system

Abstract

We provide the system. [Solution] Information gathering means for acquiring energy consumption information, An anomaly detection means that analyzes consumption patterns based on acquired information and detects abnormalities, A pricing plan optimization method that proposes the most suitable pricing plan to the user, A price fluctuation prediction method that predicts future price fluctuations based on market price information, A user terminal that displays the user's energy consumption status in real time and notifies them when an anomaly occurs, A system that includes this.

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] Among various energy tariff plans, it is difficult for consumers to select the plan most suitable for their own energy usage situation. Also, there are problems that it is difficult to detect methods for saving consumed energy and abnormal consumption, and wasteful costs are likely to occur. The purpose of this invention is to provide a system that automatically detects abnormalities in energy consumption and proposes an optimal tariff plan and consumption strategy to solve these problems.

Means for Solving the Problems

[0005] This invention provides an energy management system that includes means for acquiring energy consumption data in real time, means for analyzing consumption patterns based on the acquired data to detect anomalies, means for proposing the optimal pricing plan for the user, and means for predicting future price fluctuations based on market price data. This system enables users to achieve efficient energy consumption and cost reduction.

[0006] "Energy consumption data" refers to information that shows the amount of energy, such as electricity and gas, used by consumers.

[0007] "Data collection means" refers to a device or process that has the function of collecting energy consumption data from smart meters or other measuring devices.

[0008] An "anomaly detection means" is a device or process that has the function of detecting deviations from normal energy consumption patterns.

[0009] A "pricing plan optimization method" is a device or process that has the function of comparing various energy pricing plans and selecting the plan that best benefits the user.

[0010] A "price fluctuation prediction means" is a device or process that has the function of predicting future fluctuations in energy prices based on past data and market trends.

[0011] An "energy management system" is a concept that refers to an entire system that enables the monitoring, analysis, and optimization of energy consumption. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of 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 an 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 an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

[0016] 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.

[0017] 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.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

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

[0020] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] The energy management system according to the present invention has a configuration for collecting energy consumption data and proposing the optimal pricing plan to the user. This system consists of three main components: a server, a terminal, and a user. The roles of each are described below.

[0034] First, the server receives energy consumption data in real time from smart meters and other sources and stores it in a database. The data includes electricity and gas usage amounts and timestamps. This allows for the understanding of each user's consumption patterns.

[0035] Next, the server uses machine learning algorithms to detect anomalies based on the stored data. This involves comparing the data with past usage patterns and identifying any consumption that differs from normal as an anomaly. For example, it can issue an alert if power consumption suddenly increases during the night.

[0036] The server also notifies the user via the terminal when it detects an anomaly. The notification includes the nature of the anomaly and recommended countermeasures. Furthermore, the server compares the collected energy consumption data with the electricity company's pricing plans and suggests the most suitable plan for the user. This allows the user to reduce unnecessary costs.

[0037] The device displays notifications from the server and suggested pricing plans to the user. Based on this information, the user can review their energy usage. For example, they can take measures such as changing the time of day they use electricity to avoid peak charges.

[0038] Furthermore, the server analyzes market energy price trends and predicts future price fluctuations. This information is also provided to the user via the terminal, allowing the user to plan their energy usage strategy based on this information.

[0039] As a concrete example, when this system is applied to household energy management, the server records power consumption data daily and uses an anomaly detection module to send necessary warnings to the user in a timely manner. Furthermore, by optimizing electricity rate plans, users can reduce their monthly electricity bills. In this way, the energy management system helps users use energy efficiently and improve cost-effectiveness.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server periodically receives electricity and gas consumption data from smart meters and other IoT devices. The data is recorded as electricity usage and gas usage, along with a timestamp.

[0043] Step 2:

[0044] The server stores the received data in a database. This data is stored as time-series data and used to analyze consumption patterns.

[0045] Step 3:

[0046] The server activates an anomaly detection module based on the stored data. It utilizes machine learning models to execute algorithms that detect deviations from normal consumption patterns.

[0047] Step 4:

[0048] If an anomaly is detected, the server generates an alert and sends a notification to the user via their terminal. This notification includes details of the anomaly and recommended actions to take.

[0049] Step 5:

[0050] The server collects pricing plan data from multiple power companies and calculates the optimal pricing plan by comparing it with the user's consumption data.

[0051] Step 6:

[0052] If an optimal pricing plan is found, the server will present that information to the user via the terminal. This suggestion will include a comparison with the current plan and an estimated amount of savings.

[0053] Step 7:

[0054] The server investigates price trends in the energy market and, based on this, runs a price fluctuation prediction module. Using machine learning, it predicts future price fluctuations from historical data.

[0055] Step 8:

[0056] Price fluctuation forecasts are provided to users via their devices. Users can use this information to adjust and plan their energy consumption. By developing consumption strategies based on these forecasts, it is possible to optimize costs.

[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] With increasing energy consumption, there is a growing need to propose optimal pricing plans to individual users and improve cost efficiency. However, existing technologies are insufficient for accurately analyzing consumption patterns and detecting anomalies. Furthermore, predicting price fluctuations in the energy market and providing users with strategic energy usage suggestions based on those predictions is currently difficult. It is necessary to solve these problems and improve cost reduction and energy usage optimization for users.

[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 data collection means for acquiring energy consumption data, anomaly detection means for analyzing consumption patterns based on the acquired data and detecting anomalies, and price fluctuation prediction means for predicting future price trends based on market price information. This enables anomaly detection in energy consumption and the proposal of cost-effective pricing plans, as well as strategic optimization of energy use based on market trends.

[0062] "Energy consumption data" refers to information that shows the amount of energy used, such as electricity and gas, and the duration of that use.

[0063] A "data collection method" is a system for acquiring energy consumption data and storing it in a database or similar.

[0064] An "anomaly detection method" refers to a process or technology for identifying unusual energy usage patterns based on consumption patterns.

[0065] "Rate plan optimization methods" refer to methods for suggesting the most economical rate plan based on the user's energy consumption data.

[0066] A "price fluctuation prediction method" is a technology that analyzes market price information and predicts future price fluctuations.

[0067] "Information notification means" refers to devices or methods that notify users of information such as anomaly detection results or proposed pricing plans.

[0068] A "strategy presentation method" is a method of analyzing electricity consumption patterns and pricing structures to propose the optimal energy usage strategy to users.

[0069] An "electronic meter" is a measuring device that can measure energy consumption and transmit that data remotely.

[0070] "Numerical analysis methods" are techniques that use mathematical and statistical methods to analyze data.

[0071] The embodiments for carrying out the present invention are described below.

[0072] The energy management system consists of three main components: users, servers, and terminals.

[0073] The server acquires energy consumption data in real time from measuring devices such as electronic meters. The acquired data is stored in a database, and then anomalies are identified by comparing it with past consumption patterns using an anomaly detection method. Numerical analysis methods are used for anomaly detection, enabling rapid detection of fraudulent consumption. In addition, the server uses a pricing plan optimization method to analyze the user's consumption data and market pricing information to propose the optimal pricing plan. Furthermore, a price fluctuation prediction method predicts market price trends, allowing for forecasting of future energy costs.

[0074] The terminal's role is to present information notifications sent from the server to the user. Specifically, it displays information such as anomaly detection results, proposed pricing plans, and usage strategies based on price trend forecasts. Based on the information provided by the terminal, users can review their power usage patterns and strive to reduce energy costs.

[0075] Users can optimize their daily energy usage by referring to the various information they receive through this system. For example, by adjusting the time of day they use electricity according to the suggested pricing plan, they can reduce their electricity bill.

[0076] As a concrete example, if this system is installed in a home, the server will manage daily energy consumption, and if an anomaly is detected, the user will be quickly notified via a terminal. In addition, cost optimization will enable the expected reduction in electricity bills. In this way, the efficiency of the user's energy use will be improved.

[0077] When using a generative AI model, you can obtain more detailed information about processing methods and theories by entering a prompt such as, "Please explain the algorithm that performs anomaly detection and rate optimization based on energy usage data."

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

[0079] Step 1:

[0080] The server acquires energy consumption data in real time from electronic meters. Input includes electricity and gas usage and their timestamps. This data is first stored in a database. Specifically, the server accesses the electronic meters via the network and retrieves the data using an API. The output is a time-series consumption dataset for each user.

[0081] Step 2:

[0082] The server uses collected energy consumption data to detect anomalies. The input is the time-series consumption data obtained in step 1. The server compares this data with past normal consumption patterns and identifies anomalies using numerical analysis techniques. Specifically, a machine learning algorithm analyzes real-time data and generates an alert if an abnormal pattern is detected. The output includes the type of anomaly detected and details of the associated consumption data.

[0083] Step 3:

[0084] When an anomaly is detected, the server sends a notification to the terminal. The input used is the details of the anomaly detected in step 2. Specifically, the server uses a notification protocol to deliver an alert to the terminal, forming a message that includes the type of anomaly and recommended actions. The output includes an immediate alert notification displayed on the user interface on the terminal.

[0085] Step 4:

[0086] The server optimizes pricing plans. Inputs include user energy consumption data and pricing plan information obtained from the market. The server uses pricing plan optimization tools to compare and analyze the pricing structure of each plan against the user's consumption patterns. Specific operations include executing a cost comparison algorithm for all pricing plans. The output generates a proposal for the most suitable pricing plan for the user.

[0087] Step 5:

[0088] The server analyzes market price information and predicts future energy cost trends. Its inputs include market price data and historical price fluctuation information. Specifically, it uses time series analysis to model and predict future price fluctuations. Its output includes strategic energy use suggestions based on the predicted price fluctuations.

[0089] Step 6:

[0090] The terminal presents information from the server to the user. Inputs include anomaly detection results, proposed pricing plans, and future price forecasts. Specifically, the terminal displays the information in an intuitively understandable format through a user interface. The output includes user-operable information displays, allowing the user to make decisions regarding energy use.

[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 today's society, where energy efficiency and cost reduction are paramount, the challenge lies in providing a system that can monitor energy consumption in real time, detect anomalies, and propose optimal pricing plans. Furthermore, there is a need to create an environment where users can intuitively understand their energy usage and respond immediately when anomalies occur.

[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 an information gathering means for acquiring energy consumption information, an anomaly detection means for analyzing consumption patterns based on the acquired information and detecting anomalies, a pricing plan optimization means for proposing the most suitable pricing plan to the user, a price fluctuation prediction means for predicting future price fluctuations based on market price information, and a user terminal that displays the user's energy consumption status in real time and notifies the user when an anomaly occurs. This enables real-time optimization of energy consumption and cost reduction, as well as a rapid response when an anomaly occurs.

[0096] "Energy consumption information" refers to information collected on the amount of electricity, gas, and other energy sources used, as well as related data.

[0097] "Information gathering means" refers to devices or systems used to acquire energy consumption information.

[0098] "Consumption patterns" refer to usage trends and behaviors derived from past energy usage data.

[0099] An "anomaly detection method" is a mechanism for detecting energy usage that deviates from normal consumption patterns.

[0100] "Rate plan optimization methods" refer to functions and methods for proposing the most economical energy rate plan to the user.

[0101] "Price information" refers to data on rates and prices in the energy market.

[0102] "Price fluctuation prediction methods" refer to techniques and mechanisms for analyzing market price information and predicting future price fluctuations.

[0103] A "user terminal" refers to a device or apparatus used by a user to receive information.

[0104] "Real-time" is a concept that refers to information being acquired and processed almost simultaneously.

[0105] "Notification" refers to the act or mechanism of informing a user of information.

[0106] The system for implementing this invention consists of three main components: a server, a terminal, and a user. The server is equipped with information gathering means for acquiring energy consumption information in real time and stores consumption data such as electricity and gas in the server's database through measuring instruments. Based on this stored data, the system analyzes consumption patterns and uses machine learning algorithms to detect anomalies that deviate from past consumption trends. For example, if electricity consumption increases at a time different from the normal use of household appliances, this can be detected as an anomaly.

[0107] When an anomaly is detected, the server sends a notification to the user's device. The device displays this information clearly to the user and issues alerts as needed, enabling the user to take immediate action. The server also obtains price information from the energy market and runs an algorithm to suggest the most suitable pricing plan for the user. This makes it possible to reduce unnecessary energy consumption costs.

[0108] Furthermore, this system analyzes market energy price trends and predicts future price fluctuations, helping users create usage plans that anticipate future increases in electricity prices.

[0109] As a concrete example, in one household, a smartphone app immediately displays a notification if it detects abnormal power consumption at night. At that point, the user can review their use of home appliances and use that information to help reduce costs. As an example of a "generated AI model and prompt message," a possible prompt message would be, "Based on energy consumption data within the smart city, create a power consumption peak forecast alert for this weekend and notify the user."

[0110] Thus, the main aim of this invention is to achieve both increased energy efficiency and a more comfortable energy experience for users.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server acquires energy consumption information through measuring instruments. It receives electricity and gas usage data and their timestamps as input and stores them in a database. During this process, the data is collected and formatted and optimized for storage in a centralized storage system.

[0114] Step 2:

[0115] The server uses machine learning algorithms to detect anomalies based on accumulated energy consumption data. It takes historical consumption pattern data as input and generates output indicating whether an anomaly exists and its details. Specifically, this involves identifying data points that deviate from normal consumption and marking them as anomalies.

[0116] Step 3:

[0117] When an anomaly is detected, the server generates a notification for the terminal. It receives the anomaly detection result as input and creates user-facing alert information as output. This notification includes details of the anomaly and recommended actions, and this information is sent to the user's device.

[0118] Step 4:

[0119] The server runs a pricing plan optimization algorithm and proposes a suitable pricing plan for the user. It uses energy consumption data and market price information as input and generates the optimal pricing plan as output. In this step, multiple plans are evaluated and the best one is selected based on the user's past usage patterns and current market conditions.

[0120] Step 5:

[0121] The server analyzes energy price trends and predicts future price fluctuations. It uses market price fluctuation data as input and presents predicted price trends as output. Specifically, it uses mathematical models to simulate future price scenarios and transmits the results to the terminal.

[0122] Step 6:

[0123] The terminal displays information received from the server to the user. It receives notification and price prediction information as input and provides information that the user can visually understand as output. During this process, the user interface is updated and notification pop-ups are displayed to encourage changes in user behavior.

[0124] 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.

[0125] The energy management system according to the present invention combines functions for collecting energy consumption data, analyzing consumption patterns, detecting anomalies, optimizing pricing plans, and predicting price fluctuations with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0126] First, the server receives energy consumption data from smart meters in real time and stores it in a database as time-series data. Based on this data, the server uses machine learning algorithms to detect anomalies. When an anomaly is detected, the server immediately generates an alert and notifies the user through their terminal.

[0127] In the pricing plan optimization method, the server collects various electricity pricing plans and compares them with the user's consumption data to suggest the optimal plan. This information is presented to the user via their terminal, supporting them in making the most economical choice. Furthermore, by analyzing price trends in the energy market, future price fluctuations are predicted. These price fluctuation predictions are provided to the user as information that helps optimize their energy usage plan.

[0128] The newly integrated emotion engine analyzes user voice and text data to understand the user's emotional state in real time. For example, if a user expresses dissatisfaction with energy use, the emotion engine recognizes this and sends data to the server. As a result, the server can adjust consumption strategies based on the emotional data and provide personalized advice.

[0129] As a concrete example, suppose a user in a household expresses dissatisfaction with their electricity bill through a voice assistant. At this time, the emotion engine analyzes the user's tone of voice and words to detect stress and dissatisfaction. This information is sent to a server, which then provides appropriate feedback to the user via the device, considering further energy-saving advice and suggestions for future rate plan changes. In this way, a system is realized that can manage energy consumption more flexibly according to the user's emotional state.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server receives electricity and gas consumption data from smart meters in real time. This data is time-stamped with accurate information, along with the amount of electricity and gas used.

[0133] Step 2:

[0134] The server stores the received data in a database and uses machine learning algorithms to analyze past consumption patterns. This analysis can detect outliers that deviate from normal consumption.

[0135] Step 3:

[0136] When an anomaly is detected, the server issues an alert and promptly notifies the user via their terminal. The notification includes the nature of the anomaly and recommended actions to take.

[0137] Step 4:

[0138] The server collects electricity rate plans offered from the market and selects the most economical plan by comparing it with the user's consumption data. This result is then presented to the user via the terminal.

[0139] Step 5:

[0140] The server incorporates external market analysis data and uses algorithms to predict future price trends. It can identify peak and undervalued periods for energy.

[0141] Step 6:

[0142] The price fluctuation prediction results are provided to users via their devices and used as a reference for developing optimal energy usage strategies.

[0143] Step 7:

[0144] Users express their emotions through voice and text input. This input data is analyzed by an emotion engine to recognize the user's emotional state.

[0145] Step 8:

[0146] The server, upon receiving output from the emotion engine, adjusts energy consumption suggestions based on the emotional data. In particular, if the user indicates stress or dissatisfaction, the system adjusts to provide specific advice in response.

[0147] Step 9:

[0148] Adjustments based on emotional data are delivered to the user via their device, promoting consumer behavior that takes user satisfaction into consideration.

[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 will be referred to as the "terminal."

[0151] Conventional energy management systems provide mechanisms for detecting anomalies in energy consumption and optimizing pricing plans, but they have the drawback of not being able to optimize flexible energy usage strategies that take into account the emotional state of users. Furthermore, predicting and utilizing fluctuations in energy market prices has been difficult. Therefore, this invention aims to provide more personalized energy management that takes into account the emotional state of users.

[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 information gathering means for acquiring energy usage information, anomaly identification means for analyzing usage trends and identifying anomalies based on the acquired information, and fluctuation prediction means for predicting future price fluctuations based on market price information. This makes it possible to adjust the energy usage strategy to be personalized based on the user's emotional state.

[0154] "Energy usage information" refers to data on the consumption of electricity, gas, water, etc., in homes and facilities.

[0155] "Information gathering means" refers to devices or programs used to collect energy usage information.

[0156] "Usage trends" refer to patterns or tendencies that show how energy is consumed.

[0157] "Analysis" is the process of examining data in detail to clarify its meaning and structure.

[0158] "Anomaly identification means" refers to a device or program for detecting phenomena that deviate from normal usage patterns.

[0159] A "fee agreement" refers to an arrangement regarding fees that consumers make with service providers.

[0160] "Contract optimization means" refers to a device or program for selecting the most advantageous pricing contract for the consumer.

[0161] "Price information" refers to data on prices in the energy market.

[0162] "Fluctuation prediction means" refers to a device or program for predicting future price fluctuations.

[0163] "Emotional state" refers to the state and changes in the user's emotions.

[0164] "Emotional analysis means" refers to a device or program used to analyze a user's emotions and understand their state.

[0165] A "management system" refers to a system for comprehensive management, including the collection, analysis, and optimization of energy usage information.

[0166] This energy management system is a comprehensive system for collecting, analyzing, and optimizing energy usage information. The main components of the system are information gathering means, anomaly identification means, contract optimization means, fluctuation prediction means, and sentiment analysis means.

[0167] The server collects energy usage information in real time via measuring devices. The smart meters used as measuring devices have the capability to transmit information over the internet. This collected data is stored in a database and used for later analysis.

[0168] Anomaly detection uses an automated learning algorithm executed on the server. This algorithm employs machine learning libraries such as Scikit-learn and TENSORFLOW®. The server analyzes time-series data of energy use and detects abnormal usage patterns.

[0169] The device receives notifications from the server and provides information to the user visually. For example, if an anomaly is detected, the device sends a push notification to the user and displays detailed information.

[0170] Contract optimization calculates the optimal pricing contract based on market price information and usage patterns collected by the server. Here, pricing information is obtained using the Requests library, and analysis is performed using an optimization algorithm based on linear programming. The optimization results are presented to the user via the terminal.

[0171] As a means of sentiment analysis, the server uses Google® Cloud Speech-to-Text API to analyze the user's voice data. This analysis makes it possible to grasp the user's emotional state in real time and generate personalized feedback and advice.

[0172] For example, if a user tells a voice assistant, "I'm unhappy with my recent electricity bill," the emotion analysis system analyzes that emotion and sends the results to a server. Based on the results, the server generates appropriate advice and suggests it to the user through the device.

[0173] An example of a prompt sentence to be fed into a generative AI model is, "Please tell me how to review my household energy consumption and save more than $100."

[0174] In this way, the system can efficiently manage the user's energy usage and provide interactive feedback that takes their emotional state into account.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server acquires energy usage information in real time via measuring devices. The input is raw power consumption data provided by smart meters. This data is stored in an SQL database and converted into a format usable for later analysis. Specifically, the server opens a database connection and retrieves and stores data via a RESTful API.

[0178] Step 2:

[0179] The server analyzes energy usage trends using energy usage information stored in a database and identifies anomalies by comparing them to baseline values. The input is power consumption data organized as a time series. The Scikit-learn Isolation Forest model is used to identify anomalous data points and output them as a report. Specifically, the server executes a Python script and logs any anomalies it finds.

[0180] Step 3:

[0181] The server notifies the device that an anomaly has been detected. The input is an anomaly report, which is the output of the anomaly detection algorithm. This information is sent to the device, and an alert is displayed to the user. Specifically, the server sends the notification via Firebase Cloud Messaging, and the device displays the alert on its user interface.

[0182] Step 4:

[0183] The server retrieves energy market price information from an external database and predicts future price fluctuations. The input is price data obtained from the internet. It performs time-series forecasting using the Prophet library and outputs the forecast results. Specifically, the server communicates via API to retrieve market information and applies it to the model.

[0184] Step 5:

[0185] The terminal presents the user with optimized pricing contract information sent from the server. The input is proposed pricing contract data generated by the server. This is visually displayed in the user interface, providing options. Specifically, the terminal uses technologies to display information in graph and table formats to show the proposals to the user.

[0186] Step 6:

[0187] The server receives voice commands from the user and inputs them into an emotion analysis algorithm to determine the user's emotional state. The input is voice data obtained from a voice assistant. The voice is converted to text using the Google Cloud Speech-to-Text API, and that text is analyzed using the NLTK library. The output is the detected emotional state. Specifically, the server receives the voice stream and performs text conversion and emotion analysis in real time.

[0188] Step 7:

[0189] The server uses a generative AI model based on the analysis results to generate personalized feedback and advice for the user. The input is sentiment data from a sentiment analysis algorithm. It generates prompt sentences and sends the advice to the terminal. Specifically, the server packages the generated prompts in JSON format and sends them to the terminal to notify the user.

[0190] (Application Example 2)

[0191] 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".

[0192] Efficient energy management is essential in modern society, but conventional systems have faced the challenge of making individualized suggestions that take into account user usage patterns and emotions. In particular, there was a lack of means to accurately grasp users' feelings about energy consumption and provide advice accordingly, which prevented us from increasing user satisfaction.

[0193] 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.

[0194] In this invention, the server includes data collection means for acquiring energy consumption data, emotion analysis means for analyzing voice or text data to identify the user's emotions, and price plan optimization means for proposing the most suitable price plan to the user. This makes it possible to provide an optimal energy consumption strategy that takes into account the user's emotional state, thereby not only improving user satisfaction but also achieving efficient use of energy resources.

[0195] "Energy consumption data" refers to information about energy usage, and it serves as fundamental data for analyzing usage patterns and anomalies.

[0196] "Data collection means" refers to a device or system for generating, acquiring, or recording energy consumption data.

[0197] An "anomaly detection means" is an information processing device or algorithm for identifying unusual movements in energy consumption patterns and issuing warnings.

[0198] A "pricing plan optimization method" is a processing method that identifies economically advantageous pricing plans based on user consumption data and presents them as options.

[0199] A "price fluctuation prediction tool" is a device or software used to analyze market data and predict future trends in energy prices.

[0200] "Emotion analysis means" refers to information processing means that use a user's voice or text data to identify emotions from its content.

[0201] An "emotional response system" is a system that provides users with personalized energy consumption advice based on the results of emotional analysis.

[0202] An "energy measurement device" is a device that measures energy consumption in real time and outputs it as data.

[0203] "Computational methods" refer to mathematical and statistical tools used for data analysis and anomaly detection, and include machine learning algorithms and other numerical analysis methods.

[0204] The system according to this invention enables efficient energy use in smart cities by effectively managing energy consumption data and providing advice based on the user's emotions. The server acquires energy consumption data in real time from an energy measuring device and uses this data to analyze consumption patterns. This allows for data-driven anomaly detection and notifications to the user as needed.

[0205] Furthermore, the server helps users select the optimal long-term pricing plan by using market trend data to predict future price fluctuations. Sentiment analysis tools analyze the user's voice and text to identify their emotional state, providing flexible feedback on energy usage. Specifically, it utilizes generative AI models to generate personalized advice tailored to the user's emotions, thereby improving user satisfaction.

[0206] If a user expresses dissatisfaction with their electricity usage through the interface, for example, by saying "The air conditioning bill this summer is too high!", the emotion analysis engine identifies this as dissatisfaction and transmits that information to the server. Based on this data, the server sends appropriate energy-saving advice or suggestions for changing their plan to the user's terminal.

[0207] An example of a prompt message is: "When the user enters voice data: 'The electricity bill for the air conditioner is too high!', detect the user's stress level and generate the most appropriate energy-saving advice."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server acquires energy consumption data in real time from energy measurement devices. The input is data transmitted from the energy measurement devices, which is stored in a time-series database. The output is the stored consumption data. This provides the foundational data for identifying consumption patterns and detecting anomalies.

[0211] Step 2:

[0212] The server processes stored energy data and analyzes consumption patterns. The input is consumption data in a database, and machine learning algorithms are used to detect anomalies. If an anomaly is detected as a result of this data processing, an alert is generated. The output is information indicating whether an anomaly occurred.

[0213] Step 3:

[0214] The server analyzes market data to suggest the most suitable pricing plan to the user. Inputs are the user's consumption patterns and current market data, and the analysis identifies the optimal plan. Output is the recommended plan information provided to the user.

[0215] Step 4:

[0216] When a user sends feedback via voice or text, the device transfers that data to the server. The input is the user's feedback data, and the user's emotions are identified by sentiment analysis. The output is data about the user's emotional state.

[0217] Step 5:

[0218] The server uses a generative AI model to generate personalized energy usage advice based on the user's emotional state. The input is emotional data obtained from an emotion analysis device, and the generated advice is calculated. The output is specific advice information for the user. This information is sent to the terminal and fed back to the user. In this step, the prompt message is set to "Represent the user's emotional state and generate energy-saving advice."

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] The energy management system according to the present invention has a configuration for collecting energy consumption data and proposing the optimal pricing plan to the user. This system consists of three main components: a server, a terminal, and a user. The roles of each are described below.

[0236] First, the server receives energy consumption data in real time from smart meters and other sources and stores it in a database. The data includes electricity and gas usage amounts and timestamps. This allows for the understanding of each user's consumption patterns.

[0237] Next, the server uses machine learning algorithms to detect anomalies based on the stored data. This involves comparing the data with past usage patterns and identifying any consumption that differs from normal as an anomaly. For example, it can issue an alert if power consumption suddenly increases during the night.

[0238] The server also notifies the user via the terminal when it detects an anomaly. The notification includes the nature of the anomaly and recommended countermeasures. Furthermore, the server compares the collected energy consumption data with the electricity company's pricing plans and suggests the most suitable plan for the user. This allows the user to reduce unnecessary costs.

[0239] The device displays notifications from the server and suggested pricing plans to the user. Based on this information, the user can review their energy usage. For example, they can take measures such as changing the time of day they use electricity to avoid peak charges.

[0240] Furthermore, the server analyzes market energy price trends and predicts future price fluctuations. This information is also provided to the user via the terminal, allowing the user to plan their energy usage strategy based on this information.

[0241] As a concrete example, when this system is applied to household energy management, the server records power consumption data daily and uses an anomaly detection module to send necessary warnings to the user in a timely manner. Furthermore, by optimizing electricity rate plans, users can reduce their monthly electricity bills. In this way, the energy management system helps users use energy efficiently and improve cost-effectiveness.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server periodically receives electricity and gas consumption data from smart meters and other IoT devices. The data is recorded as electricity usage and gas usage, along with a timestamp.

[0245] Step 2:

[0246] The server stores the received data in a database. This data is stored as time-series data and used to analyze consumption patterns.

[0247] Step 3:

[0248] The server activates an anomaly detection module based on the stored data. It utilizes machine learning models to execute algorithms that detect deviations from normal consumption patterns.

[0249] Step 4:

[0250] If an anomaly is detected, the server generates an alert and sends a notification to the user via their terminal. This notification includes details of the anomaly and recommended actions to take.

[0251] Step 5:

[0252] The server collects pricing plan data from multiple power companies and calculates the optimal pricing plan by comparing it with the user's consumption data.

[0253] Step 6:

[0254] If an optimal pricing plan is found, the server will present that information to the user via the terminal. This suggestion will include a comparison with the current plan and an estimated amount of savings.

[0255] Step 7:

[0256] The server investigates price trends in the energy market and, based on this, runs a price fluctuation prediction module. Using machine learning, it predicts future price fluctuations from historical data.

[0257] Step 8:

[0258] Price fluctuation forecasts are provided to users via their devices. Users can use this information to adjust and plan their energy consumption. By developing consumption strategies based on these forecasts, it is possible to optimize costs.

[0259] (Example 1)

[0260] 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".

[0261] With increasing energy consumption, there is a growing need to propose optimal pricing plans to individual users and improve cost efficiency. However, existing technologies are insufficient for accurately analyzing consumption patterns and detecting anomalies. Furthermore, predicting price fluctuations in the energy market and providing users with strategic energy usage suggestions based on those predictions is currently difficult. It is necessary to solve these problems and improve cost reduction and energy usage optimization for users.

[0262] 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.

[0263] In this invention, the server includes data collection means for acquiring energy consumption data, anomaly detection means for analyzing consumption patterns based on the acquired data and detecting anomalies, and price fluctuation prediction means for predicting future price trends based on market price information. This enables anomaly detection in energy consumption and the proposal of cost-effective pricing plans, as well as strategic optimization of energy use based on market trends.

[0264] "Energy consumption data" refers to information that shows the amount of energy used, such as electricity and gas, and the duration of that use.

[0265] A "data collection method" is a system for acquiring energy consumption data and storing it in a database or similar.

[0266] An "anomaly detection method" refers to a process or technology for identifying unusual energy usage patterns based on consumption patterns.

[0267] "Rate plan optimization methods" refer to methods for suggesting the most economical rate plan based on the user's energy consumption data.

[0268] A "price fluctuation prediction method" is a technology that analyzes market price information and predicts future price fluctuations.

[0269] "Information notification means" refers to devices or methods that notify users of information such as anomaly detection results or proposed pricing plans.

[0270] A "strategy presentation method" is a method of analyzing electricity consumption patterns and pricing structures to propose the optimal energy usage strategy to users.

[0271] An "electronic meter" is a measuring device that can measure energy consumption and transmit that data remotely.

[0272] "Numerical analysis methods" are techniques that use mathematical and statistical methods to analyze data.

[0273] The embodiments for carrying out the present invention are described below.

[0274] The energy management system consists of three main components: users, servers, and terminals.

[0275] The server acquires energy consumption data in real time from measuring devices such as electronic meters. The acquired data is stored in a database, and then anomalies are identified by comparing it with past consumption patterns using an anomaly detection method. Numerical analysis methods are used for anomaly detection, enabling rapid detection of fraudulent consumption. In addition, the server uses a pricing plan optimization method to analyze the user's consumption data and market pricing information to propose the optimal pricing plan. Furthermore, a price fluctuation prediction method predicts market price trends, allowing for forecasting of future energy costs.

[0276] The terminal's role is to present information notifications sent from the server to the user. Specifically, it displays information such as anomaly detection results, proposed pricing plans, and usage strategies based on price trend forecasts. Based on the information provided by the terminal, users can review their power usage patterns and strive to reduce energy costs.

[0277] Users can optimize their daily energy usage by referring to the various information they receive through this system. For example, by adjusting the time of day they use electricity according to the suggested pricing plan, they can reduce their electricity bill.

[0278] As a concrete example, if this system is installed in a home, the server will manage daily energy consumption, and if an anomaly is detected, the user will be quickly notified via a terminal. In addition, cost optimization will enable the expected reduction in electricity bills. In this way, the efficiency of the user's energy use will be improved.

[0279] When using a generative AI model, you can obtain more detailed information about processing methods and theories by entering a prompt such as, "Please explain the algorithm that performs anomaly detection and rate optimization based on energy usage data."

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The server retrieves energy consumption data from the electronic meter in real time. The input includes the usage amounts of electricity and gas and their timestamps. This data is first saved in the database. As a specific operation, the server accesses the electronic meter via the network and extracts data using the API. As its output, a time-series consumption dataset for each user is obtained.

[0283] Step 2:

[0284] The server performs anomaly detection using the collected energy consumption data. As the input, the time-series consumption data obtained in Step 1 is used. The server compares with the past normal consumption patterns and identifies anomalies by numerical analysis methods. As a specific operation, a machine learning algorithm analyzes the real-time data and generates an alert if there is an improper pattern. As its output, the types of detected anomalies and the details of the consumption data associated with them are obtained.

[0285] Step 3:

[0286] When an anomaly is detected, the server sends a notification to the terminal. As the input, the details of the anomaly detected in Step 2 are used. As a specific operation, the server uses the notification protocol to deliver an alert to the terminal and forms a message including the type of anomaly and the recommended countermeasures. As its output, an immediate alert notification is included in the user interface displayed on the terminal.

[0287] Step 4:

[0288] The server optimizes pricing plans. Inputs include user energy consumption data and pricing plan information obtained from the market. The server uses pricing plan optimization tools to compare and analyze the pricing structure of each plan against the user's consumption patterns. Specific operations include executing a cost comparison algorithm for all pricing plans. The output generates a proposal for the most suitable pricing plan for the user.

[0289] Step 5:

[0290] The server analyzes market price information and predicts future energy cost trends. Its inputs include market price data and historical price fluctuation information. Specifically, it uses time series analysis to model and predict future price fluctuations. Its output includes strategic energy use suggestions based on the predicted price fluctuations.

[0291] Step 6:

[0292] The terminal presents information from the server to the user. Inputs include anomaly detection results, proposed pricing plans, and future price forecasts. Specifically, the terminal displays the information in an intuitively understandable format through a user interface. The output includes user-operable information displays, allowing the user to make decisions regarding energy use.

[0293] (Application Example 1)

[0294] 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."

[0295] In today's society, where energy efficiency and cost reduction are paramount, the challenge lies in providing a system that can monitor energy consumption in real time, detect anomalies, and propose optimal pricing plans. Furthermore, there is a need to create an environment where users can intuitively understand their energy usage and respond immediately when anomalies occur.

[0296] 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.

[0297] In this invention, the server includes an information gathering means for acquiring energy consumption information, an anomaly detection means for analyzing consumption patterns based on the acquired information and detecting anomalies, a pricing plan optimization means for proposing the most suitable pricing plan to the user, a price fluctuation prediction means for predicting future price fluctuations based on market price information, and a user terminal that displays the user's energy consumption status in real time and notifies the user when an anomaly occurs. This enables real-time optimization of energy consumption and cost reduction, as well as a rapid response when an anomaly occurs.

[0298] "Energy consumption information" refers to information collected on the amount of electricity, gas, and other energy sources used, as well as related data.

[0299] "Information gathering means" refers to devices or systems used to acquire energy consumption information.

[0300] "Consumption patterns" refer to usage trends and behaviors derived from past energy usage data.

[0301] An "anomaly detection method" is a mechanism for detecting energy usage that deviates from normal consumption patterns.

[0302] "Rate plan optimization methods" refer to functions and methods for proposing the most economical energy rate plan to the user.

[0303] "Price information" refers to data on rates and prices in the energy market.

[0304] "Price fluctuation prediction methods" refer to techniques and mechanisms for analyzing market price information and predicting future price fluctuations.

[0305] The "user terminal" refers to a device or apparatus through which a user receives information.

[0306] "Real-time" refers to the concept that information is acquired and processed almost simultaneously.

[0307] "Notification" refers to an act or mechanism of informing a user of information.

[0308] The system for implementing this invention consists of three main components: a server, a terminal, and a user. The server is equipped with information collection means for acquiring energy consumption information in real time, and accumulates consumption data such as electricity and gas in the server's database through measuring devices. Based on this accumulated data, the consumption pattern is analyzed, and by using a machine learning algorithm, anomalies deviating from past consumption trends are detected. For example, if the power consumption increases during a time period different from normal household appliance use, it can be regarded as an anomaly.

[0309] When an anomaly is detected, the server sends a notification to the terminal owned by the user. The terminal displays this information in an easy-to-understand manner for the user and issues an alert if necessary, thereby creating a state where the user can respond immediately. In addition, the server also acquires price information from the energy market and executes an algorithm for proposing an optimal tariff plan to the user. This enables energy consumption with reduced unnecessary costs.

[0310] Furthermore, this system analyzes the trends of energy prices in the market and predicts future price fluctuations, thereby assisting the user in formulating a usage plan in anticipation of future increases in electricity tariffs.

[0311] As a concrete example, in one household, a smartphone app immediately displays a notification if it detects abnormal power consumption at night. At that point, the user can review their use of home appliances and use that information to help reduce costs. As an example of a "generated AI model and prompt message," a possible prompt message would be, "Based on energy consumption data within the smart city, create a power consumption peak forecast alert for this weekend and notify the user."

[0312] Thus, the main aim of this invention is to achieve both increased energy efficiency and a more comfortable energy experience for users.

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server acquires energy consumption information through measuring instruments. It receives electricity and gas usage data and their timestamps as input and stores them in a database. During this process, the data is collected and formatted and optimized for storage in a centralized storage system.

[0316] Step 2:

[0317] The server uses machine learning algorithms to detect anomalies based on accumulated energy consumption data. It takes historical consumption pattern data as input and generates output indicating whether an anomaly exists and its details. Specifically, this involves identifying data points that deviate from normal consumption and marking them as anomalies.

[0318] Step 3:

[0319] When an anomaly is detected, the server generates a notification for the terminal. It receives the anomaly detection result as input and creates user-facing alert information as output. This notification includes details of the anomaly and recommended actions, and this information is sent to the user's device.

[0320] Step 4:

[0321] The server runs a pricing plan optimization algorithm and proposes a suitable pricing plan for the user. It uses energy consumption data and market price information as input and generates the optimal pricing plan as output. In this step, multiple plans are evaluated and the best one is selected based on the user's past usage patterns and current market conditions.

[0322] Step 5:

[0323] The server analyzes energy price trends and predicts future price fluctuations. It uses market price fluctuation data as input and presents predicted price trends as output. Specifically, it uses mathematical models to simulate future price scenarios and transmits the results to the terminal.

[0324] Step 6:

[0325] The terminal displays information received from the server to the user. It receives notification and price prediction information as input and provides information that the user can visually understand as output. During this process, the user interface is updated and notification pop-ups are displayed to encourage changes in user behavior.

[0326] 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.

[0327] The energy management system according to the present invention combines functions for collecting energy consumption data, analyzing consumption patterns, detecting anomalies, optimizing pricing plans, and predicting price fluctuations with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0328] First, the server receives energy consumption data from smart meters in real time and stores it in a database as time-series data. Based on this data, the server uses machine learning algorithms to detect anomalies. When an anomaly is detected, the server immediately generates an alert and notifies the user through their terminal.

[0329] In the pricing plan optimization method, the server collects various electricity pricing plans and compares them with the user's consumption data to suggest the optimal plan. This information is presented to the user via their terminal, supporting them in making the most economical choice. Furthermore, by analyzing price trends in the energy market, future price fluctuations are predicted. These price fluctuation predictions are provided to the user as information that helps optimize their energy usage plan.

[0330] The newly integrated emotion engine analyzes user voice and text data to understand the user's emotional state in real time. For example, if a user expresses dissatisfaction with energy use, the emotion engine recognizes this and sends data to the server. As a result, the server can adjust consumption strategies based on the emotional data and provide personalized advice.

[0331] As a concrete example, suppose a user in a household expresses dissatisfaction with their electricity bill through a voice assistant. At this time, the emotion engine analyzes the user's tone of voice and words to detect stress and dissatisfaction. This information is sent to a server, which then provides appropriate feedback to the user via the device, considering further energy-saving advice and suggestions for future rate plan changes. In this way, a system is realized that can manage energy consumption more flexibly according to the user's emotional state.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server receives electricity and gas consumption data from smart meters in real time. This data is time-stamped with accurate information, along with the amount of electricity and gas used.

[0335] Step 2:

[0336] The server stores the received data in a database and uses machine learning algorithms to analyze past consumption patterns. This analysis can detect outliers that deviate from normal consumption.

[0337] Step 3:

[0338] When an anomaly is detected, the server issues an alert and promptly notifies the user via their terminal. The notification includes the nature of the anomaly and recommended actions to take.

[0339] Step 4:

[0340] The server collects electricity rate plans offered from the market and selects the most economical plan by comparing it with the user's consumption data. This result is then presented to the user via the terminal.

[0341] Step 5:

[0342] The server incorporates external market analysis data and uses algorithms to predict future price trends. It can identify peak and undervalued periods for energy.

[0343] Step 6:

[0344] The price fluctuation prediction results are provided to users via their devices and used as a reference for developing optimal energy usage strategies.

[0345] Step 7:

[0346] Users express their emotions through voice and text input. This input data is analyzed by an emotion engine to recognize the user's emotional state.

[0347] Step 8:

[0348] The server, upon receiving output from the emotion engine, adjusts energy consumption suggestions based on the emotional data. In particular, if the user indicates stress or dissatisfaction, the system adjusts to provide specific advice in response.

[0349] Step 9:

[0350] Adjustments based on emotional data are delivered to the user via their device, promoting consumer behavior that takes user satisfaction into consideration.

[0351] (Example 2)

[0352] 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".

[0353] Conventional energy management systems provide mechanisms for detecting anomalies in energy consumption and optimizing pricing plans, but they have the drawback of not being able to optimize flexible energy usage strategies that take into account the emotional state of users. Furthermore, predicting and utilizing fluctuations in energy market prices has been difficult. Therefore, this invention aims to provide more personalized energy management that takes into account the emotional state of users.

[0354] 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.

[0355] In this invention, the server includes information gathering means for acquiring energy usage information, anomaly identification means for analyzing usage trends and identifying anomalies based on the acquired information, and fluctuation prediction means for predicting future price fluctuations based on market price information. This makes it possible to adjust the energy usage strategy to be personalized based on the user's emotional state.

[0356] "Energy usage information" refers to data on the consumption of electricity, gas, water, etc., in homes and facilities.

[0357] "Information gathering means" refers to devices or programs used to collect energy usage information.

[0358] "Usage trends" refer to patterns or tendencies that show how energy is consumed.

[0359] "Analysis" is the process of examining data in detail to clarify its meaning and structure.

[0360] "Anomaly identification means" refers to a device or program for detecting phenomena that deviate from normal usage patterns.

[0361] A "fee agreement" refers to an arrangement regarding fees that consumers make with service providers.

[0362] "Contract optimization means" refers to a device or program for selecting the most advantageous pricing contract for the consumer.

[0363] "Price information" refers to data on prices in the energy market.

[0364] "Fluctuation prediction means" refers to a device or program for predicting future price fluctuations.

[0365] "Emotional state" refers to the state and changes in the user's emotions.

[0366] "Emotional analysis means" refers to a device or program used to analyze a user's emotions and understand their state.

[0367] A "management system" refers to a system for comprehensive management, including the collection, analysis, and optimization of energy usage information.

[0368] This energy management system is a comprehensive system for collecting, analyzing, and optimizing energy usage information. The main components of the system are information gathering means, anomaly identification means, contract optimization means, fluctuation prediction means, and sentiment analysis means.

[0369] The server collects energy usage information in real time via measuring devices. The smart meters used as measuring devices have the capability to transmit information over the internet. This collected data is stored in a database and used for later analysis.

[0370] Anomaly detection uses an automated learning algorithm executed on the server. This algorithm employs machine learning libraries such as Scikit-learn and TensorFlow. The server analyzes time-series data of energy use and detects anomalous usage patterns.

[0371] The device receives notifications from the server and provides information to the user visually. For example, if an anomaly is detected, the device sends a push notification to the user and displays detailed information.

[0372] Contract optimization calculates the optimal pricing contract based on market price information and usage patterns collected by the server. Here, pricing information is obtained using the Requests library, and analysis is performed using an optimization algorithm based on linear programming. The optimization results are presented to the user via the terminal.

[0373] As a means of sentiment analysis, the server uses the Google Cloud Speech-to-Text API to analyze the user's voice data. This analysis allows for real-time understanding of the user's emotional state and the generation of personalized feedback and advice.

[0374] For example, if a user tells a voice assistant, "I'm unhappy with my recent electricity bill," the emotion analysis system analyzes that emotion and sends the results to a server. Based on the results, the server generates appropriate advice and suggests it to the user through the device.

[0375] An example of a prompt sentence to be fed into a generative AI model is, "Please tell me how to review my household energy consumption and save more than $100."

[0376] In this way, the system can efficiently manage the user's energy usage and provide interactive feedback that takes their emotional state into account.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The server acquires energy usage information in real time via measuring devices. The input is raw power consumption data provided by smart meters. This data is stored in an SQL database and converted into a format usable for later analysis. Specifically, the server opens a database connection and retrieves and stores data via a RESTful API.

[0380] Step 2:

[0381] The server analyzes energy usage trends using energy usage information stored in a database and identifies anomalies by comparing them to baseline values. The input is power consumption data organized as a time series. The Scikit-learn Isolation Forest model is used to identify anomalous data points and output them as a report. Specifically, the server executes a Python script and logs any anomalies it finds.

[0382] Step 3:

[0383] The server notifies the device that an anomaly has been detected. The input is an anomaly report, which is the output of the anomaly detection algorithm. This information is sent to the device, and an alert is displayed to the user. Specifically, the server sends the notification via Firebase Cloud Messaging, and the device displays the alert on its user interface.

[0384] Step 4:

[0385] The server retrieves energy market price information from an external database and predicts future price fluctuations. The input is price data obtained from the internet. It performs time-series forecasting using the Prophet library and outputs the forecast results. Specifically, the server communicates via API to retrieve market information and applies it to the model.

[0386] Step 5:

[0387] The terminal presents the user with optimized pricing contract information sent from the server. The input is proposed pricing contract data generated by the server. This is visually displayed in the user interface, providing options. Specifically, the terminal uses technologies to display information in graph and table formats to show the proposals to the user.

[0388] Step 6:

[0389] The server receives voice commands from the user and inputs them into an emotion analysis algorithm to determine the user's emotional state. The input is voice data obtained from a voice assistant. The voice is converted to text using the Google Cloud Speech-to-Text API, and that text is analyzed using the NLTK library. The output is the detected emotional state. Specifically, the server receives the voice stream and performs text conversion and emotion analysis in real time.

[0390] Step 7:

[0391] The server uses a generative AI model based on the analysis results to generate personalized feedback and advice for the user. The input is sentiment data from a sentiment analysis algorithm. It generates prompt sentences and sends the advice to the terminal. Specifically, the server packages the generated prompts in JSON format and sends them to the terminal to notify the user.

[0392] (Application Example 2)

[0393] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0394] Efficient energy management is essential in modern society, but conventional systems have faced the challenge of making individualized suggestions that take into account user usage patterns and emotions. In particular, there was a lack of means to accurately grasp users' feelings about energy consumption and provide advice accordingly, which prevented us from increasing user satisfaction.

[0395] 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.

[0396] In this invention, the server includes data collection means for acquiring energy consumption data, emotion analysis means for analyzing voice or text data to identify the user's emotions, and price plan optimization means for proposing the most suitable price plan to the user. This makes it possible to provide an optimal energy consumption strategy that takes into account the user's emotional state, thereby not only improving user satisfaction but also achieving efficient use of energy resources.

[0397] "Energy consumption data" refers to information about energy usage, and it serves as fundamental data for analyzing usage patterns and anomalies.

[0398] "Data collection means" refers to a device or system for generating, acquiring, or recording energy consumption data.

[0399] An "anomaly detection means" is an information processing device or algorithm for identifying unusual movements in energy consumption patterns and issuing warnings.

[0400] A "pricing plan optimization method" is a processing method that identifies economically advantageous pricing plans based on user consumption data and presents them as options.

[0401] A "price fluctuation prediction tool" is a device or software used to analyze market data and predict future trends in energy prices.

[0402] "Emotion analysis means" refers to information processing means that use a user's voice or text data to identify emotions from its content.

[0403] An "emotional response system" is a system that provides users with personalized energy consumption advice based on the results of emotional analysis.

[0404] An "energy measurement device" is a device that measures energy consumption in real time and outputs it as data.

[0405] "Computational methods" refer to mathematical and statistical tools used for data analysis and anomaly detection, and include machine learning algorithms and other numerical analysis methods.

[0406] The system according to this invention enables efficient energy use in smart cities by effectively managing energy consumption data and providing advice based on the user's emotions. The server acquires energy consumption data in real time from an energy measuring device and uses this data to analyze consumption patterns. This allows for data-driven anomaly detection and notifications to the user as needed.

[0407] Furthermore, the server helps users select the optimal long-term pricing plan by using market trend data to predict future price fluctuations. Sentiment analysis tools analyze the user's voice and text to identify their emotional state, providing flexible feedback on energy usage. Specifically, it utilizes generative AI models to generate personalized advice tailored to the user's emotions, thereby improving user satisfaction.

[0408] If a user expresses dissatisfaction with their electricity usage through the interface, for example, by saying "The air conditioning bill this summer is too high!", the emotion analysis engine identifies this as dissatisfaction and transmits that information to the server. Based on this data, the server sends appropriate energy-saving advice or suggestions for changing their plan to the user's terminal.

[0409] An example of a prompt message is: "When the user enters voice data: 'The electricity bill for the air conditioner is too high!', detect the user's stress level and generate the most appropriate energy-saving advice."

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The server acquires energy consumption data in real time from energy measurement devices. The input is data transmitted from the energy measurement devices, which is stored in a time-series database. The output is the stored consumption data. This provides the foundational data for identifying consumption patterns and detecting anomalies.

[0413] Step 2:

[0414] The server processes stored energy data and analyzes consumption patterns. The input is consumption data in a database, and machine learning algorithms are used to detect anomalies. If an anomaly is detected as a result of this data processing, an alert is generated. The output is information indicating whether an anomaly occurred.

[0415] Step 3:

[0416] The server analyzes market data to suggest the most suitable pricing plan to the user. Inputs are the user's consumption patterns and current market data, and the analysis identifies the optimal plan. Output is the recommended plan information provided to the user.

[0417] Step 4:

[0418] When a user sends feedback via voice or text, the device transfers that data to the server. The input is the user's feedback data, and the user's emotions are identified by sentiment analysis. The output is data about the user's emotional state.

[0419] Step 5:

[0420] The server uses a generative AI model to generate personalized energy usage advice based on the user's emotional state. The input is emotional data obtained from an emotion analysis device, and the generated advice is calculated. The output is specific advice information for the user. This information is sent to the terminal and fed back to the user. In this step, the prompt message is set to "Represent the user's emotional state and generate energy-saving advice."

[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 management system according to the present invention has a configuration for collecting energy consumption data and proposing the optimal pricing plan to the user. This system consists of three main components: a server, a terminal, and a user. The roles of each are described below.

[0438] First, the server receives energy consumption data in real time from smart meters and other sources and stores it in a database. The data includes electricity and gas usage amounts and timestamps. This allows for the understanding of each user's consumption patterns.

[0439] Next, the server uses machine learning algorithms to detect anomalies based on the stored data. This involves comparing the data with past usage patterns and identifying any consumption that differs from normal as an anomaly. For example, it can issue an alert if power consumption suddenly increases during the night.

[0440] The server also notifies the user via the terminal when it detects an anomaly. The notification includes the nature of the anomaly and recommended countermeasures. Furthermore, the server compares the collected energy consumption data with the electricity company's pricing plans and suggests the most suitable plan for the user. This allows the user to reduce unnecessary costs.

[0441] The device displays notifications from the server and suggested pricing plans to the user. Based on this information, the user can review their energy usage. For example, they can take measures such as changing the time of day they use electricity to avoid peak charges.

[0442] Furthermore, the server analyzes market energy price trends and predicts future price fluctuations. This information is also provided to the user via the terminal, allowing the user to plan their energy usage strategy based on this information.

[0443] As a concrete example, when this system is applied to household energy management, the server records power consumption data daily and uses an anomaly detection module to send necessary warnings to the user in a timely manner. Furthermore, by optimizing electricity rate plans, users can reduce their monthly electricity bills. In this way, the energy management system helps users use energy efficiently and improve cost-effectiveness.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The server periodically receives electricity and gas consumption data from smart meters and other IoT devices. The data is recorded as electricity usage and gas usage, along with a timestamp.

[0447] Step 2:

[0448] The server stores the received data in a database. This data is stored as time-series data and used to analyze consumption patterns.

[0449] Step 3:

[0450] The server activates an anomaly detection module based on the stored data. It utilizes machine learning models to execute algorithms that detect deviations from normal consumption patterns.

[0451] Step 4:

[0452] If an anomaly is detected, the server generates an alert and sends a notification to the user via their terminal. This notification includes details of the anomaly and recommended actions to take.

[0453] Step 5:

[0454] The server collects pricing plan data from multiple power companies and calculates the optimal pricing plan by comparing it with the user's consumption data.

[0455] Step 6:

[0456] If an optimal pricing plan is found, the server will present that information to the user via the terminal. This suggestion will include a comparison with the current plan and an estimated amount of savings.

[0457] Step 7:

[0458] The server investigates price trends in the energy market and, based on this, runs a price fluctuation prediction module. Using machine learning, it predicts future price fluctuations from historical data.

[0459] Step 8:

[0460] Price fluctuation forecasts are provided to users via their devices. Users can use this information to adjust and plan their energy consumption. By developing consumption strategies based on these forecasts, it is possible to optimize costs.

[0461] (Example 1)

[0462] 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."

[0463] With increasing energy consumption, there is a growing need to propose optimal pricing plans to individual users and improve cost efficiency. However, existing technologies are insufficient for accurately analyzing consumption patterns and detecting anomalies. Furthermore, predicting price fluctuations in the energy market and providing users with strategic energy usage suggestions based on those predictions is currently difficult. It is necessary to solve these problems and improve cost reduction and energy usage optimization for users.

[0464] 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.

[0465] In this invention, the server includes data collection means for acquiring energy consumption data, anomaly detection means for analyzing consumption patterns based on the acquired data and detecting anomalies, and price fluctuation prediction means for predicting future price trends based on market price information. This enables anomaly detection in energy consumption and the proposal of cost-effective pricing plans, as well as strategic optimization of energy use based on market trends.

[0466] "Energy consumption data" refers to information that shows the amount of energy used, such as electricity and gas, and the duration of that use.

[0467] A "data collection method" is a system for acquiring energy consumption data and storing it in a database or similar.

[0468] An "anomaly detection method" refers to a process or technology for identifying unusual energy usage patterns based on consumption patterns.

[0469] "Rate plan optimization methods" refer to methods for suggesting the most economical rate plan based on the user's energy consumption data.

[0470] A "price fluctuation prediction method" is a technology that analyzes market price information and predicts future price fluctuations.

[0471] "Information notification means" refers to devices or methods that notify users of information such as anomaly detection results or proposed pricing plans.

[0472] A "strategy presentation method" is a method of analyzing electricity consumption patterns and pricing structures to propose the optimal energy usage strategy to users.

[0473] An "electronic meter" is a measuring device that can measure energy consumption and transmit that data remotely.

[0474] "Numerical analysis methods" are techniques that use mathematical and statistical methods to analyze data.

[0475] The embodiments for carrying out the present invention are described below.

[0476] The energy management system consists of three main components: users, servers, and terminals.

[0477] The server acquires energy consumption data in real time from measuring devices such as electronic meters. The acquired data is stored in a database, and then anomalies are identified by comparing it with past consumption patterns using an anomaly detection method. Numerical analysis methods are used for anomaly detection, enabling rapid detection of fraudulent consumption. In addition, the server uses a pricing plan optimization method to analyze the user's consumption data and market pricing information to propose the optimal pricing plan. Furthermore, a price fluctuation prediction method predicts market price trends, allowing for forecasting of future energy costs.

[0478] The terminal's role is to present information notifications sent from the server to the user. Specifically, it displays information such as anomaly detection results, proposed pricing plans, and usage strategies based on price trend forecasts. Based on the information provided by the terminal, users can review their power usage patterns and strive to reduce energy costs.

[0479] Users can optimize their daily energy usage by referring to the various information they receive through this system. For example, by adjusting the time of day they use electricity according to the suggested pricing plan, they can reduce their electricity bill.

[0480] As a concrete example, if this system is installed in a home, the server will manage daily energy consumption, and if an anomaly is detected, the user will be quickly notified via a terminal. In addition, cost optimization will enable the expected reduction in electricity bills. In this way, the efficiency of the user's energy use will be improved.

[0481] When using a generative AI model, you can obtain more detailed information about processing methods and theories by entering a prompt such as, "Please explain the algorithm that performs anomaly detection and rate optimization based on energy usage data."

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The server acquires energy consumption data in real time from electronic meters. Input includes electricity and gas usage and their timestamps. This data is first stored in a database. Specifically, the server accesses the electronic meters via the network and retrieves the data using an API. The output is a time-series consumption dataset for each user.

[0485] Step 2:

[0486] The server uses collected energy consumption data to detect anomalies. The input is the time-series consumption data obtained in step 1. The server compares this data with past normal consumption patterns and identifies anomalies using numerical analysis techniques. Specifically, a machine learning algorithm analyzes real-time data and generates an alert if an abnormal pattern is detected. The output includes the type of anomaly detected and details of the associated consumption data.

[0487] Step 3:

[0488] When an anomaly is detected, the server sends a notification to the terminal. The input used is the details of the anomaly detected in step 2. Specifically, the server uses a notification protocol to deliver an alert to the terminal, forming a message that includes the type of anomaly and recommended actions. The output includes an immediate alert notification displayed on the user interface on the terminal.

[0489] Step 4:

[0490] The server optimizes pricing plans. Inputs include user energy consumption data and pricing plan information obtained from the market. The server uses pricing plan optimization tools to compare and analyze the pricing structure of each plan against the user's consumption patterns. Specific operations include executing a cost comparison algorithm for all pricing plans. The output generates a proposal for the most suitable pricing plan for the user.

[0491] Step 5:

[0492] The server analyzes market price information and predicts future energy cost trends. Its inputs include market price data and historical price fluctuation information. Specifically, it uses time series analysis to model and predict future price fluctuations. Its output includes strategic energy use suggestions based on the predicted price fluctuations.

[0493] Step 6:

[0494] The terminal presents information from the server to the user. Inputs include anomaly detection results, proposed pricing plans, and future price forecasts. Specifically, the terminal displays the information in an intuitively understandable format through a user interface. The output includes user-operable information displays, allowing the user to make decisions regarding energy use.

[0495] (Application Example 1)

[0496] 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."

[0497] In today's society, where energy efficiency and cost reduction are paramount, the challenge lies in providing a system that can monitor energy consumption in real time, detect anomalies, and propose optimal pricing plans. Furthermore, there is a need to create an environment where users can intuitively understand their energy usage and respond immediately when anomalies occur.

[0498] 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.

[0499] In this invention, the server includes an information gathering means for acquiring energy consumption information, an anomaly detection means for analyzing consumption patterns based on the acquired information and detecting anomalies, a pricing plan optimization means for proposing the most suitable pricing plan to the user, a price fluctuation prediction means for predicting future price fluctuations based on market price information, and a user terminal that displays the user's energy consumption status in real time and notifies the user when an anomaly occurs. This enables real-time optimization of energy consumption and cost reduction, as well as a rapid response when an anomaly occurs.

[0500] "Energy consumption information" refers to information collected on the amount of electricity, gas, and other energy sources used, as well as related data.

[0501] "Information gathering means" refers to devices or systems used to acquire energy consumption information.

[0502] "Consumption patterns" refer to usage trends and behaviors derived from past energy usage data.

[0503] An "anomaly detection method" is a mechanism for detecting energy usage that deviates from normal consumption patterns.

[0504] "Rate plan optimization methods" refer to functions and methods for proposing the most economical energy rate plan to the user.

[0505] "Price information" refers to data on rates and prices in the energy market.

[0506] "Price fluctuation prediction methods" refer to techniques and mechanisms for analyzing market price information and predicting future price fluctuations.

[0507] A "user terminal" refers to a device or apparatus used by a user to receive information.

[0508] "Real-time" is a concept that refers to information being acquired and processed almost simultaneously.

[0509] "Notification" refers to the act or mechanism of informing a user of information.

[0510] The system for implementing this invention consists of three main components: a server, a terminal, and a user. The server is equipped with information gathering means for acquiring energy consumption information in real time and stores consumption data such as electricity and gas in the server's database through measuring instruments. Based on this stored data, the system analyzes consumption patterns and uses machine learning algorithms to detect anomalies that deviate from past consumption trends. For example, if electricity consumption increases at a time different from the normal use of household appliances, this can be detected as an anomaly.

[0511] When an anomaly is detected, the server sends a notification to the user's device. The device displays this information clearly to the user and issues alerts as needed, enabling the user to take immediate action. The server also obtains price information from the energy market and runs an algorithm to suggest the most suitable pricing plan for the user. This makes it possible to reduce unnecessary energy consumption costs.

[0512] Furthermore, this system analyzes market energy price trends and predicts future price fluctuations, helping users create usage plans that anticipate future increases in electricity prices.

[0513] As a concrete example, in one household, a smartphone app immediately displays a notification if it detects abnormal power consumption at night. At that point, the user can review their use of home appliances and use that information to help reduce costs. As an example of a "generated AI model and prompt message," a possible prompt message would be, "Based on energy consumption data within the smart city, create a power consumption peak forecast alert for this weekend and notify the user."

[0514] Thus, the main aim of this invention is to achieve both increased energy efficiency and a more comfortable energy experience for users.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The server acquires energy consumption information through measuring instruments. It receives electricity and gas usage data and their timestamps as input and stores them in a database. During this process, the data is collected and formatted and optimized for storage in a centralized storage system.

[0518] Step 2:

[0519] The server uses machine learning algorithms to detect anomalies based on accumulated energy consumption data. It takes historical consumption pattern data as input and generates output indicating whether an anomaly exists and its details. Specifically, this involves identifying data points that deviate from normal consumption and marking them as anomalies.

[0520] Step 3:

[0521] When an anomaly is detected, the server generates a notification for the terminal. It receives the anomaly detection result as input and creates user-facing alert information as output. This notification includes details of the anomaly and recommended actions, and this information is sent to the user's device.

[0522] Step 4:

[0523] The server runs a pricing plan optimization algorithm and proposes a suitable pricing plan for the user. It uses energy consumption data and market price information as input and generates the optimal pricing plan as output. In this step, multiple plans are evaluated and the best one is selected based on the user's past usage patterns and current market conditions.

[0524] Step 5:

[0525] The server analyzes energy price trends and predicts future price fluctuations. It uses market price fluctuation data as input and presents predicted price trends as output. Specifically, it uses mathematical models to simulate future price scenarios and transmits the results to the terminal.

[0526] Step 6:

[0527] The terminal displays information received from the server to the user. It receives notification and price prediction information as input and provides information that the user can visually understand as output. During this process, the user interface is updated and notification pop-ups are displayed to encourage changes in user behavior.

[0528] 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.

[0529] The energy management system according to the present invention combines functions for collecting energy consumption data, analyzing consumption patterns, detecting anomalies, optimizing pricing plans, and predicting price fluctuations with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0530] First, the server receives energy consumption data from smart meters in real time and stores it in a database as time-series data. Based on this data, the server uses machine learning algorithms to detect anomalies. When an anomaly is detected, the server immediately generates an alert and notifies the user through their terminal.

[0531] In the pricing plan optimization method, the server collects various electricity pricing plans and compares them with the user's consumption data to suggest the optimal plan. This information is presented to the user via their terminal, supporting them in making the most economical choice. Furthermore, by analyzing price trends in the energy market, future price fluctuations are predicted. These price fluctuation predictions are provided to the user as information that helps optimize their energy usage plan.

[0532] The newly integrated emotion engine analyzes user voice and text data to understand the user's emotional state in real time. For example, if a user expresses dissatisfaction with energy use, the emotion engine recognizes this and sends data to the server. As a result, the server can adjust consumption strategies based on the emotional data and provide personalized advice.

[0533] As a concrete example, suppose a user in a household expresses dissatisfaction with their electricity bill through a voice assistant. At this time, the emotion engine analyzes the user's tone of voice and words to detect stress and dissatisfaction. This information is sent to a server, which then provides appropriate feedback to the user via the device, considering further energy-saving advice and suggestions for future rate plan changes. In this way, a system is realized that can manage energy consumption more flexibly according to the user's emotional state.

[0534] The following describes the processing flow.

[0535] Step 1:

[0536] The server receives electricity and gas consumption data from smart meters in real time. This data is time-stamped with accurate information, along with the amount of electricity and gas used.

[0537] Step 2:

[0538] The server stores the received data in a database and uses machine learning algorithms to analyze past consumption patterns. This analysis can detect outliers that deviate from normal consumption.

[0539] Step 3:

[0540] When an anomaly is detected, the server issues an alert and promptly notifies the user via their terminal. The notification includes the nature of the anomaly and recommended actions to take.

[0541] Step 4:

[0542] The server collects electricity rate plans offered from the market and selects the most economical plan by comparing it with the user's consumption data. This result is then presented to the user via the terminal.

[0543] Step 5:

[0544] The server incorporates external market analysis data and uses algorithms to predict future price trends. It can identify peak and undervalued periods for energy.

[0545] Step 6:

[0546] The price fluctuation prediction results are provided to users via their devices and used as a reference for developing optimal energy usage strategies.

[0547] Step 7:

[0548] Users express their emotions through voice and text input. This input data is analyzed by an emotion engine to recognize the user's emotional state.

[0549] Step 8:

[0550] The server, upon receiving output from the emotion engine, adjusts energy consumption suggestions based on the emotional data. In particular, if the user indicates stress or dissatisfaction, the system adjusts to provide specific advice in response.

[0551] Step 9:

[0552] Adjustments based on emotional data are delivered to the user via their device, promoting consumer behavior that takes user satisfaction into consideration.

[0553] (Example 2)

[0554] 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."

[0555] Conventional energy management systems provide mechanisms for detecting anomalies in energy consumption and optimizing pricing plans, but they have the drawback of not being able to optimize flexible energy usage strategies that take into account the emotional state of users. Furthermore, predicting and utilizing fluctuations in energy market prices has been difficult. Therefore, this invention aims to provide more personalized energy management that takes into account the emotional state of users.

[0556] 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.

[0557] In this invention, the server includes information gathering means for acquiring energy usage information, anomaly identification means for analyzing usage trends and identifying anomalies based on the acquired information, and fluctuation prediction means for predicting future price fluctuations based on market price information. This makes it possible to adjust the energy usage strategy to be personalized based on the user's emotional state.

[0558] "Energy usage information" refers to data on the consumption of electricity, gas, water, etc., in homes and facilities.

[0559] "Information gathering means" refers to devices or programs used to collect energy usage information.

[0560] "Usage trends" refer to patterns or tendencies that show how energy is consumed.

[0561] "Analysis" is the process of examining data in detail to clarify its meaning and structure.

[0562] "Anomaly identification means" refers to a device or program for detecting phenomena that deviate from normal usage patterns.

[0563] A "fee agreement" refers to an arrangement regarding fees that consumers make with service providers.

[0564] "Contract optimization means" refers to a device or program for selecting the most advantageous pricing contract for the consumer.

[0565] "Price information" refers to data on prices in the energy market.

[0566] "Fluctuation prediction means" refers to a device or program for predicting future price fluctuations.

[0567] "Emotional state" refers to the state and changes in the user's emotions.

[0568] "Emotional analysis means" refers to a device or program used to analyze a user's emotions and understand their state.

[0569] A "management system" refers to a system for comprehensive management, including the collection, analysis, and optimization of energy usage information.

[0570] This energy management system is a comprehensive system for collecting, analyzing, and optimizing energy usage information. The main components of the system are information gathering means, anomaly identification means, contract optimization means, fluctuation prediction means, and sentiment analysis means.

[0571] The server collects energy usage information in real time via measuring devices. The smart meters used as measuring devices have the capability to transmit information over the internet. This collected data is stored in a database and used for later analysis.

[0572] Anomaly detection uses an automated learning algorithm executed on the server. This algorithm employs machine learning libraries such as Scikit-learn and TensorFlow. The server analyzes time-series data of energy use and detects anomalous usage patterns.

[0573] The device receives notifications from the server and provides information to the user visually. For example, if an anomaly is detected, the device sends a push notification to the user and displays detailed information.

[0574] Contract optimization calculates the optimal pricing contract based on market price information and usage patterns collected by the server. Here, pricing information is obtained using the Requests library, and analysis is performed using an optimization algorithm based on linear programming. The optimization results are presented to the user via the terminal.

[0575] As a means of sentiment analysis, the server uses the Google Cloud Speech-to-Text API to analyze the user's voice data. This analysis allows for real-time understanding of the user's emotional state and the generation of personalized feedback and advice.

[0576] For example, if a user tells a voice assistant, "I'm unhappy with my recent electricity bill," the emotion analysis system analyzes that emotion and sends the results to a server. Based on the results, the server generates appropriate advice and suggests it to the user through the device.

[0577] An example of a prompt sentence to be fed into a generative AI model is, "Please tell me how to review my household energy consumption and save more than $100."

[0578] In this way, the system can efficiently manage the user's energy usage and provide interactive feedback that takes their emotional state into account.

[0579] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0580] Step 1:

[0581] The server acquires energy usage information in real time via measuring devices. The input is raw power consumption data provided by smart meters. This data is stored in an SQL database and converted into a format usable for later analysis. Specifically, the server opens a database connection and retrieves and stores data via a RESTful API.

[0582] Step 2:

[0583] The server analyzes energy usage trends using energy usage information stored in a database and identifies anomalies by comparing them to baseline values. The input is power consumption data organized as a time series. The Scikit-learn Isolation Forest model is used to identify anomalous data points and output them as a report. Specifically, the server executes a Python script and logs any anomalies it finds.

[0584] Step 3:

[0585] The server notifies the device that an anomaly has been detected. The input is an anomaly report, which is the output of the anomaly detection algorithm. This information is sent to the device, and an alert is displayed to the user. Specifically, the server sends the notification via Firebase Cloud Messaging, and the device displays the alert on its user interface.

[0586] Step 4:

[0587] The server retrieves energy market price information from an external database and predicts future price fluctuations. The input is price data obtained from the internet. It performs time-series forecasting using the Prophet library and outputs the forecast results. Specifically, the server communicates via API to retrieve market information and applies it to the model.

[0588] Step 5:

[0589] The terminal presents the user with optimized pricing contract information sent from the server. The input is proposed pricing contract data generated by the server. This is visually displayed in the user interface, providing options. Specifically, the terminal uses technologies to display information in graph and table formats to show the proposals to the user.

[0590] Step 6:

[0591] The server receives voice commands from the user and inputs them into an emotion analysis algorithm to determine the user's emotional state. The input is voice data obtained from a voice assistant. The voice is converted to text using the Google Cloud Speech-to-Text API, and that text is analyzed using the NLTK library. The output is the detected emotional state. Specifically, the server receives the voice stream and performs text conversion and emotion analysis in real time.

[0592] Step 7:

[0593] The server uses a generative AI model based on the analysis results to generate personalized feedback and advice for the user. The input is sentiment data from a sentiment analysis algorithm. It generates prompt sentences and sends the advice to the terminal. Specifically, the server packages the generated prompts in JSON format and sends them to the terminal to notify the user.

[0594] (Application Example 2)

[0595] 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."

[0596] Efficient energy management is essential in modern society, but conventional systems have faced the challenge of making individualized suggestions that take into account user usage patterns and emotions. In particular, there was a lack of means to accurately grasp users' feelings about energy consumption and provide advice accordingly, which prevented us from increasing user satisfaction.

[0597] 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.

[0598] In this invention, the server includes data collection means for acquiring energy consumption data, emotion analysis means for analyzing voice or text data to identify the user's emotions, and price plan optimization means for proposing the most suitable price plan to the user. This makes it possible to provide an optimal energy consumption strategy that takes into account the user's emotional state, thereby not only improving user satisfaction but also achieving efficient use of energy resources.

[0599] "Energy consumption data" refers to information about energy usage, and it serves as fundamental data for analyzing usage patterns and anomalies.

[0600] "Data collection means" refers to a device or system for generating, acquiring, or recording energy consumption data.

[0601] An "anomaly detection means" is an information processing device or algorithm for identifying unusual movements in energy consumption patterns and issuing warnings.

[0602] A "pricing plan optimization method" is a processing method that identifies economically advantageous pricing plans based on user consumption data and presents them as options.

[0603] A "price fluctuation prediction tool" is a device or software used to analyze market data and predict future trends in energy prices.

[0604] "Emotion analysis means" refers to information processing means that use a user's voice or text data to identify emotions from its content.

[0605] An "emotional response system" is a system that provides users with personalized energy consumption advice based on the results of emotional analysis.

[0606] An "energy measurement device" is a device that measures energy consumption in real time and outputs it as data.

[0607] "Computational methods" refer to mathematical and statistical tools used for data analysis and anomaly detection, and include machine learning algorithms and other numerical analysis methods.

[0608] The system according to this invention enables efficient energy use in smart cities by effectively managing energy consumption data and providing advice based on the user's emotions. The server acquires energy consumption data in real time from an energy measuring device and uses this data to analyze consumption patterns. This allows for data-driven anomaly detection and notifications to the user as needed.

[0609] Furthermore, the server helps users select the optimal long-term pricing plan by using market trend data to predict future price fluctuations. Sentiment analysis tools analyze the user's voice and text to identify their emotional state, providing flexible feedback on energy usage. Specifically, it utilizes generative AI models to generate personalized advice tailored to the user's emotions, thereby improving user satisfaction.

[0610] If a user expresses dissatisfaction with their electricity usage through the interface, for example, by saying "The air conditioning bill this summer is too high!", the emotion analysis engine identifies this as dissatisfaction and transmits that information to the server. Based on this data, the server sends appropriate energy-saving advice or suggestions for changing their plan to the user's terminal.

[0611] An example of a prompt message is: "When the user enters voice data: 'The electricity bill for the air conditioner is too high!', detect the user's stress level and generate the most appropriate energy-saving advice."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server acquires energy consumption data in real time from energy measurement devices. The input is data transmitted from the energy measurement devices, which is stored in a time-series database. The output is the stored consumption data. This provides the foundational data for identifying consumption patterns and detecting anomalies.

[0615] Step 2:

[0616] The server processes stored energy data and analyzes consumption patterns. The input is consumption data in a database, and machine learning algorithms are used to detect anomalies. If an anomaly is detected as a result of this data processing, an alert is generated. The output is information indicating whether an anomaly occurred.

[0617] Step 3:

[0618] The server analyzes market data to suggest the most suitable pricing plan to the user. Inputs are the user's consumption patterns and current market data, and the analysis identifies the optimal plan. Output is the recommended plan information provided to the user.

[0619] Step 4:

[0620] When a user sends feedback via voice or text, the device transfers that data to the server. The input is the user's feedback data, and the user's emotions are identified by sentiment analysis. The output is data about the user's emotional state.

[0621] Step 5:

[0622] The server uses a generative AI model to generate personalized energy usage advice based on the user's emotional state. The input is emotional data obtained from an emotion analysis device, and the generated advice is calculated. The output is specific advice information for the user. This information is sent to the terminal and fed back to the user. In this step, the prompt message is set to "Represent the user's emotional state and generate energy-saving advice."

[0623] 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.

[0624] 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.

[0625] 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.

[0626] [Fourth Embodiment]

[0627] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0628] 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.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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".

[0640] The energy management system according to the present invention has a configuration for collecting energy consumption data and proposing the optimal pricing plan to the user. This system consists of three main components: a server, a terminal, and a user. The roles of each are described below.

[0641] First, the server receives energy consumption data in real time from smart meters and other sources and stores it in a database. The data includes electricity and gas usage amounts and timestamps. This allows for the understanding of each user's consumption patterns.

[0642] Next, the server uses machine learning algorithms to detect anomalies based on the stored data. This involves comparing the data with past usage patterns and identifying any consumption that differs from normal as an anomaly. For example, it can issue an alert if power consumption suddenly increases during the night.

[0643] The server also notifies the user via the terminal when it detects an anomaly. The notification includes the nature of the anomaly and recommended countermeasures. Furthermore, the server compares the collected energy consumption data with the electricity company's pricing plans and suggests the most suitable plan for the user. This allows the user to reduce unnecessary costs.

[0644] The device displays notifications from the server and suggested pricing plans to the user. Based on this information, the user can review their energy usage. For example, they can take measures such as changing the time of day they use electricity to avoid peak charges.

[0645] Furthermore, the server analyzes market energy price trends and predicts future price fluctuations. This information is also provided to the user via the terminal, allowing the user to plan their energy usage strategy based on this information.

[0646] As a concrete example, when this system is applied to household energy management, the server records power consumption data daily and uses an anomaly detection module to send necessary warnings to the user in a timely manner. Furthermore, by optimizing electricity rate plans, users can reduce their monthly electricity bills. In this way, the energy management system helps users use energy efficiently and improve cost-effectiveness.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The server periodically receives electricity and gas consumption data from smart meters and other IoT devices. The data is recorded as electricity usage and gas usage, along with a timestamp.

[0650] Step 2:

[0651] The server stores the received data in a database. This data is stored as time-series data and used to analyze consumption patterns.

[0652] Step 3:

[0653] The server activates an anomaly detection module based on the stored data. It utilizes machine learning models to execute algorithms that detect deviations from normal consumption patterns.

[0654] Step 4:

[0655] If an anomaly is detected, the server generates an alert and sends a notification to the user via their terminal. This notification includes details of the anomaly and recommended actions to take.

[0656] Step 5:

[0657] The server collects pricing plan data from multiple power companies and calculates the optimal pricing plan by comparing it with the user's consumption data.

[0658] Step 6:

[0659] If an optimal pricing plan is found, the server will present that information to the user via the terminal. This suggestion will include a comparison with the current plan and an estimated amount of savings.

[0660] Step 7:

[0661] The server investigates price trends in the energy market and, based on this, runs a price fluctuation prediction module. Using machine learning, it predicts future price fluctuations from historical data.

[0662] Step 8:

[0663] Price fluctuation forecasts are provided to users via their devices. Users can use this information to adjust and plan their energy consumption. By developing consumption strategies based on these forecasts, it is possible to optimize costs.

[0664] (Example 1)

[0665] 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".

[0666] With increasing energy consumption, there is a growing need to propose optimal pricing plans to individual users and improve cost efficiency. However, existing technologies are insufficient for accurately analyzing consumption patterns and detecting anomalies. Furthermore, predicting price fluctuations in the energy market and providing users with strategic energy usage suggestions based on those predictions is currently difficult. It is necessary to solve these problems and improve cost reduction and energy usage optimization for users.

[0667] 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.

[0668] In this invention, the server includes data collection means for acquiring energy consumption data, anomaly detection means for analyzing consumption patterns based on the acquired data and detecting anomalies, and price fluctuation prediction means for predicting future price trends based on market price information. This enables anomaly detection in energy consumption and the proposal of cost-effective pricing plans, as well as strategic optimization of energy use based on market trends.

[0669] "Energy consumption data" refers to information that shows the amount of energy used, such as electricity and gas, and the duration of that use.

[0670] A "data collection method" is a system for acquiring energy consumption data and storing it in a database or similar.

[0671] An "anomaly detection method" refers to a process or technology for identifying unusual energy usage patterns based on consumption patterns.

[0672] "Rate plan optimization methods" refer to methods for suggesting the most economical rate plan based on the user's energy consumption data.

[0673] A "price fluctuation prediction method" is a technology that analyzes market price information and predicts future price fluctuations.

[0674] "Information notification means" refers to devices or methods that notify users of information such as anomaly detection results or proposed pricing plans.

[0675] A "strategy presentation method" is a method of analyzing electricity consumption patterns and pricing structures to propose the optimal energy usage strategy to users.

[0676] An "electronic meter" is a measuring device that can measure energy consumption and transmit that data remotely.

[0677] "Numerical analysis methods" are techniques that use mathematical and statistical methods to analyze data.

[0678] The embodiments for carrying out the present invention are described below.

[0679] The energy management system consists of three main components: users, servers, and terminals.

[0680] The server acquires energy consumption data in real time from measuring devices such as electronic meters. The acquired data is stored in a database, and then anomalies are identified by comparing it with past consumption patterns using an anomaly detection method. Numerical analysis methods are used for anomaly detection, enabling rapid detection of fraudulent consumption. In addition, the server uses a pricing plan optimization method to analyze the user's consumption data and market pricing information to propose the optimal pricing plan. Furthermore, a price fluctuation prediction method predicts market price trends, allowing for forecasting of future energy costs.

[0681] The terminal's role is to present information notifications sent from the server to the user. Specifically, it displays information such as anomaly detection results, proposed pricing plans, and usage strategies based on price trend forecasts. Based on the information provided by the terminal, users can review their power usage patterns and strive to reduce energy costs.

[0682] Users can optimize their daily energy usage by referring to the various information they receive through this system. For example, by adjusting the time of day they use electricity according to the suggested pricing plan, they can reduce their electricity bill.

[0683] As a concrete example, if this system is installed in a home, the server will manage daily energy consumption, and if an anomaly is detected, the user will be quickly notified via a terminal. In addition, cost optimization will enable the expected reduction in electricity bills. In this way, the efficiency of the user's energy use will be improved.

[0684] When using a generative AI model, you can obtain more detailed information about processing methods and theories by entering a prompt such as, "Please explain the algorithm that performs anomaly detection and rate optimization based on energy usage data."

[0685] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0686] Step 1:

[0687] The server acquires energy consumption data in real time from electronic meters. Input includes electricity and gas usage and their timestamps. This data is first stored in a database. Specifically, the server accesses the electronic meters via the network and retrieves the data using an API. The output is a time-series consumption dataset for each user.

[0688] Step 2:

[0689] The server uses collected energy consumption data to detect anomalies. The input is the time-series consumption data obtained in step 1. The server compares this data with past normal consumption patterns and identifies anomalies using numerical analysis techniques. Specifically, a machine learning algorithm analyzes real-time data and generates an alert if an abnormal pattern is detected. The output includes the type of anomaly detected and details of the associated consumption data.

[0690] Step 3:

[0691] When an anomaly is detected, the server sends a notification to the terminal. The input used is the details of the anomaly detected in step 2. Specifically, the server uses a notification protocol to deliver an alert to the terminal, forming a message that includes the type of anomaly and recommended actions. The output includes an immediate alert notification displayed on the user interface on the terminal.

[0692] Step 4:

[0693] The server optimizes pricing plans. Inputs include user energy consumption data and pricing plan information obtained from the market. The server uses pricing plan optimization tools to compare and analyze the pricing structure of each plan against the user's consumption patterns. Specific operations include executing a cost comparison algorithm for all pricing plans. The output generates a proposal for the most suitable pricing plan for the user.

[0694] Step 5:

[0695] The server analyzes market price information and predicts future energy cost trends. Its inputs include market price data and historical price fluctuation information. Specifically, it uses time series analysis to model and predict future price fluctuations. Its output includes strategic energy use suggestions based on the predicted price fluctuations.

[0696] Step 6:

[0697] The terminal presents information from the server to the user. Inputs include anomaly detection results, proposed pricing plans, and future price forecasts. Specifically, the terminal displays the information in an intuitively understandable format through a user interface. The output includes user-operable information displays, allowing the user to make decisions regarding energy use.

[0698] (Application Example 1)

[0699] 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".

[0700] In today's society, where energy efficiency and cost reduction are paramount, the challenge lies in providing a system that can monitor energy consumption in real time, detect anomalies, and propose optimal pricing plans. Furthermore, there is a need to create an environment where users can intuitively understand their energy usage and respond immediately when anomalies occur.

[0701] 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.

[0702] In this invention, the server includes an information gathering means for acquiring energy consumption information, an anomaly detection means for analyzing consumption patterns based on the acquired information and detecting anomalies, a pricing plan optimization means for proposing the most suitable pricing plan to the user, a price fluctuation prediction means for predicting future price fluctuations based on market price information, and a user terminal that displays the user's energy consumption status in real time and notifies the user when an anomaly occurs. This enables real-time optimization of energy consumption and cost reduction, as well as a rapid response when an anomaly occurs.

[0703] "Energy consumption information" refers to information collected on the amount of electricity, gas, and other energy sources used, as well as related data.

[0704] "Information gathering means" refers to devices or systems used to acquire energy consumption information.

[0705] "Consumption patterns" refer to usage trends and behaviors derived from past energy usage data.

[0706] An "anomaly detection method" is a mechanism for detecting energy usage that deviates from normal consumption patterns.

[0707] "Rate plan optimization methods" refer to functions and methods for proposing the most economical energy rate plan to the user.

[0708] "Price information" refers to data on rates and prices in the energy market.

[0709] "Price fluctuation prediction methods" refer to techniques and mechanisms for analyzing market price information and predicting future price fluctuations.

[0710] A "user terminal" refers to a device or apparatus used by a user to receive information.

[0711] "Real-time" is a concept that refers to information being acquired and processed almost simultaneously.

[0712] "Notification" refers to the act or mechanism of informing a user of information.

[0713] The system for implementing this invention consists of three main components: a server, a terminal, and a user. The server is equipped with information gathering means for acquiring energy consumption information in real time and stores consumption data such as electricity and gas in the server's database through measuring instruments. Based on this stored data, the system analyzes consumption patterns and uses machine learning algorithms to detect anomalies that deviate from past consumption trends. For example, if electricity consumption increases at a time different from the normal use of household appliances, this can be detected as an anomaly.

[0714] When an anomaly is detected, the server sends a notification to the user's device. The device displays this information clearly to the user and issues alerts as needed, enabling the user to take immediate action. The server also obtains price information from the energy market and runs an algorithm to suggest the most suitable pricing plan for the user. This makes it possible to reduce unnecessary energy consumption costs.

[0715] Furthermore, this system analyzes market energy price trends and predicts future price fluctuations, helping users create usage plans that anticipate future increases in electricity prices.

[0716] As a concrete example, in one household, a smartphone app immediately displays a notification if it detects abnormal power consumption at night. At that point, the user can review their use of home appliances and use that information to help reduce costs. As an example of a "generated AI model and prompt message," a possible prompt message would be, "Based on energy consumption data within the smart city, create a power consumption peak forecast alert for this weekend and notify the user."

[0717] Thus, the main aim of this invention is to achieve both increased energy efficiency and a more comfortable energy experience for users.

[0718] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0719] Step 1:

[0720] The server acquires energy consumption information through measuring instruments. It receives electricity and gas usage data and their timestamps as input and stores them in a database. During this process, the data is collected and formatted and optimized for storage in a centralized storage system.

[0721] Step 2:

[0722] The server uses machine learning algorithms to detect anomalies based on accumulated energy consumption data. It takes historical consumption pattern data as input and generates output indicating whether an anomaly exists and its details. Specifically, this involves identifying data points that deviate from normal consumption and marking them as anomalies.

[0723] Step 3:

[0724] When an anomaly is detected, the server generates a notification for the terminal. It receives the anomaly detection result as input and creates user-facing alert information as output. This notification includes details of the anomaly and recommended actions, and this information is sent to the user's device.

[0725] Step 4:

[0726] The server runs a pricing plan optimization algorithm and proposes a suitable pricing plan for the user. It uses energy consumption data and market price information as input and generates the optimal pricing plan as output. In this step, multiple plans are evaluated and the best one is selected based on the user's past usage patterns and current market conditions.

[0727] Step 5:

[0728] The server analyzes energy price trends and predicts future price fluctuations. It uses market price fluctuation data as input and presents predicted price trends as output. Specifically, it uses mathematical models to simulate future price scenarios and transmits the results to the terminal.

[0729] Step 6:

[0730] The terminal displays information received from the server to the user. It receives notification and price prediction information as input and provides information that the user can visually understand as output. During this process, the user interface is updated and notification pop-ups are displayed to encourage changes in user behavior.

[0731] 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.

[0732] The energy management system according to the present invention combines functions for collecting energy consumption data, analyzing consumption patterns, detecting anomalies, optimizing pricing plans, and predicting price fluctuations with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0733] First, the server receives energy consumption data from smart meters in real time and stores it in a database as time-series data. Based on this data, the server uses machine learning algorithms to detect anomalies. When an anomaly is detected, the server immediately generates an alert and notifies the user through their terminal.

[0734] In the pricing plan optimization method, the server collects various electricity pricing plans and compares them with the user's consumption data to suggest the optimal plan. This information is presented to the user via their terminal, supporting them in making the most economical choice. Furthermore, by analyzing price trends in the energy market, future price fluctuations are predicted. These price fluctuation predictions are provided to the user as information that helps optimize their energy usage plan.

[0735] The newly integrated emotion engine analyzes user voice and text data to understand the user's emotional state in real time. For example, if a user expresses dissatisfaction with energy use, the emotion engine recognizes this and sends data to the server. As a result, the server can adjust consumption strategies based on the emotional data and provide personalized advice.

[0736] As a concrete example, suppose a user in a household expresses dissatisfaction with their electricity bill through a voice assistant. At this time, the emotion engine analyzes the user's tone of voice and words to detect stress and dissatisfaction. This information is sent to a server, which then provides appropriate feedback to the user via the device, considering further energy-saving advice and suggestions for future rate plan changes. In this way, a system is realized that can manage energy consumption more flexibly according to the user's emotional state.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] The server receives electricity and gas consumption data from smart meters in real time. This data is time-stamped with accurate information, along with the amount of electricity and gas used.

[0740] Step 2:

[0741] The server stores the received data in a database and uses machine learning algorithms to analyze past consumption patterns. This analysis can detect outliers that deviate from normal consumption.

[0742] Step 3:

[0743] When an anomaly is detected, the server issues an alert and promptly notifies the user via their terminal. The notification includes the nature of the anomaly and recommended actions to take.

[0744] Step 4:

[0745] The server collects electricity rate plans offered from the market and selects the most economical plan by comparing it with the user's consumption data. This result is then presented to the user via the terminal.

[0746] Step 5:

[0747] The server incorporates external market analysis data and uses algorithms to predict future price trends. It can identify peak and undervalued periods for energy.

[0748] Step 6:

[0749] The price fluctuation prediction results are provided to users via their devices and used as a reference for developing optimal energy usage strategies.

[0750] Step 7:

[0751] Users express their emotions through voice and text input. This input data is analyzed by an emotion engine to recognize the user's emotional state.

[0752] Step 8:

[0753] The server, upon receiving output from the emotion engine, adjusts energy consumption suggestions based on the emotional data. In particular, if the user indicates stress or dissatisfaction, the system adjusts to provide specific advice in response.

[0754] Step 9:

[0755] Adjustments based on emotional data are delivered to the user via their device, promoting consumer behavior that takes user satisfaction into consideration.

[0756] (Example 2)

[0757] 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".

[0758] Conventional energy management systems provide mechanisms for detecting anomalies in energy consumption and optimizing pricing plans, but they have the drawback of not being able to optimize flexible energy usage strategies that take into account the emotional state of users. Furthermore, predicting and utilizing fluctuations in energy market prices has been difficult. Therefore, this invention aims to provide more personalized energy management that takes into account the emotional state of users.

[0759] 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.

[0760] In this invention, the server includes information gathering means for acquiring energy usage information, anomaly identification means for analyzing usage trends and identifying anomalies based on the acquired information, and fluctuation prediction means for predicting future price fluctuations based on market price information. This makes it possible to adjust the energy usage strategy to be personalized based on the user's emotional state.

[0761] "Energy usage information" refers to data on the consumption of electricity, gas, water, etc., in homes and facilities.

[0762] "Information gathering means" refers to devices or programs used to collect energy usage information.

[0763] "Usage trends" refer to patterns or tendencies that show how energy is consumed.

[0764] "Analysis" is the process of examining data in detail to clarify its meaning and structure.

[0765] "Anomaly identification means" refers to a device or program for detecting phenomena that deviate from normal usage patterns.

[0766] A "fee agreement" refers to an arrangement regarding fees that consumers make with service providers.

[0767] "Contract optimization means" refers to a device or program for selecting the most advantageous pricing contract for the consumer.

[0768] "Price information" refers to data on prices in the energy market.

[0769] "Fluctuation prediction means" refers to a device or program for predicting future price fluctuations.

[0770] "Emotional state" refers to the state and changes in the user's emotions.

[0771] "Emotional analysis means" refers to a device or program used to analyze a user's emotions and understand their state.

[0772] A "management system" refers to a system for comprehensive management, including the collection, analysis, and optimization of energy usage information.

[0773] This energy management system is a comprehensive system for collecting, analyzing, and optimizing energy usage information. The main components of the system are information gathering means, anomaly identification means, contract optimization means, fluctuation prediction means, and sentiment analysis means.

[0774] The server collects energy usage information in real time via measuring devices. The smart meters used as measuring devices have the capability to transmit information over the internet. This collected data is stored in a database and used for later analysis.

[0775] Anomaly detection uses an automated learning algorithm executed on the server. This algorithm employs machine learning libraries such as Scikit-learn and TensorFlow. The server analyzes time-series data of energy use and detects anomalous usage patterns.

[0776] The device receives notifications from the server and provides information to the user visually. For example, if an anomaly is detected, the device sends a push notification to the user and displays detailed information.

[0777] Contract optimization calculates the optimal pricing contract based on market price information and usage patterns collected by the server. Here, pricing information is obtained using the Requests library, and analysis is performed using an optimization algorithm based on linear programming. The optimization results are presented to the user via the terminal.

[0778] As a means of sentiment analysis, the server uses the Google Cloud Speech-to-Text API to analyze the user's voice data. This analysis allows for real-time understanding of the user's emotional state and the generation of personalized feedback and advice.

[0779] For example, if a user tells a voice assistant, "I'm unhappy with my recent electricity bill," the emotion analysis system analyzes that emotion and sends the results to a server. Based on the results, the server generates appropriate advice and suggests it to the user through the device.

[0780] An example of a prompt sentence to be fed into a generative AI model is, "Please tell me how to review my household energy consumption and save more than $100."

[0781] In this way, the system can efficiently manage the user's energy usage and provide interactive feedback that takes their emotional state into account.

[0782] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0783] Step 1:

[0784] The server acquires energy usage information in real time via measuring devices. The input is raw power consumption data provided by smart meters. This data is stored in an SQL database and converted into a format usable for later analysis. Specifically, the server opens a database connection and retrieves and stores data via a RESTful API.

[0785] Step 2:

[0786] The server analyzes energy usage trends using energy usage information stored in a database and identifies anomalies by comparing them to baseline values. The input is power consumption data organized as a time series. The Scikit-learn Isolation Forest model is used to identify anomalous data points and output them as a report. Specifically, the server executes a Python script and logs any anomalies it finds.

[0787] Step 3:

[0788] The server notifies the device that an anomaly has been detected. The input is an anomaly report, which is the output of the anomaly detection algorithm. This information is sent to the device, and an alert is displayed to the user. Specifically, the server sends the notification via Firebase Cloud Messaging, and the device displays the alert on its user interface.

[0789] Step 4:

[0790] The server retrieves energy market price information from an external database and predicts future price fluctuations. The input is price data obtained from the internet. It performs time-series forecasting using the Prophet library and outputs the forecast results. Specifically, the server communicates via API to retrieve market information and applies it to the model.

[0791] Step 5:

[0792] The terminal presents the user with optimized pricing contract information sent from the server. The input is proposed pricing contract data generated by the server. This is visually displayed in the user interface, providing options. Specifically, the terminal uses technologies to display information in graph and table formats to show the proposals to the user.

[0793] Step 6:

[0794] The server receives voice commands from the user and inputs them into an emotion analysis algorithm to determine the user's emotional state. The input is voice data obtained from a voice assistant. The voice is converted to text using the Google Cloud Speech-to-Text API, and that text is analyzed using the NLTK library. The output is the detected emotional state. Specifically, the server receives the voice stream and performs text conversion and emotion analysis in real time.

[0795] Step 7:

[0796] The server uses a generative AI model based on the analysis results to generate personalized feedback and advice for the user. The input is sentiment data from a sentiment analysis algorithm. It generates prompt sentences and sends the advice to the terminal. Specifically, the server packages the generated prompts in JSON format and sends them to the terminal to notify the user.

[0797] (Application Example 2)

[0798] 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".

[0799] Efficient energy management is essential in modern society, but conventional systems have faced the challenge of making individualized suggestions that take into account user usage patterns and emotions. In particular, there was a lack of means to accurately grasp users' feelings about energy consumption and provide advice accordingly, which prevented us from increasing user satisfaction.

[0800] 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.

[0801] In this invention, the server includes data collection means for acquiring energy consumption data, emotion analysis means for analyzing voice or text data to identify the user's emotions, and price plan optimization means for proposing the most suitable price plan to the user. This makes it possible to provide an optimal energy consumption strategy that takes into account the user's emotional state, thereby not only improving user satisfaction but also achieving efficient use of energy resources.

[0802] "Energy consumption data" refers to information about energy usage, and it serves as fundamental data for analyzing usage patterns and anomalies.

[0803] "Data collection means" refers to a device or system for generating, acquiring, or recording energy consumption data.

[0804] An "anomaly detection means" is an information processing device or algorithm for identifying unusual movements in energy consumption patterns and issuing warnings.

[0805] A "pricing plan optimization method" is a processing method that identifies economically advantageous pricing plans based on user consumption data and presents them as options.

[0806] A "price fluctuation prediction tool" is a device or software used to analyze market data and predict future trends in energy prices.

[0807] "Emotion analysis means" refers to information processing means that use a user's voice or text data to identify emotions from its content.

[0808] An "emotional response system" is a system that provides users with personalized energy consumption advice based on the results of emotional analysis.

[0809] An "energy measurement device" is a device that measures energy consumption in real time and outputs it as data.

[0810] "Computational methods" refer to mathematical and statistical tools used for data analysis and anomaly detection, and include machine learning algorithms and other numerical analysis methods.

[0811] The system according to this invention enables efficient energy use in smart cities by effectively managing energy consumption data and providing advice based on the user's emotions. The server acquires energy consumption data in real time from an energy measuring device and uses this data to analyze consumption patterns. This allows for data-driven anomaly detection and notifications to the user as needed.

[0812] Furthermore, the server helps users select the optimal long-term pricing plan by using market trend data to predict future price fluctuations. Sentiment analysis tools analyze the user's voice and text to identify their emotional state, providing flexible feedback on energy usage. Specifically, it utilizes generative AI models to generate personalized advice tailored to the user's emotions, thereby improving user satisfaction.

[0813] If a user expresses dissatisfaction with their electricity usage through the interface, for example, by saying "The air conditioning bill this summer is too high!", the emotion analysis engine identifies this as dissatisfaction and transmits that information to the server. Based on this data, the server sends appropriate energy-saving advice or suggestions for changing their plan to the user's terminal.

[0814] An example of a prompt message is: "When the user enters voice data: 'The electricity bill for the air conditioner is too high!', detect the user's stress level and generate the most appropriate energy-saving advice."

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The server acquires energy consumption data in real time from energy measurement devices. The input is data transmitted from the energy measurement devices, which is stored in a time-series database. The output is the stored consumption data. This provides the foundational data for identifying consumption patterns and detecting anomalies.

[0818] Step 2:

[0819] The server processes stored energy data and analyzes consumption patterns. The input is consumption data in a database, and machine learning algorithms are used to detect anomalies. If an anomaly is detected as a result of this data processing, an alert is generated. The output is information indicating whether an anomaly occurred.

[0820] Step 3:

[0821] The server analyzes market data to suggest the most suitable pricing plan to the user. Inputs are the user's consumption patterns and current market data, and the analysis identifies the optimal plan. Output is the recommended plan information provided to the user.

[0822] Step 4:

[0823] When a user sends feedback via voice or text, the device transfers that data to the server. The input is the user's feedback data, and the user's emotions are identified by sentiment analysis. The output is data about the user's emotional state.

[0824] Step 5:

[0825] The server uses a generative AI model to generate personalized energy usage advice based on the user's emotional state. The input is emotional data obtained from an emotion analysis device, and the generated advice is calculated. The output is specific advice information for the user. This information is sent to the terminal and fed back to the user. In this step, the prompt message is set to "Represent the user's emotional state and generate energy-saving advice."

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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."

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] The following is further disclosed regarding the embodiments described above.

[0848] (Claim 1)

[0849] A data collection method for acquiring energy consumption data,

[0850] An anomaly detection means that analyzes consumption patterns based on acquired data and detects abnormalities,

[0851] A pricing plan optimization method that proposes the most suitable pricing plan to the user,

[0852] A price fluctuation prediction method that predicts future price fluctuations based on market price data,

[0853] An energy management system that includes at least these features.

[0854] (Claim 2)

[0855] The system according to claim 1, wherein energy consumption data is acquired in real time via a smart meter.

[0856] (Claim 3)

[0857] The system according to claim 1, wherein the anomaly detection means identifies anomalies in consumption patterns using a machine learning algorithm.

[0858] "Example 1"

[0859] (Claim 1)

[0860] A data collection method for acquiring energy consumption data,

[0861] An anomaly detection means that analyzes consumption patterns based on acquired data and detects abnormalities,

[0862] A pricing plan optimization method that proposes the most suitable pricing plan to the user,

[0863] A price fluctuation prediction method that predicts future price trends based on market price information,

[0864] Information notification means that transmits the results of detecting an anomaly in energy consumption to the user using a notification device,

[0865] A strategic presentation tool that analyzes electricity consumption patterns and pricing structures to propose usage strategies,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, wherein energy consumption data is acquired in real time via an electronic meter.

[0869] (Claim 3)

[0870] The system according to claim 1, wherein the anomaly detection means identifies anomalies in the consumption pattern using a numerical analysis method.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] Information gathering means for acquiring energy consumption information,

[0874] An anomaly detection means that analyzes consumption patterns based on acquired information and detects abnormalities,

[0875] A pricing plan optimization method that proposes the most suitable pricing plan to the user,

[0876] A price fluctuation prediction method that predicts future price fluctuations based on market price information,

[0877] A user terminal that displays the user's energy consumption status in real time and notifies them when an anomaly occurs,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, wherein energy consumption information is acquired in real time via measuring instruments.

[0881] (Claim 3)

[0882] The system according to claim 1, wherein the anomaly detection means uses a machine learning algorithm to identify anomalies in consumption patterns and generates an alarm.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] Information gathering means for acquiring energy usage information,

[0886] An anomaly identification means that analyzes usage trends based on acquired information and identifies anomalies,

[0887] A contract optimization method that presents users with the most suitable pricing contract,

[0888] A fluctuation prediction means that predicts future price fluctuations based on market price information,

[0889] An emotion analysis tool that analyzes the emotional state of users and adjusts usage strategies based on that data,

[0890] A management system that includes at least these features.

[0891] (Claim 2)

[0892] The system according to claim 1, wherein energy usage information is acquired in real time via a measuring device.

[0893] (Claim 3)

[0894] The system according to claim 1, wherein the anomaly identification means identifies anomalies in usage trends using an automatic learning algorithm.

[0895] "Application example 2 when combining with an emotional engine"

[0896] (Claim 1)

[0897] A data collection method for acquiring energy consumption data,

[0898] An anomaly detection means that analyzes consumption patterns based on acquired data and detects abnormalities,

[0899] A pricing plan optimization method that proposes the most suitable pricing plan to the user,

[0900] A price fluctuation prediction method that predicts future price fluctuations based on market price data,

[0901] A sentiment analysis method that identifies a user's emotions by analyzing voice or text data,

[0902] An emotional response system that provides personalized advice on energy consumption based on the user's emotions,

[0903] A system that includes at least these.

[0904] (Claim 2)

[0905] The system according to claim 1, wherein energy consumption data is acquired in real time via an energy measuring device.

[0906] (Claim 3)

[0907] The system according to claim 1, wherein the anomaly detection means identifies anomalies in the consumption pattern using a calculation method. [Explanation of Symbols]

[0908] 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. Information gathering means for acquiring energy consumption information, An anomaly detection means that analyzes consumption patterns based on acquired information and detects abnormalities, A pricing plan optimization method that proposes the most suitable pricing plan to the user, A price fluctuation prediction method that predicts future price fluctuations based on market price information, A user terminal that displays the user's energy consumption status in real time and notifies them when an anomaly occurs, A system that includes this.

2. The system according to claim 1, wherein energy consumption information is acquired in real time via measuring instruments.

3. The system according to claim 1, wherein the anomaly detection means uses a machine learning algorithm to identify anomalies in consumption patterns and generates an alarm.

Images