System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring energy and water usage data in real time from sensors installed in each home or business; means for cleaning the acquired data, removing noise, and converting the data into a format suitable for learning; means for training a model using the cleaned data and generating an algorithm for proposing an optimal resource management method for each home or business; means for generating a specific action plan based on an analysis result and delivering the action plan to a user; and means for collecting feedback from the user and retraining the model.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] Wasteful and inefficient use of energy and water has become a serious problem in modern homes and businesses, resulting in increased environmental impact and higher operational costs. Providing effective ways to smartly manage resources and reduce waste is an urgent priority for sustainable living. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for acquiring energy and water usage data in real time from sensors installed in each home or business, a means for cleaning the acquired data, removing noise, and converting it into a format suitable for learning, a means for training a model using the cleaned data and generating an algorithm for proposing an optimal resource management method for each home or business, a means for generating a specific action plan based on the analysis results and distributing it to users, and a means for collecting feedback from users and retraining the model. This system optimizes resource use in homes and businesses, thereby reducing environmental impact and operational costs.

[0006] A "sensor" is a device that detects and captures energy and water usage data in real time.

[0007] "Energy" refers to natural or artificially produced power, such as electricity and gas, consumed in homes and businesses.

[0008] "Water" refers to liquids such as tap water, groundwater, and rainwater used in homes and businesses.

[0009] "Data cleaning" is the process of removing noise and inconsistencies from collected data and converting it into a form suitable for analysis and learning.

[0010] "Noise" is meaningless information such as inaccurate values ​​and outliers contained in data.

[0011] "Format suitable for learning" refers to data that has been formatted so that it can be used directly in data analysis and machine learning algorithms.

[0012] "Model training" is the process of using cleaned data to build and improve machine learning algorithms to perform specific tasks.

[0013] An "algorithm" is a systematized procedure or calculation method for solving a specific problem.

[0014] "Analysis Results" means specific information or insights derived from acquired and processed data.

[0015] An "action plan" is a specific course of action or measure recommended to the user based on the analysis results.

[0016] "Feedback" refers to information provided by users about the results of using the system and areas for improvement.

[0017] "Retraining" is the process of retraining an existing model based on newly collected data and feedback to improve its accuracy and effectiveness.

[0018] A "system" is an overall structure or mechanism that combines the above-mentioned means to optimize resource management in homes and businesses. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention details a system designed to optimize energy and water resource management in homes and businesses.

[0041] 1. Data collection function

[0042] The server collects real-time energy and water usage data from sensors installed in homes and businesses. This data collection is done through APIs (application programming interfaces). For example, sensors connected to electricity or water meters periodically record usage information and send it to the server.

[0043] 2. Data preprocessing function

[0044] The server cleans the acquired data. The data cleaning process removes noise and outliers and ensures data consistency. Specifically, it complements missing data and corrects frequently occurring data errors.

[0045] 3. AI model training function

[0046] The server uses the cleaned data to train AI algorithms. The AI ​​models learn from past energy and water usage patterns and predict future usage. The models are built using machine learning techniques, including deep learning and decision tree algorithms.

[0047] 4. Insight generation function

[0048] The server analyzes real-time data using the trained model, which can detect peak energy usage and unusual water usage. For example, if unusual water usage is detected in a household, it could indicate a possible leak.

[0049] 5. Action plan generation and distribution function

[0050] The server generates specific action plans based on the analysis results, such as "Schedule the use of your washing machine outside of the hours of 6:00 PM to 9:00 PM to avoid peak power usage." These action plans are delivered to the device in the form of a report.

[0051] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email.

[0052] 6. Execution and feedback functions

[0053] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0054] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[0055] Specific examples

[0056] Example 1: Reducing power usage during peak hours

[0057] 1. The server obtains household electricity consumption data from sensors.

[0058] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0059] 3. The server generates specific guidelines for reducing peak power usage.

[0060] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[0061] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[0062] Example 2: Abnormal water usage detection

[0063] 1. The server obtains water usage data from sensors on each water supply in the home.

[0064] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[0065] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[0066] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[0067] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0068] In this way, the system provides a range of functions to optimize resource management in homes and businesses and achieve sustainable living.

[0069] The processing flow will be explained below.

[0070] Energy and Water Resource Management System Processing Flow

[0071] Example 1: Reducing power usage during peak hours

[0072] Step 1: Data collection

[0073] The server obtains household electricity consumption data from sensors via an API.

[0074] Step 2: Data Preprocessing

[0075] The server cleans the acquired data and removes noise and outliers, specifically by filling in missing values ​​and correcting abnormally high values.

[0076] Step 3: Identify peak times

[0077] The server uses the cleaned data to analyze power consumption patterns over the past few weeks and identify peak times for power consumption.

[0078] Step 4: Generate an action plan

[0079] The server generates specific guidelines for reducing peak power usage, including recommendations such as "avoid using energy-intensive appliances (washers, dryers, etc.) between 6:00 PM and 9:00 PM."

[0080] Step 5: Report Distribution

[0081] The server generates a report containing the above guidelines and delivers it to the terminal.

[0082] Step 6: User Notification

[0083] The device converts the reports received from the server into a user-readable format and provides important insights, such as push notifications or in-app alerts that advise users to avoid using the device during peak power hours.

[0084] Step 7: Take Action

[0085] Based on the notification, users can change the time they use their washing machine or dryer to off-peak hours.

[0086] Example 2: Abnormal water usage detection

[0087] Step 1: Data collection

[0088] The server receives real-time water usage data from the household water supply via sensors.

[0089] Step 2: Data Preprocessing

[0090] The server cleans the acquired data and distinguishes between normal and abnormal values, specifically identifying values ​​that deviate significantly from normal usage patterns.

[0091] Step 3: Anomaly detection

[0092] The server analyzes the cleaned data and compares it with historical usage patterns to detect abnormal water usage in real time.

[0093] Step 4: Generate anomaly notifications

[0094] Based on the detected anomalies, the server generates alerts indicating possible water leaks, etc.

[0095] Step 5: Delivering notifications

[0096] The server distributes the generated alerts to the terminals.

[0097] Step 6: User Notification

[0098] The device immediately sends a notification of the abnormality detected by the server to the user, such as, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[0099] Step 7: Take Action

[0100] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[0101] Through these steps, the system optimizes resource usage in homes and businesses, reducing environmental impact and operational costs.

[0102] Example 1

[0103] 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."

[0104] Optimizing the efficiency of energy and water use in modern homes and businesses is an important challenge from the perspective of sustainable resource management. However, the processes of individual data collection, analysis, optimization proposals, and feedback based on those data are complex, and advanced technology is required to achieve effective management. Conventional methods make it difficult to consistently execute these processes, making it difficult to achieve efficient resource management.

[0105] 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.

[0106] In this invention, the server includes: means for acquiring energy and water usage data in real time from multiple sensors installed in each home or business; means for cleaning the acquired data, removing noise and outliers, and converting it into a consistent format; means for training an AI model using the cleaned data to generate an algorithm that proposes an optimal resource management method for each home or business; means for analyzing the real-time data using the trained AI model to detect energy and water usage patterns; means for generating a specific action plan based on the analysis results and distributing it to the user's device; and means for collecting feedback from the user and retraining the AI ​​model. This automates the process from consistent data collection to optimization proposals, feedback collection, and retraining, enabling efficient resource management.

[0107] "Data collection means" refers to a means for obtaining energy and water usage data in real time from multiple sensors installed in each home or business.

[0108] A "data cleaning means" is a means for cleaning acquired data, removing noise and outliers, and converting the data into a consistent format.

[0109] The "AI model training means" is a means for training an AI model using cleaned data and generating an algorithm that proposes optimal resource management methods for each household or business.

[0110] "Real-time data analysis means" means a means for analyzing real-time data using a trained AI model to detect energy and water usage patterns.

[0111] The "action plan generation means" is a means for generating a specific action plan based on the analysis results and distributing it to the user's terminal.

[0112] "Feedback collection means" refers to the means used to collect user feedback and retrain the AI ​​model.

[0113] This invention relates to a system that optimizes energy and water usage in homes and businesses. This system collects data from multiple sensors installed in each home or business and analyzes it using AI technology to propose efficient resource management. The specific configuration and operation of this system are described below.

[0114] 1. Data collection function

[0115] The server collects real-time energy and water usage data from sensors installed in each home or business. This data is collected through an API (Application Programming Interface). Specifically, sensors connected to electricity and water meters periodically record usage information and send that data to the server. For this reason, the server must be equipped with a high-performance network interface and database system.

[0116] 2. Data preprocessing function

[0117] The server cleans the acquired data. The data cleaning process involves removing noise and outliers and filling in missing data to ensure data consistency. This process uses data cleansing tools such as Pandas and NumPy.

[0118] 3. AI model training function

[0119] The server uses the cleaned data to train an AI model. Specifically, it uses deep learning frameworks (such as TensorFlow or PyTorch) and decision tree algorithms to learn past energy and water usage patterns and build a model to predict future usage. This AI model requires a lot of computing resources to accurately learn resource usage patterns.

[0120] 4. Insight generation function

[0121] The server analyzes real-time data using a trained AI model. This analysis can detect peak energy usage times and abnormal water usage. For example, if abnormal water usage is detected in a household, it could suggest a possible water leak. The analysis results are provided with high accuracy, allowing the system to suggest accurate and prompt actions to users.

[0122] 5. Action plan generation and distribution function

[0123] The server generates a specific action plan based on the analysis results, such as "Schedule the use of your washing machine outside the hours of 6:00 PM to 9:00 PM to avoid peak power usage." The generated action plan is delivered to the device in the form of a report.

[0124] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email, allowing the user to take the necessary action at the appropriate time.

[0125] 6. Execution and feedback functions

[0126] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0127] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness. This feedback loop allows the system to constantly adapt to the latest situation and provide optimal resource management.

[0128] Specific examples

[0129] Example 1: Reducing power usage during peak hours

[0130] 1. The server obtains household electricity consumption data from sensors.

[0131] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0132] 3. The server generates specific guidelines for reducing peak power usage.

[0133] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[0134] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[0135] Example 2: Abnormal water usage detection

[0136] 1. The server obtains water usage data from sensors on each water supply in the home.

[0137] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[0138] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[0139] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[0140] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0141] Prompt Sentence Examples

[0142] "Analyze electricity usage data and suggest optimal ways to reduce energy consumption during peak hours."

[0143] In this way, the system provides a range of functions to optimise resource management in homes and businesses and achieve sustainable living.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1: Data collection

[0146] The server collects real-time energy and water usage data from multiple sensors installed in each home or business, and sends the data recorded by the sensors to the server via an API.

[0147] Input: Real-time usage data recorded by sensors

[0148] Output: Raw usage data stored on the server

[0149] Specific behavior:

[0150] The server periodically sends API requests to receive data from each sensor, which is then stored in a database.

[0151] Step 2: Data Preprocessing

[0152] The server cleans the acquired data, removing noise and outliers and filling in missing data to ensure data consistency.

[0153] Input: Raw usage data

[0154] Output: Clean usage data

[0155] Specific behavior:

[0156] The server cleans the data using a data cleansing tool (e.g., Pandas, NumPy), filters out noise and outliers, and fills in missing data before storing it back in the database.

[0157] Step 3: Training the AI ​​model

[0158] The server uses the cleaned data to train an AI model, using deep learning frameworks and decision tree algorithms.

[0159] Input: Clean usage data

[0160] Output: A trained AI model

[0161] Specific behavior:

[0162] The server generates a training dataset and inputs it into the AI ​​model, and once the training process is complete, the trained model is saved.

[0163] Step 4: Insight generation

[0164] The server analyzes real-time data using a trained AI model to detect usage patterns and anomalies.

[0165] Input: Real-time data, trained AI model

[0166] Output: Detected insights (e.g. peak times, unusual usage)

[0167] Specific behavior:

[0168] The server inputs real-time data into the AI ​​model to detect anomalies and analyze peak times, and the results are stored in a database.

[0169] Step 5: Generate and distribute an action plan

[0170] The server generates a specific action plan based on the analysis results and distributes it to the device.

[0171] Input: Discovered insights

[0172] Output: Action Plan

[0173] Specific behavior:

[0174] The server generates an action plan and sends it to the device, which then converts it into a format that the user can view and delivers key insights via push notifications.

[0175] Step 6: Implementation and feedback

[0176] The user takes action according to the delivered action plan and provides the results as feedback to the server.

[0177] Input: Action Plan

[0178] Output: Actions taken and feedback

[0179] Specific behavior:

[0180] The user acts on the action plan and sends the results through the application to the server, which receives the feedback and uses it to retrain the AI ​​model.

[0181] This series of processing steps results in efficient and sustainable resource management.

[0182] (Application example 1)

[0183] 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."

[0184] Conventional energy and water management systems in homes and businesses have focused on optimizing resources for individual users, but in large facilities such as factories, it has been difficult to reduce energy usage during peak hours and quickly detect and respond to abnormal water usage. This has led to a demand for energy efficiency and reduction of water waste to reduce overall costs.

[0185] 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.

[0186] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each facility; means for cleaning the acquired data, removing noise, and converting it into a format suitable for learning; means for training a model using the cleaned data and generating an algorithm for proposing an optimal resource management method for each facility; means for generating a specific action plan based on the analysis results and distributing it to users; means for collecting feedback from users and retraining the model; means for collecting data from sensors attached to machines and devices in the factory and detecting peak times and abnormalities; means for generating an action plan to reduce energy usage during peak times; and means for notifying a manager when abnormal water usage is detected. This enables optimization of energy efficiency and water management in the factory and overall cost reduction.

[0187] "Facilities" refers to large-scale installations such as factories and production lines, where energy and water management is required.

[0188] A "sensor" is a device that collects energy and water usage data in real time.

[0189] "Noise" refers to unnecessary or erroneous information contained in data that prevents accurate analysis.

[0190] "Cleaning" is the process of removing noise and outliers from the acquired data and converting it into a format suitable for learning.

[0191] A "model" is an algorithm that is trained using cleaned data to optimize resource management methods.

[0192] An "action plan" is a specific guideline for action that is generated based on the analysis results and proposed to the user.

[0193] "User" means an individual or manager who uses the system to manage energy and water resources.

[0194] "Feedback" refers to the results and reactions to actions taken by the user, and is information that helps improve the model.

[0195] "Peak hours" are times when energy use is particularly high.

[0196] "Abnormal water usage" refers to water consumption that deviates significantly from normal usage patterns and may indicate a leak or mechanical failure.

[0197] The "server" is the central system that collects and cleans data from sensors, and trains and analyzes models.

[0198] The present invention is a system for optimizing the management of energy and water resources in large-scale facilities such as factories, etc. Specific embodiments of this system will be described below.

[0199] Program Description

[0200] Data collection function

[0201] The server collects real-time energy and water usage data from sensors installed on machines and equipment within the factory. These sensors communicate with the server through an API and periodically transmit data. This sensor network includes, for example, electricity meters and water meters.

[0202] Data preprocessing function

[0203] The server cleans the acquired data in real time. This process includes removing noise and outliers, and filling in missing data. For example, extremely high or negative values ​​are considered outliers and are removed.

[0204] AI model training function

[0205] Using the cleaned data, the server trains AI algorithms that learn from past energy and water usage patterns and predict future usage, using machine learning techniques such as deep learning and decision tree algorithms.

[0206] Insight generation features

[0207] Using a trained AI model, the server analyzes real-time data to detect peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a certain time period, that time is recognized as a peak period.

[0208] Action plan generation and distribution capabilities

[0209] The server generates specific action plans based on the analysis results, such as recommendations such as "changing machine operating times to reduce energy use during peak hours." These action plans are then distributed to terminals (such as computers or tablets used by factory managers).

[0210] Execution and feedback functions

[0211] The user (factory manager) takes specific actions according to the action plan delivered to the device. For example, they can "change the machine's operating time" or "check areas where abnormal water usage has been detected." They can also provide feedback on the results of these actions to the server. The server collects this feedback and uses it to retrain the AI ​​model. This allows the model's accuracy and effectiveness to be continuously improved.

[0212] Specific examples

[0213] For example, a factory robot equipped with this system can monitor the usage of its own charging station and manage it to avoid unnecessary charging during peak hours. Also, if a machine in the factory uses water abnormally, the system can immediately notify the manager and prompt a prompt response.

[0214] Prompt Sentence Examples

[0215] "Please predict the peak hours of energy consumption for the following week based on your weekly energy consumption patterns and propose a specific action plan to reduce energy use during peak hours."

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] The server collects real-time energy and water usage data from sensors installed on machinery and equipment within the factory. Specifically, each sensor sends data to the server at regular intervals via an API. The input is raw data from the sensors, and the output is time-series data accumulated on the server.

[0219] Step 2:

[0220] The server cleans the acquired data in real time, removing noise and outliers and arranging it into a consistent data format. Specifically, it removes negative values ​​and extremely high values ​​as outliers and fills in missing data. The input is raw data, and the output is cleaned data.

[0221] Step 3:

[0222] The server uses the cleaned data to train an AI model. It analyzes past usage data and generates algorithms to predict future energy and water usage patterns. Specifically, it uses deep learning and decision tree algorithms. The input is the cleaned data, and the output is a trained AI model.

[0223] Step 4:

[0224] The server analyzes real-time data using a trained AI model, which detects peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a particular time period, that time is recognized as a peak period. The input is real-time data, and the output is the analysis results (detection of peak times and abnormal usage).

[0225] Step 5:

[0226] The server generates a specific action plan based on the analysis results, such as proposing changes to machine operating times to reduce energy use during peak hours. The input is the analysis results, and the output is the action plan.

[0227] Step 6:

[0228] The terminal delivers the action plan received from the server to the user. The user (factory manager) takes specific actions according to this action plan. For example, they may change the operating time of a machine or check an area where abnormal water usage has been detected. The input is the action plan, and the output is the user's actions.

[0229] Step 7:

[0230] Users provide feedback on their actions to the server, which collects this feedback and uses it to retrain the AI ​​model, thereby continually improving its accuracy and effectiveness. The input is the user feedback, and the output is the retrained AI model.

[0231] 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.

[0232] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[0233] 1. Data collection function

[0234] The server receives real-time energy and water usage data via APIs from sensors installed in each home or business, including electricity meters, gas meters, water meters, or sensors that detect these types of usage data.

[0235] 2. Data preprocessing function

[0236] The server cleans the acquired data, which removes noise and outliers and maintains data quality. The cleaning process includes filling in missing data and correcting outliers.

[0237] 3. AI model training function

[0238] The server uses the cleaned data to train an AI algorithm, which then creates a model to suggest optimal resource management methods for each home or business. The AI ​​model learns electricity and water consumption patterns and makes predictions. Deep learning and decision tree algorithms are used for this.

[0239] 4. Emotion engine integration

[0240] The server uses an emotion engine to obtain the user's emotion data, which is derived from facial and voice analysis of the user. The emotion data is analyzed in real time to adjust the recommended action plan based on the user's current emotional state.

[0241] 5. Insight generation function

[0242] The server uses the trained model to analyze real-time energy and water usage data and sentiment data, detecting specific usage patterns and abnormal usage and generating specific action plans based on this analysis.

[0243] 6. Action plan generation and distribution function

[0244] Based on the analysis results, the server generates a specific action plan to recommend to the user. This action plan takes into account the user's emotional state and is flexibly adjusted as needed. Examples include recommendations such as "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[0245] The device converts the reports received from the server into a format that the user can view. Important insights and urgent action plans are notified to the user via push notifications or email. The content and timing of notifications are also adjusted according to the user's emotional state.

[0246] 7. Execution and feedback functions

[0247] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0248] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[0249] Specific examples

[0250] Example 1: Reducing power usage during peak hours

[0251] 1. The server acquires and cleans the household electricity consumption data from sensors.

[0252] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0253] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[0254] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[0255] 5. The device will send a notification to the user, recommending that they change their usage time.

[0256] 6. The user changes the usage time of the appliance based on the notification.

[0257] 7. The user feeds the results back to the server and contributes to retraining the model.

[0258] Example 2: Abnormal water usage detection

[0259] 1. The server obtains household water data from sensors and cleans it.

[0260] 2. The server detects abnormal water usage in real time.

[0261] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the timing of anomaly detection notifications so that they are sent at the most acceptable time for the user.

[0262] 4. The server generates an anomaly detection alert and delivers it to the device.

[0263] 5. The device sends a notification to the user saying, "Abnormal water usage has been detected in the kitchen tap. Please check as there may be a leak."

[0264] 6. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0265] 7. The user feeds the results back to the server and contributes to retraining the model.

[0266] In this way, the system optimizes resource management in homes and businesses, and by taking into account the user's emotions, it achieves a sustainable and stress-free lifestyle.

[0267] The processing flow will be explained below.

[0268] Processing flow in energy and water resource management systems (emotion engine integration)

[0269] Example 1: Reducing power usage during peak hours

[0270] Step 1: Data collection

[0271] The server obtains household electricity consumption data in real time via an API from sensors installed in each home.

[0272] Step 2: Data Preprocessing

[0273] The server cleans the acquired data, removing noise and outliers, specifically identifying excessively high usage and imputing it to ensure data consistency.

[0274] Step 3: Model training

[0275] The server uses the cleaned data to train an AI model to learn each household's electricity usage patterns, a process that involves deep learning and decision tree algorithms.

[0276] Step 4: Obtaining emotion data

[0277] The server acquires the user's emotional data through the emotion engine, which is collected using the camera and microphone on the user's smartphone or computer.

[0278] Step 5: Analyze peak times and emotional states

[0279] The server identifies peak times for power usage and simultaneously analyzes users' emotional data in real time to identify times when users are least likely to feel stressed.

[0280] Step 6: Generate an action plan

[0281] The server generates an action plan that recommends reducing power usage during peak hours and adjusts the plan based on the user's emotional state. For example, it suggests guidelines to reduce power usage during times when the user is relaxing.

[0282] Step 7: Report Distribution

[0283] The server delivers a report containing the generated action plan to the terminal.

[0284] Step 8: User Notification

[0285] The device converts the reports into a user-readable format and notifies users of key insights via push notifications and in-app alerts.

[0286] Step 9: Take Action

[0287] Users can adjust the usage time of their washing machine or air conditioner according to the action plan provided.

[0288] Example 2: Abnormal water usage detection

[0289] Step 1: Data collection

[0290] The server collects water usage data from each household water supply in real time from sensors.

[0291] Step 2: Data Preprocessing

[0292] The server cleans the acquired data, corrects missing values ​​and abnormal data, and prepares the data for analysis.

[0293] Step 3: Model training

[0294] The server uses the cleaned data to train an AI model that learns historical water usage patterns.

[0295] Step 4: Obtaining emotion data

[0296] The server obtains the user's emotional data through an emotion engine, which includes the ability to read emotions from the user's facial expressions and voice.

[0297] Step 5: Anomaly detection

[0298] The server compares real-time water usage data with the trained model to detect abnormal water usage, while simultaneously analyzing user sentiment data to determine the optimal timing for notification.

[0299] Step 6: Generate an action plan

[0300] If an anomaly is detected, the server generates an action plan indicating a possible water leak, taking into account the user's emotional state and notifying them at a time that minimizes stress.

[0301] Step 7: Delivering notifications

[0302] The server distributes the generated anomaly detection notification to the terminal.

[0303] Step 8: User Notification

[0304] The device will send a notification to the user about the detected abnormality. For example, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[0305] Step 9: Take Action

[0306] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[0307] In this way, through a series of processing flows including an emotion engine, this system optimizes the use of resources in homes and businesses, realizing sustainable and user-friendly improvements to lifestyles.

[0308] Example 2

[0309] 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."

[0310] Conventional energy and water resource management systems collect and analyze data in real time, but they do not generate or notify action plans that take into account the user's emotional state. This makes it difficult for users to manage resources in a stress-free manner, limiting their ability to achieve sustainable lifestyles. Furthermore, they lack a mechanism for incorporating user feedback and continuously improving the accuracy and effectiveness of the system.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0312] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each home or business; means for cleaning the acquired data, completing missing data, and correcting outliers; means for training a learning algorithm using the cleaned data to create a generative AI model for proposing optimal resource management methods for each home or business; means for acquiring user emotion data using an emotion engine, generating specific action plans based on the analysis results, and distributing them to the user; means for sending notifications to the user via their device and adjusting the content and timing of the notifications based on the user's emotional state; and means for collecting user feedback and using it to retrain the generative AI model. This enables resource management that takes user emotions into account, enabling users to achieve sustainable lifestyles with less stress. Furthermore, by incorporating user feedback, the accuracy and effectiveness of the system can be continuously improved.

[0313] "Sensors" are devices installed in homes and businesses to measure energy and water usage and collect data in real time.

[0314] "Cleaning" is the process of removing noise, missing values, and outliers from collected data and converting it into a form suitable for learning algorithms.

[0315] "Learning algorithm" is an algorithm that uses the acquired and cleaned data to analyze energy and water usage patterns and build predictive models.

[0316] A "generative AI model" is a model trained using a learning algorithm to suggest optimal resource management methods for each household or business.

[0317] The "emotion engine" is an engine that obtains the user's emotional state using means such as facial expression and voice analysis, and analyzes it in real time.

[0318] An "action plan" is a specific suggestion or instruction generated based on the analyzed data and the user's emotional state.

[0319] A "terminal" is a device used to deliver action plans and notifications to users, typically a smartphone, tablet, or other device.

[0320] "Feedback" refers to information sent to the server about the results and impressions of actions taken by the user, which is used to retrain and optimize the system.

[0321] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[0322] (Data collection function)

[0323] The server obtains energy and water usage data in real time through an API from sensors installed in each home or business. This includes electricity meters, gas meters, water meters, or sensors that detect these usage data. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive electricity consumption data.

[0324] (Data preprocessing function)

[0325] The server cleans the acquired data. The cleaning process includes filling in missing data and correcting outliers. For example, if missing data is detected, the server fills in NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with the appropriate value.

[0326] (AI model training function)

[0327] The server uses the cleaned data to train an AI algorithm. It uses deep learning and decision tree algorithms to learn and predict electricity and water consumption patterns. Specifically, the model begins training using Python's TensorFlow library, inputting data from the past year and having it learn consumption patterns.

[0328] (Emotion engine integration function)

[0329] The server obtains the user's emotional data using an emotion engine, which includes analyzing data obtained from the user's facial expressions and voice in real time. For example, the server obtains the user's emotional state through a request "GET / emotion?user_id=123" and receives a response of "{ "emotion": "happy"}".

[0330] (Insight generation function)

[0331] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and abnormal usage, and generates a specific action plan based on the detected patterns. For example, the server sends a "POST / analyze" request and generates a notification saying "Abnormal water usage detected" if an abnormality is detected.

[0332] (Action plan generation and distribution function)

[0333] The server generates a specific action plan based on the analysis results and sends it to the device. The device then converts this action plan into a format that is easy for the user to understand and notifies them. As a specific example, the server generates an action plan such as "Reduce electricity usage between 6:00 PM and 9:00 PM" and displays a push notification stating, "(Important) We recommend that you reduce electricity usage between 6:00 PM and 9:00 PM today."

[0334] (Execution and feedback function)

[0335] The user takes specific actions based on the action plan delivered to the device. For example, they may make a change such as "don't use the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback. For example, feedback is sent using "POST / feedback," and the server uses this feedback to retrain the generative AI model.

[0336] (Example)

[0337] As a concrete example, consider an action plan to reduce power usage during peak hours. The server obtains and cleans household power consumption data from sensors. Next, it analyzes consumption data from the past few weeks to identify peak power consumption times. It then uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time periods when the user is least likely to feel stressed. For example, an action plan such as "reduce power usage between 6:00 PM and 9:00 PM" is generated and distributed to the device. The device then sends a notification to the user recommending that they change their usage times. The user then changes the usage times of their home appliances based on the notification and provides feedback to the server.

[0338] In this way, the system's program gradually integrates resource management and emotion recognition to specifically optimize user behavior, enabling efficient use of energy and water and helping users live a less stressful and sustainable life. Furthermore, by incorporating user feedback, the system's accuracy and effectiveness can be continuously improved.

[0339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0340] Step 1:

[0341] Data collection

[0342] The server receives energy and water usage data from sensors installed in each home or business via an API in real time. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive power consumption data.

[0343] Input: Energy and water usage data detected by sensors

[0344] Output: Raw energy and water usage data captured on the server

[0345] Specific behavior:

[0346] The server sends a request such as "GET / energy / usage?time=now" to the sensor.

[0347] The server receives the response data "{ "electricity_usage": 15.2 kWh}"

[0348] Step 2:

[0349] Data Preprocessing

[0350] The server cleans the acquired data. For example, if missing data is detected, the server fills NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with appropriate values.

[0351] Input: Captured raw energy and water use data

[0352] Output: Cleaned energy and water usage data

[0353] Specific behavior:

[0354] The server performs a process to fill in missing data values ​​(NaN) with the average value.

[0355] The server detects and corrects outliers as data that is more than three times the standard deviation.

[0356] Step 3:

[0357] Training an AI model

[0358] The server uses the cleaned data to train an AI algorithm. For example, it uses Python's TensorFlow library to start training a model, feeding it data from the past year to learn consumption patterns.

[0359] Input: Cleaned energy and water use data

[0360] Output: A trained AI model

[0361] Specific behavior:

[0362] The server uses Python's TensorFlow library to start training the AI ​​model.

[0363] The server uses cleaned data from the past year to learn consumption patterns.

[0364] Step 4:

[0365] Acquiring emotion data

[0366] The server uses the emotion engine to obtain the user's emotional data. For example, the server obtains the user's emotional state through the request "GET / emotion?user_id=123".

[0367] Input: User's facial expressions and voice data

[0368] Output: Parsed user sentiment data

[0369] Specific behavior:

[0370] The server sends "GET / emotion?user_id=123" to the emotion engine to collect the user's emotion data.

[0371] The server receives the response data "{ "emotion": "happy"}"

[0372] Step 5:

[0373] Insight generation

[0374] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. For example, the server sends a "POST / analyze" request to start the analysis.

[0375] Input: Real-time energy and water usage data and sentiment data

[0376] Output: Insights and specific usage patterns, and anomaly detection results

[0377] Specific behavior:

[0378] The server sends a "POST / analyze" request to analyze the real-time data.

[0379] If an anomaly is detected, the server generates a notification such as "Anomaly in water usage has been detected."

[0380] Step 6:

[0381] Action plan generation and distribution

[0382] The server generates a specific action plan based on the analysis results and delivers it to the device, which then converts the action plan into a format that is easy for the user to understand and notifies them.

[0383] Input: Analysis results and emotion data

[0384] Output: A concrete action plan delivered to the user

[0385] Specific behavior:

[0386] The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and sends it to the device.

[0387] The device displays a push notification saying, "(Important) We recommend that you refrain from using electricity between 6:00 PM and 9:00 PM today."

[0388] Step 7:

[0389] Execution and Feedback

[0390] The user takes specific actions according to the action plan delivered to the device, such as "avoid using the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback.

[0391] Input: Result of action plan execution

[0392] Output: Feedback data

[0393] Specific behavior:

[0394] Users change their behavior based on notifications from their devices (e.g., change the usage time of home appliances)

[0395] The user sends the results via "POST / feedback", and the server collects this data and uses it to retrain the AI ​​model.

[0396] In this way, the system collects data, pre-processes it, trains the AI ​​model, obtains sentiment data, generates insights and delivers action plans, collects feedback and retrains it at each step, achieving efficient and stress-free resource management.

[0397] (Application example 2)

[0398] 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."

[0399] Energy and water resource management in homes and businesses is an important issue for achieving sustainable living. However, conventional resource management systems do not take into account the user's emotional state, which can cause stress. They also lack the ability to detect abnormal energy and water usage in real time and propose appropriate action plans. To address this shortcoming, a system that integrates resource management with the user's emotional state is needed.

[0400] 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 acquiring energy and water usage data in real time from sensors installed in each home or business, means for processing the acquired data, removing noise, and converting it into a format suitable for learning, means for training an artificial intelligence model using the processed data and generating an algorithm for proposing an optimal resource management method for each home or business, means for acquiring user emotion data and adjusting an action plan based on the user's emotional state, means for generating specific proposals based on the analysis results and distributing them to the user, and means for collecting user feedback and retraining the model. This makes it possible to optimize resource management and reduce user stress.

[0401] A "sensor" is a device installed in a home or business to capture real-time energy and water usage data.

[0402] "Data processing" is the process of cleaning the acquired data, removing noise, and converting it into a form suitable for learning.

[0403] An "artificial intelligence model" is one that is trained using processed data to generate algorithms that suggest optimal resource management methods for homes and businesses.

[0404] "Emotional data" is information that indicates the user's emotional state and is acquired through sensing devices such as cameras and microphones.

[0405] An "action plan" is a specific guideline of action that is generated based on the analysis results and is suggested for the user to implement.

[0406] "Feedback" is user-provided information or results that are used to retrain the model.

[0407] "API" refers to the application program interface for collecting data from sensors.

[0408] The present invention describes a system that optimizes energy and water resource management in homes and businesses, recognizing user sentiment and incorporating that data into models and action plans.

[0409] This system mainly consists of the following components: sensors, data processing function, artificial intelligence model, emotion data acquisition function, action plan generation function, feedback function, and data collection API.

[0410] 1. Sensor

[0411] Detectors are installed in homes and businesses to collect energy and water usage data in real time. Examples of such meters include electricity meters, gas meters, and water meters, as well as sensors that detect these usage data.

[0412] 2. Data processing function

[0413] The server processes the data acquired from the sensors, removes noise, and converts it into a format suitable for learning. Specifically, data cleaning removes noise and outliers, and performs missing data correction and correction. StandardScaler and other tools are used for data preprocessing.

[0414] 3. Artificial Intelligence Model

[0415] The processed data is used to train an artificial intelligence model. This model proposes optimal resource management methods for each household or business, learning and predicting electricity and water consumption patterns. Deep learning and decision tree algorithms are used for this. Keras and TensorFlow are used for the detailed implementation of the model.

[0416] 4. Emotion data acquisition function

[0417] Emotion data is acquired by analyzing the user's facial expressions and voice. Emotion recognition is performed using a camera and microphone, along with software such as EmotionRecognizer. Emotion data is analyzed in real time, and an action plan is adjusted based on the user's emotional state.

[0418] 5. Action plan generation function

[0419] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and emotion data to detect specific usage patterns and anomalies. Based on the analysis results, it generates and delivers specific action plans to users. Examples include "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[0420] 6. Feedback function

[0421] Users take specific actions based on the action plan provided and provide feedback on the results, which is then aggregated on a server and used to retrain the AI ​​model, thereby continuously improving its accuracy and effectiveness.

[0422] Specific examples

[0423] Example 1: Reducing power usage during peak hours

[0424] 1. The server acquires and cleans the household electricity consumption data from the detectors.

[0425] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0426] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[0427] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[0428] 5. The device will send a notification to the user, recommending that they change their usage time.

[0429] 6. The user changes the usage time of the appliance based on the notification.

[0430] 7. The user feeds the results back to the server and contributes to retraining the model.

[0431] Prompt Sentence Examples

[0432] "Write a Python program that monitors a home's energy and water usage data in real time, detects anomalies, and sends appropriate alerts based on the user's emotional state. Specifically, the program needs to have the following capabilities:

[0433] Data collection function

[0434] Data preprocessing function

[0435] AI model training function

[0436] Emotion engine integration

[0437] Insight generation features

[0438] Action plan generation and distribution function

[0439] As a result, this system optimizes resource management in homes and businesses and takes into account users' emotions, enabling a sustainable and stress-free lifestyle.

[0440] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0441] Step 1:

[0442] The server collects energy and water usage data in real time from sensors installed in each home or business. This data is retrieved through an API, and the collected data may contain noise and outliers. The input is raw data from the sensors, and the output is unprocessed data stored in the server.

[0443] Step 2:

[0444] The server cleans the collected data, removes noise, and converts it into a format suitable for learning. This data cleaning process includes identifying and correcting outliers and filling in missing data. Specifically, the data is standardized using tools such as StandardScaler. The input is the collected raw data, and the output is the cleaned data.

[0445] Step 3:

[0446] The server uses the cleaned data to train an artificial intelligence model. This model generates an algorithm to propose optimal resource management methods for each household or business, using deep learning and decision tree algorithms. Specifically, the model is implemented and trained using Keras and TensorFlow. The input is the cleaned data, and the output is a trained artificial intelligence model.

[0447] Step 4:

[0448] The server acquires the user's emotional data and recognizes their emotional state. Emotional data is collected through a camera and microphone and analyzed using software such as EmotionRecognizer. The input is the user's facial expression and voice data, and the output is the recognized emotional state.

[0449] Step 5:

[0450] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and anomalies and generates specific action plans based on them. The input is the latest usage data and sentiment data, and the output is the generated action plan.

[0451] Step 6:

[0452] The server delivers the generated action plan to the user. This delivery is done through the device, and the user receives the action plan by push notification or email. The input is the generated action plan, and the output is the notification delivered to the user device.

[0453] Step 7:

[0454] The user takes specific actions based on the received action plan, such as changing the time the washing machine is used or checking the location where abnormal usage has been detected. The input is the received action plan, and the output is the specific action taken by the user.

[0455] Step 8:

[0456] Users provide feedback to the server about the results of their runs, which is used to retrain the model, continually improving the accuracy and effectiveness of the system. The input is user feedback information, and the output is an updated artificial intelligence model.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] [Second embodiment]

[0461] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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).

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] In the smart glasses 214, 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.

[0472] 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."

[0473] The present invention details a system designed to optimize energy and water resource management in homes and businesses.

[0474] 1. Data collection function

[0475] The server collects real-time energy and water usage data from sensors installed in homes and businesses. This data collection is done through APIs (application programming interfaces). For example, sensors connected to electricity or water meters periodically record usage information and send it to the server.

[0476] 2. Data preprocessing function

[0477] The server cleans the acquired data. The data cleaning process removes noise and outliers and ensures data consistency. Specifically, it complements missing data and corrects frequently occurring data errors.

[0478] 3. AI model training function

[0479] The server uses the cleaned data to train AI algorithms. The AI ​​models learn from past energy and water usage patterns and predict future usage. The models are built using machine learning techniques, including deep learning and decision tree algorithms.

[0480] 4. Insight generation function

[0481] The server analyzes real-time data using the trained model, which can detect peak energy usage and unusual water usage. For example, if unusual water usage is detected in a household, it could indicate a possible leak.

[0482] 5. Action plan generation and distribution function

[0483] The server generates specific action plans based on the analysis results, such as "Schedule the use of your washing machine outside of the hours of 6:00 PM to 9:00 PM to avoid peak power usage." These action plans are delivered to the device in the form of a report.

[0484] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email.

[0485] 6. Execution and feedback functions

[0486] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0487] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[0488] Specific examples

[0489] Example 1: Reducing power usage during peak hours

[0490] 1. The server obtains household electricity consumption data from sensors.

[0491] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0492] 3. The server generates specific guidelines for reducing peak power usage.

[0493] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[0494] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[0495] Example 2: Abnormal water usage detection

[0496] 1. The server obtains water usage data from sensors on each water supply in the home.

[0497] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[0498] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[0499] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[0500] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0501] In this way, the system provides a range of functions to optimize resource management in homes and businesses and achieve sustainable living.

[0502] The processing flow will be explained below.

[0503] Energy and Water Resource Management System Processing Flow

[0504] Example 1: Reducing power usage during peak hours

[0505] Step 1: Data collection

[0506] The server obtains household electricity consumption data from sensors via an API.

[0507] Step 2: Data Preprocessing

[0508] The server cleans the acquired data and removes noise and outliers, specifically by filling in missing values ​​and correcting abnormally high values.

[0509] Step 3: Identify peak times

[0510] The server uses the cleaned data to analyze power consumption patterns over the past few weeks and identify peak times for power consumption.

[0511] Step 4: Generate an action plan

[0512] The server generates specific guidelines for reducing peak power usage, including recommendations such as "avoid using energy-intensive appliances (washers, dryers, etc.) between 6:00 PM and 9:00 PM."

[0513] Step 5: Report Distribution

[0514] The server generates a report containing the above guidelines and delivers it to the terminal.

[0515] Step 6: User Notification

[0516] The device converts the reports received from the server into a user-readable format and provides important insights, such as push notifications or in-app alerts that advise users to avoid using the device during peak power hours.

[0517] Step 7: Take Action

[0518] Based on the notification, users can change the time they use their washing machine or dryer to off-peak hours.

[0519] Example 2: Abnormal water usage detection

[0520] Step 1: Data collection

[0521] The server receives real-time water usage data from the household water supply via sensors.

[0522] Step 2: Data Preprocessing

[0523] The server cleans the acquired data and distinguishes between normal and abnormal values, specifically identifying values ​​that deviate significantly from normal usage patterns.

[0524] Step 3: Anomaly detection

[0525] The server analyzes the cleaned data and compares it with historical usage patterns to detect abnormal water usage in real time.

[0526] Step 4: Generate anomaly notifications

[0527] Based on the detected anomalies, the server generates alerts indicating possible water leaks, etc.

[0528] Step 5: Delivering notifications

[0529] The server distributes the generated alerts to the terminals.

[0530] Step 6: User Notification

[0531] The device immediately sends a notification of the abnormality detected by the server to the user, such as, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[0532] Step 7: Take Action

[0533] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[0534] Through these steps, the system optimizes resource usage in homes and businesses, reducing environmental impact and operational costs.

[0535] Example 1

[0536] 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."

[0537] Optimizing the efficiency of energy and water use in modern homes and businesses is an important challenge from the perspective of sustainable resource management. However, the processes of individual data collection, analysis, optimization proposals, and feedback based on those data are complex, and advanced technology is required to achieve effective management. Conventional methods make it difficult to consistently execute these processes, making it difficult to achieve efficient resource management.

[0538] 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.

[0539] In this invention, the server includes: means for acquiring energy and water usage data in real time from multiple sensors installed in each home or business; means for cleaning the acquired data, removing noise and outliers, and converting it into a consistent format; means for training an AI model using the cleaned data to generate an algorithm that proposes an optimal resource management method for each home or business; means for analyzing the real-time data using the trained AI model to detect energy and water usage patterns; means for generating a specific action plan based on the analysis results and distributing it to the user's device; and means for collecting feedback from the user and retraining the AI ​​model. This automates the process from consistent data collection to optimization proposals, feedback collection, and retraining, enabling efficient resource management.

[0540] "Data collection means" refers to a means for obtaining energy and water usage data in real time from multiple sensors installed in each home or business.

[0541] A "data cleaning means" is a means for cleaning acquired data, removing noise and outliers, and converting the data into a consistent format.

[0542] The "AI model training means" is a means for training an AI model using cleaned data and generating an algorithm that proposes optimal resource management methods for each household or business.

[0543] "Real-time data analysis means" means a means for analyzing real-time data using a trained AI model to detect energy and water usage patterns.

[0544] The "action plan generation means" is a means for generating a specific action plan based on the analysis results and distributing it to the user's terminal.

[0545] "Feedback collection means" refers to the means used to collect user feedback and retrain the AI ​​model.

[0546] This invention relates to a system that optimizes energy and water usage in homes and businesses. This system collects data from multiple sensors installed in each home or business and analyzes it using AI technology to propose efficient resource management. The specific configuration and operation of this system are described below.

[0547] 1. Data collection function

[0548] The server collects real-time energy and water usage data from sensors installed in each home or business. This data is collected through an API (Application Programming Interface). Specifically, sensors connected to electricity and water meters periodically record usage information and send that data to the server. For this reason, the server must be equipped with a high-performance network interface and database system.

[0549] 2. Data preprocessing function

[0550] The server cleans the acquired data. The data cleaning process involves removing noise and outliers and filling in missing data to ensure data consistency. This process uses data cleansing tools such as Pandas and NumPy.

[0551] 3. AI model training function

[0552] The server uses the cleaned data to train an AI model. Specifically, it uses deep learning frameworks (such as TensorFlow or PyTorch) and decision tree algorithms to learn past energy and water usage patterns and build a model to predict future usage. This AI model requires a lot of computing resources to accurately learn resource usage patterns.

[0553] 4. Insight generation function

[0554] The server analyzes real-time data using a trained AI model. This analysis can detect peak energy usage times and abnormal water usage. For example, if abnormal water usage is detected in a household, it could suggest a possible water leak. The analysis results are provided with high accuracy, allowing the system to suggest accurate and prompt actions to users.

[0555] 5. Action plan generation and distribution function

[0556] The server generates a specific action plan based on the analysis results, such as "Schedule the use of your washing machine outside the hours of 6:00 PM to 9:00 PM to avoid peak power usage." The generated action plan is delivered to the device in the form of a report.

[0557] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email, allowing the user to take the necessary action at the appropriate time.

[0558] 6. Execution and feedback functions

[0559] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0560] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness. This feedback loop allows the system to constantly adapt to the latest situation and provide optimal resource management.

[0561] Specific examples

[0562] Example 1: Reducing power usage during peak hours

[0563] 1. The server obtains household electricity consumption data from sensors.

[0564] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0565] 3. The server generates specific guidelines for reducing peak power usage.

[0566] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[0567] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[0568] Example 2: Abnormal water usage detection

[0569] 1. The server obtains water usage data from sensors on each water supply in the home.

[0570] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[0571] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[0572] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[0573] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0574] Prompt Sentence Examples

[0575] "Analyze electricity usage data and suggest optimal ways to reduce energy consumption during peak hours."

[0576] In this way, the system provides a range of functions to optimise resource management in homes and businesses and achieve sustainable living.

[0577] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0578] Step 1: Data collection

[0579] The server collects real-time energy and water usage data from multiple sensors installed in each home or business, and sends the data recorded by the sensors to the server via an API.

[0580] Input: Real-time usage data recorded by sensors

[0581] Output: Raw usage data stored on the server

[0582] Specific behavior:

[0583] The server periodically sends API requests to receive data from each sensor, which is then stored in a database.

[0584] Step 2: Data Preprocessing

[0585] The server cleans the acquired data, removing noise and outliers and filling in missing data to ensure data consistency.

[0586] Input: Raw usage data

[0587] Output: Clean usage data

[0588] Specific behavior:

[0589] The server cleans the data using a data cleansing tool (e.g., Pandas, NumPy), filters out noise and outliers, and fills in missing data before storing it back in the database.

[0590] Step 3: Training the AI ​​model

[0591] The server uses the cleaned data to train an AI model, using deep learning frameworks and decision tree algorithms.

[0592] Input: Clean usage data

[0593] Output: A trained AI model

[0594] Specific behavior:

[0595] The server generates a training dataset and inputs it into the AI ​​model, and once the training process is complete, the trained model is saved.

[0596] Step 4: Insight generation

[0597] The server analyzes real-time data using a trained AI model to detect usage patterns and anomalies.

[0598] Input: Real-time data, trained AI model

[0599] Output: Detected insights (e.g. peak times, unusual usage)

[0600] Specific behavior:

[0601] The server inputs real-time data into the AI ​​model to detect anomalies and analyze peak times, and the results are stored in a database.

[0602] Step 5: Generate and distribute an action plan

[0603] The server generates a specific action plan based on the analysis results and distributes it to the device.

[0604] Input: Discovered insights

[0605] Output: Action Plan

[0606] Specific behavior:

[0607] The server generates an action plan and sends it to the device, which then converts it into a format that the user can view and delivers key insights via push notifications.

[0608] Step 6: Implementation and feedback

[0609] The user takes action according to the delivered action plan and provides the results as feedback to the server.

[0610] Input: Action Plan

[0611] Output: Actions taken and feedback

[0612] Specific behavior:

[0613] The user acts on the action plan and sends the results through the application to the server, which receives the feedback and uses it to retrain the AI ​​model.

[0614] This series of processing steps results in efficient and sustainable resource management.

[0615] (Application example 1)

[0616] 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."

[0617] Conventional energy and water management systems in homes and businesses have focused on optimizing resources for individual users, but in large facilities such as factories, it has been difficult to reduce energy usage during peak hours and quickly detect and respond to abnormal water usage. This has led to a demand for energy efficiency and reduction of water waste to reduce overall costs.

[0618] 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.

[0619] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each facility; means for cleaning the acquired data, removing noise, and converting it into a format suitable for learning; means for training a model using the cleaned data and generating an algorithm for proposing an optimal resource management method for each facility; means for generating a specific action plan based on the analysis results and distributing it to users; means for collecting feedback from users and retraining the model; means for collecting data from sensors attached to machines and devices in the factory and detecting peak times and abnormalities; means for generating an action plan to reduce energy usage during peak times; and means for notifying a manager when abnormal water usage is detected. This enables optimization of energy efficiency and water management in the factory and overall cost reduction.

[0620] "Facilities" refers to large-scale installations such as factories and production lines, where energy and water management is required.

[0621] A "sensor" is a device that collects energy and water usage data in real time.

[0622] "Noise" refers to unnecessary or erroneous information contained in data that prevents accurate analysis.

[0623] "Cleaning" is the process of removing noise and outliers from the acquired data and converting it into a format suitable for learning.

[0624] A "model" is an algorithm that is trained using cleaned data to optimize resource management methods.

[0625] An "action plan" is a specific guideline for action that is generated based on the analysis results and proposed to the user.

[0626] "User" means an individual or manager who uses the system to manage energy and water resources.

[0627] "Feedback" refers to the results and reactions to actions taken by the user, and is information that helps improve the model.

[0628] "Peak hours" are times when energy use is particularly high.

[0629] "Abnormal water usage" refers to water consumption that deviates significantly from normal usage patterns and may indicate a leak or mechanical failure.

[0630] The "server" is the central system that collects and cleans data from sensors, and trains and analyzes models.

[0631] The present invention is a system for optimizing the management of energy and water resources in large-scale facilities such as factories, etc. Specific embodiments of this system will be described below.

[0632] Program Description

[0633] Data collection function

[0634] The server collects real-time energy and water usage data from sensors installed on machines and equipment within the factory. These sensors communicate with the server through an API and periodically transmit data. This sensor network includes, for example, electricity meters and water meters.

[0635] Data preprocessing function

[0636] The server cleans the acquired data in real time. This process includes removing noise and outliers, and filling in missing data. For example, extremely high or negative values ​​are considered outliers and are removed.

[0637] AI model training function

[0638] Using the cleaned data, the server trains AI algorithms that learn from past energy and water usage patterns and predict future usage, using machine learning techniques such as deep learning and decision tree algorithms.

[0639] Insight generation features

[0640] Using a trained AI model, the server analyzes real-time data to detect peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a certain time period, that time is recognized as a peak period.

[0641] Action plan generation and distribution capabilities

[0642] The server generates specific action plans based on the analysis results, such as recommendations such as "changing machine operating times to reduce energy use during peak hours." These action plans are then distributed to terminals (such as computers or tablets used by factory managers).

[0643] Execution and feedback functions

[0644] The user (factory manager) takes specific actions according to the action plan delivered to the device. For example, they can "change the machine's operating time" or "check areas where abnormal water usage has been detected." They can also provide feedback on the results of these actions to the server. The server collects this feedback and uses it to retrain the AI ​​model. This allows the model's accuracy and effectiveness to be continuously improved.

[0645] Specific examples

[0646] For example, a factory robot equipped with this system can monitor the usage of its own charging station and manage it to avoid unnecessary charging during peak hours. Also, if a machine in the factory uses water abnormally, the system can immediately notify the manager and prompt a prompt response.

[0647] Prompt Sentence Examples

[0648] "Please predict the peak hours of energy consumption for the following week based on your weekly energy consumption patterns and propose a specific action plan to reduce energy use during peak hours."

[0649] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0650] Step 1:

[0651] The server collects real-time energy and water usage data from sensors installed on machinery and equipment within the factory. Specifically, each sensor sends data to the server at regular intervals via an API. The input is raw data from the sensors, and the output is time-series data accumulated on the server.

[0652] Step 2:

[0653] The server cleans the acquired data in real time, removing noise and outliers and arranging it into a consistent data format. Specifically, it removes negative values ​​and extremely high values ​​as outliers and fills in missing data. The input is raw data, and the output is cleaned data.

[0654] Step 3:

[0655] The server uses the cleaned data to train an AI model. It analyzes past usage data and generates algorithms to predict future energy and water usage patterns. Specifically, it uses deep learning and decision tree algorithms. The input is the cleaned data, and the output is a trained AI model.

[0656] Step 4:

[0657] The server analyzes real-time data using a trained AI model, which detects peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a particular time period, that time is recognized as a peak period. The input is real-time data, and the output is the analysis results (detection of peak times and abnormal usage).

[0658] Step 5:

[0659] The server generates a specific action plan based on the analysis results, such as proposing changes to machine operating times to reduce energy use during peak hours. The input is the analysis results, and the output is the action plan.

[0660] Step 6:

[0661] The terminal delivers the action plan received from the server to the user. The user (factory manager) takes specific actions according to this action plan. For example, they may change the operating time of a machine or check an area where abnormal water usage has been detected. The input is the action plan, and the output is the user's actions.

[0662] Step 7:

[0663] Users provide feedback on their actions to the server, which collects this feedback and uses it to retrain the AI ​​model, thereby continually improving its accuracy and effectiveness. The input is the user feedback, and the output is the retrained AI model.

[0664] 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.

[0665] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[0666] 1. Data collection function

[0667] The server receives real-time energy and water usage data via APIs from sensors installed in each home or business, including electricity meters, gas meters, water meters, or sensors that detect these types of usage data.

[0668] 2. Data preprocessing function

[0669] The server cleans the acquired data, which removes noise and outliers and maintains data quality. The cleaning process includes filling in missing data and correcting outliers.

[0670] 3. AI model training function

[0671] The server uses the cleaned data to train an AI algorithm, which then creates a model to suggest optimal resource management methods for each home or business. The AI ​​model learns electricity and water consumption patterns and makes predictions. Deep learning and decision tree algorithms are used for this.

[0672] 4. Emotion engine integration

[0673] The server uses an emotion engine to obtain the user's emotion data, which is derived from facial and voice analysis of the user. The emotion data is analyzed in real time to adjust the recommended action plan based on the user's current emotional state.

[0674] 5. Insight generation function

[0675] The server uses the trained model to analyze real-time energy and water usage data and sentiment data, detecting specific usage patterns and abnormal usage and generating specific action plans based on this analysis.

[0676] 6. Action plan generation and distribution function

[0677] Based on the analysis results, the server generates a specific action plan to recommend to the user. This action plan takes into account the user's emotional state and is flexibly adjusted as needed. Examples include recommendations such as "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[0678] The device converts the reports received from the server into a format that the user can view. Important insights and urgent action plans are notified to the user via push notifications or email. The content and timing of notifications are also adjusted according to the user's emotional state.

[0679] 7. Execution and feedback functions

[0680] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0681] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[0682] Specific examples

[0683] Example 1: Reducing power usage during peak hours

[0684] 1. The server acquires and cleans the household electricity consumption data from sensors.

[0685] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0686] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[0687] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[0688] 5. The device will send a notification to the user, recommending that they change their usage time.

[0689] 6. The user changes the usage time of the appliance based on the notification.

[0690] 7. The user feeds the results back to the server and contributes to retraining the model.

[0691] Example 2: Abnormal water usage detection

[0692] 1. The server obtains household water data from sensors and cleans it.

[0693] 2. The server detects abnormal water usage in real time.

[0694] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the timing of anomaly detection notifications so that they are sent at the most acceptable time for the user.

[0695] 4. The server generates an anomaly detection alert and delivers it to the device.

[0696] 5. The device sends a notification to the user saying, "Abnormal water usage has been detected in the kitchen tap. Please check as there may be a leak."

[0697] 6. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0698] 7. The user feeds the results back to the server and contributes to retraining the model.

[0699] In this way, the system optimizes resource management in homes and businesses, and by taking into account the user's emotions, it achieves a sustainable and stress-free lifestyle.

[0700] The processing flow will be explained below.

[0701] Processing flow in energy and water resource management systems (emotion engine integration)

[0702] Example 1: Reducing power usage during peak hours

[0703] Step 1: Data collection

[0704] The server obtains household electricity consumption data in real time via an API from sensors installed in each home.

[0705] Step 2: Data Preprocessing

[0706] The server cleans the acquired data, removing noise and outliers, specifically identifying excessively high usage and imputing it to ensure data consistency.

[0707] Step 3: Model training

[0708] The server uses the cleaned data to train an AI model to learn each household's electricity usage patterns, a process that involves deep learning and decision tree algorithms.

[0709] Step 4: Obtaining emotion data

[0710] The server acquires the user's emotional data through the emotion engine, which is collected using the camera and microphone on the user's smartphone or computer.

[0711] Step 5: Analyze peak times and emotional states

[0712] The server identifies peak times for power usage and simultaneously analyzes users' emotional data in real time to identify times when users are least likely to feel stressed.

[0713] Step 6: Generate an action plan

[0714] The server generates an action plan that recommends reducing power usage during peak hours and adjusts the plan based on the user's emotional state. For example, it suggests guidelines to reduce power usage during times when the user is relaxing.

[0715] Step 7: Report Distribution

[0716] The server delivers a report containing the generated action plan to the terminal.

[0717] Step 8: User Notification

[0718] The device converts the reports into a user-readable format and notifies users of key insights via push notifications and in-app alerts.

[0719] Step 9: Take Action

[0720] Users can adjust the usage time of their washing machine or air conditioner according to the action plan provided.

[0721] Example 2: Abnormal water usage detection

[0722] Step 1: Data collection

[0723] The server collects water usage data from each household water supply in real time from sensors.

[0724] Step 2: Data Preprocessing

[0725] The server cleans the acquired data, corrects missing values ​​and abnormal data, and prepares the data for analysis.

[0726] Step 3: Model training

[0727] The server uses the cleaned data to train an AI model that learns historical water usage patterns.

[0728] Step 4: Obtaining emotion data

[0729] The server obtains the user's emotional data through an emotion engine, which includes the ability to read emotions from the user's facial expressions and voice.

[0730] Step 5: Anomaly detection

[0731] The server compares real-time water usage data with the trained model to detect abnormal water usage, while simultaneously analyzing user sentiment data to determine the optimal timing for notification.

[0732] Step 6: Generate an action plan

[0733] If an anomaly is detected, the server generates an action plan indicating a possible water leak, taking into account the user's emotional state and notifying them at a time that minimizes stress.

[0734] Step 7: Delivering notifications

[0735] The server distributes the generated anomaly detection notification to the terminal.

[0736] Step 8: User Notification

[0737] The device will send a notification to the user about the detected abnormality. For example, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[0738] Step 9: Take Action

[0739] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[0740] In this way, through a series of processing flows including an emotion engine, this system optimizes the use of resources in homes and businesses, realizing sustainable and user-friendly improvements to lifestyles.

[0741] Example 2

[0742] 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."

[0743] Conventional energy and water resource management systems collect and analyze data in real time, but they do not generate or notify action plans that take into account the user's emotional state. This makes it difficult for users to manage resources in a stress-free manner, limiting their ability to achieve sustainable lifestyles. Furthermore, they lack a mechanism for incorporating user feedback and continuously improving the accuracy and effectiveness of the system.

[0744] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0745] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each home or business; means for cleaning the acquired data, completing missing data, and correcting outliers; means for training a learning algorithm using the cleaned data to create a generative AI model for proposing optimal resource management methods for each home or business; means for acquiring user emotion data using an emotion engine, generating specific action plans based on the analysis results, and distributing them to the user; means for sending notifications to the user via their device and adjusting the content and timing of the notifications based on the user's emotional state; and means for collecting user feedback and using it to retrain the generative AI model. This enables resource management that takes user emotions into account, enabling users to achieve sustainable lifestyles with less stress. Furthermore, by incorporating user feedback, the accuracy and effectiveness of the system can be continuously improved.

[0746] "Sensors" are devices installed in homes and businesses to measure energy and water usage and collect data in real time.

[0747] "Cleaning" is the process of removing noise, missing values, and outliers from collected data and converting it into a form suitable for learning algorithms.

[0748] "Learning algorithm" is an algorithm that uses the acquired and cleaned data to analyze energy and water usage patterns and build predictive models.

[0749] A "generative AI model" is a model trained using a learning algorithm to suggest optimal resource management methods for each household or business.

[0750] The "emotion engine" is an engine that obtains the user's emotional state using means such as facial expression and voice analysis, and analyzes it in real time.

[0751] An "action plan" is a specific suggestion or instruction generated based on the analyzed data and the user's emotional state.

[0752] A "terminal" is a device used to deliver action plans and notifications to users, typically a smartphone, tablet, or other device.

[0753] "Feedback" refers to information sent to the server about the results and impressions of actions taken by the user, which is used to retrain and optimize the system.

[0754] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[0755] (Data collection function)

[0756] The server obtains energy and water usage data in real time through an API from sensors installed in each home or business. This includes electricity meters, gas meters, water meters, or sensors that detect these usage data. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive electricity consumption data.

[0757] (Data preprocessing function)

[0758] The server cleans the acquired data. The cleaning process includes filling in missing data and correcting outliers. For example, if missing data is detected, the server fills in NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with the appropriate value.

[0759] (AI model training function)

[0760] The server uses the cleaned data to train an AI algorithm. It uses deep learning and decision tree algorithms to learn and predict electricity and water consumption patterns. Specifically, the model begins training using Python's TensorFlow library, inputting data from the past year and having it learn consumption patterns.

[0761] (Emotion engine integration function)

[0762] The server obtains the user's emotional data using an emotion engine, which includes analyzing data obtained from the user's facial expressions and voice in real time. For example, the server obtains the user's emotional state through a request "GET / emotion?user_id=123" and receives a response of "{ "emotion": "happy"}".

[0763] (Insight generation function)

[0764] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and abnormal usage, and generates a specific action plan based on the detected patterns. For example, the server sends a "POST / analyze" request and generates a notification saying "Abnormal water usage detected" if an abnormality is detected.

[0765] (Action plan generation and distribution function)

[0766] The server generates a specific action plan based on the analysis results and sends it to the device. The device then converts this action plan into a format that is easy for the user to understand and notifies them. As a specific example, the server generates an action plan such as "Reduce electricity usage between 6:00 PM and 9:00 PM" and displays a push notification stating, "(Important) We recommend that you reduce electricity usage between 6:00 PM and 9:00 PM today."

[0767] (Execution and feedback function)

[0768] The user takes specific actions based on the action plan delivered to the device. For example, they may make a change such as "don't use the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback. For example, feedback is sent using "POST / feedback," and the server uses this feedback to retrain the generative AI model.

[0769] (Example)

[0770] As a concrete example, consider an action plan to reduce power usage during peak hours. The server obtains and cleans household power consumption data from sensors. Next, it analyzes consumption data from the past few weeks to identify peak power consumption times. It then uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time periods when the user is least likely to feel stressed. For example, an action plan such as "reduce power usage between 6:00 PM and 9:00 PM" is generated and distributed to the device. The device then sends a notification to the user recommending that they change their usage times. The user then changes the usage times of their home appliances based on the notification and provides feedback to the server.

[0771] In this way, the system's program gradually integrates resource management and emotion recognition to specifically optimize user behavior, enabling efficient use of energy and water and helping users live a less stressful and sustainable life. Furthermore, by incorporating user feedback, the system's accuracy and effectiveness can be continuously improved.

[0772] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0773] Step 1:

[0774] Data collection

[0775] The server receives energy and water usage data from sensors installed in each home or business via an API in real time. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive power consumption data.

[0776] Input: Energy and water usage data detected by sensors

[0777] Output: Raw energy and water usage data captured on the server

[0778] Specific behavior:

[0779] The server sends a request such as "GET / energy / usage?time=now" to the sensor.

[0780] The server receives the response data "{ "electricity_usage": 15.2 kWh}"

[0781] Step 2:

[0782] Data Preprocessing

[0783] The server cleans the acquired data. For example, if missing data is detected, the server fills NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with appropriate values.

[0784] Input: Captured raw energy and water use data

[0785] Output: Cleaned energy and water usage data

[0786] Specific behavior:

[0787] The server performs a process to fill in missing data values ​​(NaN) with the average value.

[0788] The server detects and corrects outliers as data that is more than three times the standard deviation.

[0789] Step 3:

[0790] Training an AI model

[0791] The server uses the cleaned data to train an AI algorithm. For example, it uses Python's TensorFlow library to start training a model, feeding it data from the past year to learn consumption patterns.

[0792] Input: Cleaned energy and water use data

[0793] Output: A trained AI model

[0794] Specific behavior:

[0795] The server uses Python's TensorFlow library to start training the AI ​​model.

[0796] The server uses cleaned data from the past year to learn consumption patterns.

[0797] Step 4:

[0798] Acquiring emotion data

[0799] The server uses the emotion engine to obtain the user's emotional data. For example, the server obtains the user's emotional state through the request "GET / emotion?user_id=123".

[0800] Input: User's facial expressions and voice data

[0801] Output: Parsed user sentiment data

[0802] Specific behavior:

[0803] The server sends "GET / emotion?user_id=123" to the emotion engine to collect the user's emotion data.

[0804] The server receives the response data "{ "emotion": "happy"}"

[0805] Step 5:

[0806] Insight generation

[0807] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. For example, the server sends a "POST / analyze" request to start the analysis.

[0808] Input: Real-time energy and water usage data and sentiment data

[0809] Output: Insights and specific usage patterns, and anomaly detection results

[0810] Specific behavior:

[0811] The server sends a "POST / analyze" request to analyze the real-time data.

[0812] If an anomaly is detected, the server generates a notification such as "Anomaly in water usage has been detected."

[0813] Step 6:

[0814] Action plan generation and distribution

[0815] The server generates a specific action plan based on the analysis results and delivers it to the device, which then converts the action plan into a format that is easy for the user to understand and notifies them.

[0816] Input: Analysis results and emotion data

[0817] Output: A concrete action plan delivered to the user

[0818] Specific behavior:

[0819] The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and sends it to the device.

[0820] The device displays a push notification saying, "(Important) We recommend that you refrain from using electricity between 6:00 PM and 9:00 PM today."

[0821] Step 7:

[0822] Execution and Feedback

[0823] The user takes specific actions according to the action plan delivered to the device, such as "avoid using the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback.

[0824] Input: Result of action plan execution

[0825] Output: Feedback data

[0826] Specific behavior:

[0827] Users change their behavior based on notifications from their devices (e.g., change the usage time of home appliances)

[0828] The user sends the results via "POST / feedback", and the server collects this data and uses it to retrain the AI ​​model.

[0829] In this way, the system collects data, pre-processes it, trains the AI ​​model, obtains sentiment data, generates insights and delivers action plans, collects feedback and retrains it at each step, achieving efficient and stress-free resource management.

[0830] (Application example 2)

[0831] 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."

[0832] Energy and water resource management in homes and businesses is an important issue for achieving sustainable living. However, conventional resource management systems do not take into account the user's emotional state, which can cause stress. They also lack the ability to detect abnormal energy and water usage in real time and propose appropriate action plans. To address this shortcoming, a system that integrates resource management with the user's emotional state is needed.

[0833] 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 acquiring energy and water usage data in real time from sensors installed in each home or business, means for processing the acquired data, removing noise, and converting it into a format suitable for learning, means for training an artificial intelligence model using the processed data and generating an algorithm for proposing an optimal resource management method for each home or business, means for acquiring user emotion data and adjusting an action plan based on the user's emotional state, means for generating specific proposals based on the analysis results and distributing them to the user, and means for collecting user feedback and retraining the model. This makes it possible to optimize resource management and reduce user stress.

[0834] A "sensor" is a device installed in a home or business to capture real-time energy and water usage data.

[0835] "Data processing" is the process of cleaning the acquired data, removing noise, and converting it into a form suitable for learning.

[0836] An "artificial intelligence model" is one that is trained using processed data to generate algorithms that suggest optimal resource management methods for homes and businesses.

[0837] "Emotional data" is information that indicates the user's emotional state and is acquired through sensing devices such as cameras and microphones.

[0838] An "action plan" is a specific guideline of action that is generated based on the analysis results and is suggested for the user to implement.

[0839] "Feedback" is user-provided information or results that are used to retrain the model.

[0840] "API" refers to the application program interface for collecting data from sensors.

[0841] The present invention describes a system that optimizes energy and water resource management in homes and businesses, recognizing user sentiment and incorporating that data into models and action plans.

[0842] This system mainly consists of the following components: sensors, data processing function, artificial intelligence model, emotion data acquisition function, action plan generation function, feedback function, and data collection API.

[0843] 1. Sensor

[0844] Detectors are installed in homes and businesses to collect energy and water usage data in real time. Examples of such meters include electricity meters, gas meters, and water meters, as well as sensors that detect these usage data.

[0845] 2. Data processing function

[0846] The server processes the data acquired from the sensors, removes noise, and converts it into a format suitable for learning. Specifically, data cleaning removes noise and outliers, and performs missing data correction and correction. StandardScaler and other tools are used for data preprocessing.

[0847] 3. Artificial Intelligence Model

[0848] The processed data is used to train an artificial intelligence model. This model proposes optimal resource management methods for each household or business, learning and predicting electricity and water consumption patterns. Deep learning and decision tree algorithms are used for this. Keras and TensorFlow are used for the detailed implementation of the model.

[0849] 4. Emotion data acquisition function

[0850] Emotion data is acquired by analyzing the user's facial expressions and voice. Emotion recognition is performed using a camera and microphone, along with software such as EmotionRecognizer. Emotion data is analyzed in real time, and an action plan is adjusted based on the user's emotional state.

[0851] 5. Action plan generation function

[0852] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and emotion data to detect specific usage patterns and anomalies. Based on the analysis results, it generates and delivers specific action plans to users. Examples include "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[0853] 6. Feedback function

[0854] Users take specific actions based on the action plan provided and provide feedback on the results, which is then aggregated on a server and used to retrain the AI ​​model, thereby continuously improving its accuracy and effectiveness.

[0855] Specific examples

[0856] Example 1: Reducing power usage during peak hours

[0857] 1. The server acquires and cleans the household electricity consumption data from the detectors.

[0858] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0859] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[0860] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[0861] 5. The device will send a notification to the user, recommending that they change their usage time.

[0862] 6. The user changes the usage time of the appliance based on the notification.

[0863] 7. The user feeds the results back to the server and contributes to retraining the model.

[0864] Prompt Sentence Examples

[0865] "Write a Python program that monitors a home's energy and water usage data in real time, detects anomalies, and sends appropriate alerts based on the user's emotional state. Specifically, the program needs to have the following capabilities:

[0866] Data collection function

[0867] Data preprocessing function

[0868] AI model training function

[0869] Emotion engine integration

[0870] Insight generation features

[0871] Action plan generation and distribution function

[0872] As a result, this system optimizes resource management in homes and businesses and takes into account users' emotions, enabling a sustainable and stress-free lifestyle.

[0873] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0874] Step 1:

[0875] The server collects energy and water usage data in real time from sensors installed in each home or business. This data is retrieved through an API, and the collected data may contain noise and outliers. The input is raw data from the sensors, and the output is unprocessed data stored in the server.

[0876] Step 2:

[0877] The server cleans the collected data, removes noise, and converts it into a format suitable for learning. This data cleaning process includes identifying and correcting outliers and filling in missing data. Specifically, the data is standardized using tools such as StandardScaler. The input is the collected raw data, and the output is the cleaned data.

[0878] Step 3:

[0879] The server uses the cleaned data to train an artificial intelligence model. This model generates an algorithm to propose optimal resource management methods for each household or business, using deep learning and decision tree algorithms. Specifically, the model is implemented and trained using Keras and TensorFlow. The input is the cleaned data, and the output is a trained artificial intelligence model.

[0880] Step 4:

[0881] The server acquires the user's emotional data and recognizes their emotional state. Emotional data is collected through a camera and microphone and analyzed using software such as EmotionRecognizer. The input is the user's facial expression and voice data, and the output is the recognized emotional state.

[0882] Step 5:

[0883] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and anomalies and generates specific action plans based on them. The input is the latest usage data and sentiment data, and the output is the generated action plan.

[0884] Step 6:

[0885] The server delivers the generated action plan to the user. This delivery is done through the device, and the user receives the action plan by push notification or email. The input is the generated action plan, and the output is the notification delivered to the user device.

[0886] Step 7:

[0887] The user takes specific actions based on the received action plan, such as changing the time the washing machine is used or checking the location where abnormal usage has been detected. The input is the received action plan, and the output is the specific action taken by the user.

[0888] Step 8:

[0889] Users provide feedback to the server about the results of their runs, which is used to retrain the model, continually improving the accuracy and effectiveness of the system. The input is user feedback information, and the output is an updated artificial intelligence model.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] [Third embodiment]

[0894] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0895] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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."

[0906] The present invention details a system designed to optimize energy and water resource management in homes and businesses.

[0907] 1. Data collection function

[0908] The server collects real-time energy and water usage data from sensors installed in homes and businesses. This data collection is done through APIs (application programming interfaces). For example, sensors connected to electricity or water meters periodically record usage information and send it to the server.

[0909] 2. Data preprocessing function

[0910] The server cleans the acquired data. The data cleaning process removes noise and outliers and ensures data consistency. Specifically, it complements missing data and corrects frequently occurring data errors.

[0911] 3. AI model training function

[0912] The server uses the cleaned data to train AI algorithms. The AI ​​models learn from past energy and water usage patterns and predict future usage. The models are built using machine learning techniques, including deep learning and decision tree algorithms.

[0913] 4. Insight generation function

[0914] The server analyzes real-time data using the trained model, which can detect peak energy usage and unusual water usage. For example, if unusual water usage is detected in a household, it could indicate a possible leak.

[0915] 5. Action plan generation and distribution function

[0916] The server generates specific action plans based on the analysis results, such as "Schedule the use of your washing machine outside of the hours of 6:00 PM to 9:00 PM to avoid peak power usage." These action plans are delivered to the device in the form of a report.

[0917] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email.

[0918] 6. Execution and feedback functions

[0919] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0920] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[0921] Specific examples

[0922] Example 1: Reducing power usage during peak hours

[0923] 1. The server obtains household electricity consumption data from sensors.

[0924] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0925] 3. The server generates specific guidelines for reducing peak power usage.

[0926] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[0927] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[0928] Example 2: Abnormal water usage detection

[0929] 1. The server obtains water usage data from sensors on each water supply in the home.

[0930] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[0931] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[0932] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[0933] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[0934] In this way, the system provides a range of functions to optimize resource management in homes and businesses and achieve sustainable living.

[0935] The processing flow will be explained below.

[0936] Energy and Water Resource Management System Processing Flow

[0937] Example 1: Reducing power usage during peak hours

[0938] Step 1: Data collection

[0939] The server obtains household electricity consumption data from sensors via an API.

[0940] Step 2: Data Preprocessing

[0941] The server cleans the acquired data and removes noise and outliers, specifically by filling in missing values ​​and correcting abnormally high values.

[0942] Step 3: Identify peak times

[0943] The server uses the cleaned data to analyze power consumption patterns over the past few weeks and identify peak times for power consumption.

[0944] Step 4: Generate an action plan

[0945] The server generates specific guidelines for reducing peak power usage, including recommendations such as "avoid using energy-intensive appliances (washers, dryers, etc.) between 6:00 PM and 9:00 PM."

[0946] Step 5: Report Distribution

[0947] The server generates a report containing the above guidelines and delivers it to the terminal.

[0948] Step 6: User Notification

[0949] The device converts the reports received from the server into a user-readable format and provides important insights, such as push notifications or in-app alerts that advise users to avoid using the device during peak power hours.

[0950] Step 7: Take Action

[0951] Based on the notification, users can change the time they use their washing machine or dryer to off-peak hours.

[0952] Example 2: Abnormal water usage detection

[0953] Step 1: Data collection

[0954] The server receives real-time water usage data from the household water supply via sensors.

[0955] Step 2: Data Preprocessing

[0956] The server cleans the acquired data and distinguishes between normal and abnormal values, specifically identifying values ​​that deviate significantly from normal usage patterns.

[0957] Step 3: Anomaly detection

[0958] The server analyzes the cleaned data and compares it with historical usage patterns to detect abnormal water usage in real time.

[0959] Step 4: Generate anomaly notifications

[0960] Based on the detected anomalies, the server generates alerts indicating possible water leaks, etc.

[0961] Step 5: Delivering notifications

[0962] The server distributes the generated alerts to the terminals.

[0963] Step 6: User Notification

[0964] The device immediately sends a notification of the abnormality detected by the server to the user, such as, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[0965] Step 7: Take Action

[0966] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[0967] Through these steps, the system optimizes resource usage in homes and businesses, reducing environmental impact and operational costs.

[0968] Example 1

[0969] 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."

[0970] Optimizing the efficiency of energy and water use in modern homes and businesses is an important challenge from the perspective of sustainable resource management. However, the processes of individual data collection, analysis, optimization proposals, and feedback based on those data are complex, and advanced technology is required to achieve effective management. Conventional methods make it difficult to consistently execute these processes, making it difficult to achieve efficient resource management.

[0971] 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.

[0972] In this invention, the server includes: means for acquiring energy and water usage data in real time from multiple sensors installed in each home or business; means for cleaning the acquired data, removing noise and outliers, and converting it into a consistent format; means for training an AI model using the cleaned data to generate an algorithm that proposes an optimal resource management method for each home or business; means for analyzing the real-time data using the trained AI model to detect energy and water usage patterns; means for generating a specific action plan based on the analysis results and distributing it to the user's device; and means for collecting feedback from the user and retraining the AI ​​model. This automates the process from consistent data collection to optimization proposals, feedback collection, and retraining, enabling efficient resource management.

[0973] "Data collection means" refers to a means for obtaining energy and water usage data in real time from multiple sensors installed in each home or business.

[0974] A "data cleaning means" is a means for cleaning acquired data, removing noise and outliers, and converting the data into a consistent format.

[0975] The "AI model training means" is a means for training an AI model using cleaned data and generating an algorithm that proposes optimal resource management methods for each household or business.

[0976] "Real-time data analysis means" means a means for analyzing real-time data using a trained AI model to detect energy and water usage patterns.

[0977] The "action plan generation means" is a means for generating a specific action plan based on the analysis results and distributing it to the user's terminal.

[0978] "Feedback collection means" refers to the means used to collect user feedback and retrain the AI ​​model.

[0979] This invention relates to a system that optimizes energy and water usage in homes and businesses. This system collects data from multiple sensors installed in each home or business and analyzes it using AI technology to propose efficient resource management. The specific configuration and operation of this system are described below.

[0980] 1. Data collection function

[0981] The server collects real-time energy and water usage data from sensors installed in each home or business. This data is collected through an API (Application Programming Interface). Specifically, sensors connected to electricity and water meters periodically record usage information and send that data to the server. For this reason, the server must be equipped with a high-performance network interface and database system.

[0982] 2. Data preprocessing function

[0983] The server cleans the acquired data. The data cleaning process involves removing noise and outliers and filling in missing data to ensure data consistency. This process uses data cleansing tools such as Pandas and NumPy.

[0984] 3. AI model training function

[0985] The server uses the cleaned data to train an AI model. Specifically, it uses deep learning frameworks (such as TensorFlow or PyTorch) and decision tree algorithms to learn past energy and water usage patterns and build a model to predict future usage. This AI model requires a lot of computing resources to accurately learn resource usage patterns.

[0986] 4. Insight generation function

[0987] The server analyzes real-time data using a trained AI model. This analysis can detect peak energy usage times and abnormal water usage. For example, if abnormal water usage is detected in a household, it could suggest a possible water leak. The analysis results are provided with high accuracy, allowing the system to suggest accurate and prompt actions to users.

[0988] 5. Action plan generation and distribution function

[0989] The server generates a specific action plan based on the analysis results, such as "Schedule the use of your washing machine outside the hours of 6:00 PM to 9:00 PM to avoid peak power usage." The generated action plan is delivered to the device in the form of a report.

[0990] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email, allowing the user to take the necessary action at the appropriate time.

[0991] 6. Execution and feedback functions

[0992] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[0993] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness. This feedback loop allows the system to constantly adapt to the latest situation and provide optimal resource management.

[0994] Specific examples

[0995] Example 1: Reducing power usage during peak hours

[0996] 1. The server obtains household electricity consumption data from sensors.

[0997] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[0998] 3. The server generates specific guidelines for reducing peak power usage.

[0999] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[1000] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[1001] Example 2: Abnormal water usage detection

[1002] 1. The server obtains water usage data from sensors on each water supply in the home.

[1003] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[1004] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[1005] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[1006] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[1007] Prompt Sentence Examples

[1008] "Analyze electricity usage data and suggest optimal ways to reduce energy consumption during peak hours."

[1009] In this way, the system provides a range of functions to optimise resource management in homes and businesses and achieve sustainable living.

[1010] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1011] Step 1: Data collection

[1012] The server collects real-time energy and water usage data from multiple sensors installed in each home or business, and sends the data recorded by the sensors to the server via an API.

[1013] Input: Real-time usage data recorded by sensors

[1014] Output: Raw usage data stored on the server

[1015] Specific behavior:

[1016] The server periodically sends API requests to receive data from each sensor, which is then stored in a database.

[1017] Step 2: Data Preprocessing

[1018] The server cleans the acquired data, removing noise and outliers and filling in missing data to ensure data consistency.

[1019] Input: Raw usage data

[1020] Output: Clean usage data

[1021] Specific behavior:

[1022] The server cleans the data using a data cleansing tool (e.g., Pandas, NumPy), filters out noise and outliers, and fills in missing data before storing it back in the database.

[1023] Step 3: Training the AI ​​model

[1024] The server uses the cleaned data to train an AI model, using deep learning frameworks and decision tree algorithms.

[1025] Input: Clean usage data

[1026] Output: A trained AI model

[1027] Specific behavior:

[1028] The server generates a training dataset and inputs it into the AI ​​model, and once the training process is complete, the trained model is saved.

[1029] Step 4: Insight generation

[1030] The server analyzes real-time data using a trained AI model to detect usage patterns and anomalies.

[1031] Input: Real-time data, trained AI model

[1032] Output: Detected insights (e.g. peak times, unusual usage)

[1033] Specific behavior:

[1034] The server inputs real-time data into the AI ​​model to detect anomalies and analyze peak times, and the results are stored in a database.

[1035] Step 5: Generate and distribute an action plan

[1036] The server generates a specific action plan based on the analysis results and distributes it to the device.

[1037] Input: Discovered insights

[1038] Output: Action Plan

[1039] Specific behavior:

[1040] The server generates an action plan and sends it to the device, which then converts it into a format that the user can view and delivers key insights via push notifications.

[1041] Step 6: Implementation and feedback

[1042] The user takes action according to the delivered action plan and provides the results as feedback to the server.

[1043] Input: Action Plan

[1044] Output: Actions taken and feedback

[1045] Specific behavior:

[1046] The user acts on the action plan and sends the results through the application to the server, which receives the feedback and uses it to retrain the AI ​​model.

[1047] This series of processing steps results in efficient and sustainable resource management.

[1048] (Application example 1)

[1049] 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."

[1050] Conventional energy and water management systems in homes and businesses have focused on optimizing resources for individual users, but in large facilities such as factories, it has been difficult to reduce energy usage during peak hours and quickly detect and respond to abnormal water usage. This has led to a demand for energy efficiency and reduction of water waste to reduce overall costs.

[1051] 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.

[1052] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each facility; means for cleaning the acquired data, removing noise, and converting it into a format suitable for learning; means for training a model using the cleaned data and generating an algorithm for proposing an optimal resource management method for each facility; means for generating a specific action plan based on the analysis results and distributing it to users; means for collecting feedback from users and retraining the model; means for collecting data from sensors attached to machines and devices in the factory and detecting peak times and abnormalities; means for generating an action plan to reduce energy usage during peak times; and means for notifying a manager when abnormal water usage is detected. This enables optimization of energy efficiency and water management in the factory and overall cost reduction.

[1053] "Facilities" refers to large-scale installations such as factories and production lines, where energy and water management is required.

[1054] A "sensor" is a device that collects energy and water usage data in real time.

[1055] "Noise" refers to unnecessary or erroneous information contained in data that prevents accurate analysis.

[1056] "Cleaning" is the process of removing noise and outliers from the acquired data and converting it into a format suitable for learning.

[1057] A "model" is an algorithm that is trained using cleaned data to optimize resource management methods.

[1058] An "action plan" is a specific guideline for action that is generated based on the analysis results and proposed to the user.

[1059] "User" means an individual or manager who uses the system to manage energy and water resources.

[1060] "Feedback" refers to the results and reactions to actions taken by the user, and is information that helps improve the model.

[1061] "Peak hours" are times when energy use is particularly high.

[1062] "Abnormal water usage" refers to water consumption that deviates significantly from normal usage patterns and may indicate a leak or mechanical failure.

[1063] The "server" is the central system that collects and cleans data from sensors, and trains and analyzes models.

[1064] The present invention is a system for optimizing the management of energy and water resources in large-scale facilities such as factories, etc. Specific embodiments of this system will be described below.

[1065] Program Description

[1066] Data collection function

[1067] The server collects real-time energy and water usage data from sensors installed on machines and equipment within the factory. These sensors communicate with the server through an API and periodically transmit data. This sensor network includes, for example, electricity meters and water meters.

[1068] Data preprocessing function

[1069] The server cleans the acquired data in real time. This process includes removing noise and outliers, and filling in missing data. For example, extremely high or negative values ​​are considered outliers and are removed.

[1070] AI model training function

[1071] Using the cleaned data, the server trains AI algorithms that learn from past energy and water usage patterns and predict future usage, using machine learning techniques such as deep learning and decision tree algorithms.

[1072] Insight generation features

[1073] Using a trained AI model, the server analyzes real-time data to detect peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a certain time period, that time is recognized as a peak period.

[1074] Action plan generation and distribution capabilities

[1075] The server generates specific action plans based on the analysis results, such as recommendations such as "changing machine operating times to reduce energy use during peak hours." These action plans are then distributed to terminals (such as computers or tablets used by factory managers).

[1076] Execution and feedback functions

[1077] The user (factory manager) takes specific actions according to the action plan delivered to the device. For example, they can "change the machine's operating time" or "check areas where abnormal water usage has been detected." They can also provide feedback on the results of these actions to the server. The server collects this feedback and uses it to retrain the AI ​​model. This allows the model's accuracy and effectiveness to be continuously improved.

[1078] Specific examples

[1079] For example, a factory robot equipped with this system can monitor the usage of its own charging station and manage it to avoid unnecessary charging during peak hours. Also, if a machine in the factory uses water abnormally, the system can immediately notify the manager and prompt a prompt response.

[1080] Prompt Sentence Examples

[1081] "Please predict the peak hours of energy consumption for the following week based on your weekly energy consumption patterns and propose a specific action plan to reduce energy use during peak hours."

[1082] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1083] Step 1:

[1084] The server collects real-time energy and water usage data from sensors installed on machinery and equipment within the factory. Specifically, each sensor sends data to the server at regular intervals via an API. The input is raw data from the sensors, and the output is time-series data accumulated on the server.

[1085] Step 2:

[1086] The server cleans the acquired data in real time, removing noise and outliers and arranging it into a consistent data format. Specifically, it removes negative values ​​and extremely high values ​​as outliers and fills in missing data. The input is raw data, and the output is cleaned data.

[1087] Step 3:

[1088] The server uses the cleaned data to train an AI model. It analyzes past usage data and generates algorithms to predict future energy and water usage patterns. Specifically, it uses deep learning and decision tree algorithms. The input is the cleaned data, and the output is a trained AI model.

[1089] Step 4:

[1090] The server analyzes real-time data using a trained AI model, which detects peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a particular time period, that time is recognized as a peak period. The input is real-time data, and the output is the analysis results (detection of peak times and abnormal usage).

[1091] Step 5:

[1092] The server generates a specific action plan based on the analysis results, such as proposing changes to machine operating times to reduce energy use during peak hours. The input is the analysis results, and the output is the action plan.

[1093] Step 6:

[1094] The terminal delivers the action plan received from the server to the user. The user (factory manager) takes specific actions according to this action plan. For example, they may change the operating time of a machine or check an area where abnormal water usage has been detected. The input is the action plan, and the output is the user's actions.

[1095] Step 7:

[1096] Users provide feedback on their actions to the server, which collects this feedback and uses it to retrain the AI ​​model, thereby continually improving its accuracy and effectiveness. The input is the user feedback, and the output is the retrained AI model.

[1097] 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.

[1098] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[1099] 1. Data collection function

[1100] The server receives real-time energy and water usage data via APIs from sensors installed in each home or business, including electricity meters, gas meters, water meters, or sensors that detect these types of usage data.

[1101] 2. Data preprocessing function

[1102] The server cleans the acquired data, which removes noise and outliers and maintains data quality. The cleaning process includes filling in missing data and correcting outliers.

[1103] 3. AI model training function

[1104] The server uses the cleaned data to train an AI algorithm, which then creates a model to suggest optimal resource management methods for each home or business. The AI ​​model learns electricity and water consumption patterns and makes predictions. Deep learning and decision tree algorithms are used for this.

[1105] 4. Emotion engine integration

[1106] The server uses an emotion engine to obtain the user's emotion data, which is derived from facial and voice analysis of the user. The emotion data is analyzed in real time to adjust the recommended action plan based on the user's current emotional state.

[1107] 5. Insight generation function

[1108] The server uses the trained model to analyze real-time energy and water usage data and sentiment data, detecting specific usage patterns and abnormal usage and generating specific action plans based on this analysis.

[1109] 6. Action plan generation and distribution function

[1110] Based on the analysis results, the server generates a specific action plan to recommend to the user. This action plan takes into account the user's emotional state and is flexibly adjusted as needed. Examples include recommendations such as "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[1111] The device converts the reports received from the server into a format that the user can view. Important insights and urgent action plans are notified to the user via push notifications or email. The content and timing of notifications are also adjusted according to the user's emotional state.

[1112] 7. Execution and feedback functions

[1113] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[1114] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[1115] Specific examples

[1116] Example 1: Reducing power usage during peak hours

[1117] 1. The server acquires and cleans the household electricity consumption data from sensors.

[1118] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[1119] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[1120] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[1121] 5. The device will send a notification to the user, recommending that they change their usage time.

[1122] 6. The user changes the usage time of the appliance based on the notification.

[1123] 7. The user feeds the results back to the server and contributes to retraining the model.

[1124] Example 2: Abnormal water usage detection

[1125] 1. The server obtains household water data from sensors and cleans it.

[1126] 2. The server detects abnormal water usage in real time.

[1127] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the timing of anomaly detection notifications so that they are sent at the most acceptable time for the user.

[1128] 4. The server generates an anomaly detection alert and delivers it to the device.

[1129] 5. The device sends a notification to the user saying, "Abnormal water usage has been detected in the kitchen tap. Please check as there may be a leak."

[1130] 6. The User shall check the water supply based on the notice and carry out repairs as necessary.

[1131] 7. The user feeds the results back to the server and contributes to retraining the model.

[1132] In this way, the system optimizes resource management in homes and businesses, and by taking into account the user's emotions, it achieves a sustainable and stress-free lifestyle.

[1133] The processing flow will be explained below.

[1134] Processing flow in energy and water resource management systems (emotion engine integration)

[1135] Example 1: Reducing power usage during peak hours

[1136] Step 1: Data collection

[1137] The server obtains household electricity consumption data in real time via an API from sensors installed in each home.

[1138] Step 2: Data Preprocessing

[1139] The server cleans the acquired data, removing noise and outliers, specifically identifying excessively high usage and imputing it to ensure data consistency.

[1140] Step 3: Model training

[1141] The server uses the cleaned data to train an AI model to learn each household's electricity usage patterns, a process that involves deep learning and decision tree algorithms.

[1142] Step 4: Obtaining emotion data

[1143] The server acquires the user's emotional data through the emotion engine, which is collected using the camera and microphone on the user's smartphone or computer.

[1144] Step 5: Analyze peak times and emotional states

[1145] The server identifies peak times for power usage and simultaneously analyzes users' emotional data in real time to identify times when users are least likely to feel stressed.

[1146] Step 6: Generate an action plan

[1147] The server generates an action plan that recommends reducing power usage during peak hours and adjusts the plan based on the user's emotional state. For example, it suggests guidelines to reduce power usage during times when the user is relaxing.

[1148] Step 7: Report Distribution

[1149] The server delivers a report containing the generated action plan to the terminal.

[1150] Step 8: User Notification

[1151] The device converts the reports into a user-readable format and notifies users of key insights via push notifications and in-app alerts.

[1152] Step 9: Take Action

[1153] Users can adjust the usage time of their washing machine or air conditioner according to the action plan provided.

[1154] Example 2: Abnormal water usage detection

[1155] Step 1: Data collection

[1156] The server collects water usage data from each household water supply in real time from sensors.

[1157] Step 2: Data Preprocessing

[1158] The server cleans the acquired data, corrects missing values ​​and abnormal data, and prepares the data for analysis.

[1159] Step 3: Model training

[1160] The server uses the cleaned data to train an AI model that learns historical water usage patterns.

[1161] Step 4: Obtaining emotion data

[1162] The server obtains the user's emotional data through an emotion engine, which includes the ability to read emotions from the user's facial expressions and voice.

[1163] Step 5: Anomaly detection

[1164] The server compares real-time water usage data with the trained model to detect abnormal water usage, while simultaneously analyzing user sentiment data to determine the optimal timing for notification.

[1165] Step 6: Generate an action plan

[1166] If an anomaly is detected, the server generates an action plan indicating a possible water leak, taking into account the user's emotional state and notifying them at a time that minimizes stress.

[1167] Step 7: Delivering notifications

[1168] The server distributes the generated anomaly detection notification to the terminal.

[1169] Step 8: User Notification

[1170] The device will send a notification to the user about the detected abnormality. For example, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[1171] Step 9: Take Action

[1172] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[1173] In this way, through a series of processing flows including an emotion engine, this system optimizes the use of resources in homes and businesses, realizing sustainable and user-friendly improvements to lifestyles.

[1174] Example 2

[1175] 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."

[1176] Conventional energy and water resource management systems collect and analyze data in real time, but they do not generate or notify action plans that take into account the user's emotional state. This makes it difficult for users to manage resources in a stress-free manner, limiting their ability to achieve sustainable lifestyles. Furthermore, they lack a mechanism for incorporating user feedback and continuously improving the accuracy and effectiveness of the system.

[1177] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1178] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each home or business; means for cleaning the acquired data, completing missing data, and correcting outliers; means for training a learning algorithm using the cleaned data to create a generative AI model for proposing optimal resource management methods for each home or business; means for acquiring user emotion data using an emotion engine, generating specific action plans based on the analysis results, and distributing them to the user; means for sending notifications to the user via their device and adjusting the content and timing of the notifications based on the user's emotional state; and means for collecting user feedback and using it to retrain the generative AI model. This enables resource management that takes user emotions into account, enabling users to achieve sustainable lifestyles with less stress. Furthermore, by incorporating user feedback, the accuracy and effectiveness of the system can be continuously improved.

[1179] "Sensors" are devices installed in homes and businesses to measure energy and water usage and collect data in real time.

[1180] "Cleaning" is the process of removing noise, missing values, and outliers from collected data and converting it into a form suitable for learning algorithms.

[1181] "Learning algorithm" is an algorithm that uses the acquired and cleaned data to analyze energy and water usage patterns and build predictive models.

[1182] A "generative AI model" is a model trained using a learning algorithm to suggest optimal resource management methods for each household or business.

[1183] The "emotion engine" is an engine that obtains the user's emotional state using means such as facial expression and voice analysis, and analyzes it in real time.

[1184] An "action plan" is a specific suggestion or instruction generated based on the analyzed data and the user's emotional state.

[1185] A "terminal" is a device used to deliver action plans and notifications to users, typically a smartphone, tablet, or other device.

[1186] "Feedback" refers to information sent to the server about the results and impressions of actions taken by the user, which is used to retrain and optimize the system.

[1187] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[1188] (Data collection function)

[1189] The server obtains energy and water usage data in real time through an API from sensors installed in each home or business. This includes electricity meters, gas meters, water meters, or sensors that detect these usage data. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive electricity consumption data.

[1190] (Data preprocessing function)

[1191] The server cleans the acquired data. The cleaning process includes filling in missing data and correcting outliers. For example, if missing data is detected, the server fills in NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with the appropriate value.

[1192] (AI model training function)

[1193] The server uses the cleaned data to train an AI algorithm. It uses deep learning and decision tree algorithms to learn and predict electricity and water consumption patterns. Specifically, the model begins training using Python's TensorFlow library, inputting data from the past year and having it learn consumption patterns.

[1194] (Emotion engine integration function)

[1195] The server obtains the user's emotional data using an emotion engine, which includes analyzing data obtained from the user's facial expressions and voice in real time. For example, the server obtains the user's emotional state through a request "GET / emotion?user_id=123" and receives a response of "{ "emotion": "happy"}".

[1196] (Insight generation function)

[1197] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and abnormal usage, and generates a specific action plan based on the detected patterns. For example, the server sends a "POST / analyze" request and generates a notification saying "Abnormal water usage detected" if an abnormality is detected.

[1198] (Action plan generation and distribution function)

[1199] The server generates a specific action plan based on the analysis results and sends it to the device. The device then converts this action plan into a format that is easy for the user to understand and notifies them. As a specific example, the server generates an action plan such as "Reduce electricity usage between 6:00 PM and 9:00 PM" and displays a push notification stating, "(Important) We recommend that you reduce electricity usage between 6:00 PM and 9:00 PM today."

[1200] (Execution and feedback function)

[1201] The user takes specific actions based on the action plan delivered to the device. For example, they may make a change such as "don't use the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback. For example, feedback is sent using "POST / feedback," and the server uses this feedback to retrain the generative AI model.

[1202] (Example)

[1203] As a concrete example, consider an action plan to reduce power usage during peak hours. The server obtains and cleans household power consumption data from sensors. Next, it analyzes consumption data from the past few weeks to identify peak power consumption times. It then uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time periods when the user is least likely to feel stressed. For example, an action plan such as "reduce power usage between 6:00 PM and 9:00 PM" is generated and distributed to the device. The device then sends a notification to the user recommending that they change their usage times. The user then changes the usage times of their home appliances based on the notification and provides feedback to the server.

[1204] In this way, the system's program gradually integrates resource management and emotion recognition to specifically optimize user behavior, enabling efficient use of energy and water and helping users live a less stressful and sustainable life. Furthermore, by incorporating user feedback, the system's accuracy and effectiveness can be continuously improved.

[1205] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1206] Step 1:

[1207] Data collection

[1208] The server receives energy and water usage data from sensors installed in each home or business via an API in real time. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive power consumption data.

[1209] Input: Energy and water usage data detected by sensors

[1210] Output: Raw energy and water usage data captured on the server

[1211] Specific behavior:

[1212] The server sends a request such as "GET / energy / usage?time=now" to the sensor.

[1213] The server receives the response data "{ "electricity_usage": 15.2 kWh}"

[1214] Step 2:

[1215] Data Preprocessing

[1216] The server cleans the acquired data. For example, if missing data is detected, the server fills NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with appropriate values.

[1217] Input: Captured raw energy and water use data

[1218] Output: Cleaned energy and water usage data

[1219] Specific behavior:

[1220] The server performs a process to fill in missing data values ​​(NaN) with the average value.

[1221] The server detects and corrects outliers as data that is more than three times the standard deviation.

[1222] Step 3:

[1223] Training an AI model

[1224] The server uses the cleaned data to train an AI algorithm. For example, it uses Python's TensorFlow library to start training a model, feeding it data from the past year to learn consumption patterns.

[1225] Input: Cleaned energy and water use data

[1226] Output: A trained AI model

[1227] Specific behavior:

[1228] The server uses Python's TensorFlow library to start training the AI ​​model.

[1229] The server uses cleaned data from the past year to learn consumption patterns.

[1230] Step 4:

[1231] Acquiring emotion data

[1232] The server uses the emotion engine to obtain the user's emotional data. For example, the server obtains the user's emotional state through the request "GET / emotion?user_id=123".

[1233] Input: User's facial expressions and voice data

[1234] Output: Parsed user sentiment data

[1235] Specific behavior:

[1236] The server sends "GET / emotion?user_id=123" to the emotion engine to collect the user's emotion data.

[1237] The server receives the response data "{ "emotion": "happy"}"

[1238] Step 5:

[1239] Insight generation

[1240] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. For example, the server sends a "POST / analyze" request to start the analysis.

[1241] Input: Real-time energy and water usage data and sentiment data

[1242] Output: Insights and specific usage patterns, and anomaly detection results

[1243] Specific behavior:

[1244] The server sends a "POST / analyze" request to analyze the real-time data.

[1245] If an anomaly is detected, the server generates a notification such as "Anomaly in water usage has been detected."

[1246] Step 6:

[1247] Action plan generation and distribution

[1248] The server generates a specific action plan based on the analysis results and delivers it to the device, which then converts the action plan into a format that is easy for the user to understand and notifies them.

[1249] Input: Analysis results and emotion data

[1250] Output: A concrete action plan delivered to the user

[1251] Specific behavior:

[1252] The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and sends it to the device.

[1253] The device displays a push notification saying, "(Important) We recommend that you refrain from using electricity between 6:00 PM and 9:00 PM today."

[1254] Step 7:

[1255] Execution and Feedback

[1256] The user takes specific actions according to the action plan delivered to the device, such as "avoid using the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback.

[1257] Input: Result of action plan execution

[1258] Output: Feedback data

[1259] Specific behavior:

[1260] Users change their behavior based on notifications from their devices (e.g., change the usage time of home appliances)

[1261] The user sends the results via "POST / feedback", and the server collects this data and uses it to retrain the AI ​​model.

[1262] In this way, the system collects data, pre-processes it, trains the AI ​​model, obtains sentiment data, generates insights and delivers action plans, collects feedback and retrains it at each step, achieving efficient and stress-free resource management.

[1263] (Application example 2)

[1264] 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."

[1265] Energy and water resource management in homes and businesses is an important issue for achieving sustainable living. However, conventional resource management systems do not take into account the user's emotional state, which can cause stress. They also lack the ability to detect abnormal energy and water usage in real time and propose appropriate action plans. To address this shortcoming, a system that integrates resource management with the user's emotional state is needed.

[1266] 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 acquiring energy and water usage data in real time from sensors installed in each home or business, means for processing the acquired data, removing noise, and converting it into a format suitable for learning, means for training an artificial intelligence model using the processed data and generating an algorithm for proposing an optimal resource management method for each home or business, means for acquiring user emotion data and adjusting an action plan based on the user's emotional state, means for generating specific proposals based on the analysis results and distributing them to the user, and means for collecting user feedback and retraining the model. This makes it possible to optimize resource management and reduce user stress.

[1267] A "sensor" is a device installed in a home or business to capture real-time energy and water usage data.

[1268] "Data processing" is the process of cleaning the acquired data, removing noise, and converting it into a form suitable for learning.

[1269] An "artificial intelligence model" is one that is trained using processed data to generate algorithms that suggest optimal resource management methods for homes and businesses.

[1270] "Emotional data" is information that indicates the user's emotional state and is acquired through sensing devices such as cameras and microphones.

[1271] An "action plan" is a specific guideline of action that is generated based on the analysis results and is suggested for the user to implement.

[1272] "Feedback" is user-provided information or results that are used to retrain the model.

[1273] "API" refers to the application program interface for collecting data from sensors.

[1274] The present invention describes a system that optimizes energy and water resource management in homes and businesses, recognizing user sentiment and incorporating that data into models and action plans.

[1275] This system mainly consists of the following components: sensors, data processing function, artificial intelligence model, emotion data acquisition function, action plan generation function, feedback function, and data collection API.

[1276] 1. Sensor

[1277] Detectors are installed in homes and businesses to collect energy and water usage data in real time. Examples of such meters include electricity meters, gas meters, and water meters, as well as sensors that detect these usage data.

[1278] 2. Data processing function

[1279] The server processes the data acquired from the sensors, removes noise, and converts it into a format suitable for learning. Specifically, data cleaning removes noise and outliers, and performs missing data correction and correction. StandardScaler and other tools are used for data preprocessing.

[1280] 3. Artificial Intelligence Model

[1281] The processed data is used to train an artificial intelligence model. This model proposes optimal resource management methods for each household or business, learning and predicting electricity and water consumption patterns. Deep learning and decision tree algorithms are used for this. Keras and TensorFlow are used for the detailed implementation of the model.

[1282] 4. Emotion data acquisition function

[1283] Emotion data is acquired by analyzing the user's facial expressions and voice. Emotion recognition is performed using a camera and microphone, along with software such as EmotionRecognizer. Emotion data is analyzed in real time, and an action plan is adjusted based on the user's emotional state.

[1284] 5. Action plan generation function

[1285] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and emotion data to detect specific usage patterns and anomalies. Based on the analysis results, it generates and delivers specific action plans to users. Examples include "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[1286] 6. Feedback function

[1287] Users take specific actions based on the action plan provided and provide feedback on the results, which is then aggregated on a server and used to retrain the AI ​​model, thereby continuously improving its accuracy and effectiveness.

[1288] Specific examples

[1289] Example 1: Reducing power usage during peak hours

[1290] 1. The server acquires and cleans the household electricity consumption data from the detectors.

[1291] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[1292] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[1293] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[1294] 5. The device will send a notification to the user, recommending that they change their usage time.

[1295] 6. The user changes the usage time of the appliance based on the notification.

[1296] 7. The user feeds the results back to the server and contributes to retraining the model.

[1297] Prompt Sentence Examples

[1298] "Write a Python program that monitors a home's energy and water usage data in real time, detects anomalies, and sends appropriate alerts based on the user's emotional state. Specifically, the program needs to have the following capabilities:

[1299] Data collection function

[1300] Data preprocessing function

[1301] AI model training function

[1302] Emotion engine integration

[1303] Insight generation features

[1304] Action plan generation and distribution function

[1305] As a result, this system optimizes resource management in homes and businesses and takes into account users' emotions, enabling a sustainable and stress-free lifestyle.

[1306] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1307] Step 1:

[1308] The server collects energy and water usage data in real time from sensors installed in each home or business. This data is retrieved through an API, and the collected data may contain noise and outliers. The input is raw data from the sensors, and the output is unprocessed data stored in the server.

[1309] Step 2:

[1310] The server cleans the collected data, removes noise, and converts it into a format suitable for learning. This data cleaning process includes identifying and correcting outliers and filling in missing data. Specifically, the data is standardized using tools such as StandardScaler. The input is the collected raw data, and the output is the cleaned data.

[1311] Step 3:

[1312] The server uses the cleaned data to train an artificial intelligence model. This model generates an algorithm to propose optimal resource management methods for each household or business, using deep learning and decision tree algorithms. Specifically, the model is implemented and trained using Keras and TensorFlow. The input is the cleaned data, and the output is a trained artificial intelligence model.

[1313] Step 4:

[1314] The server acquires the user's emotional data and recognizes their emotional state. Emotional data is collected through a camera and microphone and analyzed using software such as EmotionRecognizer. The input is the user's facial expression and voice data, and the output is the recognized emotional state.

[1315] Step 5:

[1316] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and anomalies and generates specific action plans based on them. The input is the latest usage data and sentiment data, and the output is the generated action plan.

[1317] Step 6:

[1318] The server delivers the generated action plan to the user. This delivery is done through the device, and the user receives the action plan by push notification or email. The input is the generated action plan, and the output is the notification delivered to the user device.

[1319] Step 7:

[1320] The user takes specific actions based on the received action plan, such as changing the time the washing machine is used or checking the location where abnormal usage has been detected. The input is the received action plan, and the output is the specific action taken by the user.

[1321] Step 8:

[1322] Users provide feedback to the server about the results of their runs, which is used to retrain the model, continually improving the accuracy and effectiveness of the system. The input is user feedback information, and the output is an updated artificial intelligence model.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] [Fourth embodiment]

[1327] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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.

[1332] 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).

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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."

[1340] The present invention details a system designed to optimize energy and water resource management in homes and businesses.

[1341] 1. Data collection function

[1342] The server collects real-time energy and water usage data from sensors installed in homes and businesses. This data collection is done through APIs (application programming interfaces). For example, sensors connected to electricity or water meters periodically record usage information and send it to the server.

[1343] 2. Data preprocessing function

[1344] The server cleans the acquired data. The data cleaning process removes noise and outliers and ensures data consistency. Specifically, it complements missing data and corrects frequently occurring data errors.

[1345] 3. AI model training function

[1346] The server uses the cleaned data to train AI algorithms. The AI ​​models learn from past energy and water usage patterns and predict future usage. The models are built using machine learning techniques, including deep learning and decision tree algorithms.

[1347] 4. Insight generation function

[1348] The server analyzes real-time data using the trained model, which can detect peak energy usage and unusual water usage. For example, if unusual water usage is detected in a household, it could indicate a possible leak.

[1349] 5. Action plan generation and distribution function

[1350] The server generates specific action plans based on the analysis results, such as "Schedule the use of your washing machine outside of the hours of 6:00 PM to 9:00 PM to avoid peak power usage." These action plans are delivered to the device in the form of a report.

[1351] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email.

[1352] 6. Execution and feedback functions

[1353] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[1354] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[1355] Specific examples

[1356] Example 1: Reducing power usage during peak hours

[1357] 1. The server obtains household electricity consumption data from sensors.

[1358] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[1359] 3. The server generates specific guidelines for reducing peak power usage.

[1360] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[1361] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[1362] Example 2: Abnormal water usage detection

[1363] 1. The server obtains water usage data from sensors on each water supply in the home.

[1364] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[1365] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[1366] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[1367] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[1368] In this way, the system provides a range of functions to optimize resource management in homes and businesses and achieve sustainable living.

[1369] The processing flow will be explained below.

[1370] Energy and Water Resource Management System Processing Flow

[1371] Example 1: Reducing power usage during peak hours

[1372] Step 1: Data collection

[1373] The server obtains household electricity consumption data from sensors via an API.

[1374] Step 2: Data Preprocessing

[1375] The server cleans the acquired data and removes noise and outliers, specifically by filling in missing values ​​and correcting abnormally high values.

[1376] Step 3: Identify peak times

[1377] The server uses the cleaned data to analyze power consumption patterns over the past few weeks and identify peak times for power consumption.

[1378] Step 4: Generate an action plan

[1379] The server generates specific guidelines for reducing peak power usage, including recommendations such as "avoid using energy-intensive appliances (washers, dryers, etc.) between 6:00 PM and 9:00 PM."

[1380] Step 5: Report Distribution

[1381] The server generates a report containing the above guidelines and delivers it to the terminal.

[1382] Step 6: User Notification

[1383] The device converts the reports received from the server into a user-readable format and provides important insights, such as push notifications or in-app alerts that advise users to avoid using the device during peak power hours.

[1384] Step 7: Take Action

[1385] Based on the notification, users can change the time they use their washing machine or dryer to off-peak hours.

[1386] Example 2: Abnormal water usage detection

[1387] Step 1: Data collection

[1388] The server receives real-time water usage data from the household water supply via sensors.

[1389] Step 2: Data Preprocessing

[1390] The server cleans the acquired data and distinguishes between normal and abnormal values, specifically identifying values ​​that deviate significantly from normal usage patterns.

[1391] Step 3: Anomaly detection

[1392] The server analyzes the cleaned data and compares it with historical usage patterns to detect abnormal water usage in real time.

[1393] Step 4: Generate anomaly notifications

[1394] Based on the detected anomalies, the server generates alerts indicating possible water leaks, etc.

[1395] Step 5: Delivering notifications

[1396] The server distributes the generated alerts to the terminals.

[1397] Step 6: User Notification

[1398] The device immediately sends a notification of the abnormality detected by the server to the user, such as, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[1399] Step 7: Take Action

[1400] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[1401] Through these steps, the system optimizes resource usage in homes and businesses, reducing environmental impact and operational costs.

[1402] Example 1

[1403] 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."

[1404] Optimizing the efficiency of energy and water use in modern homes and businesses is an important challenge from the perspective of sustainable resource management. However, the processes of individual data collection, analysis, optimization proposals, and feedback based on those data are complex, and advanced technology is required to achieve effective management. Conventional methods make it difficult to consistently execute these processes, making it difficult to achieve efficient resource management.

[1405] 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.

[1406] In this invention, the server includes: means for acquiring energy and water usage data in real time from multiple sensors installed in each home or business; means for cleaning the acquired data, removing noise and outliers, and converting it into a consistent format; means for training an AI model using the cleaned data to generate an algorithm that proposes an optimal resource management method for each home or business; means for analyzing the real-time data using the trained AI model to detect energy and water usage patterns; means for generating a specific action plan based on the analysis results and distributing it to the user's device; and means for collecting feedback from the user and retraining the AI ​​model. This automates the process from consistent data collection to optimization proposals, feedback collection, and retraining, enabling efficient resource management.

[1407] "Data collection means" refers to a means for obtaining energy and water usage data in real time from multiple sensors installed in each home or business.

[1408] A "data cleaning means" is a means for cleaning acquired data, removing noise and outliers, and converting the data into a consistent format.

[1409] The "AI model training means" is a means for training an AI model using cleaned data and generating an algorithm that proposes optimal resource management methods for each household or business.

[1410] "Real-time data analysis means" means a means for analyzing real-time data using a trained AI model to detect energy and water usage patterns.

[1411] The "action plan generation means" is a means for generating a specific action plan based on the analysis results and distributing it to the user's terminal.

[1412] "Feedback collection means" refers to the means used to collect user feedback and retrain the AI ​​model.

[1413] This invention relates to a system that optimizes energy and water usage in homes and businesses. This system collects data from multiple sensors installed in each home or business and analyzes it using AI technology to propose efficient resource management. The specific configuration and operation of this system are described below.

[1414] 1. Data collection function

[1415] The server collects real-time energy and water usage data from sensors installed in each home or business. This data is collected through an API (Application Programming Interface). Specifically, sensors connected to electricity and water meters periodically record usage information and send that data to the server. For this reason, the server must be equipped with a high-performance network interface and database system.

[1416] 2. Data preprocessing function

[1417] The server cleans the acquired data. The data cleaning process involves removing noise and outliers and filling in missing data to ensure data consistency. This process uses data cleansing tools such as Pandas and NumPy.

[1418] 3. AI model training function

[1419] The server uses the cleaned data to train an AI model. Specifically, it uses deep learning frameworks (such as TensorFlow or PyTorch) and decision tree algorithms to learn past energy and water usage patterns and build a model to predict future usage. This AI model requires a lot of computing resources to accurately learn resource usage patterns.

[1420] 4. Insight generation function

[1421] The server analyzes real-time data using a trained AI model. This analysis can detect peak energy usage times and abnormal water usage. For example, if abnormal water usage is detected in a household, it could suggest a possible water leak. The analysis results are provided with high accuracy, allowing the system to suggest accurate and prompt actions to users.

[1422] 5. Action plan generation and distribution function

[1423] The server generates a specific action plan based on the analysis results, such as "Schedule the use of your washing machine outside the hours of 6:00 PM to 9:00 PM to avoid peak power usage." The generated action plan is delivered to the device in the form of a report.

[1424] The device converts the reports received from the server into a format that the user can view, and important insights and urgent action plans are notified to the user via push notifications or email, allowing the user to take the necessary action at the appropriate time.

[1425] 6. Execution and feedback functions

[1426] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[1427] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness. This feedback loop allows the system to constantly adapt to the latest situation and provide optimal resource management.

[1428] Specific examples

[1429] Example 1: Reducing power usage during peak hours

[1430] 1. The server obtains household electricity consumption data from sensors.

[1431] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[1432] 3. The server generates specific guidelines for reducing peak power usage.

[1433] 4. The device will notify the user of guidelines and recommend avoiding use during peak power hours (e.g., 6:00 PM to 9:00 PM).

[1434] 5. The user will follow the notice and change the usage time of the washing machine or air conditioner.

[1435] Example 2: Abnormal water usage detection

[1436] 1. The server obtains water usage data from sensors on each water supply in the home.

[1437] 2. The server detects abnormal water usage by comparing it with past usage patterns.

[1438] 3. If the server detects abnormal water usage, it will notify you of a possible water leak.

[1439] 4. The device immediately sends a notification to the user that an anomaly has been detected.

[1440] 5. The User shall check the water supply based on the notice and carry out repairs as necessary.

[1441] Prompt Sentence Examples

[1442] "Analyze electricity usage data and suggest optimal ways to reduce energy consumption during peak hours."

[1443] In this way, the system provides a range of functions to optimise resource management in homes and businesses and achieve sustainable living.

[1444] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1445] Step 1: Data collection

[1446] The server collects real-time energy and water usage data from multiple sensors installed in each home or business, and sends the data recorded by the sensors to the server via an API.

[1447] Input: Real-time usage data recorded by sensors

[1448] Output: Raw usage data stored on the server

[1449] Specific behavior:

[1450] The server periodically sends API requests to receive data from each sensor, which is then stored in a database.

[1451] Step 2: Data Preprocessing

[1452] The server cleans the acquired data, removing noise and outliers and filling in missing data to ensure data consistency.

[1453] Input: Raw usage data

[1454] Output: Clean usage data

[1455] Specific behavior:

[1456] The server cleans the data using a data cleansing tool (e.g., Pandas, NumPy), filters out noise and outliers, and fills in missing data before storing it back in the database.

[1457] Step 3: Training the AI ​​model

[1458] The server uses the cleaned data to train an AI model, using deep learning frameworks and decision tree algorithms.

[1459] Input: Clean usage data

[1460] Output: A trained AI model

[1461] Specific behavior:

[1462] The server generates a training dataset and inputs it into the AI ​​model, and once the training process is complete, the trained model is saved.

[1463] Step 4: Insight generation

[1464] The server analyzes real-time data using a trained AI model to detect usage patterns and anomalies.

[1465] Input: Real-time data, trained AI model

[1466] Output: Detected insights (e.g. peak times, unusual usage)

[1467] Specific behavior:

[1468] The server inputs real-time data into the AI ​​model to detect anomalies and analyze peak times, and the results are stored in a database.

[1469] Step 5: Generate and distribute an action plan

[1470] The server generates a specific action plan based on the analysis results and distributes it to the device.

[1471] Input: Discovered insights

[1472] Output: Action Plan

[1473] Specific behavior:

[1474] The server generates an action plan and sends it to the device, which then converts it into a format that the user can view and delivers key insights via push notifications.

[1475] Step 6: Implementation and feedback

[1476] The user takes action according to the delivered action plan and provides the results as feedback to the server.

[1477] Input: Action Plan

[1478] Output: Actions taken and feedback

[1479] Specific behavior:

[1480] The user acts on the action plan and sends the results through the application to the server, which receives the feedback and uses it to retrain the AI ​​model.

[1481] This series of processing steps results in efficient and sustainable resource management.

[1482] (Application example 1)

[1483] 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."

[1484] Conventional energy and water management systems in homes and businesses have focused on optimizing resources for individual users, but in large facilities such as factories, it has been difficult to reduce energy usage during peak hours and quickly detect and respond to abnormal water usage. This has led to a demand for energy efficiency and reduction of water waste to reduce overall costs.

[1485] 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.

[1486] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each facility; means for cleaning the acquired data, removing noise, and converting it into a format suitable for learning; means for training a model using the cleaned data and generating an algorithm for proposing an optimal resource management method for each facility; means for generating a specific action plan based on the analysis results and distributing it to users; means for collecting feedback from users and retraining the model; means for collecting data from sensors attached to machines and devices in the factory and detecting peak times and abnormalities; means for generating an action plan to reduce energy usage during peak times; and means for notifying a manager when abnormal water usage is detected. This enables optimization of energy efficiency and water management in the factory and overall cost reduction.

[1487] "Facilities" refers to large-scale installations such as factories and production lines, where energy and water management is required.

[1488] A "sensor" is a device that collects energy and water usage data in real time.

[1489] "Noise" refers to unnecessary or erroneous information contained in data that prevents accurate analysis.

[1490] "Cleaning" is the process of removing noise and outliers from the acquired data and converting it into a format suitable for learning.

[1491] A "model" is an algorithm that is trained using cleaned data to optimize resource management methods.

[1492] An "action plan" is a specific guideline for action that is generated based on the analysis results and proposed to the user.

[1493] "User" means an individual or manager who uses the system to manage energy and water resources.

[1494] "Feedback" refers to the results and reactions to actions taken by the user, and is information that helps improve the model.

[1495] "Peak hours" are times when energy use is particularly high.

[1496] "Abnormal water usage" refers to water consumption that deviates significantly from normal usage patterns and may indicate a leak or mechanical failure.

[1497] The "server" is the central system that collects and cleans data from sensors, and trains and analyzes models.

[1498] The present invention is a system for optimizing the management of energy and water resources in large-scale facilities such as factories, etc. Specific embodiments of this system will be described below.

[1499] Program Description

[1500] Data collection function

[1501] The server collects real-time energy and water usage data from sensors installed on machines and equipment within the factory. These sensors communicate with the server through an API and periodically transmit data. This sensor network includes, for example, electricity meters and water meters.

[1502] Data preprocessing function

[1503] The server cleans the acquired data in real time. This process includes removing noise and outliers, and filling in missing data. For example, extremely high or negative values ​​are considered outliers and are removed.

[1504] AI model training function

[1505] Using the cleaned data, the server trains AI algorithms that learn from past energy and water usage patterns and predict future usage, using machine learning techniques such as deep learning and decision tree algorithms.

[1506] Insight generation features

[1507] Using a trained AI model, the server analyzes real-time data to detect peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a certain time period, that time is recognized as a peak period.

[1508] Action plan generation and distribution capabilities

[1509] The server generates specific action plans based on the analysis results, such as recommendations such as "changing machine operating times to reduce energy use during peak hours." These action plans are then distributed to terminals (such as computers or tablets used by factory managers).

[1510] Execution and feedback functions

[1511] The user (factory manager) takes specific actions according to the action plan delivered to the device. For example, they can "change the machine's operating time" or "check areas where abnormal water usage has been detected." They can also provide feedback on the results of these actions to the server. The server collects this feedback and uses it to retrain the AI ​​model. This allows the model's accuracy and effectiveness to be continuously improved.

[1512] Specific examples

[1513] For example, a factory robot equipped with this system can monitor the usage of its own charging station and manage it to avoid unnecessary charging during peak hours. Also, if a machine in the factory uses water abnormally, the system can immediately notify the manager and prompt a prompt response.

[1514] Prompt Sentence Examples

[1515] "Please predict the peak hours of energy consumption for the following week based on your weekly energy consumption patterns and propose a specific action plan to reduce energy use during peak hours."

[1516] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1517] Step 1:

[1518] The server collects real-time energy and water usage data from sensors installed on machinery and equipment within the factory. Specifically, each sensor sends data to the server at regular intervals via an API. The input is raw data from the sensors, and the output is time-series data accumulated on the server.

[1519] Step 2:

[1520] The server cleans the acquired data in real time, removing noise and outliers and arranging it into a consistent data format. Specifically, it removes negative values ​​and extremely high values ​​as outliers and fills in missing data. The input is raw data, and the output is cleaned data.

[1521] Step 3:

[1522] The server uses the cleaned data to train an AI model. It analyzes past usage data and generates algorithms to predict future energy and water usage patterns. Specifically, it uses deep learning and decision tree algorithms. The input is the cleaned data, and the output is a trained AI model.

[1523] Step 4:

[1524] The server analyzes real-time data using a trained AI model, which detects peak energy usage and abnormal water usage. For example, if there is a sudden increase in energy consumption during a particular time period, that time is recognized as a peak period. The input is real-time data, and the output is the analysis results (detection of peak times and abnormal usage).

[1525] Step 5:

[1526] The server generates a specific action plan based on the analysis results, such as proposing changes to machine operating times to reduce energy use during peak hours. The input is the analysis results, and the output is the action plan.

[1527] Step 6:

[1528] The terminal delivers the action plan received from the server to the user. The user (factory manager) takes specific actions according to this action plan. For example, they may change the operating time of a machine or check an area where abnormal water usage has been detected. The input is the action plan, and the output is the user's actions.

[1529] Step 7:

[1530] Users provide feedback on their actions to the server, which collects this feedback and uses it to retrain the AI ​​model, thereby continually improving its accuracy and effectiveness. The input is the user feedback, and the output is the retrained AI model.

[1531] 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.

[1532] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[1533] 1. Data collection function

[1534] The server receives real-time energy and water usage data via APIs from sensors installed in each home or business, including electricity meters, gas meters, water meters, or sensors that detect these types of usage data.

[1535] 2. Data preprocessing function

[1536] The server cleans the acquired data, which removes noise and outliers and maintains data quality. The cleaning process includes filling in missing data and correcting outliers.

[1537] 3. AI model training function

[1538] The server uses the cleaned data to train an AI algorithm, which then creates a model to suggest optimal resource management methods for each home or business. The AI ​​model learns electricity and water consumption patterns and makes predictions. Deep learning and decision tree algorithms are used for this.

[1539] 4. Emotion engine integration

[1540] The server uses an emotion engine to obtain the user's emotion data, which is derived from facial and voice analysis of the user. The emotion data is analyzed in real time to adjust the recommended action plan based on the user's current emotional state.

[1541] 5. Insight generation function

[1542] The server uses the trained model to analyze real-time energy and water usage data and sentiment data, detecting specific usage patterns and abnormal usage and generating specific action plans based on this analysis.

[1543] 6. Action plan generation and distribution function

[1544] Based on the analysis results, the server generates a specific action plan to recommend to the user. This action plan takes into account the user's emotional state and is flexibly adjusted as needed. Examples include recommendations such as "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[1545] The device converts the reports received from the server into a format that the user can view. Important insights and urgent action plans are notified to the user via push notifications or email. The content and timing of notifications are also adjusted according to the user's emotional state.

[1546] 7. Execution and feedback functions

[1547] The user can then take specific actions according to the action plan delivered to the device. For example, specific actions such as "changing the time the washing machine is used" or "checking the water supply" can be executed. After execution, feedback on the results can be provided to the server.

[1548] The server collects user feedback and uses it to retrain the AI ​​model, which continuously improves its accuracy and effectiveness.

[1549] Specific examples

[1550] Example 1: Reducing power usage during peak hours

[1551] 1. The server acquires and cleans the household electricity consumption data from sensors.

[1552] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[1553] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[1554] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[1555] 5. The device will send a notification to the user, recommending that they change their usage time.

[1556] 6. The user changes the usage time of the appliance based on the notification.

[1557] 7. The user feeds the results back to the server and contributes to retraining the model.

[1558] Example 2: Abnormal water usage detection

[1559] 1. The server obtains household water data from sensors and cleans it.

[1560] 2. The server detects abnormal water usage in real time.

[1561] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the timing of anomaly detection notifications so that they are sent at the most acceptable time for the user.

[1562] 4. The server generates an anomaly detection alert and delivers it to the device.

[1563] 5. The device sends a notification to the user saying, "Abnormal water usage has been detected in the kitchen tap. Please check as there may be a leak."

[1564] 6. The User shall check the water supply based on the notice and carry out repairs as necessary.

[1565] 7. The user feeds the results back to the server and contributes to retraining the model.

[1566] In this way, the system optimizes resource management in homes and businesses, and by taking into account the user's emotions, it achieves a sustainable and stress-free lifestyle.

[1567] The processing flow will be explained below.

[1568] Processing flow in energy and water resource management systems (emotion engine integration)

[1569] Example 1: Reducing power usage during peak hours

[1570] Step 1: Data collection

[1571] The server obtains household electricity consumption data in real time via an API from sensors installed in each home.

[1572] Step 2: Data Preprocessing

[1573] The server cleans the acquired data, removing noise and outliers, specifically identifying excessively high usage and imputing it to ensure data consistency.

[1574] Step 3: Model training

[1575] The server uses the cleaned data to train an AI model to learn each household's electricity usage patterns, a process that involves deep learning and decision tree algorithms.

[1576] Step 4: Obtaining emotion data

[1577] The server acquires the user's emotional data through the emotion engine, which is collected using the camera and microphone on the user's smartphone or computer.

[1578] Step 5: Analyze peak times and emotional states

[1579] The server identifies peak times for power usage and simultaneously analyzes users' emotional data in real time to identify times when users are least likely to feel stressed.

[1580] Step 6: Generate an action plan

[1581] The server generates an action plan that recommends reducing power usage during peak hours and adjusts the plan based on the user's emotional state. For example, it suggests guidelines to reduce power usage during times when the user is relaxing.

[1582] Step 7: Report Distribution

[1583] The server delivers a report containing the generated action plan to the terminal.

[1584] Step 8: User Notification

[1585] The device converts the reports into a user-readable format and notifies users of key insights via push notifications and in-app alerts.

[1586] Step 9: Take Action

[1587] Users can adjust the usage time of their washing machine or air conditioner according to the action plan provided.

[1588] Example 2: Abnormal water usage detection

[1589] Step 1: Data collection

[1590] The server collects water usage data from each household water supply in real time from sensors.

[1591] Step 2: Data Preprocessing

[1592] The server cleans the acquired data, corrects missing values ​​and abnormal data, and prepares the data for analysis.

[1593] Step 3: Model training

[1594] The server uses the cleaned data to train an AI model that learns historical water usage patterns.

[1595] Step 4: Obtaining emotion data

[1596] The server obtains the user's emotional data through an emotion engine, which includes the ability to read emotions from the user's facial expressions and voice.

[1597] Step 5: Anomaly detection

[1598] The server compares real-time water usage data with the trained model to detect abnormal water usage, while simultaneously analyzing user sentiment data to determine the optimal timing for notification.

[1599] Step 6: Generate an action plan

[1600] If an anomaly is detected, the server generates an action plan indicating a possible water leak, taking into account the user's emotional state and notifying them at a time that minimizes stress.

[1601] Step 7: Delivering notifications

[1602] The server distributes the generated anomaly detection notification to the terminal.

[1603] Step 8: User Notification

[1604] The device will send a notification to the user about the detected abnormality. For example, "Abnormal water usage has been detected in the kitchen tap. There may be a leak, so please check."

[1605] Step 9: Take Action

[1606] Users will be required to check their water supply based on the notification and carry out repairs if necessary.

[1607] In this way, through a series of processing flows including an emotion engine, this system optimizes the use of resources in homes and businesses, realizing sustainable and user-friendly improvements to lifestyles.

[1608] Example 2

[1609] 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."

[1610] Conventional energy and water resource management systems collect and analyze data in real time, but they do not generate or notify action plans that take into account the user's emotional state. This makes it difficult for users to manage resources in a stress-free manner, limiting their ability to achieve sustainable lifestyles. Furthermore, they lack a mechanism for incorporating user feedback and continuously improving the accuracy and effectiveness of the system.

[1611] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1612] In this invention, the server includes: means for acquiring energy and water usage data in real time from sensors installed in each home or business; means for cleaning the acquired data, completing missing data, and correcting outliers; means for training a learning algorithm using the cleaned data to create a generative AI model for proposing optimal resource management methods for each home or business; means for acquiring user emotion data using an emotion engine, generating specific action plans based on the analysis results, and distributing them to the user; means for sending notifications to the user via their device and adjusting the content and timing of the notifications based on the user's emotional state; and means for collecting user feedback and using it to retrain the generative AI model. This enables resource management that takes user emotions into account, enabling users to achieve sustainable lifestyles with less stress. Furthermore, by incorporating user feedback, the accuracy and effectiveness of the system can be continuously improved.

[1613] "Sensors" are devices installed in homes and businesses to measure energy and water usage and collect data in real time.

[1614] "Cleaning" is the process of removing noise, missing values, and outliers from collected data and converting it into a form suitable for learning algorithms.

[1615] "Learning algorithm" is an algorithm that uses the acquired and cleaned data to analyze energy and water usage patterns and build predictive models.

[1616] A "generative AI model" is a model trained using a learning algorithm to suggest optimal resource management methods for each household or business.

[1617] The "emotion engine" is an engine that obtains the user's emotional state using means such as facial expression and voice analysis, and analyzes it in real time.

[1618] An "action plan" is a specific suggestion or instruction generated based on the analyzed data and the user's emotional state.

[1619] A "terminal" is a device used to deliver action plans and notifications to users, typically a smartphone, tablet, or other device.

[1620] "Feedback" refers to information sent to the server about the results and impressions of actions taken by the user, which is used to retrain and optimize the system.

[1621] The present invention details a system that optimizes energy and water resource management in homes and businesses, and also recognizes user sentiment and incorporates that data into models and action plans.

[1622] (Data collection function)

[1623] The server obtains energy and water usage data in real time through an API from sensors installed in each home or business. This includes electricity meters, gas meters, water meters, or sensors that detect these usage data. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive electricity consumption data.

[1624] (Data preprocessing function)

[1625] The server cleans the acquired data. The cleaning process includes filling in missing data and correcting outliers. For example, if missing data is detected, the server fills in NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with the appropriate value.

[1626] (AI model training function)

[1627] The server uses the cleaned data to train an AI algorithm. It uses deep learning and decision tree algorithms to learn and predict electricity and water consumption patterns. Specifically, the model begins training using Python's TensorFlow library, inputting data from the past year and having it learn consumption patterns.

[1628] (Emotion engine integration function)

[1629] The server obtains the user's emotional data using an emotion engine, which includes analyzing data obtained from the user's facial expressions and voice in real time. For example, the server obtains the user's emotional state through a request "GET / emotion?user_id=123" and receives a response of "{ "emotion": "happy"}".

[1630] (Insight generation function)

[1631] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and abnormal usage, and generates a specific action plan based on the detected patterns. For example, the server sends a "POST / analyze" request and generates a notification saying "Abnormal water usage detected" if an abnormality is detected.

[1632] (Action plan generation and distribution function)

[1633] The server generates a specific action plan based on the analysis results and sends it to the device. The device then converts this action plan into a format that is easy for the user to understand and notifies them. As a specific example, the server generates an action plan such as "Reduce electricity usage between 6:00 PM and 9:00 PM" and displays a push notification stating, "(Important) We recommend that you reduce electricity usage between 6:00 PM and 9:00 PM today."

[1634] (Execution and feedback function)

[1635] The user takes specific actions based on the action plan delivered to the device. For example, they may make a change such as "don't use the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback. For example, feedback is sent using "POST / feedback," and the server uses this feedback to retrain the generative AI model.

[1636] (Example)

[1637] As a concrete example, consider an action plan to reduce power usage during peak hours. The server obtains and cleans household power consumption data from sensors. Next, it analyzes consumption data from the past few weeks to identify peak power consumption times. It then uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time periods when the user is least likely to feel stressed. For example, an action plan such as "reduce power usage between 6:00 PM and 9:00 PM" is generated and distributed to the device. The device then sends a notification to the user recommending that they change their usage times. The user then changes the usage times of their home appliances based on the notification and provides feedback to the server.

[1638] In this way, the system's program gradually integrates resource management and emotion recognition to specifically optimize user behavior, enabling efficient use of energy and water and helping users live a less stressful and sustainable life. Furthermore, by incorporating user feedback, the system's accuracy and effectiveness can be continuously improved.

[1639] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1640] Step 1:

[1641] Data collection

[1642] The server receives energy and water usage data from sensors installed in each home or business via an API in real time. For example, the server sends a "GET / energy / usage?time=now" request every hour on the hour to receive power consumption data.

[1643] Input: Energy and water usage data detected by sensors

[1644] Output: Raw energy and water usage data captured on the server

[1645] Specific behavior:

[1646] The server sends a request such as "GET / energy / usage?time=now" to the sensor.

[1647] The server receives the response data "{ "electricity_usage": 15.2 kWh}"

[1648] Step 2:

[1649] Data Preprocessing

[1650] The server cleans the acquired data. For example, if missing data is detected, the server fills NaN values ​​with the mean value, detects outliers as data that are more than three times the standard deviation, and replaces them with appropriate values.

[1651] Input: Captured raw energy and water use data

[1652] Output: Cleaned energy and water usage data

[1653] Specific behavior:

[1654] The server performs a process to fill in missing data values ​​(NaN) with the average value.

[1655] The server detects and corrects outliers as data that is more than three times the standard deviation.

[1656] Step 3:

[1657] Training an AI model

[1658] The server uses the cleaned data to train an AI algorithm. For example, it uses Python's TensorFlow library to start training a model, feeding it data from the past year to learn consumption patterns.

[1659] Input: Cleaned energy and water use data

[1660] Output: A trained AI model

[1661] Specific behavior:

[1662] The server uses Python's TensorFlow library to start training the AI ​​model.

[1663] The server uses cleaned data from the past year to learn consumption patterns.

[1664] Step 4:

[1665] Acquiring emotion data

[1666] The server uses the emotion engine to obtain the user's emotional data. For example, the server obtains the user's emotional state through the request "GET / emotion?user_id=123".

[1667] Input: User's facial expressions and voice data

[1668] Output: Parsed user sentiment data

[1669] Specific behavior:

[1670] The server sends "GET / emotion?user_id=123" to the emotion engine to collect the user's emotion data.

[1671] The server receives the response data "{ "emotion": "happy"}"

[1672] Step 5:

[1673] Insight generation

[1674] The server uses the trained model to analyze real-time energy and water usage data and sentiment data. For example, the server sends a "POST / analyze" request to start the analysis.

[1675] Input: Real-time energy and water usage data and sentiment data

[1676] Output: Insights and specific usage patterns, and anomaly detection results

[1677] Specific behavior:

[1678] The server sends a "POST / analyze" request to analyze the real-time data.

[1679] If an anomaly is detected, the server generates a notification such as "Anomaly in water usage has been detected."

[1680] Step 6:

[1681] Action plan generation and distribution

[1682] The server generates a specific action plan based on the analysis results and delivers it to the device, which then converts the action plan into a format that is easy for the user to understand and notifies them.

[1683] Input: Analysis results and emotion data

[1684] Output: A concrete action plan delivered to the user

[1685] Specific behavior:

[1686] The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and sends it to the device.

[1687] The device displays a push notification saying, "(Important) We recommend that you refrain from using electricity between 6:00 PM and 9:00 PM today."

[1688] Step 7:

[1689] Execution and Feedback

[1690] The user takes specific actions according to the action plan delivered to the device, such as "avoid using the washing machine between 6:00 PM and 9:00 PM." The user then sends the results of the action to the server as feedback.

[1691] Input: Result of action plan execution

[1692] Output: Feedback data

[1693] Specific behavior:

[1694] Users change their behavior based on notifications from their devices (e.g., change the usage time of home appliances)

[1695] The user sends the results via "POST / feedback", and the server collects this data and uses it to retrain the AI ​​model.

[1696] In this way, the system collects data, pre-processes it, trains the AI ​​model, obtains sentiment data, generates insights and delivers action plans, collects feedback and retrains it at each step, achieving efficient and stress-free resource management.

[1697] (Application example 2)

[1698] 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."

[1699] Energy and water resource management in homes and businesses is an important issue for achieving sustainable living. However, conventional resource management systems do not take into account the user's emotional state, which can cause stress. They also lack the ability to detect abnormal energy and water usage in real time and propose appropriate action plans. To address this shortcoming, a system that integrates resource management with the user's emotional state is needed.

[1700] 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 acquiring energy and water usage data in real time from sensors installed in each home or business, means for processing the acquired data, removing noise, and converting it into a format suitable for learning, means for training an artificial intelligence model using the processed data and generating an algorithm for proposing an optimal resource management method for each home or business, means for acquiring user emotion data and adjusting an action plan based on the user's emotional state, means for generating specific proposals based on the analysis results and distributing them to the user, and means for collecting user feedback and retraining the model. This makes it possible to optimize resource management and reduce user stress.

[1701] A "sensor" is a device installed in a home or business to capture real-time energy and water usage data.

[1702] "Data processing" is the process of cleaning the acquired data, removing noise, and converting it into a form suitable for learning.

[1703] An "artificial intelligence model" is one that is trained using processed data to generate algorithms that suggest optimal resource management methods for homes and businesses.

[1704] "Emotional data" is information that indicates the user's emotional state and is acquired through sensing devices such as cameras and microphones.

[1705] An "action plan" is a specific guideline of action that is generated based on the analysis results and is suggested for the user to implement.

[1706] "Feedback" is user-provided information or results that are used to retrain the model.

[1707] "API" refers to the application program interface for collecting data from sensors.

[1708] The present invention describes a system that optimizes energy and water resource management in homes and businesses, recognizing user sentiment and incorporating that data into models and action plans.

[1709] This system mainly consists of the following components: sensors, data processing function, artificial intelligence model, emotion data acquisition function, action plan generation function, feedback function, and data collection API.

[1710] 1. Sensor

[1711] Detectors are installed in homes and businesses to collect energy and water usage data in real time. Examples of such meters include electricity meters, gas meters, and water meters, as well as sensors that detect these usage data.

[1712] 2. Data processing function

[1713] The server processes the data acquired from the sensors, removes noise, and converts it into a format suitable for learning. Specifically, data cleaning removes noise and outliers, and performs missing data correction and correction. StandardScaler and other tools are used for data preprocessing.

[1714] 3. Artificial Intelligence Model

[1715] The processed data is used to train an artificial intelligence model. This model proposes optimal resource management methods for each household or business, learning and predicting electricity and water consumption patterns. Deep learning and decision tree algorithms are used for this. Keras and TensorFlow are used for the detailed implementation of the model.

[1716] 4. Emotion data acquisition function

[1717] Emotion data is acquired by analyzing the user's facial expressions and voice. Emotion recognition is performed using a camera and microphone, along with software such as EmotionRecognizer. Emotion data is analyzed in real time, and an action plan is adjusted based on the user's emotional state.

[1718] 5. Action plan generation function

[1719] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and emotion data to detect specific usage patterns and anomalies. Based on the analysis results, it generates and delivers specific action plans to users. Examples include "reducing electricity usage between 6:00 PM and 9:00 PM" and "checking the water supply if abnormal water usage is detected."

[1720] 6. Feedback function

[1721] Users take specific actions based on the action plan provided and provide feedback on the results, which is then aggregated on a server and used to retrain the AI ​​model, thereby continuously improving its accuracy and effectiveness.

[1722] Specific examples

[1723] Example 1: Reducing power usage during peak hours

[1724] 1. The server acquires and cleans the household electricity consumption data from the detectors.

[1725] 2. The server analyzes consumption data from the past few weeks to identify peak periods of power consumption.

[1726] 3. The server uses an emotion engine to obtain the user's emotional data and adjusts the action plan based on the time of day when the user is least likely to feel stressed.

[1727] 4. The server generates an action plan, such as "reduce electricity usage between 6:00 PM and 9:00 PM," and distributes it to the device.

[1728] 5. The device will send a notification to the user, recommending that they change their usage time.

[1729] 6. The user changes the usage time of the appliance based on the notification.

[1730] 7. The user feeds the results back to the server and contributes to retraining the model.

[1731] Prompt Sentence Examples

[1732] "Write a Python program that monitors a home's energy and water usage data in real time, detects anomalies, and sends appropriate alerts based on the user's emotional state. Specifically, the program needs to have the following capabilities:

[1733] Data collection function

[1734] Data preprocessing function

[1735] AI model training function

[1736] Emotion engine integration

[1737] Insight generation features

[1738] Action plan generation and distribution function

[1739] As a result, this system optimizes resource management in homes and businesses and takes into account users' emotions, enabling a sustainable and stress-free lifestyle.

[1740] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1741] Step 1:

[1742] The server collects energy and water usage data in real time from sensors installed in each home or business. This data is retrieved through an API, and the collected data may contain noise and outliers. The input is raw data from the sensors, and the output is unprocessed data stored in the server.

[1743] Step 2:

[1744] The server cleans the collected data, removes noise, and converts it into a format suitable for learning. This data cleaning process includes identifying and correcting outliers and filling in missing data. Specifically, the data is standardized using tools such as StandardScaler. The input is the collected raw data, and the output is the cleaned data.

[1745] Step 3:

[1746] The server uses the cleaned data to train an artificial intelligence model. This model generates an algorithm to propose optimal resource management methods for each household or business, using deep learning and decision tree algorithms. Specifically, the model is implemented and trained using Keras and TensorFlow. The input is the cleaned data, and the output is a trained artificial intelligence model.

[1747] Step 4:

[1748] The server acquires the user's emotional data and recognizes their emotional state. Emotional data is collected through a camera and microphone and analyzed using software such as EmotionRecognizer. The input is the user's facial expression and voice data, and the output is the recognized emotional state.

[1749] Step 5:

[1750] The server uses a trained artificial intelligence model to analyze real-time energy and water usage data and sentiment data. This analysis detects specific usage patterns and anomalies and generates specific action plans based on them. The input is the latest usage data and sentiment data, and the output is the generated action plan.

[1751] Step 6:

[1752] The server delivers the generated action plan to the user. This delivery is done through the device, and the user receives the action plan by push notification or email. The input is the generated action plan, and the output is the notification delivered to the user device.

[1753] Step 7:

[1754] The user takes specific actions based on the received action plan, such as changing the time the washing machine is used or checking the location where abnormal usage has been detected. The input is the received action plan, and the output is the specific action taken by the user.

[1755] Step 8:

[1756] Users provide feedback to the server about the results of their runs, which is used to retrain the model, continually improving the accuracy and effectiveness of the system. The input is user feedback information, and the output is an updated artificial intelligence model.

[1757] 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.

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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).

[1764] 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.

[1765] 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."

[1766] 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.

[1767] 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).

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] The following is further disclosed regarding the above embodiment.

[1779] (Claim 1)

[1780] A means of obtaining real-time energy and water usage data from sensors installed in homes and businesses;

[1781] A means of cleaning the acquired data, removing noise, and converting it into a form suitable for learning;

[1782] A means for training a model using the cleaned data to generate an algorithm for proposing optimal resource management methods for each household or business; and

[1783] A means to generate specific action plans based on the analysis results and deliver them to users;

[1784] A means to collect user feedback and retrain the model;

[1785] A system including:

[1786] (Claim 2)

[1787] The system of claim 1 , wherein data collection from the sensors is performed through an API.

[1788] (Claim 3)

[1789] 10. The system of claim 1, wherein the system analyzes energy consumption patterns and abnormal water usage in real time.

[1790] "Example 1"

[1791] (Claim 1)

[1792] A means of obtaining real-time energy and water usage data from multiple sensors installed in each home or business;

[1793] A means of cleaning the acquired data, removing noise and outliers, and converting it into a consistent format;

[1794] A means to train AI models using the cleaned data to generate algorithms that suggest optimal resource management methods for each household or business; and

[1795] A means of analyzing real-time data using a trained AI model to detect energy and water usage patterns;

[1796] A means of generating a specific action plan based on the analysis results and delivering it to the user's device;

[1797] A means to collect user feedback and retrain the AI ​​model;

[1798] A system including:

[1799] (Claim 2)

[1800] The system of claim 1 , wherein data collection from the sensors is performed through an API.

[1801] (Claim 3)

[1802] 10. The system of claim 1, wherein peak times of energy consumption and abnormal water usage are analyzed in real time.

[1803] "Application Example 1"

[1804] (Claim 1)

[1805] A means of obtaining real-time energy and water usage data from sensors installed at each facility;

[1806] A means of cleaning the acquired data, removing noise, and converting it into a form suitable for learning;

[1807] A means for training a model using the cleaned data to generate an algorithm for proposing optimal resource management methods for each facility; and

[1808] A means to generate specific action plans based on the analysis results and deliver them to users;

[1809] A means to collect user feedback and retrain the model;

[1810] A means of collecting data from sensors attached to machines and equipment in the factory to detect peak times and abnormalities;

[1811] a means for generating an action plan to reduce peak hour energy use;

[1812] a means for notifying management when abnormal water usage is detected;

[1813] A system including:

[1814] (Claim 2)

[1815] The system of claim 1 , wherein data collection from the sensors is performed through an API.

[1816] (Claim 3)

[1817] 10. The system of claim 1, wherein the system analyzes energy consumption patterns and abnormal water usage in real time.

[1818] "Example 2: Combining Emotion Engines"

[1819] (Claim 1)

[1820] A means of obtaining real-time energy and water usage data from sensors installed in homes and businesses;

[1821] A means of cleaning the acquired data, completing missing data, and correcting outliers;

[1822] A means to train learning algorithms using the cleaned data to create generative AI models that suggest optimal resource management strategies for each household or business.

[1823] A means for acquiring user emotional data using an emotion engine, generating specific action plans based on the analysis results, and delivering them to users;

[1824] A means of sending notifications to users via their devices and adjusting the content and timing of notifications based on the user's emotional state;

[1825] A means to collect user feedback and use it to retrain the generative AI model; and

[1826] A system including:

[1827] (Claim 2)

[1828] The system of claim 1 , wherein data collection from the sensors is performed through an API.

[1829] (Claim 3)

[1830] The system of claim 1 analyzes energy consumption patterns and abnormal water usage in real time and provides optimal notifications to users based on emotional data.

[1831] "Application example 2 when combining emotion engines"

[1832] (Claim 1)

[1833] A means of obtaining real-time energy and water usage data from sensors installed in homes and businesses;

[1834] A means of processing the acquired data, removing noise and converting it into a form suitable for learning;

[1835] A means for training an artificial intelligence model using the processed data to generate an algorithm for suggesting optimal resource management methods for each household or business;

[1836] a means for obtaining emotional data of the user and adjusting an action plan based on the emotional state;

[1837] A means of generating specific proposals based on the analysis results and delivering them to users;

[1838] A means to collect user feedback and retrain the model;

[1839] A system including:

[1840] (Claim 2)

[1841] The system of claim 1, wherein data collection from the sensors is performed through an API.

[1842] (Claim 3)

[1843] 10. The system of claim 1, further comprising the ability to analyze energy consumption patterns and unusual water usage in real time and adjust the timing of alerts based on the user's emotional state. [Explanation of symbols]

[1844] 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 obtaining real-time energy and water usage data from sensors installed in homes and businesses; A means of cleaning the acquired data, removing noise, and converting it into a form suitable for learning; A means for training a model using the cleaned data to generate an algorithm for proposing optimal resource management methods for each household or business; and A means to generate specific action plans based on the analysis results and deliver them to users; A means to collect user feedback and retrain the model; A system including:

2. The system of claim 1 , wherein data collection from the sensors is performed through an API.

3. 10. The system of claim 1, wherein the system analyzes energy consumption patterns and abnormal water usage in real time.

Images