system

Abstract

Provide a system. 【Solution means】 Means for obtaining energy consumption information in real time, Means for cleaning and normalizing the obtained information, Means for predicting energy usage patterns using a recurrent neural network or long short-term memory, Means for generating an intelligent contract based on the prediction of the consumption pattern, Means for notifying the user of the contract content and obtaining approval, Means for automatically executing an energy usage shift based on the intelligent contract, Means for comparing the prediction result with the actual usage information and improving the model, Means for monitoring the energy usage of the entire city and presenting an individual usage adjustment plan, Means for executing the presented plan in cooperation with the user's information terminal, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Due to the sudden increase in energy consumption in a specific time period, extra power generation is required during peak hours, which causes problems such as an increase in energy costs and a decrease in supply efficiency. Therefore, it is required to effectively manage unpredictable consumption spikes and shift peak-hour energy consumption.

Means for Solving the Problems

[0005] This invention provides a means for collecting real-time energy consumption data and predicting consumption spikes using deep learning techniques such as recurrent neural networks and long- and short-term memory. It also provides a means for generating smart contracts based on these predictions, notifying the user, obtaining their approval, and automatically executing energy consumption shifts. Furthermore, by analyzing actual consumption data and prediction results and improving the prediction model, the system achieves optimization of energy use and cost reduction.

[0006] "Energy consumption data" refers to information about the amount and timing of energy used in a particular system or environment.

[0007] "Real-time" refers to processing or acquiring information at a speed that is as close as possible to real-world time.

[0008] "Cleaning" is the process of improving data quality by removing noise and inaccurate elements from the data.

[0009] "Normalization" is a technique that unifies the range of data, making it possible to compare different datasets.

[0010] A "recurrent neural network (RNN)" is a type of artificial intelligence model specialized in the analysis of time-series data, characterized by its ability to predict the future using past data.

[0011] Long-Short-Term Memory (LSTM) is a type of RNN (Resonant Neural Network) and a deep learning technique that is capable of learning long-term dependencies.

[0012] A "consumption spike" refers to a phenomenon in which energy consumption increases sharply over a short period of time.

[0013] A "smart contract" is a digital contract that is automatically executed when certain conditions are met.

[0014] The "prediction model" refers to a mathematical or statistical model constructed to infer future situations using past data.

[0015] The "shift of energy consumption" is a process of reducing the peak load and enhancing efficiency by changing the energy usage time and pattern.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of the data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of the data processing device and the smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of the data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of the data processing device and the smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of the data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of the data processing device and the headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of the data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of the data processing device and the robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

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

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The energy consumption spike management system according to the present invention aims to improve the efficiency of energy consumption. This system collects energy consumption data in real time and provides technology to predict future consumption spikes by analyzing that data.

[0038] Specifically, the server first collects energy consumption data in real time from smart meters and IoT sensors. This data includes the amount of energy consumed at each facility in homes and businesses, as well as the consumption patterns over time. Next, the server cleans the collected data, normalizing it through a process that removes noise and outliers.

[0039] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze patterns in consumption data and predict future consumption spikes. Based on this prediction, the server automatically generates smart contracts to optimize energy use.

[0040] The generated smart contract is notified to the user. The user then approves the contract, and a plan to avoid consumption spikes is implemented. For example, this could involve scheduling changes such as shifting electric vehicle charging or air conditioning operation to off-peak hours.

[0041] This process allows the terminal to automatically adjust the operating time of electrical appliances after user approval, shifting energy consumption. This reduces peak energy consumption. The server also compares actual consumption data with predictive models and implements continuous improvements to enhance the system's accuracy. This invention enables reduced energy costs and sustainable energy use.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects energy consumption data in real time from smart meters and IoT sensors. This includes time-series consumption data for each device and facility.

[0045] Step 2:

[0046] The server cleans the collected data to remove noise and outliers, improving data quality. Furthermore, it normalizes the data and equalizes its scale, making analysis easier.

[0047] Step 3:

[0048] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze preprocessed data and predict future consumption spikes. This prediction identifies the time periods when energy consumption peaks are likely to occur.

[0049] Step 4:

[0050] The server automatically generates smart contracts to mitigate energy consumption during peak hours, based on predicted consumption spikes. These contracts propose shifting energy-intensive tasks to off-peak hours.

[0051] Step 5:

[0052] The server notifies the user of the generated smart contract and requests their approval of the contract terms. The notification is sent via a smartphone app or email.

[0053] Step 6:

[0054] Once the user approves the smart contract, the device automatically implements energy consumption shifts based on the contract. This adjusts the device's operation and optimizes energy use.

[0055] Step 7:

[0056] The server compares the consumption data being processed with the prediction results to evaluate the model's prediction accuracy. It modifies the model as needed and continuously improves the overall system.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In modern society, efficiently managing peak energy consumption and achieving sustainable energy use is crucial. However, there is a lack of means to accurately predict fluctuations in energy consumption and effectively optimize energy use. As a result, challenges such as wasted energy costs and instability in energy supply during peak times exist.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for collecting energy consumption information in real time using an information gathering device, means for preprocessing and normalizing the collected information, and means for predicting sudden increases in energy consumption using a learning algorithm. This makes it possible to accurately predict peak energy consumption and efficiently optimize energy use.

[0062] An "information gathering device" is a device used to collect energy consumption information in real time, and has the ability to aggregate and transmit data via a network.

[0063] "Preprocessing" is the process of removing outliers and noise from raw data collected prior to data analysis, thereby ensuring the accuracy and consistency of the data.

[0064] "Normalization" refers to the process of arranging collected data to fit within a certain range, thereby making it suitable for analysis.

[0065] A "learning algorithm" is a computational method used to learn patterns and rules from large amounts of data and predict future events.

[0066] A "sudden surge in energy consumption" refers to a phenomenon in which energy usage increases rapidly over time, potentially putting a strain on the supply system.

[0067] A "predictive algorithm" is a method for analyzing past data patterns to predict events that are likely to occur in the future.

[0068] "Contract information" refers to a set of instructions automatically generated to optimize energy consumption, and it represents information that shows a feasible energy use plan.

[0069] A "non-demand period" refers to a time of day when normal energy use is reduced, meaning that the load can be alleviated by reducing energy consumption.

[0070] "Energy-intensive operation" refers to the operation of equipment or processes that consume large amounts of electricity.

[0071] The energy consumption management system according to the present invention aims to improve energy efficiency and has the function of collecting and analyzing data in real time. This enables the prediction of peak energy consumption and the optimization of energy use to suit the user's lifestyle.

[0072] The server acquires energy consumption information from homes and businesses in real time via information collection devices. Specifically, it manages the streaming of data obtained from smart meters and IoT sensors using Apache® Kafka and stores it in MongoDB.

[0073] The acquired data is preprocessed using the Python Pandas library. This removes noise and outliers and normalizes the data. At this stage, missing values ​​are imputed using the NumPy library, preparing a dataset that can be input into the predictive model.

[0074] Next, the server uses machine learning libraries such as TENSORFLOW® and Keras to analyze energy consumption patterns using recurrent neural networks (RNNs) and long-short-term memory (LSTMs). Based on this analysis, it predicts future surges in energy consumption and automatically generates contract information based on the results.

[0075] Once contract information is generated, users are notified via smartphone applications or other means. Users can then review and approve this proposal to implement an optimized energy usage plan. This allows, for example, scheduling the use of air conditioners or electric vehicle charging during off-peak hours.

[0076] Ultimately, the device automatically adjusts and manages the operating time of electrical appliances based on user approval. The server also monitors actual consumption data, compares it with predictive algorithms, and continuously improves the model.

[0077] A concrete example would be a suggestion to shift the use of air conditioners in the home to off-peak hours. An example prompt for the generating AI model would be, "Predict peaks for the next three months and create suggestions to optimize energy use."

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Inputs include consumption data from smart meters and IoT sensors. The server streams this data using Apache Kafka and stores it in MongoDB. The output is raw data stored in a database suitable for analysis. Its specific operation includes accepting data transfers and continuously accumulating data.

[0081] Step 2:

[0082] The server preprocesses the collected raw data using the Python Pandas library. The input is raw data stored in MongoDB. Preprocessing involves executing algorithms to detect and remove outliers and noise. Using the NumPy library, missing values ​​are imputed and the data is normalized, resulting in clean data that can be input to machine learning models. The specific operation involves data cleansing and transformation processes within the pipeline.

[0083] Step 3:

[0084] The server runs an RNN or LSTM model using TensorFlow or Keras libraries with pre-processed clean data to analyze energy consumption patterns. The input is the clean data generated in step 2, and the output is a prediction of future consumption spikes. The server runs a program that trains the model using historical consumption data and makes predictions. Specific operations include training the model and performing predictions.

[0085] Step 4:

[0086] The server automatically generates contract information to optimize energy use based on the prediction results. The input is the consumption spike prediction obtained in step 3. The output is optimized energy use contract information, which includes plans such as load balancing. The server generates and stores the contract information using blockchain technology. Specifically, the contract generation process is performed based on the prediction results.

[0087] Step 5:

[0088] The user reviews the contract information notified by the server and chooses to approve or reject it. The input is the contract information notified via a smart device or application. The output is the user's selection result (approval or rejection). Specific actions include receiving the notification and performing a selection operation within the application.

[0089] Step 6:

[0090] The terminal adjusts the operating schedule based on user approval. The input is the user-approved contract information. The terminal shifts the operating times of electrical appliances and equipment, resulting in optimized energy use as output. Specific operations include updating and adjusting the operating schedule.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In modern cities, peak energy demand places a heavy burden on the supply, potentially compromising the stability of the power grid. This also leads to increased energy costs and makes sustainable energy use difficult. To address this situation, both optimizing individual consumers' energy consumption and coordinating energy use across the entire city are necessary.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for acquiring energy consumption information in real time, means for cleaning and normalizing the acquired information, means for predicting energy usage patterns using a recurrent neural network or long- and short-term memory, means for generating intelligent contracts based on the predicted consumption patterns, means for monitoring energy usage across the entire city and presenting individual usage adjustment plans, and means for coordinating and executing the presented plans with the user's information terminal. This makes it possible to optimize energy consumption across the entire city, level out peak demand to reduce energy costs, and enable sustainable energy use.

[0096] "Energy consumption information" refers to data showing the usage of electricity consumed in homes, businesses, and cities, and is acquired in real time.

[0097] "Cleaning" is the process of removing noise and outliers from acquired energy consumption information to improve data accuracy.

[0098] "Normalization" is the process of transforming cleaned data to conform to a standard value and arranging it into a consistent data format.

[0099] A "recurrent neural network" is a machine learning model specifically designed for analyzing time-series data, and it is an algorithm that uses past data to predict future energy consumption patterns.

[0100] "Long-short-term memory" refers to a machine learning model that has the ability to retain temporal dependencies over long periods, making it a suitable technique for predicting energy usage patterns.

[0101] An "intellectual contract" is a contract that is automatically generated based on energy consumption forecasts, and the energy usage plan is finalized when the user approves it.

[0102] An "energy use adjustment plan" is a set of specific action guidelines presented to improve the efficiency of energy consumption in cities and households and to level out peak consumption.

[0103] An "information terminal" is a device that allows users to receive notifications and suggestions regarding energy consumption, and to check and implement plans; smartphones are an example of such devices.

[0104] To realize this invention, a server, a terminal, and a user must collaborate. The server acquires energy consumption information, cleans and normalizes the data, and then performs analysis using a recurrent neural network (RNN) or long-short-term memory (LSTM). This allows for the prediction of energy consumption patterns and the identification of future consumption spikes. Based on this information, the server automatically generates intelligent contracts and proposes individual energy use adjustment plans. These proposals are communicated to the user's information terminal via an API built using Flask or Django as a framework. The user approves the proposed plan using the terminal, and the terminal executes the plan through a connected smart device.

[0105] The hardware used includes smart meters and standard IoT sensors for data collection, and smartphones and tablets for user notifications and operation. On the software side, the Python Pandas library is used for data processing, and TensorFlow and Keras are used for model building and prediction.

[0106] For example, if the forecast suggests a nighttime energy spike, the server recommends that the user maximize their home electricity usage during the day and take advantage of off-peak nighttime rates. The user then approves this through their device, and the device adjusts electricity usage accordingly. An example of a prompt message to the generative AI model in realizing this invention would be: "Please consider a user-specific optimization strategy to suggest a shift in energy consumption to off-peak hours in order to reduce the load on power plants."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server acquires energy consumption information from smart meters and IoT sensors. The input is real-time recorded power usage data, and the output is aggregated information from this data. This data is needed for cleaning and normalization in the next step.

[0110] Step 2:

[0111] The server cleans and normalizes the acquired energy consumption information. The input is the raw data obtained in step 1, and the output is data that has had noise and outliers removed and is formatted into a standard format. In this process, data processing and calculations are performed using the Python Pandas library.

[0112] Step 3:

[0113] The server predicts energy usage patterns using a recurrent neural network (RNN) or long-short-term memory (LSTM) based on cleaned data. The input is normalized consumption data, and the output is a prediction of future energy consumption spikes. Predictive models are built using TensorFlow or Keras, and calculations are performed based on the data.

[0114] Step 4:

[0115] The server generates intelligent contracts based on the prediction results. The input is the prediction results from step 3, and the output is a user-specific energy usage adjustment plan. At this stage, prompts are input to the generating AI model to design individual optimization strategies.

[0116] Step 5:

[0117] The server notifies the user's information terminal of the content of the generated intellectual contract. The input is the content of the intellectual contract, and the output is the notification displayed on the user's terminal. The information is transmitted via API and stored on the terminal.

[0118] Step 6:

[0119] The user reviews the received energy usage adjustment plan on their terminal and chooses to approve or reject it. The input is the notified contract information, and the output is the user's selection.

[0120] Step 7:

[0121] The terminal controls connected smart devices and executes energy usage adjustment plans, provided the user approves. The input is the energy usage plan, and the output is changes to device settings and schedules. Specific actions include adjusting the on / off times of air conditioners and lighting.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] The energy consumption spike management system according to the present invention provides, in addition to real-time energy management, a function that recognizes the user's emotions and adjusts the system's operation accordingly. This function enables more flexible and user-friendly energy management.

[0124] First, the server collects energy consumption data through smart meters and IoT sensors. This data includes time-series energy usage information and is processed sequentially. During this process, the server cleans and normalizes the data, preparing it for analysis.

[0125] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) model to identify predicted energy consumption spikes. Based on this information, it generates smart contracts to optimize consumption.

[0126] In this invention, the terminal further recognizes the user's emotional state using the user's emotion engine. This emotional data is an important factor in considering how the user accepts energy management. For example, if the user is feeling stressed, the notification method and content are flexibly changed to avoid causing psychological burden to the user.

[0127] After the user receives a notification, they approve the smart contract. At this point, the server suggests options based on sentiment data to present a plan that is more acceptable to the user.

[0128] Ultimately, the device automatically adjusts its energy consumption schedule based on approved smart contracts. This schedule improves overall energy efficiency by shifting energy-intensive tasks to off-peak hours.

[0129] Furthermore, the server continuously analyzes the results of the execution and the feedback from the emotion engine, accumulating data to improve the system. This process enables sustainable energy management while enhancing the user experience.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server collects energy consumption data in real time through smart meters and IoT sensors. This includes consumption information obtained from devices in homes and businesses, and is stored as time-series data.

[0133] Step 2:

[0134] The server cleans the collected energy consumption data. It removes outliers and missing values ​​and normalizes the data to maintain consistency. This lays the foundation for accurate future predictions.

[0135] Step 3:

[0136] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to predict consumption spikes based on the cleaned data. This prediction is performed to analyze consumption patterns during specific time periods and to anticipate peak loads.

[0137] Step 4:

[0138] The device uses an emotion engine to recognize the user's emotional state. Emotion recognition may involve voice or facial expression analysis, quantifying the user's current psychological state. This data is then used to flexibly configure the system's next actions.

[0139] Step 5:

[0140] The server combines prediction results and sentiment data to generate smart contracts to optimize consumption. Based on sentiment data, it adjusts the content and tone of notifications to create offers that are more likely to be accepted by users.

[0141] Step 6:

[0142] The server notifies the user of the generated smart contract and requests their approval. The notification is delivered in a method preferred by the user (e.g., email or push notification) and is designed to be easy for the user to use.

[0143] Step 7:

[0144] Users receive notifications and make decisions to approve or modify the presented smart contracts. This process allows for flexible dialogue that adapts to their emotional state.

[0145] Step 8:

[0146] After user approval, the device automatically shifts energy consumption based on the smart contract. This includes changing the operating schedule of electrical appliances and moving tasks to off-peak hours.

[0147] Step 9:

[0148] The server analyzes the consumption data and sentiment feedback, continuously optimizing predictive models and the user interface. This improves overall system performance and user experience.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] The sustainable use and efficient management of energy consumption are critical challenges in modern society. Conventional technologies suffer from waste due to peak energy consumption and inconvenience caused by fixed contract forms that do not consider the feelings of users. As a result, energy efficiency cannot be fully utilized. Furthermore, there is a challenge in that flexible responses that take into account the circumstances of individual users are difficult to implement, and the user experience is not sufficiently improved.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes a device for collecting energy usage data, a device for processing the collected data, and a device for predicting fluctuations in energy consumption using a predictive analysis model. This enables real-time prediction of energy consumption spikes and flexible energy management tailored to the emotional state of individual users.

[0154] "Energy usage data" refers to information that records the amount and duration of consumption of electricity, gas, and other energy sources in a household or facility.

[0155] A "data collection device" refers to equipment or a system that automatically collects energy usage data using sensors, meters, etc.

[0156] A "processing device" is a system or device used to clean, normalize, and prepare collected data for analysis.

[0157] A "predictive analytics model" is an algorithm or framework for predicting future energy consumption patterns based on data.

[0158] A "device for predicting fluctuations" is a computer system that uses predictive analysis models to forecast sudden increases or decreases in energy use.

[0159] A "contract generation device" is a system that creates optimized energy consumption contracts in response to predicted fluctuations in energy use.

[0160] A "device for obtaining consent" is a method or system for notifying an individual of the terms of a contract and collecting their consent electronically or physically.

[0161] A "planning device" is a system that automatically executes an energy usage plan based on the generated energy consumption contract.

[0162] A "device that analyzes emotional states and adjusts notification methods regarding energy use" is a device that analyzes the user's emotional state and adjusts the content and timing of notifications regarding energy consumption based on the results.

[0163] This invention is a system that enhances energy consumption management and realizes flexible energy contracts that take user feelings into consideration. This system promotes efficient energy use through the cooperation of servers, terminals, and users.

[0164] The server collects energy usage data through sensors and smart meters. This allows for real-time monitoring of energy consumption in homes and facilities. The collected data undergoes cleansing and normalization processes to be prepared as input data for predictive analytics models. Specifically, models such as recurrent neural networks (RNNs) and long-short-term memory (LSTMs) can be used.

[0165] The device is equipped with an emotion engine to analyze the user's emotional state, detecting their voice and facial expressions to identify their emotional state. This information is used to adjust notifications and contract proposals regarding energy usage. For example, if the user is feeling stressed, the device will send a flexible notification such as, "Would you like to delay the washing machine run until 2 AM tonight?"

[0166] Users receive an energy usage plan sent from the server. Based on this, they can approve or modify the application of the proposed contract. Depending on the user's selection, the server adjusts the energy consumption schedule to promote optimal energy use.

[0167] Throughout the process, the server continuously evaluates the performance of the predictive model and improves its accuracy by comparing it with actual energy consumption data. This process enables sustainable and efficient energy management.

[0168] Examples of prompts include "Suggest an optimal energy consumption plan based on tomorrow's weather forecast" and "Consider a notification method that takes into account when the user is feeling stressed." These prompts utilize generative AI models as a means to support optimal energy management for the user.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server acquires energy usage data in real time from sensors and smart meters as input. This raw data includes power consumption, time stamps, and consumption information by device. The server cleanses and normalizes this data, removing inappropriate data points and converting it into a format suitable for analysis. The output is a clear, normalized dataset that can be used by analytical models.

[0172] Step 2:

[0173] The server uses cleansed data as input to run a recurrent neural network (RNN) or long-short-term memory (LSTM) model. This model predicts the temporal fluctuations in energy consumption and identifies energy consumption spikes in specific time periods as outputs. Specifically, it learns past consumption patterns and predicts future consumption trends.

[0174] Step 3:

[0175] The server generates a smart contract to optimize energy consumption based on the model's output. This contract plans to shift energy-intensive work to off-peak hours. The input is predicted consumption spike information, and the output is the contract details, including the specific shift plan.

[0176] Step 4:

[0177] The device receives smart contract notifications sent from the server and analyzes the user's state through the user's emotion engine. Inputs include the user's facial expressions and tone of voice, and output is expressed as the user's emotional state. Based on this information, the device adjusts its suggestions and provides flexible notifications to the user.

[0178] Step 5:

[0179] The user reviews the notification received via their device and approves or modifies the presented smart contract as input. During this process, the user is presented with options that take their emotional state into consideration, and they select the appropriate option. The output is the approved or modified contract.

[0180] Step 6:

[0181] The device automatically adjusts the energy usage schedule based on a smart contract approved by the user. The input is the final approved contract, and the output is the actual device operating schedule. The device shifts operation to off-peak hours, improving overall energy efficiency.

[0182] Step 7:

[0183] The server evaluates the accuracy of the predicted model using actual energy usage data as input. As a feedback loop, new consumption and sentiment data are used to retrain the model and improve prediction accuracy. The output is the improved predictive model.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0186] In modern energy management systems, predicting energy consumption spikes and promoting efficient energy use is crucial. However, these systems typically only perform automated processing based on data and lack the flexibility to respond to individual user emotions. As a result, users may sometimes experience high psychological burden and dissatisfaction with the system. Therefore, it is necessary to incorporate features that consider user emotions into energy management systems.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] This invention includes a server that includes a method for collecting energy consumption data in real time, a method for cleaning and normalizing the collected data, a method for predicting energy consumption peaks using a recurrent neural network or long- and short-term memory, a method for creating smart contracts based on the predicted consumption peaks, a method for analyzing the user's emotional state and flexibly notifying the user of the contract details, a method for automatically adjusting energy consumption based on the smart contracts, and a method for improving the prediction model by comparing the prediction results with actual consumption data. This enables the energy management system to provide an optimal energy consumption plan tailored to each user's emotional state.

[0189] "Energy consumption data" refers to information that records energy usage in a specific location or system over time.

[0190] "Real-time data collection methods" refer to the process of instantly acquiring data and providing it to the system without any time delay.

[0191] "Cleaning" is the process of removing noise and errors from collected data and preparing it for analysis.

[0192] "Normalization" is a technique that adjusts data based on a certain range or standard to improve the accuracy and consistency of analysis.

[0193] A "recurrent neural network" is an artificial intelligence model that, unlike conventional neural networks, can handle time-series data.

[0194] "Long-Short-Term Memory" is a type of recurrent neural network that learns long-term and short-term dependencies from time-series data and uses them for prediction.

[0195] "Energy consumption peak" refers to a sharp increase in energy usage during a specific time period.

[0196] A "smart contract" is a digital form of contract that is automatically executed based on specific conditions.

[0197] "User emotional state" refers to information that indicates the user's psychological and emotional condition.

[0198] A "flexible notification method" is an approach that appropriately adjusts the way information is presented according to the recipient's state and circumstances.

[0199] "Automated execution method" refers to a function in which a system executes a process without human intervention based on pre-set conditions.

[0200] "Methods for improving predictive models" refer to techniques for improving the accuracy of future predictions by comparing collected data with actual results.

[0201] To implement this invention, the server first collects energy consumption data from smart meters and IoT sensors. This data is acquired in real time and automatically cleaned and normalized on the server. The server then uses a recurrent neural network or long- and short-term memory to predict peak energy consumption.

[0202] Next, the server analyzes the emotional state provided by the user's device. The device is equipped with sensors to detect the user's emotions in real time and transmit this information to the server. This ensures that the user's emotions are taken into consideration when determining energy consumption schedules. Specifically, if the emotional state differs from the user's normal state, the notification method is adjusted, and an emotionally sensitive smart contract is offered.

[0203] Users can review and approve the contract details displayed on their device. Based on the approved smart contract, energy consumption is automatically adjusted and shifted to predetermined off-peak hours. This adjustment is centrally monitored on the server side, and the results are recorded. This allows the server to continuously improve its predictive model.

[0204] For example, a system installed in a home might adjust the air conditioning and lighting appropriately to coincide with the time when the user returns home in the evening. It might even suggest particularly pleasant lighting for that evening to help the user relax after returning home. This creates a schedule that enhances user comfort while maintaining energy efficiency.

[0205] Example prompt for a generating AI model: "Generate suggestions for various scenarios regarding the importance of considering user emotions in energy consumption management."

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The server collects energy consumption data in real time from smart meters and IoT sensors. The input is raw data from the sensors, and the output is time-series data converted into a digital format. This data is used as foundational information necessary for subsequent data processing.

[0209] Step 2:

[0210] The server cleans and normalizes the collected energy consumption data. The input is the time-series data obtained in step 1, and the output is a denoised and standardized dataset. Removing unwanted elements from the data enables more accurate predictions.

[0211] Step 3:

[0212] The server predicts energy consumption peaks using a recurrent neural network or long- and short-term memory based on cleaned data. The input is a normalized dataset, and the output is time-series forecast information showing future consumption peaks. This forecast information contributes to the development of energy-efficient schedules.

[0213] Step 4:

[0214] The device analyzes the user's emotional state and sends that information to the server. The input is raw emotional data obtained from the camera and microphone, and the output is the user's emotional state analyzed by the emotion engine. This information is used as a reference when adjusting notification content and timing.

[0215] Step 5:

[0216] The server creates a smart contract based on predicted energy consumption peaks and the user's emotional state. The inputs are the predicted information from step 3 and the emotional data from step 4, and the output is the optimal energy consumption plan to be presented to the user. This plan is designed to minimize psychological burden.

[0217] Step 6:

[0218] The user reviews and approves the contract details via their device. The input is the smart contract received from the server, and the output is the user's approval or rejection feedback. In this step, the user's preferences are reflected in the system.

[0219] Step 7:

[0220] The server automatically adjusts energy consumption based on approved smart contracts and records the results. The input is user approval information, and the output is a record of the adjusted energy consumption status and its results. This accumulates data that can be used to improve the accuracy of future predictions.

[0221] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0227] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0228] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0229] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0230] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0231] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0232] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0233] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0234] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0235] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0236] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0237] The energy consumption spike management system according to the present invention aims to improve the efficiency of energy consumption. This system collects energy consumption data in real time and provides technology to predict future consumption spikes by analyzing that data.

[0238] Specifically, the server first collects energy consumption data in real time from smart meters and IoT sensors. This data includes the amount of energy consumed at each facility in homes and businesses, as well as the consumption patterns over time. Next, the server cleans the collected data, normalizing it through a process that removes noise and outliers.

[0239] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze patterns in consumption data and predict future consumption spikes. Based on this prediction, the server automatically generates smart contracts to optimize energy use.

[0240] The generated smart contract is notified to the user. The user then approves the contract, and a plan to avoid consumption spikes is implemented. For example, this could involve scheduling changes such as shifting electric vehicle charging or air conditioning operation to off-peak hours.

[0241] This process allows the terminal to automatically adjust the operating time of electrical appliances after user approval, shifting energy consumption. This reduces peak energy consumption. The server also compares actual consumption data with predictive models and implements continuous improvements to enhance the system's accuracy. This invention enables reduced energy costs and sustainable energy use.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server collects energy consumption data in real time from smart meters and IoT sensors. This includes time-series consumption data for each device and facility.

[0245] Step 2:

[0246] The server cleans the collected data to remove noise and outliers, improving data quality. Furthermore, it normalizes the data and equalizes its scale, making analysis easier.

[0247] Step 3:

[0248] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze preprocessed data and predict future consumption spikes. This prediction identifies the time periods when energy consumption peaks are likely to occur.

[0249] Step 4:

[0250] The server automatically generates smart contracts to mitigate energy consumption during peak hours, based on predicted consumption spikes. These contracts propose shifting energy-intensive tasks to off-peak hours.

[0251] Step 5:

[0252] The server notifies the user of the generated smart contract and requests their approval of the contract terms. The notification is sent via a smartphone app or email.

[0253] Step 6:

[0254] Once the user approves the smart contract, the device automatically implements energy consumption shifts based on the contract. This adjusts the device's operation and optimizes energy use.

[0255] Step 7:

[0256] The server compares the consumption data being processed with the prediction results to evaluate the model's prediction accuracy. It modifies the model as needed and continuously improves the overall system.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] In modern society, efficiently managing peak energy consumption and achieving sustainable energy use is crucial. However, there is a lack of means to accurately predict fluctuations in energy consumption and effectively optimize energy use. As a result, challenges such as wasted energy costs and instability in energy supply during peak times exist.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes means for collecting energy consumption information in real time using an information gathering device, means for preprocessing and normalizing the collected information, and means for predicting sudden increases in energy consumption using a learning algorithm. This makes it possible to accurately predict peak energy consumption and efficiently optimize energy use.

[0262] An "information gathering device" is a device used to collect energy consumption information in real time, and has the ability to aggregate and transmit data via a network.

[0263] "Preprocessing" is the process of removing outliers and noise from raw data collected prior to data analysis, thereby ensuring the accuracy and consistency of the data.

[0264] "Normalization" refers to the process of arranging collected data to fit within a certain range, thereby making it suitable for analysis.

[0265] A "learning algorithm" is a computational method used to learn patterns and rules from large amounts of data and predict future events.

[0266] A "sudden surge in energy consumption" refers to a phenomenon in which energy usage increases rapidly over time, potentially putting a strain on the supply system.

[0267] A "predictive algorithm" is a method for analyzing past data patterns to predict events that are likely to occur in the future.

[0268] "Contract information" refers to a set of instructions automatically generated to optimize energy consumption, and it represents information that shows a feasible energy use plan.

[0269] A "non-demand period" refers to a time of day when normal energy use is reduced, meaning that the load can be alleviated by reducing energy consumption.

[0270] "Energy-intensive operation" refers to the operation of equipment or processes that consume large amounts of electricity.

[0271] The energy consumption management system according to the present invention aims to improve energy efficiency and has the function of collecting and analyzing data in real time. This enables the prediction of peak energy consumption and the optimization of energy use to suit the user's lifestyle.

[0272] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Specifically, it manages data streaming using Apache Kafka from smart meters and IoT sensors and stores it in MongoDB.

[0273] The acquired data is preprocessed using the Python Pandas library. This removes noise and outliers and normalizes the data. At this stage, missing values ​​are imputed using the NumPy library, preparing a dataset that can be input into the predictive model.

[0274] Next, the server uses machine learning libraries such as TensorFlow and Keras to analyze energy consumption patterns using recurrent neural networks (RNNs) and long-short-term memory (LSTMs). Based on this analysis, it predicts future surges in energy consumption and automatically generates contract information based on the results.

[0275] Once contract information is generated, users are notified via smartphone applications or other means. Users can then review and approve this proposal to implement an optimized energy usage plan. This allows, for example, scheduling the use of air conditioners or electric vehicle charging during off-peak hours.

[0276] Ultimately, the device automatically adjusts and manages the operating time of electrical appliances based on user approval. The server also monitors actual consumption data, compares it with predictive algorithms, and continuously improves the model.

[0277] A concrete example would be a suggestion to shift the use of air conditioners in the home to off-peak hours. An example prompt for the generating AI model would be, "Predict peaks for the next three months and create suggestions to optimize energy use."

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Inputs include consumption data from smart meters and IoT sensors. The server streams this data using Apache Kafka and stores it in MongoDB. The output is raw data stored in a database suitable for analysis. Its specific operation includes accepting data transfers and continuously accumulating data.

[0281] Step 2:

[0282] The server preprocesses the collected raw data using the Pandas library in Python. The input is the raw data stored in MongoDB. In the preprocessing, algorithms for detecting and removing outliers and noise are executed. Using the NumPy library, missing value imputation of the data is performed, and normalization of the data is carried out, so that the output becomes clean data that can be input into the machine learning model. The specific operation is the data cleansing and transformation process within the pipeline.

[0283] Step 3:

[0284] The server executes an RNN or LSTM model using the TensorFlow or Keras library with the preprocessed clean data to analyze the pattern of energy consumption. The input is the clean data generated in Step 2, and the output is the prediction of future consumption spikes. The server runs a program that learns the model using past consumption data and makes predictions. The specific operations include training the model and making predictions.

[0285] Step 4:

[0286] Based on the prediction results, the server automatically generates contract information for optimizing energy usage. The input is the prediction of consumption spikes obtained in Step 3. The output is the optimized energy usage contract information, which includes plans such as load distribution. The server generates and stores the contract information using blockchain technology. As a specific operation, a contract generation process based on the prediction results is performed.

[0287] Step 5:

[0288] The user reviews the contract information notified by the server and chooses to approve or reject it. The input is the contract information notified via a smart device or application. The output is the user's selection result (approval or rejection). Specific actions include receiving the notification and performing a selection operation within the application.

[0289] Step 6:

[0290] The terminal adjusts the operating schedule based on user approval. The input is the user-approved contract information. The terminal shifts the operating times of electrical appliances and equipment, resulting in optimized energy use as output. Specific operations include updating and adjusting the operating schedule.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] In modern cities, peak energy demand places a heavy burden on the supply, potentially compromising the stability of the power grid. This also leads to increased energy costs and makes sustainable energy use difficult. To address this situation, both optimizing individual consumers' energy consumption and coordinating energy use across the entire city are necessary.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for acquiring energy consumption information in real time, means for cleaning and normalizing the acquired information, means for predicting energy usage patterns using a recurrent neural network or long- and short-term memory, means for generating intelligent contracts based on the predicted consumption patterns, means for monitoring energy usage across the entire city and presenting individual usage adjustment plans, and means for coordinating and executing the presented plans with the user's information terminal. This makes it possible to optimize energy consumption across the entire city, level out peak demand to reduce energy costs, and enable sustainable energy use.

[0296] "Energy consumption information" refers to data showing the usage of electricity consumed in homes, businesses, and cities, and is acquired in real time.

[0297] "Cleaning" is the process of removing noise and outliers from acquired energy consumption information to improve data accuracy.

[0298] "Normalization" is the process of transforming cleaned data to conform to a standard value and arranging it into a consistent data format.

[0299] A "recurrent neural network" is a machine learning model specifically designed for analyzing time-series data, and it is an algorithm that uses past data to predict future energy consumption patterns.

[0300] "Long-short-term memory" refers to a machine learning model that has the ability to retain temporal dependencies over long periods, making it a suitable technique for predicting energy usage patterns.

[0301] An "intellectual contract" is a contract that is automatically generated based on energy consumption forecasts, and the energy usage plan is finalized when the user approves it.

[0302] An "energy use adjustment plan" is a set of specific action guidelines presented to improve the efficiency of energy consumption in cities and households and to level out peak consumption.

[0303] An "information terminal" is a device that allows users to receive notifications and suggestions regarding energy consumption, and to check and implement plans; smartphones are an example of such devices.

[0304] To realize this invention, a server, a terminal, and a user must collaborate. The server acquires energy consumption information, cleans and normalizes the data, and then performs analysis using a recurrent neural network (RNN) or long-short-term memory (LSTM). This allows for the prediction of energy consumption patterns and the identification of future consumption spikes. Based on this information, the server automatically generates intelligent contracts and proposes individual energy use adjustment plans. These proposals are communicated to the user's information terminal via an API built using Flask or Django as a framework. The user approves the proposed plan using the terminal, and the terminal executes the plan through a connected smart device.

[0305] The hardware used includes smart meters and standard IoT sensors for data collection, and smartphones and tablets for user notifications and operation. On the software side, the Python Pandas library is used for data processing, and TensorFlow and Keras are used for model building and prediction.

[0306] For example, if the forecast suggests a nighttime energy spike, the server recommends that the user maximize their home electricity usage during the day and take advantage of off-peak nighttime rates. The user then approves this through their device, and the device adjusts electricity usage accordingly. An example of a prompt message to the generative AI model in realizing this invention would be: "Please consider a user-specific optimization strategy to suggest a shift in energy consumption to off-peak hours in order to reduce the load on power plants."

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The server acquires energy consumption information from smart meters and IoT sensors. The input is the power usage data recorded in real time, and the output is the aggregated information of this data. The data is necessary for cleaning and normalization in the next step.

[0310] Step 2:

[0311] The server cleans and normalizes the acquired energy consumption information. The input is the raw data obtained in Step 1, and the output is the data with noise and outliers removed and arranged in a standard format. In this process, data processing and operations are performed using the Pandas library in Python.

[0312] Step 3:

[0313] The server predicts the energy usage pattern using a Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM) based on the cleaned data. The input is the normalized consumption data, and the output is the predicted value of future energy consumption spikes. A prediction model is constructed using TensorFlow and Keras, and operations are performed based on the data.

[0314] Step 4:

[0315] The server generates a smart contract based on the prediction result. The input is the prediction result in Step 3, and the output is the energy usage adjustment plan for each user. At this stage, a prompt is input into the generative AI model to design an individual optimization strategy. <00​​​​ The server notifies the user's information terminal of the content of the generated intellectual contract. The input is the content of the intellectual contract, and the output is the notification displayed on the user's terminal. The information is transmitted via API and stored on the terminal.

[0318] Step 6:

[0319] The user reviews the received energy usage adjustment plan on their terminal and chooses to approve or reject it. The input is the notified contract information, and the output is the user's selection.

[0320] Step 7:

[0321] The terminal controls connected smart devices and executes energy usage adjustment plans, provided the user approves. The input is the energy usage plan, and the output is changes to device settings and schedules. Specific actions include adjusting the on / off times of air conditioners and lighting.

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] The energy consumption spike management system according to the present invention provides, in addition to real-time energy management, a function that recognizes the user's emotions and adjusts the system's operation accordingly. This function enables more flexible and user-friendly energy management.

[0324] First, the server collects energy consumption data through smart meters and IoT sensors. This data includes time-series energy usage information and is processed sequentially. During this process, the server cleans and normalizes the data, preparing it for analysis.

[0325] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) model to identify predicted energy consumption spikes. Based on this information, it generates smart contracts to optimize consumption.

[0326] In this invention, the terminal further recognizes the user's emotional state using the user's emotion engine. This emotional data is an important factor in considering how the user accepts energy management. For example, if the user is feeling stressed, the notification method and content are flexibly changed to avoid causing psychological burden to the user.

[0327] After the user receives a notification, they approve the smart contract. At this point, the server suggests options based on sentiment data to present a plan that is more acceptable to the user.

[0328] Ultimately, the device automatically adjusts its energy consumption schedule based on approved smart contracts. This schedule improves overall energy efficiency by shifting energy-intensive tasks to off-peak hours.

[0329] Furthermore, the server continuously analyzes the results of the execution and the feedback from the emotion engine, accumulating data to improve the system. This process enables sustainable energy management while enhancing the user experience.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] The server collects energy consumption data in real time through smart meters and IoT sensors. This includes consumption information obtained from devices in homes and businesses, and is stored as time-series data.

[0333] Step 2:

[0334] The server cleans the collected energy consumption data. It removes outliers and missing values ​​and normalizes the data to maintain consistency. This lays the foundation for accurate future predictions.

[0335] Step 3:

[0336] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to predict consumption spikes based on the cleaned data. This prediction is performed to analyze consumption patterns during specific time periods and to anticipate peak loads.

[0337] Step 4:

[0338] The device uses an emotion engine to recognize the user's emotional state. Emotion recognition may involve voice or facial expression analysis, quantifying the user's current psychological state. This data is then used to flexibly configure the system's next actions.

[0339] Step 5:

[0340] The server combines prediction results and sentiment data to generate smart contracts to optimize consumption. Based on sentiment data, it adjusts the content and tone of notifications to create offers that are more likely to be accepted by users.

[0341] Step 6:

[0342] The server notifies the user of the generated smart contract and requests their approval. The notification is delivered in a method preferred by the user (e.g., email or push notification) and is designed to be easy for the user to use.

[0343] Step 7:

[0344] Users receive notifications and make decisions to approve or modify the presented smart contracts. This process allows for flexible dialogue that adapts to their emotional state.

[0345] Step 8:

[0346] After user approval, the device automatically shifts energy consumption based on the smart contract. This includes changing the operating schedule of electrical appliances and moving tasks to off-peak hours.

[0347] Step 9:

[0348] The server analyzes the consumption data and sentiment feedback, continuously optimizing predictive models and the user interface. This improves overall system performance and user experience.

[0349] (Example 2)

[0350] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0351] The sustainable use and efficient management of energy consumption are critical challenges in modern society. Conventional technologies suffer from waste due to peak energy consumption and inconvenience caused by fixed contract forms that do not consider the feelings of users. As a result, energy efficiency cannot be fully utilized. Furthermore, there is a challenge in that flexible responses that take into account the circumstances of individual users are difficult to implement, and the user experience is not sufficiently improved.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes a device for collecting energy usage data, a device for processing the collected data, and a device for predicting fluctuations in energy consumption using a predictive analysis model. This enables real-time prediction of energy consumption spikes and flexible energy management tailored to the emotional state of individual users.

[0354] "Energy usage data" refers to information that records the amount and duration of consumption of electricity, gas, and other energy sources in a household or facility.

[0355] A "data collection device" refers to equipment or a system that automatically collects energy usage data using sensors, meters, etc.

[0356] A "processing device" is a system or device used to clean, normalize, and prepare collected data for analysis.

[0357] A "predictive analytics model" is an algorithm or framework for predicting future energy consumption patterns based on data.

[0358] A "device for predicting fluctuations" is a computer system that uses predictive analysis models to forecast sudden increases or decreases in energy use.

[0359] A "contract generation device" is a system that creates optimized energy consumption contracts in response to predicted fluctuations in energy use.

[0360] A "device for obtaining consent" is a method or system for notifying an individual of the terms of a contract and collecting their consent electronically or physically.

[0361] A "planning device" is a system that automatically executes an energy usage plan based on the generated energy consumption contract.

[0362] A "device that analyzes emotional states and adjusts notification methods regarding energy use" is a device that analyzes the user's emotional state and adjusts the content and timing of notifications regarding energy consumption based on the results.

[0363] This invention is a system that enhances energy consumption management and realizes flexible energy contracts that take user feelings into consideration. This system promotes efficient energy use through the cooperation of servers, terminals, and users.

[0364] The server collects energy usage data through sensors and smart meters. This allows for real-time monitoring of energy consumption in homes and facilities. The collected data undergoes cleansing and normalization processes to be prepared as input data for predictive analytics models. Specifically, models such as recurrent neural networks (RNNs) and long-short-term memory (LSTMs) can be used.

[0365] The device is equipped with an emotion engine to analyze the user's emotional state, detecting their voice and facial expressions to identify their emotional state. This information is used to adjust notifications and contract proposals regarding energy usage. For example, if the user is feeling stressed, the device will send a flexible notification such as, "Would you like to delay the washing machine run until 2 AM tonight?"

[0366] Users receive an energy usage plan sent from the server. Based on this, they can approve or modify the application of the proposed contract. Depending on the user's selection, the server adjusts the energy consumption schedule to promote optimal energy use.

[0367] Throughout the process, the server continuously evaluates the performance of the predictive model and improves its accuracy by comparing it with actual energy consumption data. This process enables sustainable and efficient energy management.

[0368] Examples of prompts include "Suggest an optimal energy consumption plan based on tomorrow's weather forecast" and "Consider a notification method that takes into account when the user is feeling stressed." These prompts utilize generative AI models as a means to support optimal energy management for the user.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server acquires energy usage data in real time from sensors and smart meters as input. This raw data includes power consumption, time stamps, and consumption information by device. The server cleanses and normalizes this data, removing inappropriate data points and converting it into a format suitable for analysis. The output is a clear, normalized dataset that can be used by analytical models.

[0372] Step 2:

[0373] The server uses cleansed data as input to run a recurrent neural network (RNN) or long-short-term memory (LSTM) model. This model predicts the temporal fluctuations in energy consumption and identifies energy consumption spikes in specific time periods as outputs. Specifically, it learns past consumption patterns and predicts future consumption trends.

[0374] Step 3:

[0375] The server generates a smart contract to optimize energy consumption based on the model's output. This contract plans to shift energy-intensive work to off-peak hours. The input is predicted consumption spike information, and the output is the contract details, including the specific shift plan.

[0376] Step 4:

[0377] The device receives smart contract notifications sent from the server and analyzes the user's state through the user's emotion engine. Inputs include the user's facial expressions and tone of voice, and output is expressed as the user's emotional state. Based on this information, the device adjusts its suggestions and provides flexible notifications to the user.

[0378] Step 5:

[0379] The user reviews the notification received via their device and approves or modifies the presented smart contract as input. During this process, the user is presented with options that take their emotional state into consideration, and they select the appropriate option. The output is the approved or modified contract.

[0380] Step 6:

[0381] The device automatically adjusts the energy usage schedule based on a smart contract approved by the user. The input is the final approved contract, and the output is the actual device operating schedule. The device shifts operation to off-peak hours, improving overall energy efficiency.

[0382] Step 7:

[0383] The server evaluates the accuracy of the predicted model using actual energy usage data as input. As a feedback loop, new consumption and sentiment data are used to retrain the model and improve prediction accuracy. The output is the improved predictive model.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0386] In modern energy management systems, predicting energy consumption spikes and promoting efficient energy use is crucial. However, these systems typically only perform automated processing based on data and lack the flexibility to respond to individual user emotions. As a result, users may sometimes experience high psychological burden and dissatisfaction with the system. Therefore, it is necessary to incorporate features that consider user emotions into energy management systems.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] This invention includes a server that includes a method for collecting energy consumption data in real time, a method for cleaning and normalizing the collected data, a method for predicting energy consumption peaks using a recurrent neural network or long- and short-term memory, a method for creating smart contracts based on the predicted consumption peaks, a method for analyzing the user's emotional state and flexibly notifying the user of the contract details, a method for automatically adjusting energy consumption based on the smart contracts, and a method for improving the prediction model by comparing the prediction results with actual consumption data. This enables the energy management system to provide an optimal energy consumption plan tailored to each user's emotional state.

[0389] "Energy consumption data" refers to information that records energy usage in a specific location or system over time.

[0390] "Real-time data collection methods" refer to the process of instantly acquiring data and providing it to the system without any time delay.

[0391] "Cleaning" is the process of removing noise and errors from collected data and preparing it for analysis.

[0392] "Normalization" is a technique that adjusts data based on a certain range or standard to improve the accuracy and consistency of analysis.

[0393] A "recurrent neural network" is an artificial intelligence model that, unlike conventional neural networks, can handle time-series data.

[0394] "Long-Short-Term Memory" is a type of recurrent neural network that learns long-term and short-term dependencies from time-series data and uses them for prediction.

[0395] "Energy consumption peak" refers to a sharp increase in energy usage during a specific time period.

[0396] A "smart contract" is a digital form of contract that is automatically executed based on specific conditions.

[0397] "User emotional state" refers to information that indicates the user's psychological and emotional condition.

[0398] A "flexible notification method" is an approach that appropriately adjusts the way information is presented according to the recipient's state and circumstances.

[0399] "Automated execution method" refers to a function in which a system executes a process without human intervention based on pre-set conditions.

[0400] "Methods for improving predictive models" refer to techniques for improving the accuracy of future predictions by comparing collected data with actual results.

[0401] To implement this invention, the server first collects energy consumption data from smart meters and IoT sensors. This data is acquired in real time and automatically cleaned and normalized on the server. The server then uses a recurrent neural network or long- and short-term memory to predict peak energy consumption.

[0402] Next, the server analyzes the emotional state provided by the user's device. The device is equipped with sensors to detect the user's emotions in real time and transmit this information to the server. This ensures that the user's emotions are taken into consideration when determining energy consumption schedules. Specifically, if the emotional state differs from the user's normal state, the notification method is adjusted, and an emotionally sensitive smart contract is offered.

[0403] Users can review and approve the contract details displayed on their device. Based on the approved smart contract, energy consumption is automatically adjusted and shifted to predetermined off-peak hours. This adjustment is centrally monitored on the server side, and the results are recorded. This allows the server to continuously improve its predictive model.

[0404] For example, a system installed in a home might adjust the air conditioning and lighting appropriately to coincide with the time when the user returns home in the evening. It might even suggest particularly pleasant lighting for that evening to help the user relax after returning home. This creates a schedule that enhances user comfort while maintaining energy efficiency.

[0405] Example prompt for a generating AI model: "Generate suggestions for various scenarios regarding the importance of considering user emotions in energy consumption management."

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The server collects energy consumption data in real time from smart meters and IoT sensors. The input is raw data from the sensors, and the output is time-series data converted into a digital format. This data is used as foundational information necessary for subsequent data processing.

[0409] Step 2:

[0410] The server cleans and normalizes the collected energy consumption data. The input is the time-series data obtained in step 1, and the output is a denoised and standardized dataset. Removing unwanted elements from the data enables more accurate predictions.

[0411] Step 3:

[0412] The server predicts energy consumption peaks using a recurrent neural network or long- and short-term memory based on cleaned data. The input is a normalized dataset, and the output is time-series forecast information showing future consumption peaks. This forecast information contributes to the development of energy-efficient schedules.

[0413] Step 4:

[0414] The device analyzes the user's emotional state and sends that information to the server. The input is raw emotional data obtained from the camera and microphone, and the output is the user's emotional state analyzed by the emotion engine. This information is used as a reference when adjusting notification content and timing.

[0415] Step 5:

[0416] The server creates a smart contract based on predicted energy consumption peaks and the user's emotional state. The inputs are the predicted information from step 3 and the emotional data from step 4, and the output is the optimal energy consumption plan to be presented to the user. This plan is designed to minimize psychological burden.

[0417] Step 6:

[0418] The user reviews and approves the contract details via their device. The input is the smart contract received from the server, and the output is the user's approval or rejection feedback. In this step, the user's preferences are reflected in the system.

[0419] Step 7:

[0420] The server automatically adjusts energy consumption based on approved smart contracts and records the results. The input is user approval information, and the output is a record of the adjusted energy consumption status and its results. This accumulates data that can be used to improve the accuracy of future predictions.

[0421] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0422] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0423] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0427] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0428] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0429] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0430] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0431] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0432] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0433] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0434] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0435] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0436] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0437] The energy consumption spike management system according to the present invention aims to improve the efficiency of energy consumption. This system collects energy consumption data in real time and provides technology to predict future consumption spikes by analyzing that data.

[0438] Specifically, the server first collects energy consumption data in real time from smart meters and IoT sensors. This data includes the amount of energy consumed at each facility in homes and businesses, as well as the consumption patterns over time. Next, the server cleans the collected data, normalizing it through a process that removes noise and outliers.

[0439] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze patterns in consumption data and predict future consumption spikes. Based on this prediction, the server automatically generates smart contracts to optimize energy use.

[0440] The generated smart contract is notified to the user. The user then approves the contract, and a plan to avoid consumption spikes is implemented. For example, this could involve scheduling changes such as shifting electric vehicle charging or air conditioning operation to off-peak hours.

[0441] This process allows the terminal to automatically adjust the operating time of electrical appliances after user approval, shifting energy consumption. This reduces peak energy consumption. The server also compares actual consumption data with predictive models and implements continuous improvements to enhance the system's accuracy. This invention enables reduced energy costs and sustainable energy use.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] The server collects energy consumption data in real time from smart meters and IoT sensors. This includes time-series consumption data for each device and facility.

[0445] Step 2:

[0446] The server cleans the collected data to remove noise and outliers, improving data quality. Furthermore, it normalizes the data and equalizes its scale, making analysis easier.

[0447] Step 3:

[0448] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze preprocessed data and predict future consumption spikes. This prediction identifies the time periods when energy consumption peaks are likely to occur.

[0449] Step 4:

[0450] The server automatically generates smart contracts to mitigate energy consumption during peak hours, based on predicted consumption spikes. These contracts propose shifting energy-intensive tasks to off-peak hours.

[0451] Step 5:

[0452] The server notifies the user of the generated smart contract and requests their approval of the contract terms. The notification is sent via a smartphone app or email.

[0453] Step 6:

[0454] Once the user approves the smart contract, the device automatically implements energy consumption shifts based on the contract. This adjusts the device's operation and optimizes energy use.

[0455] Step 7:

[0456] The server compares the consumption data being processed with the prediction results to evaluate the model's prediction accuracy. It modifies the model as needed and continuously improves the overall system.

[0457] (Example 1)

[0458] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0459] In modern society, efficiently managing peak energy consumption and achieving sustainable energy use is crucial. However, there is a lack of means to accurately predict fluctuations in energy consumption and effectively optimize energy use. As a result, challenges such as wasted energy costs and instability in energy supply during peak times exist.

[0460] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0461] In this invention, the server includes means for collecting energy consumption information in real time using an information gathering device, means for preprocessing and normalizing the collected information, and means for predicting sudden increases in energy consumption using a learning algorithm. This makes it possible to accurately predict peak energy consumption and efficiently optimize energy use.

[0462] An "information gathering device" is a device used to collect energy consumption information in real time, and has the ability to aggregate and transmit data via a network.

[0463] "Preprocessing" is the process of removing outliers and noise from raw data collected prior to data analysis, thereby ensuring the accuracy and consistency of the data.

[0464] "Normalization" refers to the process of arranging collected data to fit within a certain range, thereby making it suitable for analysis.

[0465] A "learning algorithm" is a computational method used to learn patterns and rules from large amounts of data and predict future events.

[0466] A "sudden surge in energy consumption" refers to a phenomenon in which energy usage increases rapidly over time, potentially putting a strain on the supply system.

[0467] A "predictive algorithm" is a method for analyzing past data patterns to predict events that are likely to occur in the future.

[0468] "Contract information" refers to a set of instructions automatically generated to optimize energy consumption, and it represents information that shows a feasible energy use plan.

[0469] A "non-demand period" refers to a time of day when normal energy use is reduced, meaning that the load can be alleviated by reducing energy consumption.

[0470] "Energy-intensive operation" refers to the operation of equipment or processes that consume large amounts of electricity.

[0471] The energy consumption management system according to the present invention aims to improve energy efficiency and has the function of collecting and analyzing data in real time. This enables the prediction of peak energy consumption and the optimization of energy use to suit the user's lifestyle.

[0472] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Specifically, it manages data streaming using Apache Kafka from smart meters and IoT sensors and stores it in MongoDB.

[0473] The acquired data is preprocessed using the Python Pandas library. This removes noise and outliers and normalizes the data. At this stage, missing values ​​are imputed using the NumPy library, preparing a dataset that can be input into the predictive model.

[0474] Next, the server uses machine learning libraries such as TensorFlow and Keras to analyze energy consumption patterns using recurrent neural networks (RNNs) and long-short-term memory (LSTMs). Based on this analysis, it predicts future surges in energy consumption and automatically generates contract information based on the results.

[0475] Once contract information is generated, users are notified via smartphone applications or other means. Users can then review and approve this proposal to implement an optimized energy usage plan. This allows, for example, scheduling the use of air conditioners or electric vehicle charging during off-peak hours.

[0476] Ultimately, the device automatically adjusts and manages the operating time of electrical appliances based on user approval. The server also monitors actual consumption data, compares it with predictive algorithms, and continuously improves the model.

[0477] A concrete example would be a suggestion to shift the use of air conditioners in the home to off-peak hours. An example prompt for the generating AI model would be, "Predict peaks for the next three months and create suggestions to optimize energy use."

[0478] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0479] Step 1:

[0480] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Inputs include consumption data from smart meters and IoT sensors. The server streams this data using Apache Kafka and stores it in MongoDB. The output is raw data stored in a database suitable for analysis. Its specific operation includes accepting data transfers and continuously accumulating data.

[0481] Step 2:

[0482] The server preprocesses the collected raw data using the Python Pandas library. The input is raw data stored in MongoDB. Preprocessing involves executing algorithms to detect and remove outliers and noise. Using the NumPy library, missing values ​​are imputed and the data is normalized, resulting in clean data that can be input to machine learning models. The specific operation involves data cleansing and transformation processes within the pipeline.

[0483] Step 3:

[0484] The server runs an RNN or LSTM model using TensorFlow or Keras libraries with pre-processed clean data to analyze energy consumption patterns. The input is the clean data generated in step 2, and the output is a prediction of future consumption spikes. The server runs a program that trains the model using historical consumption data and makes predictions. Specific operations include training the model and performing predictions.

[0485] Step 4:

[0486] The server automatically generates contract information to optimize energy use based on the prediction results. The input is the consumption spike prediction obtained in step 3. The output is optimized energy use contract information, which includes plans such as load balancing. The server generates and stores the contract information using blockchain technology. Specifically, the contract generation process is performed based on the prediction results.

[0487] Step 5:

[0488] The user reviews the contract information notified by the server and chooses to approve or reject it. The input is the contract information notified via a smart device or application. The output is the user's selection result (approval or rejection). Specific actions include receiving the notification and performing a selection operation within the application.

[0489] Step 6:

[0490] The terminal adjusts the operating schedule based on user approval. The input is the user-approved contract information. The terminal shifts the operating times of electrical appliances and equipment, resulting in optimized energy use as output. Specific operations include updating and adjusting the operating schedule.

[0491] (Application Example 1)

[0492] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0493] In modern cities, peak energy demand places a heavy burden on the supply, potentially compromising the stability of the power grid. This also leads to increased energy costs and makes sustainable energy use difficult. To address this situation, both optimizing individual consumers' energy consumption and coordinating energy use across the entire city are necessary.

[0494] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0495] In this invention, the server includes means for acquiring energy consumption information in real time, means for cleaning and normalizing the acquired information, means for predicting energy usage patterns using a recurrent neural network or long- and short-term memory, means for generating intelligent contracts based on the predicted consumption patterns, means for monitoring energy usage across the entire city and presenting individual usage adjustment plans, and means for coordinating and executing the presented plans with the user's information terminal. This makes it possible to optimize energy consumption across the entire city, level out peak demand to reduce energy costs, and enable sustainable energy use.

[0496] "Energy consumption information" refers to data showing the usage of electricity consumed in homes, businesses, and cities, and is acquired in real time.

[0497] "Cleaning" is the process of removing noise and outliers from acquired energy consumption information to improve data accuracy.

[0498] "Normalization" is the process of transforming cleaned data to conform to a standard value and arranging it into a consistent data format.

[0499] A "recurrent neural network" is a machine learning model specifically designed for analyzing time-series data, and it is an algorithm that uses past data to predict future energy consumption patterns.

[0500] "Long-short-term memory" refers to a machine learning model that has the ability to retain temporal dependencies over long periods, making it a suitable technique for predicting energy usage patterns.

[0501] An "intellectual contract" is a contract that is automatically generated based on energy consumption forecasts, and the energy usage plan is finalized when the user approves it.

[0502] An "energy use adjustment plan" is a set of specific action guidelines presented to improve the efficiency of energy consumption in cities and households and to level out peak consumption.

[0503] An "information terminal" is a device that allows users to receive notifications and suggestions regarding energy consumption, and to check and implement plans; smartphones are an example of such devices.

[0504] To realize this invention, a server, a terminal, and a user must collaborate. The server acquires energy consumption information, cleans and normalizes the data, and then performs analysis using a recurrent neural network (RNN) or long-short-term memory (LSTM). This allows for the prediction of energy consumption patterns and the identification of future consumption spikes. Based on this information, the server automatically generates intelligent contracts and proposes individual energy use adjustment plans. These proposals are communicated to the user's information terminal via an API built using Flask or Django as a framework. The user approves the proposed plan using the terminal, and the terminal executes the plan through a connected smart device.

[0505] The hardware used includes smart meters and standard IoT sensors for data collection, and smartphones and tablets for user notifications and operation. On the software side, the Python Pandas library is used for data processing, and TensorFlow and Keras are used for model building and prediction.

[0506] For example, if the forecast suggests a nighttime energy spike, the server recommends that the user maximize their home electricity usage during the day and take advantage of off-peak nighttime rates. The user then approves this through their device, and the device adjusts electricity usage accordingly. An example of a prompt message to the generative AI model in realizing this invention would be: "Please consider a user-specific optimization strategy to suggest a shift in energy consumption to off-peak hours in order to reduce the load on power plants."

[0507] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0508] Step 1:

[0509] The server acquires energy consumption information from smart meters and IoT sensors. The input is real-time recorded power usage data, and the output is aggregated information from this data. This data is needed for cleaning and normalization in the next step.

[0510] Step 2:

[0511] The server cleans and normalizes the acquired energy consumption information. The input is the raw data obtained in step 1, and the output is data that has had noise and outliers removed and is formatted into a standard format. In this process, data processing and calculations are performed using the Python Pandas library.

[0512] Step 3:

[0513] The server predicts energy usage patterns using a recurrent neural network (RNN) or long-short-term memory (LSTM) based on cleaned data. The input is normalized consumption data, and the output is a prediction of future energy consumption spikes. Predictive models are built using TensorFlow or Keras, and calculations are performed based on the data.

[0514] Step 4:

[0515] The server generates intelligent contracts based on the prediction results. The input is the prediction results from step 3, and the output is a user-specific energy usage adjustment plan. At this stage, prompts are input to the generating AI model to design individual optimization strategies.

[0516] Step 5:

[0517] The server notifies the user's information terminal of the content of the generated intellectual contract. The input is the content of the intellectual contract, and the output is the notification displayed on the user's terminal. The information is transmitted via API and stored on the terminal.

[0518] Step 6:

[0519] The user reviews the received energy usage adjustment plan on their terminal and chooses to approve or reject it. The input is the notified contract information, and the output is the user's selection.

[0520] Step 7:

[0521] The terminal controls connected smart devices and executes energy usage adjustment plans, provided the user approves. The input is the energy usage plan, and the output is changes to device settings and schedules. Specific actions include adjusting the on / off times of air conditioners and lighting.

[0522] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0523] The energy consumption spike management system according to the present invention provides, in addition to real-time energy management, a function that recognizes the user's emotions and adjusts the system's operation accordingly. This function enables more flexible and user-friendly energy management.

[0524] First, the server collects energy consumption data through smart meters and IoT sensors. This data includes time-series energy usage information and is processed sequentially. During this process, the server cleans and normalizes the data, preparing it for analysis.

[0525] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) model to identify predicted energy consumption spikes. Based on this information, it generates smart contracts to optimize consumption.

[0526] In this invention, the terminal further recognizes the user's emotional state using the user's emotion engine. This emotional data is an important factor in considering how the user accepts energy management. For example, if the user is feeling stressed, the notification method and content are flexibly changed to avoid causing psychological burden to the user.

[0527] After the user receives a notification, they approve the smart contract. At this point, the server suggests options based on sentiment data to present a plan that is more acceptable to the user.

[0528] Ultimately, the device automatically adjusts its energy consumption schedule based on approved smart contracts. This schedule improves overall energy efficiency by shifting energy-intensive tasks to off-peak hours.

[0529] Furthermore, the server continuously analyzes the results of the execution and the feedback from the emotion engine, accumulating data to improve the system. This process enables sustainable energy management while enhancing the user experience.

[0530] The following describes the processing flow.

[0531] Step 1:

[0532] The server collects energy consumption data in real time through smart meters and IoT sensors. This includes consumption information obtained from devices in homes and businesses, and is stored as time-series data.

[0533] Step 2:

[0534] The server cleans the collected energy consumption data. It removes outliers and missing values ​​and normalizes the data to maintain consistency. This lays the foundation for accurate future predictions.

[0535] Step 3:

[0536] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to predict consumption spikes based on the cleaned data. This prediction is performed to analyze consumption patterns during specific time periods and to anticipate peak loads.

[0537] Step 4:

[0538] The device uses an emotion engine to recognize the user's emotional state. Emotion recognition may involve voice or facial expression analysis, quantifying the user's current psychological state. This data is then used to flexibly configure the system's next actions.

[0539] Step 5:

[0540] The server combines prediction results and sentiment data to generate smart contracts to optimize consumption. Based on sentiment data, it adjusts the content and tone of notifications to create offers that are more likely to be accepted by users.

[0541] Step 6:

[0542] The server notifies the user of the generated smart contract and requests their approval. The notification is delivered in a method preferred by the user (e.g., email or push notification) and is designed to be easy for the user to use.

[0543] Step 7:

[0544] Users receive notifications and make decisions to approve or modify the presented smart contracts. This process allows for flexible dialogue that adapts to their emotional state.

[0545] Step 8:

[0546] After user approval, the device automatically shifts energy consumption based on the smart contract. This includes changing the operating schedule of electrical appliances and moving tasks to off-peak hours.

[0547] Step 9:

[0548] The server analyzes the consumption data and sentiment feedback, continuously optimizing predictive models and the user interface. This improves overall system performance and user experience.

[0549] (Example 2)

[0550] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] The sustainable use and efficient management of energy consumption are critical challenges in modern society. Conventional technologies suffer from waste due to peak energy consumption and inconvenience caused by fixed contract forms that do not consider the feelings of users. As a result, energy efficiency cannot be fully utilized. Furthermore, there is a challenge in that flexible responses that take into account the circumstances of individual users are difficult to implement, and the user experience is not sufficiently improved.

[0552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0553] In this invention, the server includes a device for collecting energy usage data, a device for processing the collected data, and a device for predicting fluctuations in energy consumption using a predictive analysis model. This enables real-time prediction of energy consumption spikes and flexible energy management tailored to the emotional state of individual users.

[0554] "Energy usage data" refers to information that records the amount and duration of consumption of electricity, gas, and other energy sources in a household or facility.

[0555] A "data collection device" refers to equipment or a system that automatically collects energy usage data using sensors, meters, etc.

[0556] A "processing device" is a system or device used to clean, normalize, and prepare collected data for analysis.

[0557] A "predictive analytics model" is an algorithm or framework for predicting future energy consumption patterns based on data.

[0558] A "device for predicting fluctuations" is a computer system that uses predictive analysis models to forecast sudden increases or decreases in energy use.

[0559] A "contract generation device" is a system that creates optimized energy consumption contracts in response to predicted fluctuations in energy use.

[0560] A "device for obtaining consent" is a method or system for notifying an individual of the terms of a contract and collecting their consent electronically or physically.

[0561] A "planning device" is a system that automatically executes an energy usage plan based on the generated energy consumption contract.

[0562] A "device that analyzes emotional states and adjusts notification methods regarding energy use" is a device that analyzes the user's emotional state and adjusts the content and timing of notifications regarding energy consumption based on the results.

[0563] This invention is a system that enhances energy consumption management and realizes flexible energy contracts that take user feelings into consideration. This system promotes efficient energy use through the cooperation of servers, terminals, and users.

[0564] The server collects energy usage data through sensors and smart meters. This allows for real-time monitoring of energy consumption in homes and facilities. The collected data undergoes cleansing and normalization processes to be prepared as input data for predictive analytics models. Specifically, models such as recurrent neural networks (RNNs) and long-short-term memory (LSTMs) can be used.

[0565] The device is equipped with an emotion engine to analyze the user's emotional state, detecting their voice and facial expressions to identify their emotional state. This information is used to adjust notifications and contract proposals regarding energy usage. For example, if the user is feeling stressed, the device will send a flexible notification such as, "Would you like to delay the washing machine run until 2 AM tonight?"

[0566] Users receive an energy usage plan sent from the server. Based on this, they can approve or modify the application of the proposed contract. Depending on the user's selection, the server adjusts the energy consumption schedule to promote optimal energy use.

[0567] Throughout the process, the server continuously evaluates the performance of the predictive model and improves its accuracy by comparing it with actual energy consumption data. This process enables sustainable and efficient energy management.

[0568] Examples of prompts include "Suggest an optimal energy consumption plan based on tomorrow's weather forecast" and "Consider a notification method that takes into account when the user is feeling stressed." These prompts utilize generative AI models as a means to support optimal energy management for the user.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The server acquires energy usage data in real time from sensors and smart meters as input. This raw data includes power consumption, time stamps, and consumption information by device. The server cleanses and normalizes this data, removing inappropriate data points and converting it into a format suitable for analysis. The output is a clear, normalized dataset that can be used by analytical models.

[0572] Step 2:

[0573] The server uses cleansed data as input to run a recurrent neural network (RNN) or long-short-term memory (LSTM) model. This model predicts the temporal fluctuations in energy consumption and identifies energy consumption spikes in specific time periods as outputs. Specifically, it learns past consumption patterns and predicts future consumption trends.

[0574] Step 3:

[0575] The server generates a smart contract to optimize energy consumption based on the model's output. This contract plans to shift energy-intensive work to off-peak hours. The input is predicted consumption spike information, and the output is the contract details, including the specific shift plan.

[0576] Step 4:

[0577] The device receives smart contract notifications sent from the server and analyzes the user's state through the user's emotion engine. Inputs include the user's facial expressions and tone of voice, and output is expressed as the user's emotional state. Based on this information, the device adjusts its suggestions and provides flexible notifications to the user.

[0578] Step 5:

[0579] The user reviews the notification received via their device and approves or modifies the presented smart contract as input. During this process, the user is presented with options that take their emotional state into consideration, and they select the appropriate option. The output is the approved or modified contract.

[0580] Step 6:

[0581] The device automatically adjusts the energy usage schedule based on a smart contract approved by the user. The input is the final approved contract, and the output is the actual device operating schedule. The device shifts operation to off-peak hours, improving overall energy efficiency.

[0582] Step 7:

[0583] The server evaluates the accuracy of the predicted model using actual energy usage data as input. As a feedback loop, new consumption and sentiment data are used to retrain the model and improve prediction accuracy. The output is the improved predictive model.

[0584] (Application Example 2)

[0585] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0586] In modern energy management systems, predicting energy consumption spikes and promoting efficient energy use is crucial. However, these systems typically only perform automated processing based on data and lack the flexibility to respond to individual user emotions. As a result, users may sometimes experience high psychological burden and dissatisfaction with the system. Therefore, it is necessary to incorporate features that consider user emotions into energy management systems.

[0587] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0588] This invention includes a server that includes a method for collecting energy consumption data in real time, a method for cleaning and normalizing the collected data, a method for predicting energy consumption peaks using a recurrent neural network or long- and short-term memory, a method for creating smart contracts based on the predicted consumption peaks, a method for analyzing the user's emotional state and flexibly notifying the user of the contract details, a method for automatically adjusting energy consumption based on the smart contracts, and a method for improving the prediction model by comparing the prediction results with actual consumption data. This enables the energy management system to provide an optimal energy consumption plan tailored to each user's emotional state.

[0589] "Energy consumption data" refers to information that records energy usage in a specific location or system over time.

[0590] "Real-time data collection methods" refer to the process of instantly acquiring data and providing it to the system without any time delay.

[0591] "Cleaning" is the process of removing noise and errors from collected data and preparing it for analysis.

[0592] "Normalization" is a technique that adjusts data based on a certain range or standard to improve the accuracy and consistency of analysis.

[0593] A "recurrent neural network" is an artificial intelligence model that, unlike conventional neural networks, can handle time-series data.

[0594] "Long-Short-Term Memory" is a type of recurrent neural network that learns long-term and short-term dependencies from time-series data and uses them for prediction.

[0595] "Energy consumption peak" refers to a sharp increase in energy usage during a specific time period.

[0596] A "smart contract" is a digital form of contract that is automatically executed based on specific conditions.

[0597] "User emotional state" refers to information that indicates the user's psychological and emotional condition.

[0598] A "flexible notification method" is an approach that appropriately adjusts the way information is presented according to the recipient's state and circumstances.

[0599] "Automated execution method" refers to a function in which a system executes a process without human intervention based on pre-set conditions.

[0600] "Methods for improving predictive models" refer to techniques for improving the accuracy of future predictions by comparing collected data with actual results.

[0601] To implement this invention, the server first collects energy consumption data from smart meters and IoT sensors. This data is acquired in real time and automatically cleaned and normalized on the server. The server then uses a recurrent neural network or long- and short-term memory to predict peak energy consumption.

[0602] Next, the server analyzes the emotional state provided by the user's device. The device is equipped with sensors to detect the user's emotions in real time and transmit this information to the server. This ensures that the user's emotions are taken into consideration when determining energy consumption schedules. Specifically, if the emotional state differs from the user's normal state, the notification method is adjusted, and an emotionally sensitive smart contract is offered.

[0603] Users can review and approve the contract details displayed on their device. Based on the approved smart contract, energy consumption is automatically adjusted and shifted to predetermined off-peak hours. This adjustment is centrally monitored on the server side, and the results are recorded. This allows the server to continuously improve its predictive model.

[0604] For example, a system installed in a home might adjust the air conditioning and lighting appropriately to coincide with the time when the user returns home in the evening. It might even suggest particularly pleasant lighting for that evening to help the user relax after returning home. This creates a schedule that enhances user comfort while maintaining energy efficiency.

[0605] Example prompt for a generating AI model: "Generate suggestions for various scenarios regarding the importance of considering user emotions in energy consumption management."

[0606] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0607] Step 1:

[0608] The server collects energy consumption data in real time from smart meters and IoT sensors. The input is raw data from the sensors, and the output is time-series data converted into a digital format. This data is used as foundational information necessary for subsequent data processing.

[0609] Step 2:

[0610] The server cleans and normalizes the collected energy consumption data. The input is the time-series data obtained in step 1, and the output is a denoised and standardized dataset. Removing unwanted elements from the data enables more accurate predictions.

[0611] Step 3:

[0612] The server predicts energy consumption peaks using a recurrent neural network or long- and short-term memory based on cleaned data. The input is a normalized dataset, and the output is time-series forecast information showing future consumption peaks. This forecast information contributes to the development of energy-efficient schedules.

[0613] Step 4:

[0614] The device analyzes the user's emotional state and sends that information to the server. The input is raw emotional data obtained from the camera and microphone, and the output is the user's emotional state analyzed by the emotion engine. This information is used as a reference when adjusting notification content and timing.

[0615] Step 5:

[0616] The server creates a smart contract based on predicted energy consumption peaks and the user's emotional state. The inputs are the predicted information from step 3 and the emotional data from step 4, and the output is the optimal energy consumption plan to be presented to the user. This plan is designed to minimize psychological burden.

[0617] Step 6:

[0618] The user reviews and approves the contract details via their device. The input is the smart contract received from the server, and the output is the user's approval or rejection feedback. In this step, the user's preferences are reflected in the system.

[0619] Step 7:

[0620] The server automatically adjusts energy consumption based on approved smart contracts and records the results. The input is user approval information, and the output is a record of the adjusted energy consumption status and its results. This accumulates data that can be used to improve the accuracy of future predictions.

[0621] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0622] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0623] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0624] [Fourth Embodiment]

[0625] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0626] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0627] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0628] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0629] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0630] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0631] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0632] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0633] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0634] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0635] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0636] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0637] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0638] The energy consumption spike management system according to the present invention aims to improve the efficiency of energy consumption. This system collects energy consumption data in real time and provides technology to predict future consumption spikes by analyzing that data.

[0639] Specifically, the server first collects energy consumption data in real time from smart meters and IoT sensors. This data includes the amount of energy consumed at each facility in homes and businesses, as well as the consumption patterns over time. Next, the server cleans the collected data, normalizing it through a process that removes noise and outliers.

[0640] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze patterns in consumption data and predict future consumption spikes. Based on this prediction, the server automatically generates smart contracts to optimize energy use.

[0641] The generated smart contract is notified to the user. The user then approves the contract, and a plan to avoid consumption spikes is implemented. For example, this could involve scheduling changes such as shifting electric vehicle charging or air conditioning operation to off-peak hours.

[0642] This process allows the terminal to automatically adjust the operating time of electrical appliances after user approval, shifting energy consumption. This reduces peak energy consumption. The server also compares actual consumption data with predictive models and implements continuous improvements to enhance the system's accuracy. This invention enables reduced energy costs and sustainable energy use.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] The server collects energy consumption data in real time from smart meters and IoT sensors. This includes time-series consumption data for each device and facility.

[0646] Step 2:

[0647] The server cleans the collected data to remove noise and outliers, improving data quality. Furthermore, it normalizes the data and equalizes its scale, making analysis easier.

[0648] Step 3:

[0649] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to analyze preprocessed data and predict future consumption spikes. This prediction identifies the time periods when energy consumption peaks are likely to occur.

[0650] Step 4:

[0651] The server automatically generates smart contracts to mitigate energy consumption during peak hours, based on predicted consumption spikes. These contracts propose shifting energy-intensive tasks to off-peak hours.

[0652] Step 5:

[0653] The server notifies the user of the generated smart contract and requests their approval of the contract terms. The notification is sent via a smartphone app or email.

[0654] Step 6:

[0655] Once the user approves the smart contract, the device automatically implements energy consumption shifts based on the contract. This adjusts the device's operation and optimizes energy use.

[0656] Step 7:

[0657] The server compares the consumption data being processed with the prediction results to evaluate the model's prediction accuracy. It modifies the model as needed and continuously improves the overall system.

[0658] (Example 1)

[0659] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0660] In modern society, efficiently managing peak energy consumption and achieving sustainable energy use is crucial. However, there is a lack of means to accurately predict fluctuations in energy consumption and effectively optimize energy use. As a result, challenges such as wasted energy costs and instability in energy supply during peak times exist.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0662] In this invention, the server includes means for collecting energy consumption information in real time using an information gathering device, means for preprocessing and normalizing the collected information, and means for predicting sudden increases in energy consumption using a learning algorithm. This makes it possible to accurately predict peak energy consumption and efficiently optimize energy use.

[0663] An "information gathering device" is a device used to collect energy consumption information in real time, and has the ability to aggregate and transmit data via a network.

[0664] "Preprocessing" is the process of removing outliers and noise from raw data collected prior to data analysis, thereby ensuring the accuracy and consistency of the data.

[0665] "Normalization" refers to the process of arranging collected data to fit within a certain range, thereby making it suitable for analysis.

[0666] A "learning algorithm" is a computational method used to learn patterns and rules from large amounts of data and predict future events.

[0667] A "sudden surge in energy consumption" refers to a phenomenon in which energy usage increases rapidly over time, potentially putting a strain on the supply system.

[0668] A "predictive algorithm" is a method for analyzing past data patterns to predict events that are likely to occur in the future.

[0669] "Contract information" refers to a set of instructions automatically generated to optimize energy consumption, and it represents information that shows a feasible energy use plan.

[0670] A "non-demand period" refers to a time of day when normal energy use is reduced, meaning that the load can be alleviated by reducing energy consumption.

[0671] "Energy-intensive operation" refers to the operation of equipment or processes that consume large amounts of electricity.

[0672] The energy consumption management system according to the present invention aims to improve energy efficiency and has the function of collecting and analyzing data in real time. This enables the prediction of peak energy consumption and the optimization of energy use to suit the user's lifestyle.

[0673] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Specifically, it manages data streaming using Apache Kafka from smart meters and IoT sensors and stores it in MongoDB.

[0674] The acquired data is preprocessed using the Python Pandas library. This removes noise and outliers and normalizes the data. At this stage, missing values ​​are imputed using the NumPy library, preparing a dataset that can be input into the predictive model.

[0675] Next, the server uses machine learning libraries such as TensorFlow and Keras to analyze energy consumption patterns using recurrent neural networks (RNNs) and long-short-term memory (LSTMs). Based on this analysis, it predicts future surges in energy consumption and automatically generates contract information based on the results.

[0676] Once contract information is generated, users are notified via smartphone applications or other means. Users can then review and approve this proposal to implement an optimized energy usage plan. This allows, for example, scheduling the use of air conditioners or electric vehicle charging during off-peak hours.

[0677] Ultimately, the device automatically adjusts and manages the operating time of electrical appliances based on user approval. The server also monitors actual consumption data, compares it with predictive algorithms, and continuously improves the model.

[0678] A concrete example would be a suggestion to shift the use of air conditioners in the home to off-peak hours. An example prompt for the generating AI model would be, "Predict peaks for the next three months and create suggestions to optimize energy use."

[0679] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0680] Step 1:

[0681] The server acquires real-time energy consumption information from homes and businesses via data collection devices. Inputs include consumption data from smart meters and IoT sensors. The server streams this data using Apache Kafka and stores it in MongoDB. The output is raw data stored in a database suitable for analysis. Its specific operation includes accepting data transfers and continuously accumulating data.

[0682] Step 2:

[0683] The server preprocesses the collected raw data using the Python Pandas library. The input is raw data stored in MongoDB. Preprocessing involves executing algorithms to detect and remove outliers and noise. Using the NumPy library, missing values ​​are imputed and the data is normalized, resulting in clean data that can be input to machine learning models. The specific operation involves data cleansing and transformation processes within the pipeline.

[0684] Step 3:

[0685] The server runs an RNN or LSTM model using TensorFlow or Keras libraries with pre-processed clean data to analyze energy consumption patterns. The input is the clean data generated in step 2, and the output is a prediction of future consumption spikes. The server runs a program that trains the model using historical consumption data and makes predictions. Specific operations include training the model and performing predictions.

[0686] Step 4:

[0687] The server automatically generates contract information to optimize energy use based on the prediction results. The input is the consumption spike prediction obtained in step 3. The output is optimized energy use contract information, which includes plans such as load balancing. The server generates and stores the contract information using blockchain technology. Specifically, the contract generation process is performed based on the prediction results.

[0688] Step 5:

[0689] The user reviews the contract information notified by the server and chooses to approve or reject it. The input is the contract information notified via a smart device or application. The output is the user's selection result (approval or rejection). Specific actions include receiving the notification and performing a selection operation within the application.

[0690] Step 6:

[0691] The terminal adjusts the operating schedule based on user approval. The input is the user-approved contract information. The terminal shifts the operating times of electrical appliances and equipment, resulting in optimized energy use as output. Specific operations include updating and adjusting the operating schedule.

[0692] (Application Example 1)

[0693] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0694] In modern cities, peak energy demand places a heavy burden on the supply, potentially compromising the stability of the power grid. This also leads to increased energy costs and makes sustainable energy use difficult. To address this situation, both optimizing individual consumers' energy consumption and coordinating energy use across the entire city are necessary.

[0695] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0696] In this invention, the server includes means for acquiring energy consumption information in real time, means for cleaning and normalizing the acquired information, means for predicting energy usage patterns using a recurrent neural network or long- and short-term memory, means for generating intelligent contracts based on the predicted consumption patterns, means for monitoring energy usage across the entire city and presenting individual usage adjustment plans, and means for coordinating and executing the presented plans with the user's information terminal. This makes it possible to optimize energy consumption across the entire city, level out peak demand to reduce energy costs, and enable sustainable energy use.

[0697] "Energy consumption information" refers to data showing the usage of electricity consumed in homes, businesses, and cities, and is acquired in real time.

[0698] "Cleaning" is the process of removing noise and outliers from acquired energy consumption information to improve data accuracy.

[0699] "Normalization" is the process of transforming cleaned data to conform to a standard value and arranging it into a consistent data format.

[0700] A "recurrent neural network" is a machine learning model specifically designed for analyzing time-series data, and it is an algorithm that uses past data to predict future energy consumption patterns.

[0701] "Long-short-term memory" refers to a machine learning model that has the ability to retain temporal dependencies over long periods, making it a suitable technique for predicting energy usage patterns.

[0702] An "intellectual contract" is a contract that is automatically generated based on energy consumption forecasts, and the energy usage plan is finalized when the user approves it.

[0703] An "energy use adjustment plan" is a set of specific action guidelines presented to improve the efficiency of energy consumption in cities and households and to level out peak consumption.

[0704] An "information terminal" is a device that allows users to receive notifications and suggestions regarding energy consumption, and to check and implement plans; smartphones are an example of such devices.

[0705] To realize this invention, a server, a terminal, and a user must collaborate. The server acquires energy consumption information, cleans and normalizes the data, and then performs analysis using a recurrent neural network (RNN) or long-short-term memory (LSTM). This allows for the prediction of energy consumption patterns and the identification of future consumption spikes. Based on this information, the server automatically generates intelligent contracts and proposes individual energy use adjustment plans. These proposals are communicated to the user's information terminal via an API built using Flask or Django as a framework. The user approves the proposed plan using the terminal, and the terminal executes the plan through a connected smart device.

[0706] The hardware used includes smart meters and standard IoT sensors for data collection, and smartphones and tablets for user notifications and operation. On the software side, the Python Pandas library is used for data processing, and TensorFlow and Keras are used for model building and prediction.

[0707] For example, if the forecast suggests a nighttime energy spike, the server recommends that the user maximize their home electricity usage during the day and take advantage of off-peak nighttime rates. The user then approves this through their device, and the device adjusts electricity usage accordingly. An example of a prompt message to the generative AI model in realizing this invention would be: "Please consider a user-specific optimization strategy to suggest a shift in energy consumption to off-peak hours in order to reduce the load on power plants."

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The server acquires energy consumption information from smart meters and IoT sensors. The input is real-time recorded power usage data, and the output is aggregated information from this data. This data is needed for cleaning and normalization in the next step.

[0711] Step 2:

[0712] The server cleans and normalizes the acquired energy consumption information. The input is the raw data obtained in step 1, and the output is data that has had noise and outliers removed and is formatted into a standard format. In this process, data processing and calculations are performed using the Python Pandas library.

[0713] Step 3:

[0714] The server predicts energy usage patterns using a recurrent neural network (RNN) or long-short-term memory (LSTM) based on cleaned data. The input is normalized consumption data, and the output is a prediction of future energy consumption spikes. Predictive models are built using TensorFlow or Keras, and calculations are performed based on the data.

[0715] Step 4:

[0716] The server generates intelligent contracts based on the prediction results. The input is the prediction results from step 3, and the output is a user-specific energy usage adjustment plan. At this stage, prompts are input to the generating AI model to design individual optimization strategies.

[0717] Step 5:

[0718] The server notifies the user's information terminal of the content of the generated intellectual contract. The input is the content of the intellectual contract, and the output is the notification displayed on the user's terminal. The information is transmitted via API and stored on the terminal.

[0719] Step 6:

[0720] The user reviews the received energy usage adjustment plan on their terminal and chooses to approve or reject it. The input is the notified contract information, and the output is the user's selection.

[0721] Step 7:

[0722] The terminal controls connected smart devices and executes energy usage adjustment plans, provided the user approves. The input is the energy usage plan, and the output is changes to device settings and schedules. Specific actions include adjusting the on / off times of air conditioners and lighting.

[0723] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0724] The energy consumption spike management system according to the present invention provides, in addition to real-time energy management, a function that recognizes the user's emotions and adjusts the system's operation accordingly. This function enables more flexible and user-friendly energy management.

[0725] First, the server collects energy consumption data through smart meters and IoT sensors. This data includes time-series energy usage information and is processed sequentially. During this process, the server cleans and normalizes the data, preparing it for analysis.

[0726] Next, the server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) model to identify predicted energy consumption spikes. Based on this information, it generates smart contracts to optimize consumption.

[0727] In this invention, the terminal further recognizes the user's emotional state using the user's emotion engine. This emotional data is an important factor in considering how the user accepts energy management. For example, if the user is feeling stressed, the notification method and content are flexibly changed to avoid causing psychological burden to the user.

[0728] After the user receives a notification, they approve the smart contract. At this point, the server suggests options based on sentiment data to present a plan that is more acceptable to the user.

[0729] Ultimately, the device automatically adjusts its energy consumption schedule based on approved smart contracts. This schedule improves overall energy efficiency by shifting energy-intensive tasks to off-peak hours.

[0730] Furthermore, the server continuously analyzes the results of the execution and the feedback from the emotion engine, accumulating data to improve the system. This process enables sustainable energy management while enhancing the user experience.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] The server collects energy consumption data in real time through smart meters and IoT sensors. This includes consumption information obtained from devices in homes and businesses, and is stored as time-series data.

[0734] Step 2:

[0735] The server cleans the collected energy consumption data. It removes outliers and missing values ​​and normalizes the data to maintain consistency. This lays the foundation for accurate future predictions.

[0736] Step 3:

[0737] The server uses a recurrent neural network (RNN) or long-short-term memory (LSTM) to predict consumption spikes based on the cleaned data. This prediction is performed to analyze consumption patterns during specific time periods and to anticipate peak loads.

[0738] Step 4:

[0739] The device uses an emotion engine to recognize the user's emotional state. Emotion recognition may involve voice or facial expression analysis, quantifying the user's current psychological state. This data is then used to flexibly configure the system's next actions.

[0740] Step 5:

[0741] The server combines prediction results and sentiment data to generate smart contracts to optimize consumption. Based on sentiment data, it adjusts the content and tone of notifications to create offers that are more likely to be accepted by users.

[0742] Step 6:

[0743] The server notifies the user of the generated smart contract and requests their approval. The notification is delivered in a method preferred by the user (e.g., email or push notification) and is designed to be easy for the user to use.

[0744] Step 7:

[0745] Users receive notifications and make decisions to approve or modify the presented smart contracts. This process allows for flexible dialogue that adapts to their emotional state.

[0746] Step 8:

[0747] After user approval, the device automatically shifts energy consumption based on the smart contract. This includes changing the operating schedule of electrical appliances and moving tasks to off-peak hours.

[0748] Step 9:

[0749] The server analyzes the consumption data and sentiment feedback, continuously optimizing predictive models and the user interface. This improves overall system performance and user experience.

[0750] (Example 2)

[0751] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0752] The sustainable use and efficient management of energy consumption are critical challenges in modern society. Conventional technologies suffer from waste due to peak energy consumption and inconvenience caused by fixed contract forms that do not consider the feelings of users. As a result, energy efficiency cannot be fully utilized. Furthermore, there is a challenge in that flexible responses that take into account the circumstances of individual users are difficult to implement, and the user experience is not sufficiently improved.

[0753] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0754] In this invention, the server includes a device for collecting energy usage data, a device for processing the collected data, and a device for predicting fluctuations in energy consumption using a predictive analysis model. This enables real-time prediction of energy consumption spikes and flexible energy management tailored to the emotional state of individual users.

[0755] "Energy usage data" refers to information that records the amount and duration of consumption of electricity, gas, and other energy sources in a household or facility.

[0756] A "data collection device" refers to equipment or a system that automatically collects energy usage data using sensors, meters, etc.

[0757] A "processing device" is a system or device used to clean, normalize, and prepare collected data for analysis.

[0758] A "predictive analytics model" is an algorithm or framework for predicting future energy consumption patterns based on data.

[0759] A "device for predicting fluctuations" is a computer system that uses predictive analysis models to forecast sudden increases or decreases in energy use.

[0760] A "contract generation device" is a system that creates optimized energy consumption contracts in response to predicted fluctuations in energy use.

[0761] A "device for obtaining consent" is a method or system for notifying an individual of the terms of a contract and collecting their consent electronically or physically.

[0762] A "planning device" is a system that automatically executes an energy usage plan based on the generated energy consumption contract.

[0763] A "device that analyzes emotional states and adjusts notification methods regarding energy use" is a device that analyzes the user's emotional state and adjusts the content and timing of notifications regarding energy consumption based on the results.

[0764] This invention is a system that enhances energy consumption management and realizes flexible energy contracts that take user feelings into consideration. This system promotes efficient energy use through the cooperation of servers, terminals, and users.

[0765] The server collects energy usage data through sensors and smart meters. This allows for real-time monitoring of energy consumption in homes and facilities. The collected data undergoes cleansing and normalization processes to be prepared as input data for predictive analytics models. Specifically, models such as recurrent neural networks (RNNs) and long-short-term memory (LSTMs) can be used.

[0766] The device is equipped with an emotion engine to analyze the user's emotional state, detecting their voice and facial expressions to identify their emotional state. This information is used to adjust notifications and contract proposals regarding energy usage. For example, if the user is feeling stressed, the device will send a flexible notification such as, "Would you like to delay the washing machine run until 2 AM tonight?"

[0767] Users receive an energy usage plan sent from the server. Based on this, they can approve or modify the application of the proposed contract. Depending on the user's selection, the server adjusts the energy consumption schedule to promote optimal energy use.

[0768] Throughout the process, the server continuously evaluates the performance of the predictive model and improves its accuracy by comparing it with actual energy consumption data. This process enables sustainable and efficient energy management.

[0769] Examples of prompts include "Suggest an optimal energy consumption plan based on tomorrow's weather forecast" and "Consider a notification method that takes into account when the user is feeling stressed." These prompts utilize generative AI models as a means to support optimal energy management for the user.

[0770] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0771] Step 1:

[0772] The server acquires energy usage data in real time from sensors and smart meters as input. This raw data includes power consumption, time stamps, and consumption information by device. The server cleanses and normalizes this data, removing inappropriate data points and converting it into a format suitable for analysis. The output is a clear, normalized dataset that can be used by analytical models.

[0773] Step 2:

[0774] The server uses cleansed data as input to run a recurrent neural network (RNN) or long-short-term memory (LSTM) model. This model predicts the temporal fluctuations in energy consumption and identifies energy consumption spikes in specific time periods as outputs. Specifically, it learns past consumption patterns and predicts future consumption trends.

[0775] Step 3:

[0776] The server generates a smart contract to optimize energy consumption based on the model's output. This contract plans to shift energy-intensive work to off-peak hours. The input is predicted consumption spike information, and the output is the contract details, including the specific shift plan.

[0777] Step 4:

[0778] The device receives smart contract notifications sent from the server and analyzes the user's state through the user's emotion engine. Inputs include the user's facial expressions and tone of voice, and output is expressed as the user's emotional state. Based on this information, the device adjusts its suggestions and provides flexible notifications to the user.

[0779] Step 5:

[0780] The user reviews the notification received via their device and approves or modifies the presented smart contract as input. During this process, the user is presented with options that take their emotional state into consideration, and they select the appropriate option. The output is the approved or modified contract.

[0781] Step 6:

[0782] The device automatically adjusts the energy usage schedule based on a smart contract approved by the user. The input is the final approved contract, and the output is the actual device operating schedule. The device shifts operation to off-peak hours, improving overall energy efficiency.

[0783] Step 7:

[0784] The server evaluates the accuracy of the predicted model using actual energy usage data as input. As a feedback loop, new consumption and sentiment data are used to retrain the model and improve prediction accuracy. The output is the improved predictive model.

[0785] (Application Example 2)

[0786] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] In modern energy management systems, predicting energy consumption spikes and promoting efficient energy use is crucial. However, these systems typically only perform automated processing based on data and lack the flexibility to respond to individual user emotions. As a result, users may sometimes experience high psychological burden and dissatisfaction with the system. Therefore, it is necessary to incorporate features that consider user emotions into energy management systems.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0789] This invention includes a server that includes a method for collecting energy consumption data in real time, a method for cleaning and normalizing the collected data, a method for predicting energy consumption peaks using a recurrent neural network or long- and short-term memory, a method for creating smart contracts based on the predicted consumption peaks, a method for analyzing the user's emotional state and flexibly notifying the user of the contract details, a method for automatically adjusting energy consumption based on the smart contracts, and a method for improving the prediction model by comparing the prediction results with actual consumption data. This enables the energy management system to provide an optimal energy consumption plan tailored to each user's emotional state.

[0790] "Energy consumption data" refers to information that records energy usage in a specific location or system over time.

[0791] "Real-time data collection methods" refer to the process of instantly acquiring data and providing it to the system without any time delay.

[0792] "Cleaning" is the process of removing noise and errors from collected data and preparing it for analysis.

[0793] "Normalization" is a technique that adjusts data based on a certain range or standard to improve the accuracy and consistency of analysis.

[0794] A "recurrent neural network" is an artificial intelligence model that, unlike conventional neural networks, can handle time-series data.

[0795] "Long-Short-Term Memory" is a type of recurrent neural network that learns long-term and short-term dependencies from time-series data and uses them for prediction.

[0796] "Energy consumption peak" refers to a sharp increase in energy usage during a specific time period.

[0797] A "smart contract" is a digital form of contract that is automatically executed based on specific conditions.

[0798] "User emotional state" refers to information that indicates the user's psychological and emotional condition.

[0799] A "flexible notification method" is an approach that appropriately adjusts the way information is presented according to the recipient's state and circumstances.

[0800] "Automated execution method" refers to a function in which a system executes a process without human intervention based on pre-set conditions.

[0801] "Methods for improving predictive models" refer to techniques for improving the accuracy of future predictions by comparing collected data with actual results.

[0802] To implement this invention, the server first collects energy consumption data from smart meters and IoT sensors. This data is acquired in real time and automatically cleaned and normalized on the server. The server then uses a recurrent neural network or long- and short-term memory to predict peak energy consumption.

[0803] Next, the server analyzes the emotional state provided by the user's device. The device is equipped with sensors to detect the user's emotions in real time and transmit this information to the server. This ensures that the user's emotions are taken into consideration when determining energy consumption schedules. Specifically, if the emotional state differs from the user's normal state, the notification method is adjusted, and an emotionally sensitive smart contract is offered.

[0804] Users can review and approve the contract details displayed on their device. Based on the approved smart contract, energy consumption is automatically adjusted and shifted to predetermined off-peak hours. This adjustment is centrally monitored on the server side, and the results are recorded. This allows the server to continuously improve its predictive model.

[0805] For example, a system installed in a home might adjust the air conditioning and lighting appropriately to coincide with the time when the user returns home in the evening. It might even suggest particularly pleasant lighting for that evening to help the user relax after returning home. This creates a schedule that enhances user comfort while maintaining energy efficiency.

[0806] Example prompt for a generating AI model: "Generate suggestions for various scenarios regarding the importance of considering user emotions in energy consumption management."

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1:

[0809] The server collects energy consumption data in real time from smart meters and IoT sensors. The input is raw data from the sensors, and the output is time-series data converted into a digital format. This data is used as foundational information necessary for subsequent data processing.

[0810] Step 2:

[0811] The server cleans and normalizes the collected energy consumption data. The input is the time-series data obtained in step 1, and the output is a denoised and standardized dataset. Removing unwanted elements from the data enables more accurate predictions.

[0812] Step 3:

[0813] The server predicts energy consumption peaks using a recurrent neural network or long- and short-term memory based on cleaned data. The input is a normalized dataset, and the output is time-series forecast information showing future consumption peaks. This forecast information contributes to the development of energy-efficient schedules.

[0814] Step 4:

[0815] The device analyzes the user's emotional state and sends that information to the server. The input is raw emotional data obtained from the camera and microphone, and the output is the user's emotional state analyzed by the emotion engine. This information is used as a reference when adjusting notification content and timing.

[0816] Step 5:

[0817] The server creates a smart contract based on predicted energy consumption peaks and the user's emotional state. The inputs are the predicted information from step 3 and the emotional data from step 4, and the output is the optimal energy consumption plan to be presented to the user. This plan is designed to minimize psychological burden.

[0818] Step 6:

[0819] The user reviews and approves the contract details via their device. The input is the smart contract received from the server, and the output is the user's approval or rejection feedback. In this step, the user's preferences are reflected in the system.

[0820] Step 7:

[0821] The server automatically adjusts energy consumption based on approved smart contracts and records the results. The input is user approval information, and the output is a record of the adjusted energy consumption status and its results. This accumulates data that can be used to improve the accuracy of future predictions.

[0822] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0823] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0824] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0825] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0826] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0827] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0828] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0829] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0830] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0831] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0832] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0833] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0834] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0835] 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.

[0836] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0837] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0838] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0839] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0840] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0841] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0842] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0843] The following is further disclosed regarding the embodiments described above.

[0844] (Claim 1)

[0845] A means of collecting energy consumption data in real time,

[0846] A method for cleaning and normalizing the collected data,

[0847] A means for predicting energy consumption spikes using a recurrent neural network or long- and short-term memory,

[0848] A means of generating smart contracts based on predictions of consumption spikes,

[0849] A means of notifying users of the contract details and obtaining their approval,

[0850] A means of automatically executing a shift in energy consumption based on smart contracts,

[0851] A method for improving the prediction model by comparing the prediction results with actual consumption data,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, which acquires consumption data from a smart meter and sensors.

[0855] (Claim 3)

[0856] The system according to claim 1, which schedules energy-intensive tasks during off-peak hours.

[0857] "Example 1"

[0858] (Claim 1)

[0859] A means of collecting energy consumption information in real time using an information gathering device,

[0860] A means of preprocessing and normalizing the collected information,

[0861] A method for predicting a surge in energy consumption using a learning algorithm,

[0862] A means of automatically generating contract information based on predictions,

[0863] Means of notifying users of contract information and obtaining their consent,

[0864] A means of automatically adjusting energy consumption based on contract information,

[0865] A means of improving the prediction algorithm by comparing predicted information with actual consumption information,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, which acquires consumption information from multiple measuring devices.

[0869] (Claim 3)

[0870] The system according to claim 1, which adjusts the timing of energy-intensive operations during periods of low demand.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] A means of obtaining energy consumption information in real time,

[0874] A means of cleaning and normalizing the acquired information,

[0875] A means for predicting energy usage patterns using a recurrent neural network or long- and short-term memory,

[0876] A means for generating intelligent contracts based on predictions of consumption patterns,

[0877] A means of notifying the user of the contract details and obtaining their approval,

[0878] A means of automatically executing a shift in energy use based on an intelligent contract,

[0879] A means of improving the model by comparing prediction results with actual usage information,

[0880] A means of monitoring energy use across the entire city and presenting individual use adjustment plans,

[0881] A means of executing the presented plan in conjunction with the user's information terminal,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, which acquires information from an energy information collection device and a detection device.

[0885] (Claim 3)

[0886] The system according to claim 1, which schedules energy-intensive activities during off-peak hours.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] A device for collecting energy usage data,

[0890] A device for processing the collected data,

[0891] A device that predicts fluctuations in energy consumption using a predictive analysis model,

[0892] A device that generates contracts based on fluctuations in energy consumption,

[0893] A device that notifies individuals of the contract details and obtains their consent,

[0894] Equipment for implementing energy usage plans based on contracts,

[0895] A device for evaluating usage results and prediction results to improve predictive analysis models,

[0896] A device that analyzes emotional states and adjusts notification methods regarding energy utilization,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, which receives usage data from a detection device.

[0900] (Claim 3)

[0901] The system according to claim 1, which schedules tasks that contribute to energy efficiency to unplanned time slots.

[0902] "Application example 2 when combining with an emotional engine"

[0903] (Claim 1)

[0904] Methods for collecting energy consumption data in real time,

[0905] Methods for cleaning and normalizing collected data,

[0906] A method for predicting energy consumption peaks using recurrent neural networks or long- and short-term memory,

[0907] How to create smart contracts based on predicted consumption peaks,

[0908] A method for analyzing the user's emotional state and flexibly informing the user of the contract details,

[0909] A method for automatically adjusting energy consumption based on a smart contract,

[0910] A method for improving the prediction model by comparing the prediction results with actual consumption data,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, which acquires consumption data from a smart meter and sensors.

[0914] (Claim 3)

[0915] The system according to claim 1, which schedules energy-intensive tasks during off-peak hours. [Explanation of symbols]

[0916] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining energy consumption information in real time, A means of cleaning and normalizing the acquired information, A means for predicting energy usage patterns using a recurrent neural network or long- and short-term memory, A means for generating intelligent contracts based on predictions of consumption patterns, A means of notifying the user of the contract details and obtaining their approval, A means of automatically executing a shift in energy use based on an intelligent contract, A means of improving the model by comparing prediction results with actual usage information, A means of monitoring energy use across the entire city and presenting individual use adjustment plans, A means of executing the presented plan in conjunction with the user's information terminal, A system that includes this.

2. The system according to claim 1, which acquires information from an energy information collection device and a detection device.

3. The system according to claim 1, which schedules energy-intensive activities during off-peak hours.

Images