimal maintenance schedule. This system ensures the safety and longevity of stores by exchanging data between servers, terminals, and users, and by analyzing and notifying them. It also combines an emotion engine to recognize the user's emotional state and provide notifications and advice at the appropriate time and with the right content, thereby improving maintenance efficiency and user satisfaction.

[0371] 1. Data collection and capture

[0372] server

[0373] The server provides an interface for collecting building information. Users can input the information through a web app or mobile app. The server receives the basic building information (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[0374] User

[0375] The user inputs basic information about the building, its maintenance history, and the characteristics of the building materials through the interface. The data entered by the user is sent to the server.

[0376] 2. Analyzing the data and applying the model

[0377] server

[0378] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the building's deterioration pattern and lifespan, and identifies the optimal maintenance timing and content. The results of this analysis are stored in a database.

[0379] 3. Creating a proposal and notifying users

[0380] server

[0381] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, provides notifications and advice at the optimal timing and content. Notifications can be sent via email, in-app messages, SMS, etc.

[0382] User

[0383] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[0384] 4. Regular follow-up

[0385] server

[0386] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0387] Specific examples

[0388] Example 1: Collecting Data

[0389] The user enters basic information about his store and its past maintenance history into the system, for example, entering that the walls were repainted in 2020. The server stores this information in a database.

[0390] Example 2: Analyzing Data

[0391] The server runs a generative AI model based on the user's store data, which analyzes the deterioration patterns of the walls and predicts when the next repainting will be necessary.

[0392] Example 3: Notifications and feedback

[0393] The server notifies the user of the next scheduled maintenance. "We recommend that the next wall repainting be done in April 2025." The user makes preparations based on this notification, and after actually carrying out the maintenance, feeds the results back to the system. The emotion engine analyzes the user's feedback data and recognizes his emotional state. The next notification or advice will be given taking the results into consideration.

[0394] Prompt Sentence Examples

[0395] "Create the optimal next maintenance schedule based on your store data and maintenance history. Information to consider is:

[0396] Store construction year, address, structure

[0397] Characteristics of the building materials used (manufacturer, model number, material, etc.)

[0398] Past maintenance history (date, time, contents, materials used, etc.)

[0399] Store manager's emotional state

[0400] Please suggest specific maintenance items and recommended times.

[0401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0402] Step 1:

[0403] Data collection

[0404] Input: Basic information about the building, maintenance history, and property data of building materials

[0405] Processing: Using a web app or mobile app, users input basic building information (e.g., year of construction, address, structure, etc.), past maintenance details (e.g., date and time, details, materials used, etc.), and building material characteristics data (e.g., manufacturer, model number, material, etc.). This input data is sent to the server via the interface.

[0406] Output: The input data is sent to the server and stored in a database.

[0407] Step 2:

[0408] Cleaning and shaping the data

[0409] Input: Basic building information, maintenance history, and building material characteristics data stored on the server

[0410] Processing: The server analyzes the stored data and detects missing data or outliers. If any missing data or outliers are found, the server notifies the user and asks them to complete the data.

[0411] Output: Cleaned and formatted data is generated and stored in a database.

[0412] Step 3:

[0413] Data analysis and feature extraction

[0414] Input: Clean and formatted data

[0415] Processing: The server begins analysis using a generative AI model (e.g., using Python or TensorFlow). The model extracts features from the input data and predicts the building's deterioration pattern and lifespan. This allows appropriate maintenance timing and content to be identified.

[0416] Output: Analysis results are generated and stored in a database.

[0417] Step 4:

[0418] Creating a maintenance schedule

[0419] Input: Analysis results from generative AI model

[0420] Processing: The server creates an optimal maintenance schedule based on the analysis results, which includes specific maintenance items and their recommended times.

[0421] Output: A maintenance schedule is generated and stored in the database.

[0422] Step 5:

[0423] Sentiment analysis with emotion engine

[0424] Input: User feedback data and maintenance history

[0425] Processing: The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's emotional state from their input data and feedback data. Based on this, it optimizes the content and timing of notifications and advice.

[0426] Output: The results of the sentiment analysis are generated and stored in a database.

[0427] Step 6:

[0428] User Notification

[0429] Input: Maintenance schedule, sentiment analysis results

[0430] Processing: The server notifies users of maintenance schedules and advice at appropriate times via email, in-app messages, SMS, etc.

[0431] Output: A notification is sent to the user.

[0432] Step 7:

[0433] Collecting feedback

[0434] Input: Feedback data from users

[0435] Processing: After the user actually performs the maintenance, they provide feedback to the server via the interface, including the results and their impressions. The received feedback data is reanalyzed by the emotion engine and stored in the database.

[0436] Output: The updated feedback data is saved in the database.

[0437] Step 8:

[0438] Sending periodic reminders

[0439] Input: Stored feedback data, maintenance schedule

[0440] Processing: The server periodically sends reminders to users about upcoming maintenance schedules. The timing and content of the notifications are adjusted based on the analysis results of the emotion engine.

[0441] Output: A reminder notification is sent to the user.

[0442] This series of processes enables store operators to plan and implement maintenance efficiently and effectively.

[0443] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0444] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0445] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0446] [Second embodiment]

[0447] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0448] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0449] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0450] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0451] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0453] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0454] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0455] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0456] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0457] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0458] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0459] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notification.

[0460] 1. Data collection and capture

[0461] server

[0462] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This can be a web app or a mobile app. The server provides forms and options for users to enter this information and stores the entered data in a database. The stored data is pre-processed to ensure standardization and consistency.

[0463] User

[0464] The user enters basic information about the house (year of construction, address, structure, etc.) and past maintenance history (date, time, contents, materials used, etc.) into the system. The user also enters characteristic data of the building materials used (manufacturer, model number, quality, etc.). The data entered by the user is sent to the server.

[0465] 2. Analyzing the data and applying the model

[0466] server

[0467] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[0468] 3. Creating a proposal and notifying users

[0469] server

[0470] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The created schedule is notified to the user. Notification methods include email, in-app message, and SMS.

[0471] User

[0472] The user can check the notified maintenance schedule and prepare for the next maintenance to be performed. Based on the schedule, they can gather the necessary tools and materials or call in a specialist. They can also provide feedback and new information to the server, which allows the system to reanalyze and update the database based on the latest information.

[0473] 4. Regular follow-up

[0474] server

[0475] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at the appropriate time. Based on the periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0476] Specific examples

[0477] Example 1: Collecting Data

[0478] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[0479] Example 2: Analyzing Data

[0480] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[0481] Example 3: Notifications and feedback

[0482] The server notifies Yamada of the next scheduled maintenance date: "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system.

[0483] In this way, collaboration between the server, generating AI, and user can assist in creating optimal maintenance plans for homes, ensuring their safety and long lifespan.

[0484] The processing flow will be explained below.

[0485] Step 1:

[0486] The server provides an interface for collecting information about the home, allowing users to enter the information through a web app or mobile app.

[0487] Step 2:

[0488] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[0489] Step 3:

[0490] The server receives the data entered by the user and stores it in a database, where it is pre-processed to ensure standardization and consistency.

[0491] Step 4:

[0492] The server feeds the collected data into the generative AI model, cleaning and formatting the data to check for missing data or outliers.

[0493] Step 5:

[0494] The generative AI extracts features based on the data provided and analyzes the home's deterioration patterns and lifespan predictions.

[0495] Step 6:

[0496] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[0497] Step 7:

[0498] The server notifies the user of the created maintenance schedule via email, in-app message, SMS, etc.

[0499] Step 8:

[0500] The user checks the received maintenance schedule and prepares for the next maintenance, and if necessary, sends questions or feedback to the server through the interface.

[0501] Step 9:

[0502] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[0503] Step 10:

[0504] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at an appropriate time.

[0505] Step 11:

[0506] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[0507] Example 1

[0508] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0509] In home maintenance and management, it is difficult to determine the appropriate timing for maintenance, and neglecting it leads to further deterioration of the home and higher repair costs. Furthermore, if maintenance history and data on building material characteristics are insufficient, it is difficult to accurately predict deterioration and create a maintenance schedule. This presents a challenge in ensuring the safety and long life of homes.

[0510] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0511] In this invention, the server includes means for collecting basic information about the home, maintenance history, and property data of building materials, means for saving the data entered by the user in a database, and means for standardizing and preprocessing the saved data, thereby maintaining the consistency of the collected data and enabling accurate deterioration prediction and the creation of an optimal maintenance schedule.

[0512] "Basic information about the home" refers to basic data such as the year the home was built, its address, and its structure.

[0513] "Maintenance history" refers to records of past repairs and maintenance carried out on a home, including the date, time, details, and materials used.

[0514] "Building material characteristic data" refers to information such as the manufacturer, model number, and material of the building materials used in the home.

[0515] A "generative AI model" refers to an artificial intelligence model that extracts features from collected data and performs analysis.

[0516] "Means for feature extraction and analysis" refers to the process of using generative AI models to extract useful information from collected data and then analyzing that information.

[0517] "Means for creating an optimal maintenance schedule and notifying the user" refers to the process of creating a maintenance plan based on the analysis results and notifying the user of the plan.

[0518] "Means for collecting feedback data and updating the database" refers to the process of collecting user opinions and new data and reflecting them in the database.

[0519] "Means for determining deterioration patterns and predictions" refers to the process of predicting the degree of deterioration of a home based on collected data and identifying when future maintenance will be required.

[0520] "Means for detecting missing data or abnormal values ​​and notifying users to supplement the missing data or abnormal values" refers to the process of informing users when there are gaps or abnormalities in the collected data and having the users provide additional data.

[0521] "Means for sending periodic reminders" refers to a process for sending notifications to users when the next maintenance date and time is approaching.

[0522] "Means for updating the generative AI model" refers to the process of retraining the generative AI model based on feedback data to improve its analytical accuracy.

[0523] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. The system is composed mainly of a server, terminals, and users, and their cooperation ensures the safety and long life of the home.

[0524] Data collection and ingestion

[0525] server

[0526] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. Specifically, it will have web and mobile apps developed using React Native and Flutter. Forms and drop-down menus will be included to make it easy for users to enter information.

[0527] User

[0528] Using a web or mobile app, users input basic information about their home (year of construction, address, structure, etc.), maintenance history (date, time, details, materials used, etc.), and building material characteristics data (manufacturer, model number, material, etc.). This data is then sent from the device to the server.

[0529] server

[0530] The server stores the transmitted data in a database using an RDBMS such as MySQL or PostgreSQL. The stored data is standardized using tools such as Pandas.

[0531] Analyzing the data and applying the model

[0532] server

[0533] The server applies a generative AI model, built with TensorFlow or PyTorch, to the collected data, cleaning and shaping the data, and detecting missing values ​​and outliers.

[0534] Generative AI Models

[0535] The generative AI model predicts the deterioration patterns and lifespan of a home. For example, it analyzes the deterioration pattern of a roof based on past maintenance history and predicts when the next maintenance is due.

[0536] server

[0537] The server stores the analysis results in a database, and if missing data or abnormal values ​​are detected, the server notifies the user.

[0538] Creating proposals and notifying users

[0539] server

[0540] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model, which includes specific maintenance items and their recommended timing.

[0541] server

[0542] The server allows the user to select a notification method (email, in-app message, SMS, etc.) and notifies the user of the maintenance schedule based on the selection.

[0543] Regular follow-up

[0544] server

[0545] The server periodically sends reminders to users of upcoming maintenance, allowing them to perform the maintenance at the appropriate time.

[0546] server

[0547] The server collects feedback data from users and updates the database. Based on the feedback data, the generative AI model is updated to improve analysis accuracy.

[0548] Specific examples

[0549] Example 1: Collecting Data

[0550] Users access the app using their smartphones and enter basic information about their home (year built: 2010, location: urban area, structure: wooden). They also enter that the roof was repaired in 2016. This information is sent to the server and stored in a database.

[0551] Example 2: Analyzing Data

[0552] The server runs a generative AI model based on the user's home data. The generative AI analyzes the roof's deterioration pattern and predicts that the next repair will be required in June 2023.

[0553] Example 3: Notifications and feedback

[0554] The server sends a notification to the user stating, "We recommend that the next roof inspection and repair be performed in June 2023." The user receives this notification, prepares for the maintenance, and after actually performing the maintenance, feeds the results back into the system. The system then reanalyzes the feedback and updates the database with the latest information.

[0555] Prompt Sentence Examples

[0556] "You enter your home's building materials and past maintenance history. We then run a generative AI model to analyze your home's deterioration patterns and identify predicted maintenance needs."

[0557] By implementing this invention, the maintenance and management of a house can be carried out efficiently, and its safety and long life can be ensured.

[0558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0559] Step 1: Collect and ingest data

[0560] In step 1, the server provides a web app or mobile app for collecting housing information. The user enters basic information about the house (year of construction, address, structure, etc.), maintenance history (date and time, contents, materials used, etc.), and building material characteristic data (manufacturer, model number, quality, etc.) into these interfaces. The entered data is sent from the terminal to the server. The server saves the sent data in a database. The saved data is standardized using tools such as Pandas. The input is the house information, maintenance history, and building material characteristic data from the user, and the output is the data saved in the database after standardization processing.

[0561] Step 2: Analyze the data and apply the model

[0562] In step 2, the server applies the generative AI model to the collected data. The generative AI model estimates the deterioration pattern and predicts the lifespan. The server cleans the data and removes missing values ​​and outliers. Based on this, the generative AI model estimates the deterioration pattern of the house and makes a prediction. These analysis results are then saved back into the database. The inputs are the collected data and the generative AI model, and the output is the analysis results.

[0563] Step 3: Create a proposal and notify users

[0564] In step 3, the server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and recommended times. Next, the server sends a prompt to the user to select a notification method. After the user selects a notification method (email, in-app message, SMS, etc.), the server notifies the user of the maintenance schedule based on this selection. The input is the analysis results and the user's selection of the notification method, and the output is a notification of the maintenance schedule.

[0565] Step 4: Regular follow-up

[0566] In step 4, the server periodically sends the user a reminder for the next maintenance. It collects feedback data from users and updates the database. The generative AI model retrains based on this feedback data to improve its analysis accuracy. The inputs are the output results of the generative AI model and feedback data from users, and the outputs are an updated database and the latest maintenance schedule.

[0567] Through the above processing steps, the server, terminals, and users work together to realize a system that supports optimal home maintenance planning and ensures the safety and long life of homes.

[0568] (Application example 1)

[0569] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0570] Homes and factory facilities are used for long periods of time, but their upkeep and maintenance take time and effort, requiring efficient schedule management. Furthermore, if maintenance is not performed at the appropriate time, it can lead to a decrease in safety and a shortened lifespan. However, current maintenance management systems have difficulty collecting and analyzing data individually, requiring a great deal of effort. Furthermore, incompleteness in the collected data and the presence of abnormal values ​​can reduce the reliability of the system. To solve these issues, there is a need for technology that can comprehensively manage basic information, maintenance history, and characteristic data for homes and factory facilities, and efficiently generate maintenance schedules.

[0571] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0572] In this invention, the server includes means for collecting basic information, maintenance history, and property data of building materials for homes, means for collecting basic information, maintenance history, and property data of factory equipment, means for a generative AI model to extract and analyze features based on the collected data, means for creating an optimal maintenance schedule based on the analysis results and notifying the user, and means for collecting feedback data from users who have received the notification and updating the database. This enables efficient and accurate maintenance schedule management for homes and factory equipment.

[0573] A "house" is a building constructed using building materials for human habitation.

[0574] "Basic information" refers to basic data such as the structure of the object, the year of installation, the address, and the materials used.

[0575] "Maintenance history" refers to data on the date, time, and content of past repairs and maintenance work, as well as the materials used.

[0576] "Characteristic data" refers to detailed data such as the manufacturer, model number, and material of the building materials and equipment used.

[0577] "Factory equipment" is a general term for machines and devices installed for manufacturing and production activities.

[0578] A "data collection means" is a method or system for inputting, recording, or obtaining information about an object.

[0579] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and perform tasks such as prediction and classification.

[0580] "Means for extracting features and performing analysis" refers to methods or systems that efficiently find relevant information and patterns from collected data and perform analysis based on them.

[0581] The "optimal maintenance period" refers to the most appropriate time to perform maintenance depending on the condition of the equipment and building materials.

[0582] "Feedback data" refers to data provided by the user regarding the results of the performed maintenance and new information.

[0583] A "means for updating a database" is a method or system for adding or modifying new collected data to an existing database.

[0584] A "means for notifying" is a method or system for conveying information to a user.

[0585] This invention relates to a system for generating optimal maintenance schedules for residential and factory facilities. Servers, terminals, and users work together to collect, analyze, and notify data, thereby achieving efficient maintenance management.

[0586] Hardware and Software Configuration

[0587] Hardware

[0588] Server: A server for hosting the database and generative AI model. Examples include AWS EC2 and Google Cloud.

[0589] Client Device: Smartphone, tablet, or head-mounted display (HMD) used for data collection and notification. Examples include iPhone, Android devices, and Microsoft HoloLens.

[0590] software

[0591] Data collection interface: A web or mobile app that allows users to enter basic information about home and industrial facilities, maintenance history, and characteristics of building materials and equipment.

[0592] Generative AI model: An AI model implemented using TensorFlow or PyTorch that analyzes data and predicts maintenance times.

[0593] Notification system: A notification system using a microservices architecture that notifies users about scheduled maintenance via email, SMS, or in-app messages.

[0594] System operation explanation

[0595] 1. Data collection

[0596] The server collects basic information about the home and factory facilities provided by the user, maintenance history, and characteristic data of building materials and equipment. The user enters this data through the application form and sends it to the server.

[0597] 2. Data Analysis

[0598] The server uses generative AI models to extract features and analyze the collected data, cleaning and pre-processing the data, and notifying the user if missing data or outliers are detected.

[0599] 3. Generate a maintenance schedule

[0600] The generative AI model predicts the optimal maintenance period based on the collected data. The server generates a maintenance schedule based on the analysis results and notifies each user.

[0601] 4. Notifying users and gathering feedback

[0602] The server notifies users of the scheduled maintenance. Users receive the notification and prepare for the next maintenance based on the notification. After the actual maintenance is performed, users input their feedback into the system, and the database is updated.

[0603] Specific examples

[0604] For example, a factory manager can collect maintenance data for equipment in a factory and use an AI model to predict when the next maintenance will be required. The AI ​​model analyzes the deterioration pattern of the equipment based on past maintenance history and equipment characteristic data, and determines the optimal maintenance timing. As a result, the factory manager will be notified via a notification system with a specific date and time, such as "The next maintenance for equipment ID: 001 is December 15, 2023."

[0605] Prompt Sentence Examples

[0606] Equipment ID: 001

[0607] Last maintenance date: 2022-06-10

[0608] Materials used: bearings, lubricants

[0609] Current status: Driving

[0610] In this way, an embodiment of a system that realizes efficient and highly accurate maintenance management is constructed.

[0611] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0612] Step 1:

[0613] The user inputs basic information about the home or factory facility, maintenance history, and characteristic data of building materials and equipment.

[0614] Input: Basic information about the home or factory facilities, maintenance history, and characteristic data of building materials and equipment

[0615] Specific operation: A user enters information about a home or factory facility into a form via a smartphone or tablet application, such as the year of construction or details of past maintenance work.

[0616] Output: The input data is sent to the server.

[0617] Step 2:

[0618] The server stores the received data in a database.

[0619] Input: Basic information sent by the user, maintenance history, property data of building materials and equipment

[0620] What happens: The server receives the data and stores it in a consistent format in the database. Data normalization and preprocessing are also performed at this stage.

[0621] Output: Saved data

[0622] Step 3:

[0623] The server begins analysis based on the stored data.

[0624] Input: Basic information stored in the database, maintenance history, property data of building materials and equipment

[0625] Data processing: Preprocessing involves cleaning the data and detecting missing data and outliers.

[0626] What it does: The server performs data cleaning to detect missing data and outliers, notifies the user of any detected missing data or outliers, collects user feedback if necessary, and updates the database.

[0627] Output: Cleaned data

[0628] Step 4:

[0629] Analysis is performed using a generative AI model.

[0630] Input: Basic information on cleaning, maintenance history, property data of building materials and equipment

[0631] Data computation: Generative AI models extract features and predict degradation patterns and lifespan.

[0632] How it works: The server analyzes the data using a generative AI model built using TensorFlow and PyTorch. The generative AI model extracts features based on each data point and predicts degradation patterns and lifespan.

[0633] Output: Analysis results (next maintenance time and recommendations)

[0634] Step 5:

[0635] The server creates an optimal maintenance schedule based on the analysis results and notifies the user.

[0636] Input: Analysis results of the generative AI model

[0637] How it works: The server receives the analysis results and creates an optimal maintenance schedule for each facility or home, then notifies the user via email, SMS, or in-app message.

[0638] Output: Maintenance schedule notification sent to user

[0639] Step 6:

[0640] The user receives the notification and enters the feedback data.

[0641] Input: Maintenance schedule notification, feedback data

[0642] Specific operation: The user confirms the notification and starts preparations for the next maintenance. After the actual maintenance is completed, the results are entered as feedback data through the application and sent to the server.

[0643] Output: Feedback data is sent to the server

[0644] Step 7:

[0645] The server updates the database based on the received feedback data.

[0646] Input: Feedback data

[0647] What happens: The server receives the feedback data and updates the database, ensuring that the next analysis is based on the most up-to-date information.

[0648] Output: Updated database

[0649] This enables users, servers, and generative AI models to work together to efficiently manage the maintenance of residential and factory facilities.

[0650] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0651] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and building material characteristics data to generate an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notifications. Furthermore, by combining it with an emotion engine, the system recognizes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[0652] 1. Data collection and capture

[0653] server

[0654] The server provides an interface for collecting information about homes. Users can enter the information through a web app or mobile app. The server receives the basic information about the home (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[0655] User

[0656] The user inputs basic information about the house, its maintenance history, and the characteristics of the building materials through the interface, and the data entered by the user is sent to the server.

[0657] 2. Analyzing the data and applying the model

[0658] server

[0659] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[0660] 3. Creating a proposal and notifying users

[0661] server

[0662] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended times. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, notifies the user with the optimal timing and content. Notification methods include email, in-app messages, and SMS.

[0663] User

[0664] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[0665] 4. Regular follow-up

[0666] server

[0667] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0668] Specific examples

[0669] Example 1: Collecting Data

[0670] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[0671] Example 2: Analyzing Data

[0672] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[0673] Example 3: Notifications and feedback

[0674] The server notifies Yamada of the next scheduled maintenance. "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system. The emotion engine analyzes Yamada's feedback data and recognizes his emotional state. The next notification and advice will be given taking the results into account.

[0675] In this way, collaboration between the server, generative AI, emotion engine, and user can assist in optimal home maintenance planning, ensuring the safety and longevity of the home.

[0676] The processing flow will be explained below.

[0677] Step 1:

[0678] The server provides an interface for collecting housing information, allowing users to enter the information through a web app or mobile app.

[0679] Step 2:

[0680] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[0681] Step 3:

[0682] The server receives the data entered by the user and stores it in a database, where it is standardized and pre-processed for consistency.

[0683] Step 4:

[0684] The server feeds the collected data into a generative AI model, which cleans and shapes the data to detect missing data and outliers.

[0685] Step 5:

[0686] The generative AI extracts features from the data provided, analyzes the deterioration pattern of the home, and predicts its lifespan, predicting the progress of deterioration and when the next maintenance will be required.

[0687] Step 6:

[0688] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[0689] Step 7:

[0690] The server will notify the user of the optimal maintenance schedule via email, in-app message, SMS, etc.

[0691] Step 8:

[0692] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, the user can send questions or feedback to the server through the interface.

[0693] Step 9:

[0694] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[0695] Step 10:

[0696] The server runs an emotion engine that recognizes emotions from user input and feedback data, analyzes the user's emotional state, and adjusts advice and reminders accordingly.

[0697] Step 11:

[0698] The server sends users advice and reminders based on their emotional state, which are tailored to improve their motivation.

[0699] Step 12:

[0700] The server periodically sends reminders to users for the next maintenance appointment, and the emotion engine adjusts the timing and content of the reminders based on the user's latest emotional state.

[0701] Step 13:

[0702] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[0703] Example 2

[0704] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0705] Home maintenance typically requires users to understand the home's past history and current condition, and then perform the maintenance at the appropriate time and with the appropriate content based on that information. However, many homeowners find it difficult to manage this properly, and as a result, maintenance is often neglected. This problem accelerates the deterioration of the home, ultimately leading to the need for serious repairs and shortening the home's lifespan. Furthermore, existing systems have difficulty providing appropriate notifications and feedback that take the user's emotional state into account, which can lead to issues such as reduced user satisfaction and reduced system usage efficiency.

[0706] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the home, maintenance history, and property data of building materials; means for cleaning and shaping the collected data and detecting missing data and outliers; means for applying a generative AI model to the shaped data to extract and analyze features; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state from feedback data and input data using an emotion engine and adjusting the timing and content of the notification; means for collecting feedback data from the user who received the notification and updating the database; and means for periodically sending a reminder for the next maintenance and performing a new analysis using the generative AI model. This enables efficient maintenance that takes the user's emotional state into consideration while ensuring the safety and long life of the home.

[0707] "Basic information about the house" refers to basic data about the house itself, such as the year it was built, its address, and its structure.

[0708] "Maintenance history" is a record of the date, time, content, materials used, etc. of past maintenance work.

[0709] "Characteristic data of building materials" is data that indicates characteristics such as the manufacturer, model number, and material of the building materials used in the house.

[0710] "Means of collection" refers to the mechanism by which a user inputs information through an interface, the server receives it, and stores it in a database.

[0711] A "generative AI model" is an artificial intelligence model that extracts features based on input data and performs analysis.

[0712] "Cleaning and shaping" refers to the process of detecting missing or outliers in data and correcting or modifying them.

[0713] "Means for analysis" refers to the mechanism for extracting and analyzing the characteristics of collected data using a generative AI model.

[0714] The "optimal maintenance schedule" is a schedule that includes specific maintenance items and their recommended timing, proposed based on deterioration patterns and lifespan predictions.

[0715] "Means of notification" refers to the method of communicating the maintenance schedule to users, including email, in-app messages, SMS, etc.

[0716] "Emotion engine" refers to technology that analyzes a user's emotional state from feedback data and input data, and adjusts the timing and content of notifications based on that.

[0717] "Feedback data" refers to data including results reports and opinions provided by users after maintenance has been performed.

[0718] "Means for updating the database" refers to a mechanism for adding or amending collected feedback data to an existing database.

[0719] A "reminder" is a periodic message that notifies the user again of the next scheduled maintenance.

[0720] "New analysis" means that the generative AI model uses regularly collected feedback data to conduct the latest analysis and reflect the results.

[0721] This invention relates to a system that collects information about a home and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging information between a server, terminals, and users, and by analyzing and notifying them. Furthermore, it uses an emotion engine to recognize the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[0722] The server first provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This interface is implemented as a web app or mobile app, through which users can input data. Specifically, the server receives the basic information (year built, address, structure, etc.), maintenance history (date, time, content, materials used, etc.), and the characteristics of building materials (manufacturer, model number, material, etc.) and stores them in a database.

[0723] The collected data is cleaned and shaped by the server. If missing data or outliers are detected, the server automatically sends a notification to the user requesting them to complete or correct them. After cleaning and shaping, the data is applied to the generative AI model.

[0724] The generative AI model uses the formatted data to predict the home's deterioration patterns and lifespan. The model identifies the optimal maintenance period and content for the home and stores the analysis results in a database. Based on the analysis results, the server creates an optimal maintenance schedule and notifies the user. This notification is sent via email, in-app messages, SMS, etc.

[0725] Furthermore, the emotion engine analyzes the user's emotional state from feedback data and input data, and adjusts the timing and content of notifications. This helps users to carry out maintenance at the appropriate time. The user checks the notified schedule and carries out the maintenance. After carrying out the maintenance, the results can be fed back to the system. The server collects this feedback data and updates the database.

[0726] The server also periodically sends reminders to users for upcoming maintenance. The emotion engine adjusts the timing and content of the reminders, allowing users to appropriately prepare for the next maintenance. Based on the periodically collected feedback data, the generative AI model performs new analysis and updates the maintenance schedule accordingly.

[0727] As a concrete example, the following prompt sentences are used when the user inputs house data:

[0728] Prompt Sentence Examples

[0729] Generate a deterioration prediction and an optimal maintenance schedule for a home based on basic information, maintenance history, and building material characteristics data entered by the user. Below are some examples of specific data.

[0730] basic information:

[0731] Construction year: 2010

[0732] Address: Shinjuku-ku, Tokyo

[0733] Structure: wooden

[0734] Maintenance history:

[0735] Date: March 2016

[0736] Content: Roof repair

[0737] Materials used: Material A

[0738] Building material property data:

[0739] Manufacturer: Manufacturer X

[0740] Model number: YZ123

[0741] Material: Cement

[0742] Predict the optimal maintenance timing and content.

[0743] As described above, collaboration between the server, generative AI model, emotion engine, and user can efficiently support home maintenance planning and ensure the safety and long life of homes.

[0744] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0745] Step 1:

[0746] User

[0747] Users enter basic information about the home, maintenance history, and characteristic data of building materials using input forms in the web app or mobile app. The data entered includes the year of construction, address, structure, past maintenance dates and times, details, materials used, manufacturer, model number, and quality of building materials. This information is sent to the server by the user manually entering it and pressing the send button. Input: Basic information about the home, maintenance history, characteristic data of building materials. Output: Data sent to the server.

[0748] Step 2:

[0749] server

[0750] The server receives data sent by the user and saves it in the database in real time. Processing performed here includes format checks for input data, confirmation of required fields, and detection of missing data. For example, if the address or year of construction is not entered, an error message is generated. Input: Data sent by the user. Output: Data saved in the database, error message (if necessary).

[0751] Step 3:

[0752] server

[0753] The server cleans and formats the stored data. It detects missing data and outliers and sends a completion request to the user accordingly. For example, if there is missing data, it automatically sends a completion request email saying, "The construction year has not been entered. Please enter it." Input: Stored data. Output: Cleaned and formatted data, completion request email.

[0754] Step 4:

[0755] server

[0756] The server inputs the cleaned and formatted data into a generative AI model, which extracts and analyzes features. The generative AI model predicts the deterioration pattern and lifespan of the home, and identifies the optimal maintenance timing and content. For example, it may predict that "roof repairs will be required in June 2023." Input: Cleaned and formatted data. Output: Deterioration pattern, lifespan prediction, optimal maintenance timing.

[0757] Step 5:

[0758] server

[0759] The server automatically creates an optimal maintenance schedule based on the analysis results of the generative AI model. This schedule includes specific maintenance items and their recommended timing. For example, it may include the content, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Analysis results of the generative AI model. Output: Optimal maintenance schedule.

[0760] Step 6:

[0761] server

[0762] The server uses an emotion engine to analyze the user's emotional state from their feedback data and input data. Based on these results, it adjusts the timing and content of notifications. For example, if past feedback indicates that the user is feeling stressed, it sends a message that takes this into consideration. Input: Feedback data, input data. Output: Emotional state analysis results, adjusted notification content.

[0763] Step 7:

[0764] server

[0765] The server notifies the user of the optimal maintenance schedule via email, in-app message, SMS, etc. For example, it sends a message saying, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Optimal maintenance schedule, adjusted notification content. Output: Notification to the user.

[0766] Step 8:

[0767] User

[0768] The user receives a notification from the server and prepares for maintenance. The user carries out the maintenance according to the notification and feeds back the results to the server through the interface. For example, the user can enter and send information such as "The roof was inspected and repaired in June 2023." Input: Feedback data. Output: Sending results to the server.

[0769] Step 9:

[0770] server

[0771] The server receives feedback data from users and updates the database. The updated data is used for the next analysis and to generate maintenance schedules. Input: Feedback data from users. Output: Updated database.

[0772] Step 10:

[0773] server

[0774] The server periodically sends reminders to users about upcoming maintenance. The timing and content of these reminders are adjusted by the emotion engine. For example, a reminder such as "Don't forget to come for your next scheduled inspection" can be sent. Input: Next maintenance information based on the database. Output: Reminder notification.

[0775] Step 11:

[0776] server

[0777] The server runs the generative AI model again based on the feedback data collected periodically, and performs a new analysis. Based on the analysis results, the maintenance schedule is updated as appropriate. Input: Feedback data. Output: Updated analysis results and maintenance schedule.

[0778] Through the above steps, this system can efficiently support users in planning their home maintenance, ensuring the safety and longevity of their homes.

[0779] (Application example 2)

[0780] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0781] In recent years, physical store operators have been required to ensure operational efficiency and safety by properly maintaining their store buildings. However, determining the appropriate timing and content of maintenance is difficult, and maintenance work is often postponed depending on the operator's busy schedule or mood. This problem can lead to further deterioration of the building, resulting in large repair costs. There is also a risk that overlooking maintenance could compromise the safety of the store. Therefore, a system that allows physical store operators to plan and carry out maintenance at the appropriate time is needed.

[0782] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the building, maintenance history, and characteristic data of building materials; means for a generative AI model to extract and analyze features based on the collected data; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state using an emotion engine and providing notifications and advice at appropriate times and with appropriate content; and means for collecting feedback data from users who have received the notifications and updating the database. This enables operators of physical stores to plan and implement optimal maintenance at appropriate times, ensuring the safety and long life of the store.

[0783] "Basic building information" refers to data including basic attributes and information of a building, such as the year of construction, address, and construction structure of the building.

[0784] "Maintenance history" is data that shows records of the date, time, content, materials used, etc. of maintenance work that has been carried out on a building in the past.

[0785] "Building material characteristic data" is data that includes detailed attribute information such as the manufacturer, model number, and quality of various building materials used in a building.

[0786] A "generative AI model" is an artificial intelligence model that extracts features from collected data and predicts building deterioration patterns and lifespans.

[0787] The "emotion engine" is a system that analyzes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content based on that analysis.

[0788] "User" means the person or entity that is the owner or manager of the building and uses the maintenance management system.

[0789] "Database" means an electronic record system for storing collected basic building information, maintenance history, building material characteristic data, and feedback data.

[0790] "Feedback data" refers to information including the results and impressions of the maintenance carried out based on the maintenance schedule notified to the user.

[0791] A "maintenance schedule" is a plan created by a generative AI model that indicates the optimal time and content of building maintenance work.

[0792] "Notification" is a means of communicating generated maintenance schedules and other important information to users.

[0793] This invention relates to a system that collects and analyzes basic information about brick-and-mortar store buildings, maintenance history, and building material characteristic data to generate an optimal maintenance schedule. This system ensures the safety and longevity of stores by exchanging data between servers, terminals, and users, and by analyzing and notifying them. It also combines an emotion engine to recognize the user's emotional state and provide notifications and advice at the appropriate time and with the right content, thereby improving maintenance efficiency and user satisfaction.

[0794] 1. Data collection and capture

[0795] server

[0796] The server provides an interface for collecting building information. Users can input the information through a web app or mobile app. The server receives the basic building information (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[0797] User

[0798] The user inputs basic information about the building, its maintenance history, and the characteristics of the building materials through the interface. The data entered by the user is sent to the server.

[0799] 2. Analyzing the data and applying the model

[0800] server

[0801] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the building's deterioration pattern and lifespan, and identifies the optimal maintenance timing and content. The results of this analysis are stored in a database.

[0802] 3. Creating a proposal and notifying users

[0803] server

[0804] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, provides notifications and advice at the optimal timing and content. Notifications can be sent via email, in-app messages, SMS, etc.

[0805] User

[0806] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[0807] 4. Regular follow-up

[0808] server

[0809] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0810] Specific examples

[0811] Example 1: Collecting Data

[0812] The user enters basic information about his store and its past maintenance history into the system, for example, entering that the walls were repainted in 2020. The server stores this information in a database.

[0813] Example 2: Analyzing Data

[0814] The server runs a generative AI model based on the user's store data, which analyzes the deterioration patterns of the walls and predicts when the next repainting will be necessary.

[0815] Example 3: Notifications and feedback

[0816] The server notifies the user of the next scheduled maintenance. "We recommend that the next wall repainting be done in April 2025." The user makes preparations based on this notification, and after actually carrying out the maintenance, feeds the results back to the system. The emotion engine analyzes the user's feedback data and recognizes his emotional state. The next notification or advice will be given taking the results into consideration.

[0817] Prompt Sentence Examples

[0818] "Create the optimal next maintenance schedule based on your store data and maintenance history. Information to consider is:

[0819] Store construction year, address, structure

[0820] Characteristics of the building materials used (manufacturer, model number, material, etc.)

[0821] Past maintenance history (date, time, contents, materials used, etc.)

[0822] Store manager's emotional state

[0823] Please suggest specific maintenance items and recommended times.

[0824] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0825] Step 1:

[0826] Data collection

[0827] Input: Basic information about the building, maintenance history, and property data of building materials

[0828] Processing: Using a web app or mobile app, users input basic building information (e.g., year of construction, address, structure, etc.), past maintenance details (e.g., date and time, details, materials used, etc.), and building material characteristics data (e.g., manufacturer, model number, material, etc.). This input data is sent to the server via the interface.

[0829] Output: The input data is sent to the server and stored in a database.

[0830] Step 2:

[0831] Cleaning and shaping the data

[0832] Input: Basic building information, maintenance history, and building material characteristics data stored on the server

[0833] Processing: The server analyzes the stored data and detects missing data or outliers. If any missing data or outliers are found, the server notifies the user and asks them to complete the data.

[0834] Output: Cleaned and formatted data is generated and stored in a database.

[0835] Step 3:

[0836] Data analysis and feature extraction

[0837] Input: Clean and formatted data

[0838] Processing: The server begins analysis using a generative AI model (e.g., using Python or TensorFlow). The model extracts features from the input data and predicts the building's deterioration pattern and lifespan. This allows appropriate maintenance timing and content to be identified.

[0839] Output: Analysis results are generated and stored in a database.

[0840] Step 4:

[0841] Creating a maintenance schedule

[0842] Input: Analysis results from generative AI model

[0843] Processing: The server creates an optimal maintenance schedule based on the analysis results, which includes specific maintenance items and their recommended times.

[0844] Output: A maintenance schedule is generated and stored in the database.

[0845] Step 5:

[0846] Sentiment analysis with emotion engine

[0847] Input: User feedback data and maintenance history

[0848] Processing: The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's emotional state from their input data and feedback data. Based on this, it optimizes the content and timing of notifications and advice.

[0849] Output: The results of the sentiment analysis are generated and stored in a database.

[0850] Step 6:

[0851] User Notification

[0852] Input: Maintenance schedule, sentiment analysis results

[0853] Processing: The server notifies users of maintenance schedules and advice at appropriate times via email, in-app messages, SMS, etc.

[0854] Output: A notification is sent to the user.

[0855] Step 7:

[0856] Collecting feedback

[0857] Input: Feedback data from users

[0858] Processing: After the user actually performs the maintenance, they provide feedback to the server via the interface, including the results and their impressions. The received feedback data is reanalyzed by the emotion engine and stored in the database.

[0859] Output: The updated feedback data is saved in the database.

[0860] Step 8:

[0861] Sending periodic reminders

[0862] Input: Stored feedback data, maintenance schedule

[0863] Processing: The server periodically sends reminders to users about upcoming maintenance schedules. The timing and content of the notifications are adjusted based on the analysis results of the emotion engine.

[0864] Output: A reminder notification is sent to the user.

[0865] This series of processes enables store operators to plan and implement maintenance efficiently and effectively.

[0866] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0867] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0868] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0869] [Third embodiment]

[0870] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0871] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0872] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0873] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0874] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0875] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0876] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0877] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0878] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0879] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0880] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0881] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0882] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notification.

[0883] 1. Data collection and capture

[0884] server

[0885] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This can be a web app or a mobile app. The server provides forms and options for users to enter this information and stores the entered data in a database. The stored data is pre-processed to ensure standardization and consistency.

[0886] User

[0887] The user enters basic information about the house (year of construction, address, structure, etc.) and past maintenance history (date, time, contents, materials used, etc.) into the system. The user also enters characteristic data of the building materials used (manufacturer, model number, quality, etc.). The data entered by the user is sent to the server.

[0888] 2. Analyzing the data and applying the model

[0889] server

[0890] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[0891] 3. Creating a proposal and notifying users

[0892] server

[0893] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The created schedule is notified to the user. Notification methods include email, in-app message, and SMS.

[0894] User

[0895] The user can check the notified maintenance schedule and prepare for the next maintenance to be performed. Based on the schedule, they can gather the necessary tools and materials or call in a specialist. They can also provide feedback and new information to the server, which allows the system to reanalyze and update the database based on the latest information.

[0896] 4. Regular follow-up

[0897] server

[0898] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at the appropriate time. Based on the periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[0899] Specific examples

[0900] Example 1: Collecting Data

[0901] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[0902] Example 2: Analyzing Data

[0903] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[0904] Example 3: Notifications and feedback

[0905] The server notifies Yamada of the next scheduled maintenance date: "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system.

[0906] In this way, collaboration between the server, generating AI, and user can assist in creating optimal maintenance plans for homes, ensuring their safety and long lifespan.

[0907] The processing flow will be explained below.

[0908] Step 1:

[0909] The server provides an interface for collecting information about the home, allowing users to enter the information through a web app or mobile app.

[0910] Step 2:

[0911] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[0912] Step 3:

[0913] The server receives the data entered by the user and stores it in a database, where it is pre-processed to ensure standardization and consistency.

[0914] Step 4:

[0915] The server feeds the collected data into the generative AI model, cleaning and formatting the data to check for missing data or outliers.

[0916] Step 5:

[0917] The generative AI extracts features based on the data provided and analyzes the home's deterioration patterns and lifespan predictions.

[0918] Step 6:

[0919] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[0920] Step 7:

[0921] The server notifies the user of the created maintenance schedule via email, in-app message, SMS, etc.

[0922] Step 8:

[0923] The user checks the received maintenance schedule and prepares for the next maintenance, and if necessary, sends questions or feedback to the server through the interface.

[0924] Step 9:

[0925] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[0926] Step 10:

[0927] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at an appropriate time.

[0928] Step 11:

[0929] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[0930] Example 1

[0931] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0932] In home maintenance and management, it is difficult to determine the appropriate timing for maintenance, and neglecting it leads to further deterioration of the home and higher repair costs. Furthermore, if maintenance history and data on building material characteristics are insufficient, it is difficult to accurately predict deterioration and create a maintenance schedule. This presents a challenge in ensuring the safety and long life of homes.

[0933] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0934] In this invention, the server includes means for collecting basic information about the home, maintenance history, and property data of building materials, means for saving the data entered by the user in a database, and means for standardizing and preprocessing the saved data, thereby maintaining the consistency of the collected data and enabling accurate deterioration prediction and the creation of an optimal maintenance schedule.

[0935] "Basic information about the home" refers to basic data such as the year the home was built, its address, and its structure.

[0936] "Maintenance history" refers to records of past repairs and maintenance carried out on a home, including the date, time, details, and materials used.

[0937] "Building material characteristic data" refers to information such as the manufacturer, model number, and material of the building materials used in the home.

[0938] A "generative AI model" refers to an artificial intelligence model that extracts features from collected data and performs analysis.

[0939] "Means for feature extraction and analysis" refers to the process of using generative AI models to extract useful information from collected data and then analyzing that information.

[0940] "Means for creating an optimal maintenance schedule and notifying the user" refers to the process of creating a maintenance plan based on the analysis results and notifying the user of the plan.

[0941] "Means for collecting feedback data and updating the database" refers to the process of collecting user opinions and new data and reflecting them in the database.

[0942] "Means for determining deterioration patterns and predictions" refers to the process of predicting the degree of deterioration of a home based on collected data and identifying when future maintenance will be required.

[0943] "Means for detecting missing data or abnormal values ​​and notifying users to supplement the missing data or abnormal values" refers to the process of informing users when there are gaps or abnormalities in the collected data and having the users provide additional data.

[0944] "Means for sending periodic reminders" refers to a process for sending notifications to users when the next maintenance date and time is approaching.

[0945] "Means for updating the generative AI model" refers to the process of retraining the generative AI model based on feedback data to improve its analytical accuracy.

[0946] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. The system is composed mainly of a server, terminals, and users, and their cooperation ensures the safety and long life of the home.

[0947] Data collection and ingestion

[0948] server

[0949] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. Specifically, it will have web and mobile apps developed using React Native and Flutter. Forms and drop-down menus will be included to make it easy for users to enter information.

[0950] User

[0951] Using a web or mobile app, users input basic information about their home (year of construction, address, structure, etc.), maintenance history (date, time, details, materials used, etc.), and building material characteristics data (manufacturer, model number, material, etc.). This data is then sent from the device to the server.

[0952] server

[0953] The server stores the transmitted data in a database using an RDBMS such as MySQL or PostgreSQL. The stored data is standardized using tools such as Pandas.

[0954] Analyzing the data and applying the model

[0955] server

[0956] The server applies a generative AI model, built with TensorFlow or PyTorch, to the collected data, cleaning and shaping the data, and detecting missing values ​​and outliers.

[0957] Generative AI Models

[0958] The generative AI model predicts the deterioration patterns and lifespan of a home. For example, it analyzes the deterioration pattern of a roof based on past maintenance history and predicts when the next maintenance is due.

[0959] server

[0960] The server stores the analysis results in a database, and if missing data or abnormal values ​​are detected, the server notifies the user.

[0961] Creating proposals and notifying users

[0962] server

[0963] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model, which includes specific maintenance items and their recommended timing.

[0964] server

[0965] The server allows the user to select a notification method (email, in-app message, SMS, etc.) and notifies the user of the maintenance schedule based on the selection.

[0966] Regular follow-up

[0967] server

[0968] The server periodically sends reminders to users of upcoming maintenance, allowing them to perform the maintenance at the appropriate time.

[0969] server

[0970] The server collects feedback data from users and updates the database. Based on the feedback data, the generative AI model is updated to improve analysis accuracy.

[0971] Specific examples

[0972] Example 1: Collecting Data

[0973] Users access the app using their smartphones and enter basic information about their home (year built: 2010, location: urban area, structure: wooden). They also enter that the roof was repaired in 2016. This information is sent to the server and stored in a database.

[0974] Example 2: Analyzing Data

[0975] The server runs a generative AI model based on the user's home data. The generative AI analyzes the roof's deterioration pattern and predicts that the next repair will be required in June 2023.

[0976] Example 3: Notifications and feedback

[0977] The server sends a notification to the user stating, "We recommend that the next roof inspection and repair be performed in June 2023." The user receives this notification, prepares for the maintenance, and after actually performing the maintenance, feeds the results back into the system. The system then reanalyzes the feedback and updates the database with the latest information.

[0978] Prompt Sentence Examples

[0979] "You enter your home's building materials and past maintenance history. We then run a generative AI model to analyze your home's deterioration patterns and identify predicted maintenance needs."

[0980] By implementing this invention, the maintenance and management of a house can be carried out efficiently, and its safety and long life can be ensured.

[0981] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0982] Step 1: Collect and ingest data

[0983] In step 1, the server provides a web app or mobile app for collecting housing information. The user enters basic information about the house (year of construction, address, structure, etc.), maintenance history (date and time, contents, materials used, etc.), and building material characteristic data (manufacturer, model number, quality, etc.) into these interfaces. The entered data is sent from the terminal to the server. The server saves the sent data in a database. The saved data is standardized using tools such as Pandas. The input is the house information, maintenance history, and building material characteristic data from the user, and the output is the data saved in the database after standardization processing.

[0984] Step 2: Analyze the data and apply the model

[0985] In step 2, the server applies the generative AI model to the collected data. The generative AI model estimates the deterioration pattern and predicts the lifespan. The server cleans the data and removes missing values ​​and outliers. Based on this, the generative AI model estimates the deterioration pattern of the house and makes a prediction. These analysis results are then saved back into the database. The inputs are the collected data and the generative AI model, and the output is the analysis results.

[0986] Step 3: Create a proposal and notify users

[0987] In step 3, the server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and recommended times. Next, the server sends a prompt to the user to select a notification method. After the user selects a notification method (email, in-app message, SMS, etc.), the server notifies the user of the maintenance schedule based on this selection. The input is the analysis results and the user's selection of the notification method, and the output is a notification of the maintenance schedule.

[0988] Step 4: Regular follow-up

[0989] In step 4, the server periodically sends the user a reminder for the next maintenance. It collects feedback data from users and updates the database. The generative AI model retrains based on this feedback data to improve its analysis accuracy. The inputs are the output results of the generative AI model and feedback data from users, and the outputs are an updated database and the latest maintenance schedule.

[0990] Through the above processing steps, the server, terminals, and users work together to realize a system that supports optimal home maintenance planning and ensures the safety and long life of homes.

[0991] (Application example 1)

[0992] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0993] Homes and factory facilities are used for long periods of time, but their upkeep and maintenance take time and effort, requiring efficient schedule management. Furthermore, if maintenance is not performed at the appropriate time, it can lead to a decrease in safety and a shortened lifespan. However, current maintenance management systems have difficulty collecting and analyzing data individually, requiring a great deal of effort. Furthermore, incompleteness in the collected data and the presence of abnormal values ​​can reduce the reliability of the system. To solve these issues, there is a need for technology that can comprehensively manage basic information, maintenance history, and characteristic data for homes and factory facilities, and efficiently generate maintenance schedules.

[0994] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0995] In this invention, the server includes means for collecting basic information, maintenance history, and property data of building materials for homes, means for collecting basic information, maintenance history, and property data of factory equipment, means for a generative AI model to extract and analyze features based on the collected data, means for creating an optimal maintenance schedule based on the analysis results and notifying the user, and means for collecting feedback data from users who have received the notification and updating the database. This enables efficient and accurate maintenance schedule management for homes and factory equipment.

[0996] A "house" is a building constructed using building materials for human habitation.

[0997] "Basic information" refers to basic data such as the structure of the object, the year of installation, the address, and the materials used.

[0998] "Maintenance history" refers to data on the date, time, and content of past repairs and maintenance work, as well as the materials used.

[0999] "Characteristic data" refers to detailed data such as the manufacturer, model number, and material of the building materials and equipment used.

[1000] "Factory equipment" is a general term for machines and devices installed for manufacturing and production activities.

[1001] A "data collection means" is a method or system for inputting, recording, or obtaining information about an object.

[1002] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and perform tasks such as prediction and classification.

[1003] "Means for extracting features and performing analysis" refers to methods or systems that efficiently find relevant information and patterns from collected data and perform analysis based on them.

[1004] The "optimal maintenance period" refers to the most appropriate time to perform maintenance depending on the condition of the equipment and building materials.

[1005] "Feedback data" refers to data provided by the user regarding the results of the performed maintenance and new information.

[1006] A "means for updating a database" is a method or system for adding or modifying new collected data to an existing database.

[1007] A "means for notifying" is a method or system for conveying information to a user.

[1008] This invention relates to a system for generating optimal maintenance schedules for residential and factory facilities. Servers, terminals, and users work together to collect, analyze, and notify data, thereby achieving efficient maintenance management.

[1009] Hardware and Software Configuration

[1010] Hardware

[1011] Server: A server for hosting the database and generative AI model. Examples include AWS EC2 and Google Cloud.

[1012] Client Device: Smartphone, tablet, or head-mounted display (HMD) used for data collection and notification. Examples include iPhone, Android devices, and Microsoft HoloLens.

[1013] software

[1014] Data collection interface: A web or mobile app that allows users to enter basic information about home and industrial facilities, maintenance history, and characteristics of building materials and equipment.

[1015] Generative AI model: An AI model implemented using TensorFlow or PyTorch that analyzes data and predicts maintenance times.

[1016] Notification system: A notification system using a microservices architecture that notifies users about scheduled maintenance via email, SMS, or in-app messages.

[1017] System operation explanation

[1018] 1. Data collection

[1019] The server collects basic information about the home and factory facilities provided by the user, maintenance history, and characteristic data of building materials and equipment. The user enters this data through the application form and sends it to the server.

[1020] 2. Data Analysis

[1021] The server uses generative AI models to extract features and analyze the collected data, cleaning and pre-processing the data, and notifying the user if missing data or outliers are detected.

[1022] 3. Generate a maintenance schedule

[1023] The generative AI model predicts the optimal maintenance period based on the collected data. The server generates a maintenance schedule based on the analysis results and notifies each user.

[1024] 4. Notifying users and gathering feedback

[1025] The server notifies users of the scheduled maintenance. Users receive the notification and prepare for the next maintenance based on the notification. After the actual maintenance is performed, users input their feedback into the system, and the database is updated.

[1026] Specific examples

[1027] For example, a factory manager can collect maintenance data for equipment in a factory and use an AI model to predict when the next maintenance will be required. The AI ​​model analyzes the deterioration pattern of the equipment based on past maintenance history and equipment characteristic data, and determines the optimal maintenance timing. As a result, the factory manager will be notified via a notification system with a specific date and time, such as "The next maintenance for equipment ID: 001 is December 15, 2023."

[1028] Prompt Sentence Examples

[1029] Equipment ID: 001

[1030] Last maintenance date: 2022-06-10

[1031] Materials used: bearings, lubricants

[1032] Current status: Driving

[1033] In this way, an embodiment of a system that realizes efficient and highly accurate maintenance management is constructed.

[1034] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1035] Step 1:

[1036] The user inputs basic information about the home or factory facility, maintenance history, and characteristic data of building materials and equipment.

[1037] Input: Basic information about the home or factory facilities, maintenance history, and characteristic data of building materials and equipment

[1038] Specific operation: A user enters information about a home or factory facility into a form via a smartphone or tablet application, such as the year of construction or details of past maintenance work.

[1039] Output: The input data is sent to the server.

[1040] Step 2:

[1041] The server stores the received data in a database.

[1042] Input: Basic information sent by the user, maintenance history, property data of building materials and equipment

[1043] What happens: The server receives the data and stores it in a consistent format in the database. Data normalization and preprocessing are also performed at this stage.

[1044] Output: Saved data

[1045] Step 3:

[1046] The server begins analysis based on the stored data.

[1047] Input: Basic information stored in the database, maintenance history, property data of building materials and equipment

[1048] Data processing: Preprocessing involves cleaning the data and detecting missing data and outliers.

[1049] What it does: The server performs data cleaning to detect missing data and outliers, notifies the user of any detected missing data or outliers, collects user feedback if necessary, and updates the database.

[1050] Output: Cleaned data

[1051] Step 4:

[1052] Analysis is performed using a generative AI model.

[1053] Input: Basic information on cleaning, maintenance history, property data of building materials and equipment

[1054] Data computation: Generative AI models extract features and predict degradation patterns and lifespan.

[1055] How it works: The server analyzes the data using a generative AI model built using TensorFlow and PyTorch. The generative AI model extracts features based on each data point and predicts degradation patterns and lifespan.

[1056] Output: Analysis results (next maintenance time and recommendations)

[1057] Step 5:

[1058] The server creates an optimal maintenance schedule based on the analysis results and notifies the user.

[1059] Input: Analysis results of the generative AI model

[1060] How it works: The server receives the analysis results and creates an optimal maintenance schedule for each facility or home, then notifies the user via email, SMS, or in-app message.

[1061] Output: Maintenance schedule notification sent to user

[1062] Step 6:

[1063] The user receives the notification and enters the feedback data.

[1064] Input: Maintenance schedule notification, feedback data

[1065] Specific operation: The user confirms the notification and starts preparations for the next maintenance. After the actual maintenance is completed, the results are entered as feedback data through the application and sent to the server.

[1066] Output: Feedback data is sent to the server

[1067] Step 7:

[1068] The server updates the database based on the received feedback data.

[1069] Input: Feedback data

[1070] What happens: The server receives the feedback data and updates the database, ensuring that the next analysis is based on the most up-to-date information.

[1071] Output: Updated database

[1072] This enables users, servers, and generative AI models to work together to efficiently manage the maintenance of residential and factory facilities.

[1073] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1074] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and building material characteristics data to generate an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notifications. Furthermore, by combining it with an emotion engine, the system recognizes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[1075] 1. Data collection and capture

[1076] server

[1077] The server provides an interface for collecting information about homes. Users can enter the information through a web app or mobile app. The server receives the basic information about the home (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[1078] User

[1079] The user inputs basic information about the house, its maintenance history, and the characteristics of the building materials through the interface, and the data entered by the user is sent to the server.

[1080] 2. Analyzing the data and applying the model

[1081] server

[1082] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[1083] 3. Creating a proposal and notifying users

[1084] server

[1085] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended times. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, notifies the user with the optimal timing and content. Notification methods include email, in-app messages, and SMS.

[1086] User

[1087] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[1088] 4. Regular follow-up

[1089] server

[1090] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[1091] Specific examples

[1092] Example 1: Collecting Data

[1093] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[1094] Example 2: Analyzing Data

[1095] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[1096] Example 3: Notifications and feedback

[1097] The server notifies Yamada of the next scheduled maintenance. "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system. The emotion engine analyzes Yamada's feedback data and recognizes his emotional state. The next notification and advice will be given taking the results into account.

[1098] In this way, collaboration between the server, generative AI, emotion engine, and user can assist in optimal home maintenance planning, ensuring the safety and longevity of the home.

[1099] The processing flow will be explained below.

[1100] Step 1:

[1101] The server provides an interface for collecting housing information, allowing users to enter the information through a web app or mobile app.

[1102] Step 2:

[1103] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[1104] Step 3:

[1105] The server receives the data entered by the user and stores it in a database, where it is standardized and pre-processed for consistency.

[1106] Step 4:

[1107] The server feeds the collected data into a generative AI model, which cleans and shapes the data to detect missing data and outliers.

[1108] Step 5:

[1109] The generative AI extracts features from the data provided, analyzes the deterioration pattern of the home, and predicts its lifespan, predicting the progress of deterioration and when the next maintenance will be required.

[1110] Step 6:

[1111] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[1112] Step 7:

[1113] The server will notify the user of the optimal maintenance schedule via email, in-app message, SMS, etc.

[1114] Step 8:

[1115] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, the user can send questions or feedback to the server through the interface.

[1116] Step 9:

[1117] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[1118] Step 10:

[1119] The server runs an emotion engine that recognizes emotions from user input and feedback data, analyzes the user's emotional state, and adjusts advice and reminders accordingly.

[1120] Step 11:

[1121] The server sends users advice and reminders based on their emotional state, which are tailored to improve their motivation.

[1122] Step 12:

[1123] The server periodically sends reminders to users for the next maintenance appointment, and the emotion engine adjusts the timing and content of the reminders based on the user's latest emotional state.

[1124] Step 13:

[1125] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[1126] Example 2

[1127] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1128] Home maintenance typically requires users to understand the home's past history and current condition, and then perform the maintenance at the appropriate time and with the appropriate content based on that information. However, many homeowners find it difficult to manage this properly, and as a result, maintenance is often neglected. This problem accelerates the deterioration of the home, ultimately leading to the need for serious repairs and shortening the home's lifespan. Furthermore, existing systems have difficulty providing appropriate notifications and feedback that take the user's emotional state into account, which can lead to issues such as reduced user satisfaction and reduced system usage efficiency.

[1129] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the home, maintenance history, and property data of building materials; means for cleaning and shaping the collected data and detecting missing data and outliers; means for applying a generative AI model to the shaped data to extract and analyze features; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state from feedback data and input data using an emotion engine and adjusting the timing and content of the notification; means for collecting feedback data from the user who received the notification and updating the database; and means for periodically sending a reminder for the next maintenance and performing a new analysis using the generative AI model. This enables efficient maintenance that takes the user's emotional state into consideration while ensuring the safety and long life of the home.

[1130] "Basic information about the house" refers to basic data about the house itself, such as the year it was built, its address, and its structure.

[1131] "Maintenance history" is a record of the date, time, content, materials used, etc. of past maintenance work.

[1132] "Characteristic data of building materials" is data that indicates characteristics such as the manufacturer, model number, and material of the building materials used in the house.

[1133] "Means of collection" refers to the mechanism by which a user inputs information through an interface, the server receives it, and stores it in a database.

[1134] A "generative AI model" is an artificial intelligence model that extracts features based on input data and performs analysis.

[1135] "Cleaning and shaping" refers to the process of detecting missing or outliers in data and correcting or modifying them.

[1136] "Means for analysis" refers to the mechanism for extracting and analyzing the characteristics of collected data using a generative AI model.

[1137] The "optimal maintenance schedule" is a schedule that includes specific maintenance items and their recommended timing, proposed based on deterioration patterns and lifespan predictions.

[1138] "Means of notification" refers to the method of communicating the maintenance schedule to users, including email, in-app messages, SMS, etc.

[1139] "Emotion engine" refers to technology that analyzes a user's emotional state from feedback data and input data, and adjusts the timing and content of notifications based on that.

[1140] "Feedback data" refers to data including results reports and opinions provided by users after maintenance has been performed.

[1141] "Means for updating the database" refers to a mechanism for adding or amending collected feedback data to an existing database.

[1142] A "reminder" is a periodic message that notifies the user again of the next scheduled maintenance.

[1143] "New analysis" means that the generative AI model uses regularly collected feedback data to conduct the latest analysis and reflect the results.

[1144] This invention relates to a system that collects information about a home and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging information between a server, terminals, and users, and by analyzing and notifying them. Furthermore, it uses an emotion engine to recognize the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[1145] The server first provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This interface is implemented as a web app or mobile app, through which users can input data. Specifically, the server receives the basic information (year built, address, structure, etc.), maintenance history (date, time, content, materials used, etc.), and the characteristics of building materials (manufacturer, model number, material, etc.) and stores them in a database.

[1146] The collected data is cleaned and shaped by the server. If missing data or outliers are detected, the server automatically sends a notification to the user requesting them to complete or correct them. After cleaning and shaping, the data is applied to the generative AI model.

[1147] The generative AI model uses the formatted data to predict the home's deterioration patterns and lifespan. The model identifies the optimal maintenance period and content for the home and stores the analysis results in a database. Based on the analysis results, the server creates an optimal maintenance schedule and notifies the user. This notification is sent via email, in-app messages, SMS, etc.

[1148] Furthermore, the emotion engine analyzes the user's emotional state from feedback data and input data, and adjusts the timing and content of notifications. This helps users to carry out maintenance at the appropriate time. The user checks the notified schedule and carries out the maintenance. After carrying out the maintenance, the results can be fed back to the system. The server collects this feedback data and updates the database.

[1149] The server also periodically sends reminders to users for upcoming maintenance. The emotion engine adjusts the timing and content of the reminders, allowing users to appropriately prepare for the next maintenance. Based on the periodically collected feedback data, the generative AI model performs new analysis and updates the maintenance schedule accordingly.

[1150] As a concrete example, the following prompt sentences are used when the user inputs house data:

[1151] Prompt Sentence Examples

[1152] Generate a deterioration prediction and an optimal maintenance schedule for a home based on basic information, maintenance history, and building material characteristics data entered by the user. Below are some examples of specific data.

[1153] basic information:

[1154] Construction year: 2010

[1155] Address: Shinjuku-ku, Tokyo

[1156] Structure: wooden

[1157] Maintenance history:

[1158] Date: March 2016

[1159] Content: Roof repair

[1160] Materials used: Material A

[1161] Building material property data:

[1162] Manufacturer: Manufacturer X

[1163] Model number: YZ123

[1164] Material: Cement

[1165] Predict the optimal maintenance timing and content.

[1166] As described above, collaboration between the server, generative AI model, emotion engine, and user can efficiently support home maintenance planning and ensure the safety and long life of homes.

[1167] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1168] Step 1:

[1169] User

[1170] Users enter basic information about the home, maintenance history, and characteristic data of building materials using input forms in the web app or mobile app. The data entered includes the year of construction, address, structure, past maintenance dates and times, details, materials used, manufacturer, model number, and quality of building materials. This information is sent to the server by the user manually entering it and pressing the send button. Input: Basic information about the home, maintenance history, characteristic data of building materials. Output: Data sent to the server.

[1171] Step 2:

[1172] server

[1173] The server receives data sent by the user and saves it in the database in real time. Processing performed here includes format checks for input data, confirmation of required fields, and detection of missing data. For example, if the address or year of construction is not entered, an error message is generated. Input: Data sent by the user. Output: Data saved in the database, error message (if necessary).

[1174] Step 3:

[1175] server

[1176] The server cleans and formats the stored data. It detects missing data and outliers and sends a completion request to the user accordingly. For example, if there is missing data, it automatically sends a completion request email saying, "The construction year has not been entered. Please enter it." Input: Stored data. Output: Cleaned and formatted data, completion request email.

[1177] Step 4:

[1178] server

[1179] The server inputs the cleaned and formatted data into a generative AI model, which extracts and analyzes features. The generative AI model predicts the deterioration pattern and lifespan of the home, and identifies the optimal maintenance timing and content. For example, it may predict that "roof repairs will be required in June 2023." Input: Cleaned and formatted data. Output: Deterioration pattern, lifespan prediction, optimal maintenance timing.

[1180] Step 5:

[1181] server

[1182] The server automatically creates an optimal maintenance schedule based on the analysis results of the generative AI model. This schedule includes specific maintenance items and their recommended timing. For example, it may include the content, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Analysis results of the generative AI model. Output: Optimal maintenance schedule.

[1183] Step 6:

[1184] server

[1185] The server uses an emotion engine to analyze the user's emotional state from their feedback data and input data. Based on these results, it adjusts the timing and content of notifications. For example, if past feedback indicates that the user is feeling stressed, it sends a message that takes this into consideration. Input: Feedback data, input data. Output: Emotional state analysis results, adjusted notification content.

[1186] Step 7:

[1187] server

[1188] The server notifies the user of the optimal maintenance schedule via email, in-app message, SMS, etc. For example, it sends a message saying, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Optimal maintenance schedule, adjusted notification content. Output: Notification to the user.

[1189] Step 8:

[1190] User

[1191] The user receives a notification from the server and prepares for maintenance. The user carries out the maintenance according to the notification and feeds back the results to the server through the interface. For example, the user can enter and send information such as "The roof was inspected and repaired in June 2023." Input: Feedback data. Output: Sending results to the server.

[1192] Step 9:

[1193] server

[1194] The server receives feedback data from users and updates the database. The updated data is used for the next analysis and to generate maintenance schedules. Input: Feedback data from users. Output: Updated database.

[1195] Step 10:

[1196] server

[1197] The server periodically sends reminders to users about upcoming maintenance. The timing and content of these reminders are adjusted by the emotion engine. For example, a reminder such as "Don't forget to come for your next scheduled inspection" can be sent. Input: Next maintenance information based on the database. Output: Reminder notification.

[1198] Step 11:

[1199] server

[1200] The server runs the generative AI model again based on the feedback data collected periodically, and performs a new analysis. Based on the analysis results, the maintenance schedule is updated as appropriate. Input: Feedback data. Output: Updated analysis results and maintenance schedule.

[1201] Through the above steps, this system can efficiently support users in planning their home maintenance, ensuring the safety and longevity of their homes.

[1202] (Application example 2)

[1203] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1204] In recent years, physical store operators have been required to ensure operational efficiency and safety by properly maintaining their store buildings. However, determining the appropriate timing and content of maintenance is difficult, and maintenance work is often postponed depending on the operator's busy schedule or mood. This problem can lead to further deterioration of the building, resulting in large repair costs. There is also a risk that overlooking maintenance could compromise the safety of the store. Therefore, a system that allows physical store operators to plan and carry out maintenance at the appropriate time is needed.

[1205] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the building, maintenance history, and characteristic data of building materials; means for a generative AI model to extract and analyze features based on the collected data; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state using an emotion engine and providing notifications and advice at appropriate times and with appropriate content; and means for collecting feedback data from users who have received the notifications and updating the database. This enables operators of physical stores to plan and implement optimal maintenance at appropriate times, ensuring the safety and long life of the store.

[1206] "Basic building information" refers to data including basic attributes and information of a building, such as the year of construction, address, and construction structure of the building.

[1207] "Maintenance history" is data that shows records of the date, time, content, materials used, etc. of maintenance work that has been carried out on a building in the past.

[1208] "Building material characteristic data" is data that includes detailed attribute information such as the manufacturer, model number, and quality of various building materials used in a building.

[1209] A "generative AI model" is an artificial intelligence model that extracts features from collected data and predicts building deterioration patterns and lifespans.

[1210] The "emotion engine" is a system that analyzes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content based on that analysis.

[1211] "User" means the person or entity that is the owner or manager of the building and uses the maintenance management system.

[1212] "Database" means an electronic record system for storing collected basic building information, maintenance history, building material characteristic data, and feedback data.

[1213] "Feedback data" refers to information including the results and impressions of the maintenance carried out based on the maintenance schedule notified to the user.

[1214] A "maintenance schedule" is a plan created by a generative AI model that indicates the optimal time and content of building maintenance work.

[1215] "Notification" is a means of communicating generated maintenance schedules and other important information to users.

[1216] This invention relates to a system that collects and analyzes basic information about brick-and-mortar store buildings, maintenance history, and building material characteristic data to generate an optimal maintenance schedule. This system ensures the safety and longevity of stores by exchanging data between servers, terminals, and users, and by analyzing and notifying them. It also combines an emotion engine to recognize the user's emotional state and provide notifications and advice at the appropriate time and with the right content, thereby improving maintenance efficiency and user satisfaction.

[1217] 1. Data collection and capture

[1218] server

[1219] The server provides an interface for collecting building information. Users can input the information through a web app or mobile app. The server receives the basic building information (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[1220] User

[1221] The user inputs basic information about the building, its maintenance history, and the characteristics of the building materials through the interface. The data entered by the user is sent to the server.

[1222] 2. Analyzing the data and applying the model

[1223] server

[1224] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the building's deterioration pattern and lifespan, and identifies the optimal maintenance timing and content. The results of this analysis are stored in a database.

[1225] 3. Creating a proposal and notifying users

[1226] server

[1227] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, provides notifications and advice at the optimal timing and content. Notifications can be sent via email, in-app messages, SMS, etc.

[1228] User

[1229] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[1230] 4. Regular follow-up

[1231] server

[1232] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[1233] Specific examples

[1234] Example 1: Collecting Data

[1235] The user enters basic information about his store and its past maintenance history into the system, for example, entering that the walls were repainted in 2020. The server stores this information in a database.

[1236] Example 2: Analyzing Data

[1237] The server runs a generative AI model based on the user's store data, which analyzes the deterioration patterns of the walls and predicts when the next repainting will be necessary.

[1238] Example 3: Notifications and feedback

[1239] The server notifies the user of the next scheduled maintenance. "We recommend that the next wall repainting be done in April 2025." The user makes preparations based on this notification, and after actually carrying out the maintenance, feeds the results back to the system. The emotion engine analyzes the user's feedback data and recognizes his emotional state. The next notification or advice will be given taking the results into consideration.

[1240] Prompt Sentence Examples

[1241] "Create the optimal next maintenance schedule based on your store data and maintenance history. Information to consider is:

[1242] Store construction year, address, structure

[1243] Characteristics of the building materials used (manufacturer, model number, material, etc.)

[1244] Past maintenance history (date, time, contents, materials used, etc.)

[1245] Store manager's emotional state

[1246] Please suggest specific maintenance items and recommended times.

[1247] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1248] Step 1:

[1249] Data collection

[1250] Input: Basic information about the building, maintenance history, and property data of building materials

[1251] Processing: Using a web app or mobile app, users input basic building information (e.g., year of construction, address, structure, etc.), past maintenance details (e.g., date and time, details, materials used, etc.), and building material characteristics data (e.g., manufacturer, model number, material, etc.). This input data is sent to the server via the interface.

[1252] Output: The input data is sent to the server and stored in a database.

[1253] Step 2:

[1254] Cleaning and shaping the data

[1255] Input: Basic building information, maintenance history, and building material characteristics data stored on the server

[1256] Processing: The server analyzes the stored data and detects missing data or outliers. If any missing data or outliers are found, the server notifies the user and asks them to complete the data.

[1257] Output: Cleaned and formatted data is generated and stored in a database.

[1258] Step 3:

[1259] Data analysis and feature extraction

[1260] Input: Clean and formatted data

[1261] Processing: The server begins analysis using a generative AI model (e.g., using Python or TensorFlow). The model extracts features from the input data and predicts the building's deterioration pattern and lifespan. This allows appropriate maintenance timing and content to be identified.

[1262] Output: Analysis results are generated and stored in a database.

[1263] Step 4:

[1264] Creating a maintenance schedule

[1265] Input: Analysis results from generative AI model

[1266] Processing: The server creates an optimal maintenance schedule based on the analysis results, which includes specific maintenance items and their recommended times.

[1267] Output: A maintenance schedule is generated and stored in the database.

[1268] Step 5:

[1269] Sentiment analysis with emotion engine

[1270] Input: User feedback data and maintenance history

[1271] Processing: The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's emotional state from their input data and feedback data. Based on this, it optimizes the content and timing of notifications and advice.

[1272] Output: The results of the sentiment analysis are generated and stored in a database.

[1273] Step 6:

[1274] User Notification

[1275] Input: Maintenance schedule, sentiment analysis results

[1276] Processing: The server notifies users of maintenance schedules and advice at appropriate times via email, in-app messages, SMS, etc.

[1277] Output: A notification is sent to the user.

[1278] Step 7:

[1279] Collecting feedback

[1280] Input: Feedback data from users

[1281] Processing: After the user actually performs the maintenance, they provide feedback to the server via the interface, including the results and their impressions. The received feedback data is reanalyzed by the emotion engine and stored in the database.

[1282] Output: The updated feedback data is saved in the database.

[1283] Step 8:

[1284] Sending periodic reminders

[1285] Input: Stored feedback data, maintenance schedule

[1286] Processing: The server periodically sends reminders to users about upcoming maintenance schedules. The timing and content of the notifications are adjusted based on the analysis results of the emotion engine.

[1287] Output: A reminder notification is sent to the user.

[1288] This series of processes enables store operators to plan and implement maintenance efficiently and effectively.

[1289] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1290] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1291] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1292] [Fourth embodiment]

[1293] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1294] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1295] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1296] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1297] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1298] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1299] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1300] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1301] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1302] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1303] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1304] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1305] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1306] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notification.

[1307] 1. Data collection and capture

[1308] server

[1309] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This can be a web app or a mobile app. The server provides forms and options for users to enter this information and stores the entered data in a database. The stored data is pre-processed to ensure standardization and consistency.

[1310] User

[1311] The user enters basic information about the house (year of construction, address, structure, etc.) and past maintenance history (date, time, contents, materials used, etc.) into the system. The user also enters characteristic data of the building materials used (manufacturer, model number, quality, etc.). The data entered by the user is sent to the server.

[1312] 2. Analyzing the data and applying the model

[1313] server

[1314] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[1315] 3. Creating a proposal and notifying users

[1316] server

[1317] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The created schedule is notified to the user. Notification methods include email, in-app message, and SMS.

[1318] User

[1319] The user can check the notified maintenance schedule and prepare for the next maintenance to be performed. Based on the schedule, they can gather the necessary tools and materials or call in a specialist. They can also provide feedback and new information to the server, which allows the system to reanalyze and update the database based on the latest information.

[1320] 4. Regular follow-up

[1321] server

[1322] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at the appropriate time. Based on the periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[1323] Specific examples

[1324] Example 1: Collecting Data

[1325] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[1326] Example 2: Analyzing Data

[1327] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[1328] Example 3: Notifications and feedback

[1329] The server notifies Yamada of the next scheduled maintenance date: "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system.

[1330] In this way, collaboration between the server, generating AI, and user can assist in creating optimal maintenance plans for homes, ensuring their safety and long lifespan.

[1331] The processing flow will be explained below.

[1332] Step 1:

[1333] The server provides an interface for collecting information about the home, allowing users to enter the information through a web app or mobile app.

[1334] Step 2:

[1335] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[1336] Step 3:

[1337] The server receives the data entered by the user and stores it in a database, where it is pre-processed to ensure standardization and consistency.

[1338] Step 4:

[1339] The server feeds the collected data into the generative AI model, cleaning and formatting the data to check for missing data or outliers.

[1340] Step 5:

[1341] The generative AI extracts features based on the data provided and analyzes the home's deterioration patterns and lifespan predictions.

[1342] Step 6:

[1343] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[1344] Step 7:

[1345] The server notifies the user of the created maintenance schedule via email, in-app message, SMS, etc.

[1346] Step 8:

[1347] The user checks the received maintenance schedule and prepares for the next maintenance, and if necessary, sends questions or feedback to the server through the interface.

[1348] Step 9:

[1349] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[1350] Step 10:

[1351] The server periodically sends reminders to users about upcoming maintenance, allowing them to perform maintenance at an appropriate time.

[1352] Step 11:

[1353] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[1354] Example 1

[1355] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1356] In home maintenance and management, it is difficult to determine the appropriate timing for maintenance, and neglecting it leads to further deterioration of the home and higher repair costs. Furthermore, if maintenance history and data on building material characteristics are insufficient, it is difficult to accurately predict deterioration and create a maintenance schedule. This presents a challenge in ensuring the safety and long life of homes.

[1357] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1358] In this invention, the server includes means for collecting basic information about the home, maintenance history, and property data of building materials, means for saving the data entered by the user in a database, and means for standardizing and preprocessing the saved data, thereby maintaining the consistency of the collected data and enabling accurate deterioration prediction and the creation of an optimal maintenance schedule.

[1359] "Basic information about the home" refers to basic data such as the year the home was built, its address, and its structure.

[1360] "Maintenance history" refers to records of past repairs and maintenance carried out on a home, including the date, time, details, and materials used.

[1361] "Building material characteristic data" refers to information such as the manufacturer, model number, and material of the building materials used in the home.

[1362] A "generative AI model" refers to an artificial intelligence model that extracts features from collected data and performs analysis.

[1363] "Means for feature extraction and analysis" refers to the process of using generative AI models to extract useful information from collected data and then analyzing that information.

[1364] "Means for creating an optimal maintenance schedule and notifying the user" refers to the process of creating a maintenance plan based on the analysis results and notifying the user of the plan.

[1365] "Means for collecting feedback data and updating the database" refers to the process of collecting user opinions and new data and reflecting them in the database.

[1366] "Means for determining deterioration patterns and predictions" refers to the process of predicting the degree of deterioration of a home based on collected data and identifying when future maintenance will be required.

[1367] "Means for detecting missing data or abnormal values ​​and notifying users to supplement the missing data or abnormal values" refers to the process of informing users when there are gaps or abnormalities in the collected data and having the users provide additional data.

[1368] "Means for sending periodic reminders" refers to a process for sending notifications to users when the next maintenance date and time is approaching.

[1369] "Means for updating the generative AI model" refers to the process of retraining the generative AI model based on feedback data to improve its analytical accuracy.

[1370] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and the characteristics of building materials, and generates an optimal maintenance schedule. The system is composed mainly of a server, terminals, and users, and their cooperation ensures the safety and long life of the home.

[1371] Data collection and ingestion

[1372] server

[1373] The server provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. Specifically, it will have web and mobile apps developed using React Native and Flutter. Forms and drop-down menus will be included to make it easy for users to enter information.

[1374] User

[1375] Using a web or mobile app, users input basic information about their home (year of construction, address, structure, etc.), maintenance history (date, time, details, materials used, etc.), and building material characteristics data (manufacturer, model number, material, etc.). This data is then sent from the device to the server.

[1376] server

[1377] The server stores the transmitted data in a database using an RDBMS such as MySQL or PostgreSQL. The stored data is standardized using tools such as Pandas.

[1378] Analyzing the data and applying the model

[1379] server

[1380] The server applies a generative AI model, built with TensorFlow or PyTorch, to the collected data, cleaning and shaping the data, and detecting missing values ​​and outliers.

[1381] Generative AI Models

[1382] The generative AI model predicts the deterioration patterns and lifespan of a home. For example, it analyzes the deterioration pattern of a roof based on past maintenance history and predicts when the next maintenance is due.

[1383] server

[1384] The server stores the analysis results in a database, and if missing data or abnormal values ​​are detected, the server notifies the user.

[1385] Creating proposals and notifying users

[1386] server

[1387] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model, which includes specific maintenance items and their recommended timing.

[1388] server

[1389] The server allows the user to select a notification method (email, in-app message, SMS, etc.) and notifies the user of the maintenance schedule based on the selection.

[1390] Regular follow-up

[1391] server

[1392] The server periodically sends reminders to users of upcoming maintenance, allowing them to perform the maintenance at the appropriate time.

[1393] server

[1394] The server collects feedback data from users and updates the database. Based on the feedback data, the generative AI model is updated to improve analysis accuracy.

[1395] Specific examples

[1396] Example 1: Collecting Data

[1397] Users access the app using their smartphones and enter basic information about their home (year built: 2010, location: urban area, structure: wooden). They also enter that the roof was repaired in 2016. This information is sent to the server and stored in a database.

[1398] Example 2: Analyzing Data

[1399] The server runs a generative AI model based on the user's home data. The generative AI analyzes the roof's deterioration pattern and predicts that the next repair will be required in June 2023.

[1400] Example 3: Notifications and feedback

[1401] The server sends a notification to the user stating, "We recommend that the next roof inspection and repair be performed in June 2023." The user receives this notification, prepares for the maintenance, and after actually performing the maintenance, feeds the results back into the system. The system then reanalyzes the feedback and updates the database with the latest information.

[1402] Prompt Sentence Examples

[1403] "You enter your home's building materials and past maintenance history. We then run a generative AI model to analyze your home's deterioration patterns and identify predicted maintenance needs."

[1404] By implementing this invention, the maintenance and management of a house can be carried out efficiently, and its safety and long life can be ensured.

[1405] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1406] Step 1: Collect and ingest data

[1407] In step 1, the server provides a web app or mobile app for collecting housing information. The user enters basic information about the house (year of construction, address, structure, etc.), maintenance history (date and time, contents, materials used, etc.), and building material characteristic data (manufacturer, model number, quality, etc.) into these interfaces. The entered data is sent from the terminal to the server. The server saves the sent data in a database. The saved data is standardized using tools such as Pandas. The input is the house information, maintenance history, and building material characteristic data from the user, and the output is the data saved in the database after standardization processing.

[1408] Step 2: Analyze the data and apply the model

[1409] In step 2, the server applies the generative AI model to the collected data. The generative AI model estimates the deterioration pattern and predicts the lifespan. The server cleans the data and removes missing values ​​and outliers. Based on this, the generative AI model estimates the deterioration pattern of the house and makes a prediction. These analysis results are then saved back into the database. The inputs are the collected data and the generative AI model, and the output is the analysis results.

[1410] Step 3: Create a proposal and notify users

[1411] In step 3, the server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and recommended times. Next, the server sends a prompt to the user to select a notification method. After the user selects a notification method (email, in-app message, SMS, etc.), the server notifies the user of the maintenance schedule based on this selection. The input is the analysis results and the user's selection of the notification method, and the output is a notification of the maintenance schedule.

[1412] Step 4: Regular follow-up

[1413] In step 4, the server periodically sends the user a reminder for the next maintenance. It collects feedback data from users and updates the database. The generative AI model retrains based on this feedback data to improve its analysis accuracy. The inputs are the output results of the generative AI model and feedback data from users, and the outputs are an updated database and the latest maintenance schedule.

[1414] Through the above processing steps, the server, terminals, and users work together to realize a system that supports optimal home maintenance planning and ensures the safety and long life of homes.

[1415] (Application example 1)

[1416] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1417] Homes and factory facilities are used for long periods of time, but their upkeep and maintenance take time and effort, requiring efficient schedule management. Furthermore, if maintenance is not performed at the appropriate time, it can lead to a decrease in safety and a shortened lifespan. However, current maintenance management systems have difficulty collecting and analyzing data individually, requiring a great deal of effort. Furthermore, incompleteness in the collected data and the presence of abnormal values ​​can reduce the reliability of the system. To solve these issues, there is a need for technology that can comprehensively manage basic information, maintenance history, and characteristic data for homes and factory facilities, and efficiently generate maintenance schedules.

[1418] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1419] In this invention, the server includes means for collecting basic information, maintenance history, and property data of building materials for homes, means for collecting basic information, maintenance history, and property data of factory equipment, means for a generative AI model to extract and analyze features based on the collected data, means for creating an optimal maintenance schedule based on the analysis results and notifying the user, and means for collecting feedback data from users who have received the notification and updating the database. This enables efficient and accurate maintenance schedule management for homes and factory equipment.

[1420] A "house" is a building constructed using building materials for human habitation.

[1421] "Basic information" refers to basic data such as the structure of the object, the year of installation, the address, and the materials used.

[1422] "Maintenance history" refers to data on the date, time, and content of past repairs and maintenance work, as well as the materials used.

[1423] "Characteristic data" refers to detailed data such as the manufacturer, model number, and material of the building materials and equipment used.

[1424] "Factory equipment" is a general term for machines and devices installed for manufacturing and production activities.

[1425] A "data collection means" is a method or system for inputting, recording, or obtaining information about an object.

[1426] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and perform tasks such as prediction and classification.

[1427] "Means for extracting features and performing analysis" refers to methods or systems that efficiently find relevant information and patterns from collected data and perform analysis based on them.

[1428] The "optimal maintenance period" refers to the most appropriate time to perform maintenance depending on the condition of the equipment and building materials.

[1429] "Feedback data" refers to data provided by the user regarding the results of the performed maintenance and new information.

[1430] A "means for updating a database" is a method or system for adding or modifying new collected data to an existing database.

[1431] A "means for notifying" is a method or system for conveying information to a user.

[1432] This invention relates to a system for generating optimal maintenance schedules for residential and factory facilities. Servers, terminals, and users work together to collect, analyze, and notify data, thereby achieving efficient maintenance management.

[1433] Hardware and Software Configuration

[1434] Hardware

[1435] Server: A server for hosting the database and generative AI model. Examples include AWS EC2 and Google Cloud.

[1436] Client Device: Smartphone, tablet, or head-mounted display (HMD) used for data collection and notification. Examples include iPhone, Android devices, and Microsoft HoloLens.

[1437] software

[1438] Data collection interface: A web or mobile app that allows users to enter basic information about home and industrial facilities, maintenance history, and characteristics of building materials and equipment.

[1439] Generative AI model: An AI model implemented using TensorFlow or PyTorch that analyzes data and predicts maintenance times.

[1440] Notification system: A notification system using a microservices architecture that notifies users about scheduled maintenance via email, SMS, or in-app messages.

[1441] System operation explanation

[1442] 1. Data collection

[1443] The server collects basic information about the home and factory facilities provided by the user, maintenance history, and characteristic data of building materials and equipment. The user enters this data through the application form and sends it to the server.

[1444] 2. Data Analysis

[1445] The server uses generative AI models to extract features and analyze the collected data, cleaning and pre-processing the data, and notifying the user if missing data or outliers are detected.

[1446] 3. Generate a maintenance schedule

[1447] The generative AI model predicts the optimal maintenance period based on the collected data. The server generates a maintenance schedule based on the analysis results and notifies each user.

[1448] 4. Notifying users and gathering feedback

[1449] The server notifies users of the scheduled maintenance. Users receive the notification and prepare for the next maintenance based on the notification. After the actual maintenance is performed, users input their feedback into the system, and the database is updated.

[1450] Specific examples

[1451] For example, a factory manager can collect maintenance data for equipment in a factory and use an AI model to predict when the next maintenance will be required. The AI ​​model analyzes the deterioration pattern of the equipment based on past maintenance history and equipment characteristic data, and determines the optimal maintenance timing. As a result, the factory manager will be notified via a notification system with a specific date and time, such as "The next maintenance for equipment ID: 001 is December 15, 2023."

[1452] Prompt Sentence Examples

[1453] Equipment ID: 001

[1454] Last maintenance date: 2022-06-10

[1455] Materials used: bearings, lubricants

[1456] Current status: Driving

[1457] In this way, an embodiment of a system that realizes efficient and highly accurate maintenance management is constructed.

[1458] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1459] Step 1:

[1460] The user inputs basic information about the home or factory facility, maintenance history, and characteristic data of building materials and equipment.

[1461] Input: Basic information about the home or factory facilities, maintenance history, and characteristic data of building materials and equipment

[1462] Specific operation: A user enters information about a home or factory facility into a form via a smartphone or tablet application, such as the year of construction or details of past maintenance work.

[1463] Output: The input data is sent to the server.

[1464] Step 2:

[1465] The server stores the received data in a database.

[1466] Input: Basic information sent by the user, maintenance history, property data of building materials and equipment

[1467] What happens: The server receives the data and stores it in a consistent format in the database. Data normalization and preprocessing are also performed at this stage.

[1468] Output: Saved data

[1469] Step 3:

[1470] The server begins analysis based on the stored data.

[1471] Input: Basic information stored in the database, maintenance history, property data of building materials and equipment

[1472] Data processing: Preprocessing involves cleaning the data and detecting missing data and outliers.

[1473] What it does: The server performs data cleaning to detect missing data and outliers, notifies the user of any detected missing data or outliers, collects user feedback if necessary, and updates the database.

[1474] Output: Cleaned data

[1475] Step 4:

[1476] Analysis is performed using a generative AI model.

[1477] Input: Basic information on cleaning, maintenance history, property data of building materials and equipment

[1478] Data computation: Generative AI models extract features and predict degradation patterns and lifespan.

[1479] How it works: The server analyzes the data using a generative AI model built using TensorFlow and PyTorch. The generative AI model extracts features based on each data point and predicts degradation patterns and lifespan.

[1480] Output: Analysis results (next maintenance time and recommendations)

[1481] Step 5:

[1482] The server creates an optimal maintenance schedule based on the analysis results and notifies the user.

[1483] Input: Analysis results of the generative AI model

[1484] How it works: The server receives the analysis results and creates an optimal maintenance schedule for each facility or home, then notifies the user via email, SMS, or in-app message.

[1485] Output: Maintenance schedule notification sent to user

[1486] Step 6:

[1487] The user receives the notification and enters the feedback data.

[1488] Input: Maintenance schedule notification, feedback data

[1489] Specific operation: The user confirms the notification and starts preparations for the next maintenance. After the actual maintenance is completed, the results are entered as feedback data through the application and sent to the server.

[1490] Output: Feedback data is sent to the server

[1491] Step 7:

[1492] The server updates the database based on the received feedback data.

[1493] Input: Feedback data

[1494] What happens: The server receives the feedback data and updates the database, ensuring that the next analysis is based on the most up-to-date information.

[1495] Output: Updated database

[1496] This enables users, servers, and generative AI models to work together to efficiently manage the maintenance of residential and factory facilities.

[1497] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1498] This invention relates to a system that collects and analyzes basic information about a home, its maintenance history, and building material characteristics data to generate an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging data between a server, terminals, and users, and by performing analysis and notifications. Furthermore, by combining it with an emotion engine, the system recognizes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[1499] 1. Data collection and capture

[1500] server

[1501] The server provides an interface for collecting information about homes. Users can enter the information through a web app or mobile app. The server receives the basic information about the home (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[1502] User

[1503] The user inputs basic information about the house, its maintenance history, and the characteristics of the building materials through the interface, and the data entered by the user is sent to the server.

[1504] 2. Analyzing the data and applying the model

[1505] server

[1506] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the home's deterioration pattern and lifespan, and identifies the optimal maintenance period and content. The analysis results are stored in a database.

[1507] 3. Creating a proposal and notifying users

[1508] server

[1509] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended times. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, notifies the user with the optimal timing and content. Notification methods include email, in-app messages, and SMS.

[1510] User

[1511] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[1512] 4. Regular follow-up

[1513] server

[1514] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[1515] Specific examples

[1516] Example 1: Collecting Data

[1517] Mr. Yamada (the user) enters basic information about his house and its past maintenance history into the system. For example, he enters that the roof was repaired in 2016. The server stores this information in a database.

[1518] Example 2: Analyzing Data

[1519] The server runs a generative AI model based on Yamada's house data, which analyzes the roof's deterioration patterns and predicts when the next repairs will be required.

[1520] Example 3: Notifications and feedback

[1521] The server notifies Yamada of the next scheduled maintenance. "We recommend that the next roof inspection and repair be performed in June 2023." Yamada makes preparations based on this notification, and after actually performing the maintenance, feeds the results back into the system. The emotion engine analyzes Yamada's feedback data and recognizes his emotional state. The next notification and advice will be given taking the results into account.

[1522] In this way, collaboration between the server, generative AI, emotion engine, and user can assist in optimal home maintenance planning, ensuring the safety and longevity of the home.

[1523] The processing flow will be explained below.

[1524] Step 1:

[1525] The server provides an interface for collecting housing information, allowing users to enter the information through a web app or mobile app.

[1526] Step 2:

[1527] Through the interface, users input basic information about the house (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.).

[1528] Step 3:

[1529] The server receives the data entered by the user and stores it in a database, where it is standardized and pre-processed for consistency.

[1530] Step 4:

[1531] The server feeds the collected data into a generative AI model, which cleans and shapes the data to detect missing data and outliers.

[1532] Step 5:

[1533] The generative AI extracts features from the data provided, analyzes the deterioration pattern of the home, and predicts its lifespan, predicting the progress of deterioration and when the next maintenance will be required.

[1534] Step 6:

[1535] The server creates an optimal maintenance schedule based on the analysis results of the generative AI, which includes specific maintenance items and their recommended times.

[1536] Step 7:

[1537] The server will notify the user of the optimal maintenance schedule via email, in-app message, SMS, etc.

[1538] Step 8:

[1539] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, the user can send questions or feedback to the server through the interface.

[1540] Step 9:

[1541] The server receives feedback data from users and updates the database to reflect the most up-to-date information.

[1542] Step 10:

[1543] The server runs an emotion engine that recognizes emotions from user input and feedback data, analyzes the user's emotional state, and adjusts advice and reminders accordingly.

[1544] Step 11:

[1545] The server sends users advice and reminders based on their emotional state, which are tailored to improve their motivation.

[1546] Step 12:

[1547] The server periodically sends reminders to users for the next maintenance appointment, and the emotion engine adjusts the timing and content of the reminders based on the user's latest emotional state.

[1548] Step 13:

[1549] The server continuously analyzes the collected data to improve the performance of the generative AI model, and updates the maintenance schedule and notifies users as needed.

[1550] Example 2

[1551] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1552] Home maintenance typically requires users to understand the home's past history and current condition, and then perform the maintenance at the appropriate time and with the appropriate content based on that information. However, many homeowners find it difficult to manage this properly, and as a result, maintenance is often neglected. This problem accelerates the deterioration of the home, ultimately leading to the need for serious repairs and shortening the home's lifespan. Furthermore, existing systems have difficulty providing appropriate notifications and feedback that take the user's emotional state into account, which can lead to issues such as reduced user satisfaction and reduced system usage efficiency.

[1553] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the home, maintenance history, and property data of building materials; means for cleaning and shaping the collected data and detecting missing data and outliers; means for applying a generative AI model to the shaped data to extract and analyze features; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state from feedback data and input data using an emotion engine and adjusting the timing and content of the notification; means for collecting feedback data from the user who received the notification and updating the database; and means for periodically sending a reminder for the next maintenance and performing a new analysis using the generative AI model. This enables efficient maintenance that takes the user's emotional state into consideration while ensuring the safety and long life of the home.

[1554] "Basic information about the house" refers to basic data about the house itself, such as the year it was built, its address, and its structure.

[1555] "Maintenance history" is a record of the date, time, content, materials used, etc. of past maintenance work.

[1556] "Characteristic data of building materials" is data that indicates characteristics such as the manufacturer, model number, and material of the building materials used in the house.

[1557] "Means of collection" refers to the mechanism by which a user inputs information through an interface, the server receives it, and stores it in a database.

[1558] A "generative AI model" is an artificial intelligence model that extracts features based on input data and performs analysis.

[1559] "Cleaning and shaping" refers to the process of detecting missing or outliers in data and correcting or modifying them.

[1560] "Means for analysis" refers to the mechanism for extracting and analyzing the characteristics of collected data using a generative AI model.

[1561] The "optimal maintenance schedule" is a schedule that includes specific maintenance items and their recommended timing, proposed based on deterioration patterns and lifespan predictions.

[1562] "Means of notification" refers to the method of communicating the maintenance schedule to users, including email, in-app messages, SMS, etc.

[1563] "Emotion engine" refers to technology that analyzes a user's emotional state from feedback data and input data, and adjusts the timing and content of notifications based on that.

[1564] "Feedback data" refers to data including results reports and opinions provided by users after maintenance has been performed.

[1565] "Means for updating the database" refers to a mechanism for adding or amending collected feedback data to an existing database.

[1566] A "reminder" is a periodic message that notifies the user again of the next scheduled maintenance.

[1567] "New analysis" means that the generative AI model uses regularly collected feedback data to conduct the latest analysis and reflect the results.

[1568] This invention relates to a system that collects information about a home and generates an optimal maintenance schedule. This system ensures the safety and longevity of the home by exchanging information between a server, terminals, and users, and by analyzing and notifying them. Furthermore, it uses an emotion engine to recognize the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content, thereby improving maintenance efficiency and user satisfaction.

[1569] The server first provides an interface for collecting basic information about the home, its maintenance history, and the characteristics of building materials. This interface is implemented as a web app or mobile app, through which users can input data. Specifically, the server receives the basic information (year built, address, structure, etc.), maintenance history (date, time, content, materials used, etc.), and the characteristics of building materials (manufacturer, model number, material, etc.) and stores them in a database.

[1570] The collected data is cleaned and shaped by the server. If missing data or outliers are detected, the server automatically sends a notification to the user requesting them to complete or correct them. After cleaning and shaping, the data is applied to the generative AI model.

[1571] The generative AI model uses the formatted data to predict the home's deterioration patterns and lifespan. The model identifies the optimal maintenance period and content for the home and stores the analysis results in a database. Based on the analysis results, the server creates an optimal maintenance schedule and notifies the user. This notification is sent via email, in-app messages, SMS, etc.

[1572] Furthermore, the emotion engine analyzes the user's emotional state from feedback data and input data, and adjusts the timing and content of notifications. This helps users to carry out maintenance at the appropriate time. The user checks the notified schedule and carries out the maintenance. After carrying out the maintenance, the results can be fed back to the system. The server collects this feedback data and updates the database.

[1573] The server also periodically sends reminders to users for upcoming maintenance. The emotion engine adjusts the timing and content of the reminders, allowing users to appropriately prepare for the next maintenance. Based on the periodically collected feedback data, the generative AI model performs new analysis and updates the maintenance schedule accordingly.

[1574] As a concrete example, the following prompt sentences are used when the user inputs house data:

[1575] Prompt Sentence Examples

[1576] Generate a deterioration prediction and an optimal maintenance schedule for a home based on basic information, maintenance history, and building material characteristics data entered by the user. Below are some examples of specific data.

[1577] basic information:

[1578] Construction year: 2010

[1579] Address: Shinjuku-ku, Tokyo

[1580] Structure: wooden

[1581] Maintenance history:

[1582] Date: March 2016

[1583] Content: Roof repair

[1584] Materials used: Material A

[1585] Building material property data:

[1586] Manufacturer: Manufacturer X

[1587] Model number: YZ123

[1588] Material: Cement

[1589] Predict the optimal maintenance timing and content.

[1590] As described above, collaboration between the server, generative AI model, emotion engine, and user can efficiently support home maintenance planning and ensure the safety and long life of homes.

[1591] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1592] Step 1:

[1593] User

[1594] Users enter basic information about the home, maintenance history, and characteristic data of building materials using input forms in the web app or mobile app. The data entered includes the year of construction, address, structure, past maintenance dates and times, details, materials used, manufacturer, model number, and quality of building materials. This information is sent to the server by the user manually entering it and pressing the send button. Input: Basic information about the home, maintenance history, characteristic data of building materials. Output: Data sent to the server.

[1595] Step 2:

[1596] server

[1597] The server receives data sent by the user and saves it in the database in real time. Processing performed here includes format checks for input data, confirmation of required fields, and detection of missing data. For example, if the address or year of construction is not entered, an error message is generated. Input: Data sent by the user. Output: Data saved in the database, error message (if necessary).

[1598] Step 3:

[1599] server

[1600] The server cleans and formats the stored data. It detects missing data and outliers and sends a completion request to the user accordingly. For example, if there is missing data, it automatically sends a completion request email saying, "The construction year has not been entered. Please enter it." Input: Stored data. Output: Cleaned and formatted data, completion request email.

[1601] Step 4:

[1602] server

[1603] The server inputs the cleaned and formatted data into a generative AI model, which extracts and analyzes features. The generative AI model predicts the deterioration pattern and lifespan of the home, and identifies the optimal maintenance timing and content. For example, it may predict that "roof repairs will be required in June 2023." Input: Cleaned and formatted data. Output: Deterioration pattern, lifespan prediction, optimal maintenance timing.

[1604] Step 5:

[1605] server

[1606] The server automatically creates an optimal maintenance schedule based on the analysis results of the generative AI model. This schedule includes specific maintenance items and their recommended timing. For example, it may include the content, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Analysis results of the generative AI model. Output: Optimal maintenance schedule.

[1607] Step 6:

[1608] server

[1609] The server uses an emotion engine to analyze the user's emotional state from their feedback data and input data. Based on these results, it adjusts the timing and content of notifications. For example, if past feedback indicates that the user is feeling stressed, it sends a message that takes this into consideration. Input: Feedback data, input data. Output: Emotional state analysis results, adjusted notification content.

[1610] Step 7:

[1611] server

[1612] The server notifies the user of the optimal maintenance schedule via email, in-app message, SMS, etc. For example, it sends a message saying, "We recommend that the next roof inspection and repair be performed in June 2023." Input: Optimal maintenance schedule, adjusted notification content. Output: Notification to the user.

[1613] Step 8:

[1614] User

[1615] The user receives a notification from the server and prepares for maintenance. The user carries out the maintenance according to the notification and feeds back the results to the server through the interface. For example, the user can enter and send information such as "The roof was inspected and repaired in June 2023." Input: Feedback data. Output: Sending results to the server.

[1616] Step 9:

[1617] server

[1618] The server receives feedback data from users and updates the database. The updated data is used for the next analysis and to generate maintenance schedules. Input: Feedback data from users. Output: Updated database.

[1619] Step 10:

[1620] server

[1621] The server periodically sends reminders to users about upcoming maintenance. The timing and content of these reminders are adjusted by the emotion engine. For example, a reminder such as "Don't forget to come for your next scheduled inspection" can be sent. Input: Next maintenance information based on the database. Output: Reminder notification.

[1622] Step 11:

[1623] server

[1624] The server runs the generative AI model again based on the feedback data collected periodically, and performs a new analysis. Based on the analysis results, the maintenance schedule is updated as appropriate. Input: Feedback data. Output: Updated analysis results and maintenance schedule.

[1625] Through the above steps, this system can efficiently support users in planning their home maintenance, ensuring the safety and longevity of their homes.

[1626] (Application example 2)

[1627] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1628] In recent years, physical store operators have been required to ensure operational efficiency and safety by properly maintaining their store buildings. However, determining the appropriate timing and content of maintenance is difficult, and maintenance work is often postponed depending on the operator's busy schedule or mood. This problem can lead to further deterioration of the building, resulting in large repair costs. There is also a risk that overlooking maintenance could compromise the safety of the store. Therefore, a system that allows physical store operators to plan and carry out maintenance at the appropriate time is needed.

[1629] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting basic information about the building, maintenance history, and characteristic data of building materials; means for a generative AI model to extract and analyze features based on the collected data; means for creating an optimal maintenance schedule based on the analysis results and notifying the user; means for analyzing the user's emotional state using an emotion engine and providing notifications and advice at appropriate times and with appropriate content; and means for collecting feedback data from users who have received the notifications and updating the database. This enables operators of physical stores to plan and implement optimal maintenance at appropriate times, ensuring the safety and long life of the store.

[1630] "Basic building information" refers to data including basic attributes and information of a building, such as the year of construction, address, and construction structure of the building.

[1631] "Maintenance history" is data that shows records of the date, time, content, materials used, etc. of maintenance work that has been carried out on a building in the past.

[1632] "Building material characteristic data" is data that includes detailed attribute information such as the manufacturer, model number, and quality of various building materials used in a building.

[1633] A "generative AI model" is an artificial intelligence model that extracts features from collected data and predicts building deterioration patterns and lifespans.

[1634] The "emotion engine" is a system that analyzes the user's emotional state and provides notifications and advice at the appropriate time and with the appropriate content based on that analysis.

[1635] "User" means the person or entity that is the owner or manager of the building and uses the maintenance management system.

[1636] "Database" means an electronic record system for storing collected basic building information, maintenance history, building material characteristic data, and feedback data.

[1637] "Feedback data" refers to information including the results and impressions of the maintenance carried out based on the maintenance schedule notified to the user.

[1638] A "maintenance schedule" is a plan created by a generative AI model that indicates the optimal time and content of building maintenance work.

[1639] "Notification" is a means of communicating generated maintenance schedules and other important information to users.

[1640] This invention relates to a system that collects and analyzes basic information about brick-and-mortar store buildings, maintenance history, and building material characteristic data to generate an optimal maintenance schedule. This system ensures the safety and longevity of stores by exchanging data between servers, terminals, and users, and by analyzing and notifying them. It also combines an emotion engine to recognize the user's emotional state and provide notifications and advice at the appropriate time and with the right content, thereby improving maintenance efficiency and user satisfaction.

[1641] 1. Data collection and capture

[1642] server

[1643] The server provides an interface for collecting building information. Users can input the information through a web app or mobile app. The server receives the basic building information (year built, address, structure, etc.), past maintenance history (date, time, contents, materials used, etc.), and characteristic data of the building materials used (manufacturer, model number, material, etc.) entered by the user, and stores them in a database.

[1644] User

[1645] The user inputs basic information about the building, its maintenance history, and the characteristics of the building materials through the interface. The data entered by the user is sent to the server.

[1646] 2. Analyzing the data and applying the model

[1647] server

[1648] The server applies a generative AI model to the collected data and begins processing to extract and analyze features. The data is cleaned and formatted, and if missing data or outliers are detected, the server notifies the user. The generative AI model predicts the building's deterioration pattern and lifespan, and identifies the optimal maintenance timing and content. The results of this analysis are stored in a database.

[1649] 3. Creating a proposal and notifying users

[1650] server

[1651] The server creates an optimal maintenance schedule based on the analysis results of the generative AI model. The schedule includes specific maintenance items and their recommended timing. The emotion engine also analyzes the user's emotional state based on feedback data and input data, and based on that, provides notifications and advice at the optimal timing and content. Notifications can be sent via email, in-app messages, SMS, etc.

[1652] User

[1653] The user checks the notified maintenance schedule and prepares for the next maintenance. If necessary, they can send questions or feedback to the server through the interface. The emotion engine recognizes the user's emotional state from the feedback data entered by the user and adjusts the content of the next notification or advice accordingly.

[1654] 4. Regular follow-up

[1655] server

[1656] The server periodically sends reminders to users for the next maintenance. The emotion engine adjusts the timing and content of these reminders to match the user's emotional state, allowing users to perform maintenance at the appropriate time. Furthermore, based on periodically collected feedback data, the generative AI model performs new analyses and updates the maintenance schedule accordingly.

[1657] Specific examples

[1658] Example 1: Collecting Data

[1659] The user enters basic information about his store and its past maintenance history into the system, for example, entering that the walls were repainted in 2020. The server stores this information in a database.

[1660] Example 2: Analyzing Data

[1661] The server runs a generative AI model based on the user's store data, which analyzes the deterioration patterns of the walls and predicts when the next repainting will be necessary.

[1662] Example 3: Notifications and feedback

[1663] The server notifies the user of the next scheduled maintenance. "We recommend that the next wall repainting be done in April 2025." The user makes preparations based on this notification, and after actually carrying out the maintenance, feeds the results back to the system. The emotion engine analyzes the user's feedback data and recognizes his emotional state. The next notification or advice will be given taking the results into consideration.

[1664] Prompt Sentence Examples

[1665] "Create the optimal next maintenance schedule based on your store data and maintenance history. Information to consider is:

[1666] Store construction year, address, structure

[1667] Characteristics of the building materials used (manufacturer, model number, material, etc.)

[1668] Past maintenance history (date, time, contents, materials used, etc.)

[1669] Store manager's emotional state

[1670] Please suggest specific maintenance items and recommended times.

[1671] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1672] Step 1:

[1673] Data collection

[1674] Input: Basic information about the building, maintenance history, and property data of building materials

[1675] Processing: Using a web app or mobile app, users input basic building information (e.g., year of construction, address, structure, etc.), past maintenance details (e.g., date and time, details, materials used, etc.), and building material characteristics data (e.g., manufacturer, model number, material, etc.). This input data is sent to the server via the interface.

[1676] Output: The input data is sent to the server and stored in a database.

[1677] Step 2:

[1678] Cleaning and shaping the data

[1679] Input: Basic building information, maintenance history, and building material characteristics data stored on the server

[1680] Processing: The server analyzes the stored data and detects missing data or outliers. If any missing data or outliers are found, the server notifies the user and asks them to complete the data.

[1681] Output: Cleaned and formatted data is generated and stored in a database.

[1682] Step 3:

[1683] Data analysis and feature extraction

[1684] Input: Clean and formatted data

[1685] Processing: The server begins analysis using a generative AI model (e.g., using Python or TensorFlow). The model extracts features from the input data and predicts the building's deterioration pattern and lifespan. This allows appropriate maintenance timing and content to be identified.

[1686] Output: Analysis results are generated and stored in a database.

[1687] Step 4:

[1688] Creating a maintenance schedule

[1689] Input: Analysis results from generative AI model

[1690] Processing: The server creates an optimal maintenance schedule based on the analysis results, which includes specific maintenance items and their recommended times.

[1691] Output: A maintenance schedule is generated and stored in the database.

[1692] Step 5:

[1693] Sentiment analysis with emotion engine

[1694] Input: User feedback data and maintenance history

[1695] Processing: The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's emotional state from their input data and feedback data. Based on this, it optimizes the content and timing of notifications and advice.

[1696] Output: The results of the sentiment analysis are generated and stored in a database.

[1697] Step 6:

[1698] User Notification

[1699] Input: Maintenance schedule, sentiment analysis results

[1700] Processing: The server notifies users of maintenance schedules and advice at appropriate times via email, in-app messages, SMS, etc.

[1701] Output: A notification is sent to the user.

[1702] Step 7:

[1703] Collecting feedback

[1704] Input: Feedback data from users

[1705] Processing: After the user actually performs the maintenance, they provide feedback to the server via the interface, including the results and their impressions. The received feedback data is reanalyzed by the emotion engine and stored in the database.

[1706] Output: The updated feedback data is saved in the database.

[1707] Step 8:

[1708] Sending periodic reminders

[1709] Input: Stored feedback data, maintenance schedule

[1710] Processing: The server periodically sends reminders to users about upcoming maintenance schedules. The timing and content of the notifications are adjusted based on the analysis results of the emotion engine.

[1711] Output: A reminder notification is sent to the user.

[1712] This series of processes enables store operators to plan and implement maintenance efficiently and effectively.

[1713] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1714] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1715] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1716] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1717] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1718] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1719] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1720] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1721] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1722] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1723] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1724] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1725] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1726] 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.

[1727] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1728] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1729] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1730] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1731] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1732] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1733] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1734] The following is further disclosed regarding the above embodiment.

[1735] (Claim 1)

[1736] A means of collecting basic information about the home, its maintenance history, and building material characteristics data;

[1737] A means for a generative AI model to extract and analyze features based on the collected data;

[1738] A means for creating an optimal maintenance schedule based on the analysis results and notifying the user of the schedule;

[1739] means for collecting feedback data from users who have received the notification and updating the database;

[1740] A system including:

[1741] (Claim 2)

[1742] The system of claim 1, wherein the generative AI model includes means for predicting deterioration patterns and lifespans of a home and identifying optimal maintenance times.

[1743] (Claim 3)

[1744] 2. The system according to claim 1, further comprising means for detecting a shortage or an abnormal value in the collected data and notifying a user to supplement the shortage or abnormal value.

[1745] "Example 1"

[1746] (Claim 1)

[1747] A means of collecting basic information about the home, its maintenance history, and building material characteristics data;

[1748] a means for storing the user-entered data in a database;

[1749] a means of standardizing and preprocessing the stored data;

[1750] A means for the generative AI model to extract and analyze features based on the collected data;

[1751] A means for creating an optimal maintenance schedule based on the analysis results, allowing the user to select a notification method, and notifying the user;

[1752] a means for collecting feedback data from notified users and updating the database;

[1753] a means for periodically sending reminders to the user of upcoming maintenance;

[1754] A means to update the generative AI model based on feedback data; and

[1755] A system including:

[1756] (Claim 2)

[1757] 10. The system of claim 1, wherein the generative AI model includes means for generating and predicting home deterioration patterns and identifying optimal maintenance periods.

[1758] (Claim 3)

[1759] 10. The system of claim 1, further comprising means for detecting missing or outliers in the collected data and notifying a user to complete the missing or outlier data.

[1760] "Application Example 1"

[1761] (Claim 1)

[1762] A means of collecting basic information about the home, its maintenance history, and building material characteristics data;

[1763] A means of collecting basic information, maintenance history, and equipment characteristics data for factory equipment;

[1764] A means for a generative AI model to extract and analyze features based on the collected data;

[1765] A means for creating an optimal maintenance schedule based on the analysis results and notifying the user of the schedule;

[1766] means for collecting feedback data from users who have received the notification and updating the database;

[1767] A system including:

[1768] (Claim 2)

[1769] The system of claim 1, wherein the generative AI model includes means for predicting deterioration patterns and lifespans of residential and factory equipment and identifying optimal maintenance times.

[1770] (Claim 3)

[1771] 2. The system according to claim 1, further comprising means for detecting a shortage or an abnormal value in the collected data and notifying a user to supplement the shortage or abnormal value.

[1772] "Example 2: Combining Emotion Engines"

[1773] (Claim 1)

[1774] A means of collecting basic information about the home, its maintenance history, and building material characteristics data;

[1775] a means for cleaning and shaping the collected data to detect missing data and outliers;

[1776] A means for applying a generative AI model based on the formatted data to extract and analyze features;

[1777] A means for creating an optimal maintenance schedule based on the analysis results and notifying the user of the schedule;

[1778] A means for analyzing the emotional state of a user from feedback data and input data using an emotion engine and adjusting the timing and content of notifications;

[1779] means for collecting feedback data from users who have received the notification and updating the database;

[1780] A means to periodically send reminders for upcoming maintenance and run new analyses using generative AI models;

[1781] A system including:

[1782] (Claim 2)

[1783] The system of claim 1, wherein the generative AI model includes means for predicting deterioration patterns and lifespans of a home and identifying optimal maintenance times.

[1784] (Claim 3)

[1785] 2. The system according to claim 1, further comprising means for detecting a shortage or an abnormal value in the collected data and notifying a user to supplement the shortage or abnormal value.

[1786] "Application example 2 when combining emotion engines"

[1787] (Claim 1)

[1788] A means of collecting basic building information, maintenance history, and building material characteristics data;

[1789] A means for a generative AI model to extract and analyze features based on the collected data;

[1790] A means for creating an optimal maintenance schedule based on the analysis results and notifying the user of the schedule;

[1791] A means of analyzing the user's emotional state using an emotion engine and providing notifications and advice at appropriate times and with appropriate content;

[1792] a means for collecting feedback data from users who have received the notification and updating the database;

[1793] A system including:

[1794] (Claim 2)

[1795] The system of claim 1, wherein the generative AI model includes means for predicting building deterioration patterns and lifespans and identifying optimal maintenance times.

[1796] (Claim 3)

[1797] The system according to claim 1, further comprising means for detecting a shortage or an abnormal value in the collected data and notifying a user to supplement the shortage or abnormal value. [Explanation of symbols]

[1798] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting basic information about the home, its maintenance history, and building material characteristics data; A means for a generative AI model to extract and analyze features based on the collected data; A means for creating an optimal maintenance schedule based on the analysis results and notifying the user of the schedule; means for collecting feedback data from users who have received the notification and updating the database; A system including:

2. The system of claim 1 , wherein the generative AI model includes means for predicting deterioration patterns and lifespans of a home and identifying optimal maintenance times.

3. The system according to claim 1 , further comprising means for detecting a shortage or an abnormal value in the collected data and notifying a user to supplement the shortage or abnormal value.

Images