system

Abstract

We provide the system. [Solution] Means for collecting energy consumption data, A means for detecting anomalies using the aforementioned data, A method for analyzing multiple pricing plans and recommending the optimal plan, Means for notifying the user of the aforementioned anomaly and recommended plan, 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, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Due to the increase in energy costs and the existence of various tariff plans, it has become difficult for users to select an optimal energy consumption strategy. Also, there is a problem in that means for detecting and responding to abnormal and wasteful energy consumption in real time are limited. The present invention aims to solve these problems and provide an optimal energy consumption strategy for users.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for collecting energy consumption data, means for detecting anomalies using the data, means for analyzing multiple pricing plans and recommending the optimal plan, and means for notifying the user of the anomaly and the recommended plan. The energy consumption data is obtained from a smart meter, and a machine learning algorithm is used for anomaly detection to achieve highly accurate anomaly detection and recommendation of the optimal plan.

[0006] "Energy consumption data" refers to information about the amount of energy used, such as electricity and gas, in households and businesses.

[0007] "Anomaly detection" is the process of identifying improper or wasteful energy use that deviates from normal energy consumption patterns.

[0008] A "pricing plan" refers to the method of setting charges and pricing structure for energy consumption offered by an energy supply company.

[0009] A "recommendation" is the act of presenting an option that is judged to be the most effective or efficient under specific conditions.

[0010] A "machine learning algorithm" is a computational method that learns patterns from data and uses them to make predictions and classifications about future data.

[0011] "Real-time" means processing and analyzing data almost simultaneously with real-world time.

[0012] A "smart meter" is a device that digitally records electricity and gas usage and allows for remote monitoring and management of that information through communication functions.

[0013] A "user" refers to an individual or organization that utilizes energy consumption data to reduce costs or improve efficiency. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map 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.

Mode for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the labeled 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.

[0018] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the labeled 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, etc.

[0020] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for efficiently utilizing energy consumption data. This system mainly consists of a server, terminals, and users.

[0036] The server is responsible for collecting energy consumption data from smart meters in real time. The collected data is stored in a database for analysis. The server uses machine learning algorithms to detect anomalies based on the collected data. This anomaly detection makes it possible to identify deviations from normal consumption patterns in real time.

[0037] The terminal receives data from the server and issues an alert to the user if an anomaly is detected. The alert is notified with a specific message, such as "Abnormal consumption has occurred." The terminal also has the function to analyze multiple pricing plans provided by the server and select the plan that best suits the user's actual consumption pattern. This function makes it possible to recommend plans to the user or suggest new pricing plans.

[0038] Users receive notifications from their devices and can consider taking action regarding abnormal consumption or switching to a more economical pricing plan. Based on the information received, users can review their appliance usage or change their contract plan as needed.

[0039] As a concrete example, consider a case where electricity consumption in a household suddenly increases during the night. In this case, the server detects this anomaly and notifies the user via a terminal. Based on the notification, the user can investigate the household appliances operating at night and take measures such as turning off unnecessary devices. Furthermore, by switching to a rate plan suggested by the terminal, the user can save on their monthly electricity bill. In this way, the present invention provides an effective means for optimizing energy consumption.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects energy consumption data from homes or businesses via a smart meter API. This data includes electricity and gas usage during specific time periods and is stored in a database in real time.

[0043] Step 2:

[0044] The server executes an anomaly detection algorithm based on the collected data. Here, a machine learning algorithm is used to identify data points that deviate from normal consumption patterns, i.e., abnormal consumption.

[0045] Step 3:

[0046] If an anomaly is detected, the terminal receives the information from the server and generates an anomaly alert for the user. The alert includes information about the time period when the anomaly occurred and detailed consumption patterns.

[0047] Step 4:

[0048] The server considers multiple pricing plans and analyzes which plan offers the most economic benefit using user consumption data. Clustering techniques are then used to evaluate the suitability of each plan.

[0049] Step 5:

[0050] Based on the analysis results, the device will notify the user of the most suitable pricing plan. The notification will include the benefits of the new plan and the potential savings compared to the current plan.

[0051] Step 6:

[0052] Users receive notifications from their devices and take specific actions. For example, they can reduce energy costs by checking the usage of home appliances to eliminate the cause of abnormal consumption or by changing to a suggested plan.

[0053] (Example 1)

[0054] 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."

[0055] Optimizing energy consumption is a crucial issue in modern homes and businesses, but it is difficult for consumers to understand their own consumption patterns and select appropriate pricing plans. Furthermore, there is the challenge of quickly identifying and addressing the cause of sudden, abnormal consumption.

[0056] 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.

[0057] In this invention, the server includes means for collecting energy consumption data from a measuring device in real time, means for preprocessing the data and detecting abnormal consumption patterns using a machine learning algorithm, and means for selecting and visualizing the optimal pricing plan based on the analysis results. This enables efficient energy management and rapid response to anomalies.

[0058] "Energy consumption data" refers to data that contains detailed information about energy use, and is usually digital data showing the usage of electricity, gas, water, etc.

[0059] A "measuring device" is a device used to measure energy consumption, and is commonly known as a smart meter.

[0060] "Real-time" means that data and information are processed immediately and are available without any time delay.

[0061] "Preprocessing" refers to the process of converting raw data into a format that can be analyzed, and includes operations such as data cleaning and formatting standardization.

[0062] A "machine learning algorithm" is a mathematical model used to learn patterns and rules from data, and is a technique used for anomaly detection and predictive analytics.

[0063] An "abnormal consumption pattern" refers to consumption patterns or trends that deviate significantly from normal energy consumption, and usually suggests malfunction or failure.

[0064] A "pricing plan" is a pricing option offered by an energy supplier to consumers, and includes different billing systems based on usage and time of day.

[0065] "Visualization" refers to the visual representation of data and analysis results, using graphs, charts, and other tools to make information easily understandable.

[0066] An "electronic notification device" is a device that notifies information by electronic means, and includes communication terminals such as smartphones and computers.

[0067] This invention provides a system that enables efficient management of energy consumption and includes server, terminal, and user components. Each component plays a specific role, and together they contribute to optimizing the user's energy consumption.

[0068] The server first collects energy consumption data in real time from measuring devices. To do this, an API is developed using a programming language such as Python to communicate with the measuring devices. The collected data is stored in a database and preprocessed using Pandas. The scikit-learn library in Python is used to apply machine learning algorithms to the preprocessed data to detect abnormal consumption patterns. This anomaly detection enables early detection and rapid response to fraudulent consumption.

[0069] The device receives analysis results sent from the server and electronically notifies the user. The device uses JavaScript® to visualize the collected data and displays it in a user-friendly format. The notifications sent to the user are specific, including details such as, "Twice the normal consumption was detected during the late-night hours." The device also uses Python's NumPy to analyze multiple pricing plans and suggest the optimal plan to the user. This allows the user to consider a rational plan change based on their consumption patterns.

[0070] Users receive notifications from their devices and adjust their electricity consumption as needed. Based on these notifications, they can take specific actions, such as turning off devices that are currently running, to prevent wasted energy. Furthermore, users can switch to new pricing plans based on the device's suggestions, achieving efficient energy management.

[0071] As a concrete example, one could input a prompt like the following into a generative AI model: "Explain how the system works by detecting sudden spikes in electricity consumption during the night and suggesting the optimal pricing plan." Such a prompt would allow the generative AI to generate a natural language explanation that accurately reflects its understanding of the system's operation. Based on this explanation, the user can further enjoy the system's convenience.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects energy consumption data in real time from the measuring device. The input is data from the measuring device, which is retrieved into the server via an API. Specifically, a Python program is used to send an HTTP request to the measuring device and receive the returned data in JSON format. The output is the collected energy consumption data.

[0075] Step 2:

[0076] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, it performs actions such as imputing missing values, correcting outliers, and converting data types. The Python Pandas library is used for this. The output is the cleaned-up data.

[0077] Step 3:

[0078] The server uses pre-processed data to detect abnormal consumption patterns. The input is the clean data obtained in step 2. Specifically, it uses Python's scikit-learn to apply machine learning algorithms. Clustering and outlier detection algorithms are used as an anomaly detection model. The output is alert information when an anomaly is detected.

[0079] Step 4:

[0080] The terminal receives analysis results from the server and sends an alert to the user. The input is the alert information generated in step 3. Specific actions include sending push notifications via email services or mobile apps. The output is the specific notification message sent to the user.

[0081] Step 5:

[0082] The device analyzes the user's energy consumption patterns and selects the optimal pricing plan. The input is the clean data from step 2. Specifically, it uses Python's NumPy to analyze multiple pricing plans and calculate the plan most suitable for the user. It then presents the visualized plan in a graph format. The output is information suggesting the optimal pricing plan for the user.

[0083] Step 6:

[0084] The user receives notifications on their device and takes appropriate action. The input is the notification and plan information obtained in steps 4 and 5. Specifically, the user follows the notification and adjusts the device's operation or changes their pricing plan. This results in energy savings and cost reductions. The output is the optimized state of energy consumption and associated costs.

[0085] (Application Example 1)

[0086] 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."

[0087] Modern cities require optimized energy resource management, but there are problems with the rapid detection of fraudulent consumption data from residents and public facilities, and the selection of optimal plans. Furthermore, while real-time monitoring of consumption patterns is expected to lead to more efficient energy management, current systems lack the information processing capabilities to achieve this.

[0088] 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.

[0089] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies using the information, and means for analyzing multiple pricing plans and recommending the optimal plan. This enables real-time monitoring of energy consumption and efficient energy management in public facilities.

[0090] "Energy consumption information" refers to data related to the amount of energy used, such as electricity, gas, and water.

[0091] "Anomaly detection" is a function that identifies fraudulent or abnormal energy usage that deviates from normal consumption patterns.

[0092] A "pricing plan" refers to a contract option offered by an energy supplier that has a different pricing structure.

[0093] "Means of notifying users" refers to communication methods or systems for informing users or related parties about anomalies or recommended plans.

[0094] "Real-time monitoring" is the process of observing information immediately and responding quickly as needed.

[0095] "Public facilities" refer to buildings or places owned by private companies or the government, such as libraries, parks, and hospitals, that are used by many people.

[0096] "Energy management" is the process of planning and implementing measures to optimize energy use and improve efficiency.

[0097] In an embodiment of this invention, the server collects energy consumption information in real time and processes it to detect anomalies. The server stores the data obtained from the smart meter in a database and uses a machine learning algorithm to identify unusual consumption patterns. The results of this anomaly detection are notified to the terminal.

[0098] The device receives anomaly alerts sent from the server and notifies the user. These notifications include specific details about the anomaly and suggestions for changing the plan. Furthermore, the device has the functionality to select and recommend the optimal pricing plan based on the user's consumption patterns.

[0099] Based on notifications from their devices, users can take steps to reduce energy waste. For example, they can check for unnecessary power consumption at night and adjust their use of electrical appliances. They can also switch to a more economical energy plan based on plan suggestions from their devices.

[0100] For example, if a household records a sudden surge in electricity consumption at night, the server will detect this as an anomaly and send a notification to the terminal. The terminal will warn the user that "abnormal consumption has occurred" and simultaneously offer suggestions such as "Why not switch to a more cost-effective rate plan?" Through this process, energy management is carried out efficiently and effectively.

[0101] An example of a prompt is, "Explain how to analyze energy consumption data and suggest an efficient plan."

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server collects energy consumption information from smart meters in real time. This input data records hourly consumption and is stored in a database. In this step, the server processes the collected raw data into a format that can be analyzed.

[0105] Step 2:

[0106] The server performs anomaly detection based on collected energy consumption information. Consumption data stored in the database is input into a machine learning model to determine if it deviates from normal consumption patterns. Cases identified as anomaly are flagged and passed on to the next process.

[0107] Step 3:

[0108] The server analyzes each user's energy consumption patterns along with the anomaly detection results. Based on this analysis, it performs calculations to select the optimal plan from multiple pricing plans. This selection result is sent to the terminal as a recommended plan.

[0109] Step 4:

[0110] The device receives anomaly alerts and recommended plans from the server. Based on this input information, it notifies the user of specific anomaly warnings and suggestions for changing their pricing plan. Notifications are made visually and audibly to draw the user's attention.

[0111] Step 5:

[0112] Users check notifications from their devices and take action based on the information presented. Specifically, they review their devices and settings to check for abnormal energy consumption and consider switching to a plan suggested by the device. This final action by the user completes a feedback loop that optimizes energy management.

[0113] 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.

[0114] This invention provides a system that efficiently analyzes energy consumption data and takes into account the user's emotional state to offer more personalized energy management. The system primarily consists of a server, terminals, and users, and incorporates an emotion engine.

[0115] The server collects energy consumption data from smart meters and uses machine learning algorithms to detect anomalies. This allows it to identify deviations from normal consumption patterns. The server also has the functionality to analyze pricing plans and recommend the most suitable plan for the user.

[0116] The device receives anomalies detected by the server and recommended pricing plans, and notifies the user. In addition, the device has an emotion engine that can evaluate the user's emotions based on their facial expression and voice data. The content and method of notifications are adjusted according to the output of the emotion engine. In this way, it becomes possible to provide information that takes the user's state into consideration.

[0117] Users receive anomaly alerts and recommended plans via their devices. Furthermore, they can provide feedback on their emotional state through interaction with an emotion engine. This enables energy management that reduces user stress and frustration.

[0118] As a concrete example, if electricity consumption suddenly increases in a household late at night, the server detects this anomaly and notifies the terminal. The terminal simultaneously assesses the user's emotions, determining whether they are worried or indifferent. If the user indicates anxiety, the system provides a detailed cause analysis and suggested solutions, tailoring the notification to enhance the user's sense of security. This aims to achieve energy management that goes beyond mere data provision and is more user-centric.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server collects energy consumption data via a smart meter API and stores it in a database. The data includes information on electricity and gas usage, as well as time of day.

[0122] Step 2:

[0123] The server uses machine learning algorithms to detect abnormal consumption patterns from the collected data. It identifies fraudulent or wasteful energy use and records it as an alert.

[0124] Step 3:

[0125] The server evaluates pricing plans based on the user's past consumption data and calculates the most suitable plan for the user. It compares multiple plans and selects the one with the best cost-performance ratio.

[0126] Step 4:

[0127] The device receives anomaly alerts and recommended pricing plans from the server and notifies the user of this information. The alerts include details of the unusual consumption.

[0128] Step 5:

[0129] The device uses an emotion engine to analyze the user's facial expressions and voice data, and evaluates their emotional state in real time. As a result, notification methods and content are adjusted according to the user's emotional state.

[0130] Step 6:

[0131] Users can check notifications from their devices and consider taking action regarding abnormal consumption or switching to a recommended plan. Based on feedback from the emotion engine, they can respond in a way that suits their own emotions.

[0132] Step 7:

[0133] The server and terminal analyze interaction data based on the emotion engine to continuously improve the personalization of the entire energy management system. The learned results are then used to improve the user experience.

[0134] (Example 2)

[0135] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0136] Conventional energy management systems detect anomalies in energy consumption and suggest pricing plans, but they do not provide personalized information that takes into account the user's emotional state. As a result, they are insufficient in alleviating user anxiety and doubts, and have limitations in providing an optimal energy management experience.

[0137] 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.

[0138] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies, and means for evaluating the user's emotional state. This enables optimal energy management while appropriately adjusting notification content based on the user's emotional state and reducing the user's anxiety.

[0139] "Energy consumption information" refers to data showing the electricity usage in homes and facilities, and is acquired using smart meters or similar measuring devices.

[0140] "Anomaly detection" is the process of analyzing collected energy consumption information to identify phenomena that deviate from normal consumption patterns, and it is achieved using machine learning techniques.

[0141] "Rate plan analysis" is a process that evaluates existing electricity rate plans based on energy consumption information and recommends the most economical and efficient plan to users.

[0142] "User emotional state" refers to the psychological condition evaluated based on data such as the user's facial expressions and voice, and is a factor that influences the understanding and acceptance of information.

[0143] "Adjusting notification content" is a process that takes into account the user's emotional state and customizes the format and content of information provided by the system to ensure more appropriate and effective communication.

[0144] This invention is a system for efficiently managing energy consumption information, and is composed primarily of a server, terminals, and users. This system collects energy consumption information in real time and enables anomaly detection, optimal pricing plan suggestions, and notification adjustments based on the user's emotional state.

[0145] The server acquires energy consumption information from measuring devices. This data collection is performed regularly and automatically, accumulating a large amount of data. The server analyzes the data using machine learning techniques (e.g., anomaly detection algorithms) to identify anomalies that deviate from normal consumption patterns. Furthermore, it has the ability to evaluate multiple existing pricing plans and propose the most suitable pricing plan for the user.

[0146] The terminal notifies the user of anomaly detection information and pricing plan suggestions sent from the server. During this process, a built-in emotion engine analyzes the user's facial expression and voice data to evaluate their emotional state. The notification content and method are adjusted based on this emotion evaluation, enabling the provision of information that takes the user's psychological state into consideration.

[0147] Users can review the information received via their device and provide feedback to the system as needed. This allows users to effectively manage their energy levels without feeling anxious or stressed.

[0148] For example, if a household experiences a sudden surge in electricity consumption late at night, the server detects this anomaly and promptly notifies the terminal. The terminal then communicates this information to the user and simultaneously assesses the user's emotional state. If the user is feeling anxious, the terminal provides a detailed cause analysis and solutions to alleviate their concerns. This process allows the user to have a better energy management experience.

[0149] An example of a prompt to input into the generating AI model might be, "Generate a notification method to reduce user anxiety when there is abnormal energy consumption." Based on this prompt, the AI ​​model can make specific and useful suggestions.

[0150] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0151] Step 1:

[0152] The server periodically acquires energy consumption information from the measuring device. In this process, power usage information transmitted from the measuring device is input to the server, and this data is stored in a database in real time. The collected data is formatted for analysis and output as hourly consumption patterns.

[0153] Step 2:

[0154] The server feeds the collected energy consumption information into machine learning methods to detect anomalies. The input data is compared to normal usage patterns, detecting sudden fluctuations in consumption and usage times that defy common sense. As a result of this analysis, output data indicating anomalies is generated, preparing for the next step.

[0155] Step 3:

[0156] The server analyzes existing pricing plans based on anomaly detection results and proposes the optimal plan to the user. Using anomaly detection data and current pricing plan information as input, it performs calculations to output the most cost-effective pricing plan for the user.

[0157] Step 4:

[0158] The terminal displays anomaly notifications and pricing plan suggestions received from the server to the user. The terminal has a built-in emotion engine that takes the user's facial expressions and voice data as input. The emotion engine analyzes this data and outputs the user's emotional state.

[0159] Step 5:

[0160] The device adjusts notification content according to the user's emotional state. If the user indicates anxiety, it generates and outputs a detailed notification that includes a specific cause analysis and reassuring messages. This enables appropriate information delivery tailored to the user's psychological state.

[0161] Step 6:

[0162] Users review notifications received through their devices and provide feedback as needed. This user feedback is entered into the server for future data analysis and notification adjustments, and is used to improve the entire system. This process results in a better energy management experience.

[0163] (Application Example 2)

[0164] 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".

[0165] In modern society, the efficient use of energy is a crucial issue. In particular, there is a need to quickly detect anomalies in energy consumption and communicate this information to users in an easily understandable way. However, current systems merely present data and fail to provide feedback that takes into account the user's emotional state. As a result, users may experience unnecessary stress. To solve these problems and provide more effective energy consumption management, it is necessary to provide information that is tailored to the user's emotional state.

[0166] 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.

[0167] In this invention, the server includes means for collecting energy consumption data, means for detecting anomalies, means for analyzing multiple pricing plans and recommending the optimal plan, and means for adjusting notification content and methods based on emotional state. This enables energy management and optimization that takes user emotions into consideration.

[0168] "Means for collecting energy consumption data" refers to a device or system that has the function of collecting information on energy usage obtained from measuring devices or sensors.

[0169] "Means for detecting anomalies" refers to a device or system that has the function of automatically identifying data that deviates from normal consumption patterns and issuing warnings.

[0170] "A means of analyzing multiple pricing plans and recommending the optimal plan" refers to a device or system that has the function of comparing various available pricing plans and proposing the most cost-effective plan based on individual consumption patterns.

[0171] "Means for evaluating a user's emotional state" refers to a device or system that has the function of determining a user's emotions and psychological state using technologies such as speech recognition and facial expression analysis.

[0172] "Means for adjusting notification content and method based on emotional state" refers to a device or system that has the function of selecting the most effective means and content of information delivery according to the user's current emotions.

[0173] A "measuring device" is a device that has the function of measuring energy consumption and electronically transmitting that data.

[0174] "Machine learning techniques" are advanced algorithms and technologies used to find regularities and patterns in data and make predictions and decisions based on them.

[0175] The system for carrying out the present invention consists of a server, a terminal, and a user.

[0176] The server is primarily responsible for collecting energy consumption data and detecting anomalies. A metering device is connected to the server, from which it acquires data on energy usage. The server receives data transmitted from the metering device and uses machine learning techniques to automatically detect abnormal consumption patterns. Furthermore, the server analyzes multiple pricing plans, selects the optimal plan based on the data, and generates recommendations. The software used for this process includes Python for data analysis and Tensorflow® for machine learning.

[0177] The terminal receives information about anomalies and recommended plans detected by the server and notifies the user. The terminal is equipped with functions to assess the user's emotional state, performing voice recognition and facial expression analysis through the camera and microphone. This allows the terminal to analyze the user's current emotions and adjust the notification content and format accordingly. The user interface uses Unity and features an intuitive design.

[0178] Users receive information via their devices. By reviewing their consumption patterns and responding to suggestions based on the notifications, they can achieve more efficient energy management. User feedback on their emotions helps the system strive to provide even more accurate notifications.

[0179] For example, if a rapid temperature increase is predicted in a certain area, energy consumption may increase. In this case, the system will detect the anomaly and suggest efficient air conditioner usage methods and optimal pricing plans to alleviate the user's concerns.

[0180] An example of a prompt to a generative AI model would be: "Temperatures are forecast to be higher than usual this weekend. Increased energy consumption is expected, but we need advice on how to stay comfortable while being efficient. Please suggest an optimal energy consumption plan."

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The server periodically collects energy consumption data from the metering device. It receives real-time consumption data transmitted from the metering device as input and stores it directly in the database. This initiates data accumulation.

[0184] Step 2:

[0185] The server inputs the collected energy data into a machine learning model and runs an anomaly detection algorithm. The input data is compared to past normal consumption patterns, and anomalous data points are identified as output. This process utilizes a TensorFlow anomaly detection model.

[0186] Step 3:

[0187] The server uses the results of an anomaly detection algorithm to analyze multiple pricing plans and select the optimal plan based on usage patterns. The input includes detected anomaly data and existing pricing plan information, and the output recommends the most suitable pricing plan for the user. This analysis is performed using Python.

[0188] Step 4:

[0189] The terminal prepares to notify the user of anomaly warnings and pricing plans received from the server. It receives recommended data from the server as input and outputs it in a form integrated into the user interface. Visual notifications are provided on the terminal using Unity.

[0190] Step 5:

[0191] The device uses a camera and microphone to evaluate the user's emotional state. It acquires audio data and facial expression data as input and processes them using an emotion analysis algorithm. The output is data representing the analyzed emotional state of the user. This evaluation utilizes natural language processing and facial expression recognition technologies.

[0192] Step 6:

[0193] The device selects the optimal notification content and method based on the analyzed emotional state. The input consists of emotional state data and notification content, and the output is an optimized notification sent to the user. During this process, the notification content is adjusted to avoid causing stress to the user.

[0194] Step 7:

[0195] Users receive information provided through their devices and take action as needed. Users input feedback into their devices, and the system adjusts accordingly so that it is reflected in future notifications. This improves the accuracy of the system and the user experience.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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".

[0212] This invention is a system for efficiently utilizing energy consumption data. This system mainly consists of a server, terminals, and users.

[0213] The server is responsible for collecting energy consumption data from smart meters in real time. The collected data is stored in a database for analysis. The server uses machine learning algorithms to detect anomalies based on the collected data. This anomaly detection makes it possible to identify deviations from normal consumption patterns in real time.

[0214] The terminal receives data from the server and issues an alert to the user if an anomaly is detected. The alert is notified with a specific message, such as "Abnormal consumption has occurred." The terminal also has the function to analyze multiple pricing plans provided by the server and select the plan that best suits the user's actual consumption pattern. This function makes it possible to recommend plans to the user or suggest new pricing plans.

[0215] Users receive notifications from their devices and can consider taking action regarding abnormal consumption or switching to a more economical pricing plan. Based on the information received, users can review their appliance usage or change their contract plan as needed.

[0216] As a concrete example, consider a case where electricity consumption in a household suddenly increases during the night. In this case, the server detects this anomaly and notifies the user via a terminal. Based on the notification, the user can investigate the household appliances operating at night and take measures such as turning off unnecessary devices. Furthermore, by switching to a rate plan suggested by the terminal, the user can save on their monthly electricity bill. In this way, the present invention provides an effective means for optimizing energy consumption.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The server collects energy consumption data from homes or businesses via a smart meter API. This data includes electricity and gas usage during specific time periods and is stored in a database in real time.

[0220] Step 2:

[0221] The server executes an anomaly detection algorithm based on the collected data. Here, a machine learning algorithm is used to identify data points that deviate from normal consumption patterns, i.e., anomalous consumption.

[0222] Step 3:

[0223] If an anomaly is detected, the terminal receives the information from the server and generates an anomaly alert for the user. The alert includes information about the time period when the anomaly occurred and detailed consumption patterns.

[0224] Step 4:

[0225] The server considers multiple pricing plans and analyzes which plan offers the most economic benefit using user consumption data. Clustering techniques are then used to evaluate the suitability of each plan.

[0226] Step 5:

[0227] Based on the analysis results, the device will notify the user of the most suitable pricing plan. The notification will include the benefits of the new plan and the potential savings compared to the current plan.

[0228] Step 6:

[0229] Users receive notifications from their devices and take specific actions. For example, they can reduce energy costs by checking the usage of home appliances to eliminate the cause of abnormal consumption or by changing to a suggested plan.

[0230] (Example 1)

[0231] 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."

[0232] Optimizing energy consumption is a crucial issue in modern homes and businesses, but it is difficult for consumers to understand their own consumption patterns and select appropriate pricing plans. Furthermore, there is the challenge of quickly identifying and addressing the cause of sudden, abnormal consumption.

[0233] 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.

[0234] In this invention, the server includes means for collecting energy consumption data from a measuring device in real time, means for preprocessing the data and detecting abnormal consumption patterns using a machine learning algorithm, and means for selecting and visualizing the optimal pricing plan based on the analysis results. This enables efficient energy management and rapid response to anomalies.

[0235] "Energy consumption data" refers to data that contains detailed information about energy use, and is usually digital data showing the usage of electricity, gas, water, etc.

[0236] A "measuring device" is a device used to measure energy consumption, and is commonly known as a smart meter.

[0237] "Real-time" means that data and information are processed immediately and are available without any time delay.

[0238] "Preprocessing" refers to the process of converting raw data into a format that can be analyzed, and includes operations such as data cleaning and formatting standardization.

[0239] A "machine learning algorithm" is a mathematical model used to learn patterns and rules from data, and is a technique used for anomaly detection and predictive analytics.

[0240] An "abnormal consumption pattern" refers to consumption patterns or trends that deviate significantly from normal energy consumption, and usually suggests malfunction or failure.

[0241] A "pricing plan" is a pricing option offered by an energy supplier to consumers, and includes different billing systems based on usage and time of day.

[0242] "Visualization" refers to the visual representation of data and analysis results, using graphs, charts, and other tools to make information easily understandable.

[0243] An "electronic notification device" is a device that notifies information by electronic means, and includes communication terminals such as smartphones and computers.

[0244] This invention provides a system that enables efficient management of energy consumption and includes server, terminal, and user components. Each component plays a specific role, and together they contribute to optimizing the user's energy consumption.

[0245] The server first collects energy consumption data in real time from measuring devices. To do this, an API is developed using a programming language such as Python to communicate with the measuring devices. The collected data is stored in a database and preprocessed using Pandas. The scikit-learn library in Python is used to apply machine learning algorithms to the preprocessed data to detect abnormal consumption patterns. This anomaly detection enables early detection and rapid response to fraudulent consumption.

[0246] The device receives analysis results sent from the server and electronically notifies the user. The device uses JavaScript to visualize the collected data and displays it in an easy-to-understand format. The notifications sent to the user are specific, including details such as, "Twice the normal consumption was detected during the late-night hours." The device also uses Python's NumPy to analyze multiple pricing plans and suggest the optimal plan to the user. This allows the user to consider a rational plan change based on their consumption patterns.

[0247] Users receive notifications from their devices and adjust their electricity consumption as needed. Based on these notifications, they can take specific actions, such as turning off devices that are currently running, to prevent wasted energy. Furthermore, users can switch to new pricing plans based on the device's suggestions, achieving efficient energy management.

[0248] As a concrete example, one could input a prompt like the following into a generative AI model: "Explain how the system works by detecting sudden spikes in electricity consumption during the night and suggesting the optimal pricing plan." Such a prompt would allow the generative AI to generate a natural language explanation that accurately reflects its understanding of the system's operation. Based on this explanation, the user can further enjoy the system's convenience.

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The server collects energy consumption data in real time from the measuring device. The input is data from the measuring device, which is retrieved into the server via an API. Specifically, a Python program is used to send an HTTP request to the measuring device and receive the returned data in JSON format. The output is the collected energy consumption data.

[0252] Step 2:

[0253] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, it performs actions such as imputing missing values, correcting outliers, and converting data types. The Python Pandas library is used for this. The output is the cleaned-up data.

[0254] Step 3:

[0255] The server uses pre-processed data to detect abnormal consumption patterns. The input is the clean data obtained in step 2. Specifically, it uses Python's scikit-learn to apply machine learning algorithms. Clustering and outlier detection algorithms are used as an anomaly detection model. The output is alert information when an anomaly is detected.

[0256] Step 4:

[0257] The terminal receives analysis results from the server and sends an alert to the user. The input is the alert information generated in step 3. Specific actions include sending push notifications via email services or mobile apps. The output is the specific notification message sent to the user.

[0258] Step 5:

[0259] The device analyzes the user's energy consumption patterns and selects the optimal pricing plan. The input is the clean data from step 2. Specifically, it uses Python's NumPy to analyze multiple pricing plans and calculate the plan most suitable for the user. It then presents the visualized plan in a graph format. The output is information suggesting the optimal pricing plan for the user.

[0260] Step 6:

[0261] The user receives notifications on their device and takes appropriate action. The input is the notification and plan information obtained in steps 4 and 5. Specifically, the user follows the notification and adjusts the device's operation or changes their pricing plan. This results in energy savings and cost reductions. The output is the optimized state of energy consumption and associated costs.

[0262] (Application Example 1)

[0263] 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."

[0264] Modern cities require optimized energy resource management, but there are problems with the rapid detection of fraudulent consumption data from residents and public facilities, and the selection of optimal plans. Furthermore, while real-time monitoring of consumption patterns is expected to lead to more efficient energy management, current systems lack the information processing capabilities to achieve this.

[0265] 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.

[0266] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies using the information, and means for analyzing multiple pricing plans and recommending the optimal plan. This enables real-time monitoring of energy consumption and efficient energy management in public facilities.

[0267] "Energy consumption information" refers to data related to the amount of energy used, such as electricity, gas, and water.

[0268] "Anomaly detection" is a function that identifies fraudulent or abnormal energy usage that deviates from normal consumption patterns.

[0269] A "pricing plan" refers to a contract option offered by an energy supplier that has a different pricing structure.

[0270] "Means of notifying users" refers to communication methods or systems for informing users or related parties about anomalies or recommended plans.

[0271] "Real-time monitoring" is the process of observing information immediately and responding quickly as needed.

[0272] "Public facilities" refer to buildings or places owned by private companies or the government, such as libraries, parks, and hospitals, that are used by many people.

[0273] "Energy management" is the process of planning and implementing measures to optimize energy use and improve efficiency.

[0274] In an embodiment of this invention, the server collects energy consumption information in real time and processes it to detect anomalies. The server stores the data obtained from the smart meter in a database and uses a machine learning algorithm to identify unusual consumption patterns. The results of this anomaly detection are notified to the terminal.

[0275] The device receives anomaly alerts sent from the server and notifies the user. These notifications include specific details about the anomaly and suggestions for changing the plan. Furthermore, the device has the functionality to select and recommend the optimal pricing plan based on the user's consumption patterns.

[0276] Based on notifications from their devices, users can take steps to reduce energy waste. For example, they can check for unnecessary power consumption at night and adjust their use of electrical appliances. They can also switch to a more economical energy plan based on plan suggestions from their devices.

[0277] For example, if a household records a sudden surge in electricity consumption at night, the server will detect this as an anomaly and send a notification to the terminal. The terminal will warn the user that "abnormal consumption has occurred" and simultaneously offer suggestions such as "Why not switch to a more cost-effective rate plan?" Through this process, energy management is carried out efficiently and effectively.

[0278] An example of a prompt is, "Explain how to analyze energy consumption data and suggest an efficient plan."

[0279] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0280] Step 1:

[0281] The server collects energy consumption information from the smart meter in real time. This input data records the consumption amount for each time period and is stored in the database. In this step, the server performs a process of formatting the collected raw data into an analyzable format.

[0282] Step 2:

[0283] The server performs anomaly detection based on the collected energy consumption information. The consumption data stored in the database is input into the machine learning model to determine whether it deviates from the normal consumption pattern. Cases determined to be abnormal are flagged and passed on to the next process.

[0284] Step 3:

[0285] The server performs an analysis of the energy consumption pattern for each user together with the anomaly determination result. Based on this analysis result, an operation is carried out to select the optimal plan from multiple tariff plans. This selection result is transmitted to the terminal as the recommended plan.

[0286] Step 4:

[0287] The terminal receives the anomaly alert and the recommended plan from the server. Based on these input information, a warning about the specific abnormal content and a proposal for changing the tariff plan are notified to the user. The notification is carried out visually and audibly to prompt the user's attention.

[0288] Step 5:

[0289] Users check notifications from their devices and take action based on the information presented. Specifically, they review their devices and settings to check for abnormal energy consumption and consider switching to a plan suggested by the device. This final action by the user completes a feedback loop that optimizes energy management.

[0290] 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.

[0291] This invention provides a system that efficiently analyzes energy consumption data and takes into account the user's emotional state to offer more personalized energy management. The system primarily consists of a server, terminals, and users, and incorporates an emotion engine.

[0292] The server collects energy consumption data from smart meters and uses machine learning algorithms to detect anomalies. This allows it to identify deviations from normal consumption patterns. The server also has the functionality to analyze pricing plans and recommend the most suitable plan for the user.

[0293] The device receives anomalies detected by the server and recommended pricing plans, and notifies the user. In addition, the device has an emotion engine that can evaluate the user's emotions based on their facial expression and voice data. The content and method of notifications are adjusted according to the output of the emotion engine. In this way, it becomes possible to provide information that takes the user's state into consideration.

[0294] Users receive anomaly alerts and recommended plans via their devices. Furthermore, they can provide feedback on their emotional state through interaction with an emotion engine. This enables energy management that reduces user stress and frustration.

[0295] As a concrete example, if electricity consumption suddenly increases in a household late at night, the server detects this anomaly and notifies the terminal. The terminal simultaneously assesses the user's emotions, determining whether they are worried or indifferent. If the user indicates anxiety, the system provides a detailed cause analysis and suggested solutions, tailoring the notification to enhance the user's sense of security. This aims to achieve energy management that goes beyond mere data provision and is more user-centric.

[0296] The following describes the processing flow.

[0297] Step 1:

[0298] The server collects energy consumption data via a smart meter API and stores it in a database. The data includes information on electricity and gas usage, as well as time of day.

[0299] Step 2:

[0300] The server uses machine learning algorithms to detect abnormal consumption patterns from the collected data. It identifies fraudulent or wasteful energy use and records it as an alert.

[0301] Step 3:

[0302] The server evaluates pricing plans based on the user's past consumption data and calculates the most suitable plan for the user. It compares multiple plans and selects the one with the best cost-performance ratio.

[0303] Step 4:

[0304] The device receives anomaly alerts and recommended pricing plans from the server and notifies the user of this information. The alerts include details of the unusual consumption.

[0305] Step 5:

[0306] The terminal uses an emotion engine to analyze the user's facial expression and voice data, and evaluate the emotional state in real time. As a result, the notification method and content are adjusted according to the user's emotional state.

[0307] Step 6:

[0308] The user checks the notification from the terminal and considers taking measures against abnormal consumption or changing to a recommended plan. Based on the feedback from the emotion engine, the user can respond according to their own emotions.

[0309] Step 7:

[0310] The server and the terminal analyze the interaction data based on the emotion engine, and continuously improve the personalization of the entire energy management system. To improve the user experience, the learning results are utilized next.

[0311] (Example 2)

[0312] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0313] In the conventional energy management system, although abnormal detection of energy consumption and proposal of a fee plan are performed, personalized information provision considering the user's emotional state has not been provided. Therefore, the effect of reducing the user's anxiety and suspicion is insufficient, and there is a limit to providing an optimal energy management experience.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0315] In this invention, the server includes means for collecting energy consumption information, means for detecting abnormalities, and means for evaluating the user's emotional state. As a result, the notification content can be appropriately adjusted based on the user's emotional state, and optimal energy management can be achieved while reducing the user's anxiety.

[0316] "Energy consumption information" refers to data showing the electricity usage in homes and facilities, and is acquired using smart meters or similar measuring devices.

[0317] "Anomaly detection" is the process of analyzing collected energy consumption information to identify phenomena that deviate from normal consumption patterns, and it is achieved using machine learning techniques.

[0318] "Rate plan analysis" is a process that evaluates existing electricity rate plans based on energy consumption information and recommends the most economical and efficient plan to users.

[0319] "User emotional state" refers to the psychological condition evaluated based on data such as the user's facial expressions and voice, and is a factor that influences the understanding and acceptance of information.

[0320] "Adjusting notification content" is a process that takes into account the user's emotional state and customizes the format and content of information provided by the system to ensure more appropriate and effective communication.

[0321] This invention is a system for efficiently managing energy consumption information, and is composed primarily of a server, terminals, and users. This system collects energy consumption information in real time and enables anomaly detection, optimal pricing plan suggestions, and notification adjustments based on the user's emotional state.

[0322] The server acquires energy consumption information from measuring devices. This data collection is performed regularly and automatically, accumulating a large amount of data. The server analyzes the data using machine learning techniques (e.g., anomaly detection algorithms) to identify anomalies that deviate from normal consumption patterns. Furthermore, it has the ability to evaluate multiple existing pricing plans and propose the most suitable pricing plan for the user.

[0323] The terminal notifies the user of anomaly detection information and pricing plan suggestions sent from the server. During this process, a built-in emotion engine analyzes the user's facial expression and voice data to evaluate their emotional state. The notification content and method are adjusted based on this emotion evaluation, enabling the provision of information that takes the user's psychological state into consideration.

[0324] Users can review the information received via their device and provide feedback to the system as needed. This allows users to effectively manage their energy levels without feeling anxious or stressed.

[0325] For example, if a household experiences a sudden surge in electricity consumption late at night, the server detects this anomaly and promptly notifies the terminal. The terminal then communicates this information to the user and simultaneously assesses the user's emotional state. If the user is feeling anxious, the terminal provides a detailed cause analysis and solutions to alleviate their concerns. This process allows the user to have a better energy management experience.

[0326] An example of a prompt to input into the generating AI model might be, "Generate a notification method to reduce user anxiety when there is abnormal energy consumption." Based on this prompt, the AI ​​model can make specific and useful suggestions.

[0327] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0328] Step 1:

[0329] The server periodically acquires energy consumption information from the measuring device. In this process, power usage information transmitted from the measuring device is input to the server, and this data is stored in a database in real time. The collected data is formatted for analysis and output as hourly consumption patterns.

[0330] Step 2:

[0331] The server feeds the collected energy consumption information into machine learning methods to detect anomalies. The input data is compared to normal usage patterns, detecting sudden fluctuations in consumption and usage times that defy common sense. As a result of this analysis, output data indicating anomalies is generated, preparing for the next step.

[0332] Step 3:

[0333] The server analyzes existing pricing plans based on anomaly detection results and proposes the optimal plan to the user. Using anomaly detection data and current pricing plan information as input, it performs calculations to output the most cost-effective pricing plan for the user.

[0334] Step 4:

[0335] The terminal displays anomaly notifications and pricing plan suggestions received from the server to the user. The terminal has a built-in emotion engine that takes the user's facial expressions and voice data as input. The emotion engine analyzes this data and outputs the user's emotional state.

[0336] Step 5:

[0337] The device adjusts notification content according to the user's emotional state. If the user indicates anxiety, it generates and outputs a detailed notification that includes a specific cause analysis and reassuring messages. This enables appropriate information delivery tailored to the user's psychological state.

[0338] Step 6:

[0339] Users review notifications received through their devices and provide feedback as needed. This user feedback is entered into the server for future data analysis and notification adjustments, and is used to improve the entire system. This process results in a better energy management experience.

[0340] (Application Example 2)

[0341] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0342] In modern society, the efficient use of energy is a crucial issue. In particular, there is a need to quickly detect anomalies in energy consumption and communicate this information to users in an easily understandable way. However, current systems merely present data and fail to provide feedback that takes into account the user's emotional state. As a result, users may experience unnecessary stress. To solve these problems and provide more effective energy consumption management, it is necessary to provide information that is tailored to the user's emotional state.

[0343] 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.

[0344] In this invention, the server includes means for collecting energy consumption data, means for detecting anomalies, means for analyzing multiple pricing plans and recommending the optimal plan, and means for adjusting notification content and methods based on emotional state. This enables energy management and optimization that takes user emotions into consideration.

[0345] "Means for collecting energy consumption data" refers to a device or system that has the function of collecting information on energy usage obtained from measuring devices or sensors.

[0346] "Means for detecting anomalies" refers to a device or system that has the function of automatically identifying data that deviates from normal consumption patterns and issuing warnings.

[0347] "A means of analyzing multiple pricing plans and recommending the optimal plan" refers to a device or system that has the function of comparing various available pricing plans and proposing the most cost-effective plan based on individual consumption patterns.

[0348] "Means for evaluating a user's emotional state" refers to a device or system that has the function of determining a user's emotions and psychological state using technologies such as speech recognition and facial expression analysis.

[0349] "Means for adjusting notification content and method based on emotional state" refers to a device or system that has the function of selecting the most effective means and content of information delivery according to the user's current emotions.

[0350] A "measuring device" is a device that has the function of measuring energy consumption and electronically transmitting that data.

[0351] "Machine learning techniques" are advanced algorithms and technologies used to find regularities and patterns in data and make predictions and decisions based on them.

[0352] The system for carrying out the present invention consists of a server, a terminal, and a user.

[0353] The server is primarily responsible for collecting energy consumption data and detecting anomalies. A metering device is connected to the server, from which it acquires data on energy usage. The server receives the data transmitted from the metering device and uses machine learning techniques to automatically detect abnormal consumption patterns. Furthermore, the server analyzes multiple pricing plans, selects the optimal plan based on the data, and generates recommendations. The software used for this process includes Python for data analysis and TensorFlow for machine learning.

[0354] The terminal receives information about anomalies and recommended plans detected by the server and notifies the user. The terminal is equipped with functions to assess the user's emotional state, performing voice recognition and facial expression analysis through the camera and microphone. This allows the terminal to analyze the user's current emotions and adjust the notification content and format accordingly. The user interface uses Unity and features an intuitive design.

[0355] Users receive information via their devices. By reviewing their consumption patterns and responding to suggestions based on the notifications, they can achieve more efficient energy management. User feedback on their emotions helps the system strive to provide even more accurate notifications.

[0356] For example, if a rapid temperature increase is predicted in a certain area, energy consumption may increase. In this case, the system will detect the anomaly and suggest efficient air conditioner usage methods and optimal pricing plans to alleviate the user's concerns.

[0357] An example of a prompt to a generative AI model would be: "Temperatures are forecast to be higher than usual this weekend. Increased energy consumption is expected, but we need advice on how to stay comfortable while being efficient. Please suggest an optimal energy consumption plan."

[0358] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0359] Step 1:

[0360] The server periodically collects energy consumption data from the metering device. It receives real-time consumption data transmitted from the metering device as input and stores it directly in the database. This initiates data accumulation.

[0361] Step 2:

[0362] The server inputs the collected energy data into a machine learning model and runs an anomaly detection algorithm. The input data is compared to past normal consumption patterns, and anomalous data points are identified as output. This process utilizes a TensorFlow anomaly detection model.

[0363] Step 3:

[0364] The server uses the results of an anomaly detection algorithm to analyze multiple pricing plans and select the optimal plan based on usage patterns. The input includes detected anomaly data and existing pricing plan information, and the output recommends the most suitable pricing plan for the user. This analysis is performed using Python.

[0365] Step 4:

[0366] The terminal prepares to notify the user of anomaly warnings and pricing plans received from the server. It receives recommended data from the server as input and outputs it in a form integrated into the user interface. Visual notifications are provided on the terminal using Unity.

[0367] Step 5:

[0368] The device uses a camera and microphone to evaluate the user's emotional state. It acquires audio data and facial expression data as input and processes them using an emotion analysis algorithm. The output is data representing the analyzed emotional state of the user. This evaluation utilizes natural language processing and facial expression recognition technologies.

[0369] Step 6:

[0370] The device selects the optimal notification content and method based on the analyzed emotional state. The input consists of emotional state data and notification content, and the output is an optimized notification sent to the user. During this process, the notification content is adjusted to avoid causing stress to the user.

[0371] Step 7:

[0372] Users receive information provided through their devices and take action as needed. Users input feedback into their devices, and the system adjusts accordingly so that it is reflected in future notifications. This improves the accuracy of the system and the user experience.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] [Third Embodiment]

[0377] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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".

[0389] This invention is a system for efficiently utilizing energy consumption data. This system mainly consists of a server, terminals, and users.

[0390] The server is responsible for collecting energy consumption data from smart meters in real time. The collected data is stored in a database for analysis. The server uses machine learning algorithms to detect anomalies based on the collected data. This anomaly detection makes it possible to identify deviations from normal consumption patterns in real time.

[0391] The terminal receives data from the server and issues an alert to the user if an anomaly is detected. The alert is notified with a specific message, such as "Abnormal consumption has occurred." The terminal also has the function to analyze multiple pricing plans provided by the server and select the plan that best suits the user's actual consumption pattern. This function makes it possible to recommend plans to the user or suggest new pricing plans.

[0392] Users receive notifications from their devices and can consider taking action regarding abnormal consumption or switching to a more economical pricing plan. Based on the information received, users can review their appliance usage or change their contract plan as needed.

[0393] As a concrete example, consider a case where electricity consumption in a household suddenly increases during the night. In this case, the server detects this anomaly and notifies the user via a terminal. Based on the notification, the user can investigate the household appliances operating at night and take measures such as turning off unnecessary devices. Furthermore, by switching to a rate plan suggested by the terminal, the user can save on their monthly electricity bill. In this way, the present invention provides an effective means for optimizing energy consumption.

[0394] The following describes the processing flow.

[0395] Step 1:

[0396] The server collects energy consumption data from homes or businesses via a smart meter API. This data includes electricity and gas usage during specific time periods and is stored in a database in real time.

[0397] Step 2:

[0398] The server executes an anomaly detection algorithm based on the collected data. Here, a machine learning algorithm is used to identify data points that deviate from normal consumption patterns, i.e., abnormal consumption.

[0399] Step 3:

[0400] If an anomaly is detected, the terminal receives the information from the server and generates an anomaly alert for the user. The alert includes information about the time period when the anomaly occurred and detailed consumption patterns.

[0401] Step 4:

[0402] The server considers multiple pricing plans and analyzes which plan offers the most economic benefit using user consumption data. Clustering techniques are then used to evaluate the suitability of each plan.

[0403] Step 5:

[0404] Based on the analysis results, the device will notify the user of the most suitable pricing plan. The notification will include the benefits of the new plan and the potential savings compared to the current plan.

[0405] Step 6:

[0406] Users receive notifications from their devices and take specific actions. For example, they can reduce energy costs by checking the usage of home appliances to eliminate the cause of abnormal consumption or by changing to a suggested plan.

[0407] (Example 1)

[0408] 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."

[0409] Optimizing energy consumption is a crucial issue in modern homes and businesses, but it is difficult for consumers to understand their own consumption patterns and select appropriate pricing plans. Furthermore, there is the challenge of quickly identifying and addressing the cause of sudden, abnormal consumption.

[0410] 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.

[0411] In this invention, the server includes means for collecting energy consumption data from a measuring device in real time, means for preprocessing the data and detecting abnormal consumption patterns using a machine learning algorithm, and means for selecting and visualizing the optimal pricing plan based on the analysis results. This enables efficient energy management and rapid response to anomalies.

[0412] "Energy consumption data" refers to data that contains detailed information about energy use, and is usually digital data showing the usage of electricity, gas, water, etc.

[0413] A "measuring device" is a device used to measure energy consumption, and is commonly known as a smart meter.

[0414] "Real-time" means that data and information are processed immediately and are available without any time delay.

[0415] "Preprocessing" refers to the process of converting raw data into a format that can be analyzed, and includes operations such as data cleaning and formatting standardization.

[0416] A "machine learning algorithm" is a mathematical model used to learn patterns and rules from data, and is a technique used for anomaly detection and predictive analytics.

[0417] An "abnormal consumption pattern" refers to consumption patterns or trends that deviate significantly from normal energy consumption, and usually suggests malfunction or failure.

[0418] A "pricing plan" is a pricing option offered by an energy supplier to consumers, and includes different billing systems based on usage and time of day.

[0419] "Visualization" refers to the visual representation of data and analysis results, using graphs, charts, and other tools to make information easily understandable.

[0420] An "electronic notification device" is a device that notifies information by electronic means, and includes communication terminals such as smartphones and computers.

[0421] This invention provides a system that enables efficient management of energy consumption and includes server, terminal, and user components. Each component plays a specific role, and together they contribute to optimizing the user's energy consumption.

[0422] The server first collects energy consumption data in real time from measuring devices. To do this, an API is developed using a programming language such as Python to communicate with the measuring devices. The collected data is stored in a database and preprocessed using Pandas. The scikit-learn library in Python is used to apply machine learning algorithms to the preprocessed data to detect abnormal consumption patterns. This anomaly detection enables early detection and rapid response to fraudulent consumption.

[0423] The device receives analysis results sent from the server and electronically notifies the user. The device uses JavaScript to visualize the collected data and displays it in an easy-to-understand format. The notifications sent to the user are specific, including details such as, "Twice the normal consumption was detected during the late-night hours." The device also uses Python's NumPy to analyze multiple pricing plans and suggest the optimal plan to the user. This allows the user to consider a rational plan change based on their consumption patterns.

[0424] Users receive notifications from their devices and adjust their electricity consumption as needed. Based on these notifications, they can take specific actions, such as turning off devices that are currently running, to prevent wasted energy. Furthermore, users can switch to new pricing plans based on the device's suggestions, achieving efficient energy management.

[0425] As a concrete example, one could input a prompt like the following into a generative AI model: "Explain how the system works by detecting sudden spikes in electricity consumption during the night and suggesting the optimal pricing plan." Such a prompt would allow the generative AI to generate a natural language explanation that accurately reflects its understanding of the system's operation. Based on this explanation, the user can further enjoy the system's convenience.

[0426] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0427] Step 1:

[0428] The server collects energy consumption data in real time from the measuring device. The input is data from the measuring device, which is retrieved into the server via an API. Specifically, a Python program is used to send an HTTP request to the measuring device and receive the returned data in JSON format. The output is the collected energy consumption data.

[0429] Step 2:

[0430] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, it performs actions such as imputing missing values, correcting outliers, and converting data types. The Python Pandas library is used for this. The output is the cleaned-up data.

[0431] Step 3:

[0432] The server uses pre-processed data to detect abnormal consumption patterns. The input is the clean data obtained in step 2. Specifically, it uses Python's scikit-learn to apply machine learning algorithms. Clustering and outlier detection algorithms are used as an anomaly detection model. The output is alert information when an anomaly is detected.

[0433] Step 4:

[0434] The terminal receives analysis results from the server and sends an alert to the user. The input is the alert information generated in step 3. Specific actions include sending push notifications via email services or mobile apps. The output is the specific notification message sent to the user.

[0435] Step 5:

[0436] The device analyzes the user's energy consumption patterns and selects the optimal pricing plan. The input is the clean data from step 2. Specifically, it uses Python's NumPy to analyze multiple pricing plans and calculate the plan most suitable for the user. It then presents the visualized plan in a graph format. The output is information suggesting the optimal pricing plan for the user.

[0437] Step 6:

[0438] The user receives notifications on their device and takes appropriate action. The input is the notification and plan information obtained in steps 4 and 5. Specifically, the user follows the notification and adjusts the device's operation or changes their pricing plan. This results in energy savings and cost reductions. The output is the optimized state of energy consumption and associated costs.

[0439] (Application Example 1)

[0440] 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."

[0441] Modern cities require optimized energy resource management, but there are problems with the rapid detection of fraudulent consumption data from residents and public facilities, and the selection of optimal plans. Furthermore, while real-time monitoring of consumption patterns is expected to lead to more efficient energy management, current systems lack the information processing capabilities to achieve this.

[0442] 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.

[0443] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies using the information, and means for analyzing multiple pricing plans and recommending the optimal plan. This enables real-time monitoring of energy consumption and efficient energy management in public facilities.

[0444] "Energy consumption information" refers to data related to the amount of energy used, such as electricity, gas, and water.

[0445] "Anomaly detection" is a function that identifies fraudulent or abnormal energy usage that deviates from normal consumption patterns.

[0446] A "pricing plan" refers to a contract option offered by an energy supplier that has a different pricing structure.

[0447] "Means of notifying users" refers to communication methods or systems for informing users or related parties about anomalies or recommended plans.

[0448] "Real-time monitoring" is the process of observing information immediately and responding quickly as needed.

[0449] "Public facilities" refer to buildings or places owned by private companies or the government, such as libraries, parks, and hospitals, that are used by many people.

[0450] "Energy management" is the process of planning and implementing measures to optimize energy use and improve efficiency.

[0451] In an embodiment of this invention, the server collects energy consumption information in real time and processes it to detect anomalies. The server stores the data obtained from the smart meter in a database and uses a machine learning algorithm to identify unusual consumption patterns. The results of this anomaly detection are notified to the terminal.

[0452] The device receives anomaly alerts sent from the server and notifies the user. These notifications include specific details about the anomaly and suggestions for changing the plan. Furthermore, the device has the functionality to select and recommend the optimal pricing plan based on the user's consumption patterns.

[0453] Based on notifications from their devices, users can take steps to reduce energy waste. For example, they can check for unnecessary power consumption at night and adjust their use of electrical appliances. They can also switch to a more economical energy plan based on plan suggestions from their devices.

[0454] For example, if a household records a sudden surge in electricity consumption at night, the server will detect this as an anomaly and send a notification to the terminal. The terminal will warn the user that "abnormal consumption has occurred" and simultaneously offer suggestions such as "Why not switch to a more cost-effective rate plan?" Through this process, energy management is carried out efficiently and effectively.

[0455] An example of a prompt is, "Explain how to analyze energy consumption data and suggest an efficient plan."

[0456] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0457] Step 1:

[0458] The server collects energy consumption information from smart meters in real time. This input data records hourly consumption and is stored in a database. In this step, the server processes the collected raw data into a format that can be analyzed.

[0459] Step 2:

[0460] The server performs anomaly detection based on collected energy consumption information. Consumption data stored in the database is input into a machine learning model to determine if it deviates from normal consumption patterns. Cases identified as anomaly are flagged and passed on to the next process.

[0461] Step 3:

[0462] The server analyzes each user's energy consumption patterns along with the anomaly detection results. Based on this analysis, it performs calculations to select the optimal plan from multiple pricing plans. This selection result is sent to the terminal as a recommended plan.

[0463] Step 4:

[0464] The device receives anomaly alerts and recommended plans from the server. Based on this input information, it notifies the user of specific anomaly warnings and suggestions for changing their pricing plan. Notifications are made visually and audibly to draw the user's attention.

[0465] Step 5:

[0466] Users check notifications from their devices and take action based on the information presented. Specifically, they review their devices and settings to check for abnormal energy consumption and consider switching to a plan suggested by the device. This final action by the user completes a feedback loop that optimizes energy management.

[0467] 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.

[0468] This invention provides a system that efficiently analyzes energy consumption data and takes into account the user's emotional state to offer more personalized energy management. The system primarily consists of a server, terminals, and users, and incorporates an emotion engine.

[0469] The server collects energy consumption data from smart meters and uses machine learning algorithms to detect anomalies. This allows it to identify deviations from normal consumption patterns. The server also has the functionality to analyze pricing plans and recommend the most suitable plan for the user.

[0470] The device receives anomalies detected by the server and recommended pricing plans, and notifies the user. In addition, the device has an emotion engine that can evaluate the user's emotions based on their facial expression and voice data. The content and method of notifications are adjusted according to the output of the emotion engine. In this way, it becomes possible to provide information that takes the user's state into consideration.

[0471] Users receive anomaly alerts and recommended plans via their devices. Furthermore, they can provide feedback on their emotional state through interaction with an emotion engine. This enables energy management in a way that reduces user stress and frustration.

[0472] As a concrete example, if electricity consumption suddenly increases in a household late at night, the server detects this anomaly and notifies the terminal. The terminal simultaneously assesses the user's emotions, determining whether they are worried or indifferent. If the user indicates anxiety, the system provides a detailed cause analysis and suggested solutions, tailoring the notification to enhance the user's sense of security. This aims to achieve energy management that goes beyond mere data provision and is more user-centric.

[0473] The following describes the processing flow.

[0474] Step 1:

[0475] The server collects energy consumption data via a smart meter API and stores it in a database. The data includes information on electricity and gas usage, as well as time of day.

[0476] Step 2:

[0477] The server uses machine learning algorithms to detect abnormal consumption patterns from the collected data. It identifies fraudulent or wasteful energy use and records it as an alert.

[0478] Step 3:

[0479] The server evaluates pricing plans based on the user's past consumption data and calculates the most suitable plan for the user. It compares multiple plans and selects the one with the best cost-performance ratio.

[0480] Step 4:

[0481] The device receives anomaly alerts and recommended pricing plans from the server and notifies the user of this information. The alerts include details of the unusual consumption.

[0482] Step 5:

[0483] The device uses an emotion engine to analyze the user's facial expressions and voice data, and evaluates their emotional state in real time. As a result, notification methods and content are adjusted according to the user's emotional state.

[0484] Step 6:

[0485] Users can check notifications from their devices and consider taking action regarding abnormal consumption or switching to a recommended plan. Based on feedback from the emotion engine, they can respond in a way that suits their own emotions.

[0486] Step 7:

[0487] The server and terminal analyze interaction data based on the emotion engine to continuously improve the personalization of the entire energy management system. The learned results are then used to improve the user experience.

[0488] (Example 2)

[0489] 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."

[0490] Conventional energy management systems detect anomalies in energy consumption and suggest pricing plans, but they do not provide personalized information that takes into account the user's emotional state. As a result, they are insufficient in alleviating user anxiety and doubts, and have limitations in providing an optimal energy management experience.

[0491] 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.

[0492] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies, and means for evaluating the user's emotional state. This enables optimal energy management while appropriately adjusting notification content based on the user's emotional state and reducing the user's anxiety.

[0493] "Energy consumption information" refers to data showing the electricity usage in homes and facilities, and is acquired using smart meters or similar measuring devices.

[0494] "Anomaly detection" is the process of analyzing collected energy consumption information to identify phenomena that deviate from normal consumption patterns, and it is achieved using machine learning techniques.

[0495] "Rate plan analysis" is a process that evaluates existing electricity rate plans based on energy consumption information and recommends the most economical and efficient plan to users.

[0496] "User emotional state" refers to the psychological condition evaluated based on data such as the user's facial expressions and voice, and is a factor that influences the understanding and acceptance of information.

[0497] "Adjusting notification content" is a process that takes into account the user's emotional state and customizes the format and content of information provided by the system to ensure more appropriate and effective communication.

[0498] This invention is a system for efficiently managing energy consumption information, and is composed primarily of a server, terminals, and users. This system collects energy consumption information in real time and enables anomaly detection, optimal pricing plan suggestions, and notification adjustments based on the user's emotional state.

[0499] The server acquires energy consumption information from measuring devices. This data collection is performed regularly and automatically, accumulating a large amount of data. The server analyzes the data using machine learning techniques (e.g., anomaly detection algorithms) to identify anomalies that deviate from normal consumption patterns. Furthermore, it has the ability to evaluate multiple existing pricing plans and propose the most suitable pricing plan for the user.

[0500] The terminal notifies the user of anomaly detection information and pricing plan suggestions sent from the server. During this process, a built-in emotion engine analyzes the user's facial expression and voice data to evaluate their emotional state. The notification content and method are adjusted based on this emotion evaluation, enabling the provision of information that takes the user's psychological state into consideration.

[0501] Users can review the information received via their device and provide feedback to the system as needed. This allows users to effectively manage their energy levels without feeling anxious or stressed.

[0502] For example, if a household experiences a sudden surge in electricity consumption late at night, the server detects this anomaly and promptly notifies the terminal. The terminal then communicates this information to the user and simultaneously assesses the user's emotional state. If the user is feeling anxious, the terminal provides a detailed cause analysis and solutions to alleviate their concerns. This process allows the user to have a better energy management experience.

[0503] An example of a prompt to input into the generating AI model might be, "Generate a notification method to reduce user anxiety when there is abnormal energy consumption." Based on this prompt, the AI ​​model can make specific and useful suggestions.

[0504] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0505] Step 1:

[0506] The server periodically acquires energy consumption information from the measuring device. In this process, power usage information transmitted from the measuring device is input to the server, and this data is stored in a database in real time. The collected data is formatted for analysis and output as hourly consumption patterns.

[0507] Step 2:

[0508] The server feeds the collected energy consumption information into machine learning methods to detect anomalies. The input data is compared to normal usage patterns, detecting sudden fluctuations in consumption and usage times that defy common sense. As a result of this analysis, output data indicating anomalies is generated, preparing for the next step.

[0509] Step 3:

[0510] The server analyzes existing pricing plans based on anomaly detection results and proposes the optimal plan to the user. Using anomaly detection data and current pricing plan information as input, it performs calculations to output the most cost-effective pricing plan for the user.

[0511] Step 4:

[0512] The terminal displays anomaly notifications and pricing plan suggestions received from the server to the user. The terminal has a built-in emotion engine that takes the user's facial expressions and voice data as input. The emotion engine analyzes this data and outputs the user's emotional state.

[0513] Step 5:

[0514] The device adjusts notification content according to the user's emotional state. If the user indicates anxiety, it generates and outputs a detailed notification that includes a specific cause analysis and reassuring messages. This enables appropriate information delivery tailored to the user's psychological state.

[0515] Step 6:

[0516] Users review notifications received through their devices and provide feedback as needed. This user feedback is entered into the server for future data analysis and notification adjustments, and is used to improve the entire system. This process results in a better energy management experience.

[0517] (Application Example 2)

[0518] 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."

[0519] In modern society, the efficient use of energy is a crucial issue. In particular, there is a need to quickly detect anomalies in energy consumption and communicate this information to users in an easily understandable way. However, current systems merely present data and fail to provide feedback that takes into account the user's emotional state. As a result, users may experience unnecessary stress. To solve these problems and provide more effective energy consumption management, it is necessary to provide information that is tailored to the user's emotional state.

[0520] 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.

[0521] In this invention, the server includes means for collecting energy consumption data, means for detecting anomalies, means for analyzing multiple pricing plans and recommending the optimal plan, and means for adjusting notification content and methods based on emotional state. This enables energy management and optimization that takes user emotions into consideration.

[0522] "Means for collecting energy consumption data" refers to a device or system that has the function of collecting information on energy usage obtained from measuring devices or sensors.

[0523] "Means for detecting anomalies" refers to a device or system that has the function of automatically identifying data that deviates from normal consumption patterns and issuing warnings.

[0524] "A means of analyzing multiple pricing plans and recommending the optimal plan" refers to a device or system that has the function of comparing various available pricing plans and proposing the most cost-effective plan based on individual consumption patterns.

[0525] "Means for evaluating a user's emotional state" refers to a device or system that has the function of determining a user's emotions and psychological state using technologies such as speech recognition and facial expression analysis.

[0526] "Means for adjusting notification content and method based on emotional state" refers to a device or system that has the function of selecting the most effective means and content of information delivery according to the user's current emotions.

[0527] A "measuring device" is a device that has the function of measuring energy consumption and electronically transmitting that data.

[0528] "Machine learning techniques" are advanced algorithms and technologies used to find regularities and patterns in data and make predictions and decisions based on them.

[0529] The system for carrying out the present invention consists of a server, a terminal, and a user.

[0530] The server is primarily responsible for collecting energy consumption data and detecting anomalies. A metering device is connected to the server, from which it acquires data on energy usage. The server receives the data transmitted from the metering device and uses machine learning techniques to automatically detect abnormal consumption patterns. Furthermore, the server analyzes multiple pricing plans, selects the optimal plan based on the data, and generates recommendations. The software used for this process includes Python for data analysis and TensorFlow for machine learning.

[0531] The terminal receives information about anomalies and recommended plans detected by the server and notifies the user. The terminal is equipped with functions to assess the user's emotional state, performing voice recognition and facial expression analysis through the camera and microphone. This allows the terminal to analyze the user's current emotions and adjust the notification content and format accordingly. The user interface uses Unity and features an intuitive design.

[0532] Users receive information via their devices. By reviewing their consumption patterns and responding to suggestions based on the notifications, they can achieve more efficient energy management. User feedback on their emotions helps the system strive to provide even more accurate notifications.

[0533] For example, if a rapid temperature increase is predicted in a certain area, energy consumption may increase. In this case, the system will detect the anomaly and suggest efficient air conditioner usage methods and optimal pricing plans to alleviate the user's concerns.

[0534] An example of a prompt to a generative AI model would be: "Temperatures are forecast to be higher than usual this weekend. Increased energy consumption is expected, but we need advice on how to stay comfortable while being efficient. Please suggest an optimal energy consumption plan."

[0535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0536] Step 1:

[0537] The server periodically collects energy consumption data from the metering device. It receives real-time consumption data transmitted from the metering device as input and stores it directly in the database. This initiates data accumulation.

[0538] Step 2:

[0539] The server inputs the collected energy data into a machine learning model and runs an anomaly detection algorithm. The input data is compared to past normal consumption patterns, and anomalous data points are identified as output. This process utilizes a TensorFlow anomaly detection model.

[0540] Step 3:

[0541] The server uses the results of an anomaly detection algorithm to analyze multiple pricing plans and select the optimal plan based on usage patterns. The input includes detected anomaly data and existing pricing plan information, and the output recommends the most suitable pricing plan for the user. This analysis is performed using Python.

[0542] Step 4:

[0543] The terminal prepares to notify the user of anomaly warnings and pricing plans received from the server. It receives recommended data from the server as input and outputs it in a form integrated into the user interface. Visual notifications are provided on the terminal using Unity.

[0544] Step 5:

[0545] The device uses a camera and microphone to evaluate the user's emotional state. It acquires audio data and facial expression data as input and processes them using an emotion analysis algorithm. The output is data representing the analyzed emotional state of the user. This evaluation utilizes natural language processing and facial expression recognition technologies.

[0546] Step 6:

[0547] The device selects the optimal notification content and method based on the analyzed emotional state. The input consists of emotional state data and notification content, and the output is an optimized notification sent to the user. During this process, the notification content is adjusted to avoid causing stress to the user.

[0548] Step 7:

[0549] Users receive information provided through their devices and take action as needed. Users input feedback into their devices, and the system adjusts accordingly so that it is reflected in future notifications. This improves the accuracy of the system and the user experience.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] [Fourth Embodiment]

[0554] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0555] 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.

[0556] 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).

[0557] 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.

[0558] 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.

[0559] 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).

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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".

[0567] This invention is a system for efficiently utilizing energy consumption data. This system mainly consists of a server, terminals, and users.

[0568] The server is responsible for collecting energy consumption data from smart meters in real time. The collected data is stored in a database for analysis. The server uses machine learning algorithms to detect anomalies based on the collected data. This anomaly detection makes it possible to identify deviations from normal consumption patterns in real time.

[0569] The terminal receives data from the server and issues an alert to the user if an anomaly is detected. The alert is notified with a specific message, such as "Abnormal consumption has occurred." The terminal also has the function to analyze multiple pricing plans provided by the server and select the plan that best suits the user's actual consumption pattern. This function makes it possible to recommend plans to the user or suggest new pricing plans.

[0570] Users receive notifications from their devices and can consider taking action regarding abnormal consumption or switching to a more economical pricing plan. Based on the information received, users can review their appliance usage or change their contract plan as needed.

[0571] As a concrete example, consider a case where electricity consumption in a household suddenly increases during the night. In this case, the server detects this anomaly and notifies the user via a terminal. Based on the notification, the user can investigate the household appliances operating at night and take measures such as turning off unnecessary devices. Furthermore, by switching to a rate plan suggested by the terminal, the user can save on their monthly electricity bill. In this way, the present invention provides an effective means for optimizing energy consumption.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] The server collects energy consumption data from homes or businesses via a smart meter API. This data includes electricity and gas usage during specific time periods and is stored in a database in real time.

[0575] Step 2:

[0576] The server executes an anomaly detection algorithm based on the collected data. Here, a machine learning algorithm is used to identify data points that deviate from normal consumption patterns, i.e., abnormal consumption.

[0577] Step 3:

[0578] If an anomaly is detected, the terminal receives the information from the server and generates an anomaly alert for the user. The alert includes information about the time period when the anomaly occurred and detailed consumption patterns.

[0579] Step 4:

[0580] The server considers multiple pricing plans and analyzes which plan offers the most economic benefit using user consumption data. Clustering techniques are then used to evaluate the suitability of each plan.

[0581] Step 5:

[0582] Based on the analysis results, the device will notify the user of the most suitable pricing plan. The notification will include the benefits of the new plan and the potential savings compared to the current plan.

[0583] Step 6:

[0584] Users receive notifications from their devices and take specific actions. For example, they can reduce energy costs by checking the usage of home appliances to eliminate the cause of abnormal consumption or by changing to a suggested plan.

[0585] (Example 1)

[0586] 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".

[0587] Optimizing energy consumption is a crucial issue in modern homes and businesses, but it is difficult for consumers to understand their own consumption patterns and select appropriate pricing plans. Furthermore, there is the challenge of quickly identifying and addressing the cause of sudden, abnormal consumption.

[0588] 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.

[0589] In this invention, the server includes means for collecting energy consumption data from a measuring device in real time, means for preprocessing the data and detecting abnormal consumption patterns using a machine learning algorithm, and means for selecting and visualizing the optimal pricing plan based on the analysis results. This enables efficient energy management and rapid response to anomalies.

[0590] "Energy consumption data" refers to data that contains detailed information about energy use, and is usually digital data showing the usage of electricity, gas, water, etc.

[0591] A "measuring device" is a device used to measure energy consumption, and is commonly known as a smart meter.

[0592] "Real-time" means that data and information are processed immediately and are available without any time delay.

[0593] "Preprocessing" refers to the process of converting raw data into a format that can be analyzed, and includes operations such as data cleaning and formatting standardization.

[0594] A "machine learning algorithm" is a mathematical model used to learn patterns and rules from data, and is a technique used for anomaly detection and predictive analytics.

[0595] An "abnormal consumption pattern" refers to consumption patterns or trends that deviate significantly from normal energy consumption, and usually suggests malfunction or failure.

[0596] A "pricing plan" is a pricing option offered by an energy supplier to consumers, and includes different billing systems based on usage and time of day.

[0597] "Visualization" refers to the visual representation of data and analysis results, using graphs, charts, and other tools to make information easily understandable.

[0598] An "electronic notification device" is a device that notifies information by electronic means, and includes communication terminals such as smartphones and computers.

[0599] This invention provides a system that enables efficient management of energy consumption and includes server, terminal, and user components. Each component plays a specific role, and together they contribute to optimizing the user's energy consumption.

[0600] The server first collects energy consumption data in real time from measuring devices. To do this, an API is developed using a programming language such as Python to communicate with the measuring devices. The collected data is stored in a database and preprocessed using Pandas. The scikit-learn library in Python is used to apply machine learning algorithms to the preprocessed data to detect abnormal consumption patterns. This anomaly detection enables early detection and rapid response to fraudulent consumption.

[0601] The device receives analysis results sent from the server and electronically notifies the user. The device uses JavaScript to visualize the collected data and displays it in an easy-to-understand format. The notifications sent to the user are specific, including details such as, "Twice the normal consumption was detected during the late-night hours." The device also uses Python's NumPy to analyze multiple pricing plans and suggest the optimal plan to the user. This allows the user to consider a rational plan change based on their consumption patterns.

[0602] Users receive notifications from their devices and adjust their electricity consumption as needed. Based on these notifications, they can take specific actions, such as turning off devices that are currently running, to prevent wasted energy. Furthermore, users can switch to new pricing plans based on the device's suggestions, achieving efficient energy management.

[0603] As a concrete example, one could input a prompt like the following into a generative AI model: "Explain how the system works by detecting sudden spikes in electricity consumption during the night and suggesting the optimal pricing plan." Such a prompt would allow the generative AI to generate a natural language explanation that accurately reflects its understanding of the system's operation. Based on this explanation, the user can further enjoy the system's convenience.

[0604] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0605] Step 1:

[0606] The server collects energy consumption data in real time from the measuring device. The input is data from the measuring device, which is retrieved into the server via an API. Specifically, a Python program is used to send an HTTP request to the measuring device and receive the returned data in JSON format. The output is the collected energy consumption data.

[0607] Step 2:

[0608] The server preprocesses the collected data. The input is the raw data obtained in step 1. Specifically, it performs actions such as imputing missing values, correcting outliers, and converting data types. The Python Pandas library is used for this. The output is the cleaned-up data.

[0609] Step 3:

[0610] The server uses pre-processed data to detect abnormal consumption patterns. The input is the clean data obtained in step 2. Specifically, it uses Python's scikit-learn to apply machine learning algorithms. Clustering and outlier detection algorithms are used as an anomaly detection model. The output is alert information when an anomaly is detected.

[0611] Step 4:

[0612] The terminal receives analysis results from the server and sends an alert to the user. The input is the alert information generated in step 3. Specific actions include sending push notifications via email services or mobile apps. The output is the specific notification message sent to the user.

[0613] Step 5:

[0614] The device analyzes the user's energy consumption patterns and selects the optimal pricing plan. The input is the clean data from step 2. Specifically, it uses Python's NumPy to analyze multiple pricing plans and calculate the plan most suitable for the user. It then presents the visualized plan in a graph format. The output is information suggesting the optimal pricing plan for the user.

[0615] Step 6:

[0616] The user receives notifications on their device and takes appropriate action. The input is the notification and plan information obtained in steps 4 and 5. Specifically, the user follows the notification and adjusts the device's operation or changes their pricing plan. This results in energy savings and cost reductions. The output is the optimized state of energy consumption and associated costs.

[0617] (Application Example 1)

[0618] 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".

[0619] Modern cities require optimized energy resource management, but there are problems with the rapid detection of fraudulent consumption data from residents and public facilities, and the selection of optimal plans. Furthermore, while real-time monitoring of consumption patterns is expected to lead to more efficient energy management, current systems lack the information processing capabilities to achieve this.

[0620] 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.

[0621] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies using the information, and means for analyzing multiple pricing plans and recommending the optimal plan. This enables real-time monitoring of energy consumption and efficient energy management in public facilities.

[0622] "Energy consumption information" refers to data related to the amount of energy used, such as electricity, gas, and water.

[0623] "Anomaly detection" is a function that identifies fraudulent or abnormal energy usage that deviates from normal consumption patterns.

[0624] A "pricing plan" refers to a contract option offered by an energy supplier that has a different pricing structure.

[0625] "Means of notifying users" refers to communication methods or systems for informing users or related parties about anomalies or recommended plans.

[0626] "Real-time monitoring" is the process of observing information immediately and responding quickly as needed.

[0627] "Public facilities" refer to buildings or places owned by private companies or the government, such as libraries, parks, and hospitals, that are used by many people.

[0628] "Energy management" is the process of planning and implementing measures to optimize energy use and improve efficiency.

[0629] In an embodiment of this invention, the server collects energy consumption information in real time and processes it to detect anomalies. The server stores the data obtained from the smart meter in a database and uses a machine learning algorithm to identify unusual consumption patterns. The results of this anomaly detection are notified to the terminal.

[0630] The device receives anomaly alerts sent from the server and notifies the user. These notifications include specific details about the anomaly and suggestions for changing the plan. Furthermore, the device has the functionality to select and recommend the optimal pricing plan based on the user's consumption patterns.

[0631] Based on notifications from their devices, users can take steps to reduce energy waste. For example, they can check for unnecessary power consumption at night and adjust their use of electrical appliances. They can also switch to a more economical energy plan based on plan suggestions from their devices.

[0632] For example, if a household records a sudden surge in electricity consumption at night, the server will detect this as an anomaly and send a notification to the terminal. The terminal will warn the user that "abnormal consumption has occurred" and simultaneously offer suggestions such as "Why not switch to a more cost-effective rate plan?" Through this process, energy management is carried out efficiently and effectively.

[0633] An example of a prompt is, "Explain how to analyze energy consumption data and suggest an efficient plan."

[0634] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0635] Step 1:

[0636] The server collects energy consumption information from smart meters in real time. This input data records hourly consumption and is stored in a database. In this step, the server processes the collected raw data into a format that can be analyzed.

[0637] Step 2:

[0638] The server performs anomaly detection based on collected energy consumption information. Consumption data stored in the database is input into a machine learning model to determine if it deviates from normal consumption patterns. Cases identified as anomaly are flagged and passed on to the next process.

[0639] Step 3:

[0640] The server analyzes each user's energy consumption patterns along with the anomaly detection results. Based on this analysis, it performs calculations to select the optimal plan from multiple pricing plans. This selection result is sent to the terminal as a recommended plan.

[0641] Step 4:

[0642] The device receives anomaly alerts and recommended plans from the server. Based on this input information, it notifies the user of specific anomaly warnings and suggestions for changing their pricing plan. Notifications are made visually and audibly to draw the user's attention.

[0643] Step 5:

[0644] Users check notifications from their devices and take action based on the information presented. Specifically, they review their devices and settings to check for abnormal energy consumption and consider switching to a plan suggested by the device. This final action by the user completes a feedback loop that optimizes energy management.

[0645] 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.

[0646] This invention provides a system that efficiently analyzes energy consumption data and takes into account the user's emotional state to offer more personalized energy management. The system primarily consists of a server, terminals, and users, and incorporates an emotion engine.

[0647] The server collects energy consumption data from smart meters and uses machine learning algorithms to detect anomalies. This allows it to identify deviations from normal consumption patterns. The server also has the functionality to analyze pricing plans and recommend the most suitable plan for the user.

[0648] The device receives anomalies detected by the server and recommended pricing plans, and notifies the user. In addition, the device has an emotion engine that can evaluate the user's emotions based on their facial expression and voice data. The content and method of notifications are adjusted according to the output of the emotion engine. In this way, it becomes possible to provide information that takes the user's state into consideration.

[0649] Users receive anomaly alerts and recommended plans via their devices. Furthermore, they can provide feedback on their emotional state through interaction with an emotion engine. This enables energy management that reduces user stress and frustration.

[0650] As a concrete example, if electricity consumption suddenly increases in a household late at night, the server detects this anomaly and notifies the terminal. The terminal simultaneously assesses the user's emotions, determining whether they are worried or indifferent. If the user indicates anxiety, the system provides a detailed cause analysis and suggested solutions, tailoring the notification to enhance the user's sense of security. This aims to achieve energy management that goes beyond mere data provision and is more user-centric.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server collects energy consumption data via a smart meter API and stores it in a database. The data includes information on electricity and gas usage, as well as time of day.

[0654] Step 2:

[0655] The server uses machine learning algorithms to detect abnormal consumption patterns from the collected data. It identifies fraudulent or wasteful energy use and records it as an alert.

[0656] Step 3:

[0657] The server evaluates pricing plans based on the user's past consumption data and calculates the most suitable plan for the user. It compares multiple plans and selects the one with the best cost-performance ratio.

[0658] Step 4:

[0659] The device receives anomaly alerts and recommended pricing plans from the server and notifies the user of this information. The alerts include details of the unusual consumption.

[0660] Step 5:

[0661] The device uses an emotion engine to analyze the user's facial expressions and voice data, and evaluates their emotional state in real time. As a result, notification methods and content are adjusted according to the user's emotional state.

[0662] Step 6:

[0663] Users can check notifications from their devices and consider taking action regarding abnormal consumption or switching to a recommended plan. Based on feedback from the emotion engine, they can respond in a way that suits their own emotions.

[0664] Step 7:

[0665] The server and terminal analyze interaction data based on the emotion engine to continuously improve the personalization of the entire energy management system. The learned results are then used to improve the user experience.

[0666] (Example 2)

[0667] 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".

[0668] Conventional energy management systems detect anomalies in energy consumption and suggest pricing plans, but they do not provide personalized information that takes into account the user's emotional state. As a result, they are insufficient in alleviating user anxiety and doubts, and have limitations in providing an optimal energy management experience.

[0669] 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.

[0670] In this invention, the server includes means for collecting energy consumption information, means for detecting anomalies, and means for evaluating the user's emotional state. This enables optimal energy management while appropriately adjusting notification content based on the user's emotional state and reducing the user's anxiety.

[0671] "Energy consumption information" refers to data showing the electricity usage in homes and facilities, and is acquired using smart meters or similar measuring devices.

[0672] "Anomaly detection" is the process of analyzing collected energy consumption information to identify phenomena that deviate from normal consumption patterns, and it is achieved using machine learning techniques.

[0673] "Rate plan analysis" is a process that evaluates existing electricity rate plans based on energy consumption information and recommends the most economical and efficient plan to users.

[0674] "User emotional state" refers to the psychological condition evaluated based on data such as the user's facial expressions and voice, and is a factor that influences the understanding and acceptance of information.

[0675] "Adjusting notification content" is a process that takes into account the user's emotional state and customizes the format and content of information provided by the system to ensure more appropriate and effective communication.

[0676] This invention is a system for efficiently managing energy consumption information, and is composed primarily of a server, terminals, and users. This system collects energy consumption information in real time and enables anomaly detection, optimal pricing plan suggestions, and notification adjustments based on the user's emotional state.

[0677] The server acquires energy consumption information from measuring devices. This data collection is performed regularly and automatically, accumulating a large amount of data. The server analyzes the data using machine learning techniques (e.g., anomaly detection algorithms) to identify anomalies that deviate from normal consumption patterns. Furthermore, it has the ability to evaluate multiple existing pricing plans and propose the most suitable pricing plan for the user.

[0678] The terminal notifies the user of anomaly detection information and pricing plan suggestions sent from the server. During this process, a built-in emotion engine analyzes the user's facial expression and voice data to evaluate their emotional state. The notification content and method are adjusted based on this emotion evaluation, enabling the provision of information that takes the user's psychological state into consideration.

[0679] Users can review the information received via their device and provide feedback to the system as needed. This allows users to effectively manage their energy levels without feeling anxious or stressed.

[0680] For example, if a household experiences a sudden surge in electricity consumption late at night, the server detects this anomaly and promptly notifies the terminal. The terminal then communicates this information to the user and simultaneously assesses the user's emotional state. If the user is feeling anxious, the terminal provides a detailed cause analysis and solutions to alleviate their concerns. This process allows the user to have a better energy management experience.

[0681] An example of a prompt to input into the generating AI model might be, "Generate a notification method to reduce user anxiety when there is abnormal energy consumption." Based on this prompt, the AI ​​model can make specific and useful suggestions.

[0682] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0683] Step 1:

[0684] The server periodically acquires energy consumption information from the measuring device. In this process, power usage information transmitted from the measuring device is input to the server, and this data is stored in a database in real time. The collected data is formatted for analysis and output as hourly consumption patterns.

[0685] Step 2:

[0686] The server feeds the collected energy consumption information into machine learning methods to detect anomalies. The input data is compared to normal usage patterns, detecting sudden fluctuations in consumption and usage times that defy common sense. As a result of this analysis, output data indicating anomalies is generated, preparing for the next step.

[0687] Step 3:

[0688] The server analyzes existing pricing plans based on anomaly detection results and proposes the optimal plan to the user. Using anomaly detection data and current pricing plan information as input, it performs calculations to output the most cost-effective pricing plan for the user.

[0689] Step 4:

[0690] The terminal displays anomaly notifications and pricing plan suggestions received from the server to the user. The terminal has a built-in emotion engine that takes the user's facial expressions and voice data as input. The emotion engine analyzes this data and outputs the user's emotional state.

[0691] Step 5:

[0692] The device adjusts notification content according to the user's emotional state. If the user indicates anxiety, it generates and outputs a detailed notification that includes a specific cause analysis and reassuring messages. This enables appropriate information delivery tailored to the user's psychological state.

[0693] Step 6:

[0694] Users review notifications received through their devices and provide feedback as needed. This user feedback is entered into the server for future data analysis and notification adjustments, and is used to improve the entire system. This process results in a better energy management experience.

[0695] (Application Example 2)

[0696] 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".

[0697] In modern society, the efficient use of energy is a crucial issue. In particular, there is a need to quickly detect anomalies in energy consumption and communicate this information to users in an easily understandable way. However, current systems merely present data and fail to provide feedback that takes into account the user's emotional state. As a result, users may experience unnecessary stress. To solve these problems and provide more effective energy consumption management, it is necessary to provide information that is tailored to the user's emotional state.

[0698] 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.

[0699] In this invention, the server includes means for collecting energy consumption data, means for detecting anomalies, means for analyzing multiple pricing plans and recommending the optimal plan, and means for adjusting notification content and methods based on emotional state. This enables energy management and optimization that takes user emotions into consideration.

[0700] "Means for collecting energy consumption data" refers to a device or system that has the function of collecting information on energy usage obtained from measuring devices or sensors.

[0701] "Means for detecting anomalies" refers to a device or system that has the function of automatically identifying data that deviates from normal consumption patterns and issuing warnings.

[0702] "A means of analyzing multiple pricing plans and recommending the optimal plan" refers to a device or system that has the function of comparing various available pricing plans and proposing the most cost-effective plan based on individual consumption patterns.

[0703] "Means for evaluating a user's emotional state" refers to a device or system that has the function of determining a user's emotions and psychological state using technologies such as speech recognition and facial expression analysis.

[0704] "Means for adjusting notification content and method based on emotional state" refers to a device or system that has the function of selecting the most effective means and content of information delivery according to the user's current emotions.

[0705] A "measuring device" is a device that has the function of measuring energy consumption and electronically transmitting that data.

[0706] "Machine learning techniques" are advanced algorithms and technologies used to find regularities and patterns in data and make predictions and decisions based on them.

[0707] The system for carrying out the present invention consists of a server, a terminal, and a user.

[0708] The server is primarily responsible for collecting energy consumption data and detecting anomalies. A metering device is connected to the server, from which it acquires data on energy usage. The server receives the data transmitted from the metering device and uses machine learning techniques to automatically detect abnormal consumption patterns. Furthermore, the server analyzes multiple pricing plans, selects the optimal plan based on the data, and generates recommendations. The software used for this process includes Python for data analysis and TensorFlow for machine learning.

[0709] The terminal receives information about anomalies and recommended plans detected by the server and notifies the user. The terminal is equipped with functions to assess the user's emotional state, performing voice recognition and facial expression analysis through the camera and microphone. This allows the terminal to analyze the user's current emotions and adjust the notification content and format accordingly. The user interface uses Unity and features an intuitive design.

[0710] Users receive information via their devices. By reviewing their consumption patterns and responding to suggestions based on the notifications, they can achieve more efficient energy management. User feedback on their emotions helps the system strive to provide even more accurate notifications.

[0711] For example, if a rapid temperature increase is predicted in a certain area, energy consumption may increase. In this case, the system will detect the anomaly and suggest efficient air conditioner usage methods and optimal pricing plans to alleviate the user's concerns.

[0712] An example of a prompt to a generative AI model would be: "Temperatures are forecast to be higher than usual this weekend. Increased energy consumption is expected, but we need advice on how to stay comfortable while being efficient. Please suggest an optimal energy consumption plan."

[0713] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0714] Step 1:

[0715] The server periodically collects energy consumption data from the metering device. It receives real-time consumption data transmitted from the metering device as input and stores it directly in the database. This initiates data accumulation.

[0716] Step 2:

[0717] The server inputs the collected energy data into a machine learning model and runs an anomaly detection algorithm. The input data is compared to past normal consumption patterns, and anomalous data points are identified as output. This process utilizes a TensorFlow anomaly detection model.

[0718] Step 3:

[0719] The server uses the results of an anomaly detection algorithm to analyze multiple pricing plans and select the optimal plan based on usage patterns. The input includes detected anomaly data and existing pricing plan information, and the output recommends the most suitable pricing plan for the user. This analysis is performed using Python.

[0720] Step 4:

[0721] The terminal prepares to notify the user of anomaly warnings and pricing plans received from the server. It receives recommended data from the server as input and outputs it in a form integrated into the user interface. Visual notifications are provided on the terminal using Unity.

[0722] Step 5:

[0723] The device uses a camera and microphone to evaluate the user's emotional state. It acquires audio data and facial expression data as input and processes them using an emotion analysis algorithm. The output is data representing the analyzed emotional state of the user. This evaluation utilizes natural language processing and facial expression recognition technologies.

[0724] Step 6:

[0725] The device selects the optimal notification content and method based on the analyzed emotional state. The input consists of emotional state data and notification content, and the output is an optimized notification sent to the user. During this process, the notification content is adjusted to avoid causing stress to the user.

[0726] Step 7:

[0727] Users receive information provided through their devices and take action as needed. Users input feedback into their devices, and the system adjusts accordingly so that it is reflected in future notifications. This improves the accuracy of the system and the user experience.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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."

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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 as being incorporated by reference.

[0749] The following is further disclosed regarding the embodiments described above.

[0750] (Claim 1)

[0751] Means for collecting energy consumption data,

[0752] A means for detecting anomalies using the aforementioned data,

[0753] A method for analyzing multiple pricing plans and recommending the optimal plan,

[0754] Means for notifying the user of the aforementioned anomaly and recommended plan,

[0755] A system that includes this.

[0756] (Claim 2)

[0757] The system according to claim 1, wherein the aforementioned energy consumption data is obtained from a smart meter.

[0758] (Claim 3)

[0759] The system according to claim 1, wherein the detection of the anomaly uses a machine learning algorithm for identifying fraudulent consumption patterns.

[0760] "Example 1"

[0761] (Claim 1)

[0762] A means of collecting energy consumption data in real time from a measuring device,

[0763] A means for preprocessing the aforementioned data and detecting abnormal consumption patterns using a machine learning algorithm,

[0764] A means to select and visualize the optimal pricing plan based on the analysis results,

[0765] Means for notifying the user of the anomaly detection and recommended plan via an electronic notification device,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, wherein the energy consumption data is obtained from a metering device.

[0769] (Claim 3)

[0770] The system according to claim 1, wherein the detection of the anomaly identifies an illegal consumption pattern using a mathematical model.

[0771] "Application Example 1"

[0772] (Claim 1)

[0773] Means for collecting energy consumption information,

[0774] A means for detecting an anomaly using the aforementioned information,

[0775] A method for analyzing multiple pricing plans and recommending the optimal plan,

[0776] Means for notifying users of the aforementioned abnormality and recommended plan,

[0777] A means to monitor energy consumption patterns in real time and streamline energy management in public facilities,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, wherein the aforementioned energy consumption information is obtained from a measuring device.

[0781] (Claim 3)

[0782] The system according to claim 1, wherein the detection of the anomaly uses a learning algorithm for identifying fraudulent consumption patterns.

[0783] "Example 2 of combining an emotion engine"

[0784] (Claim 1)

[0785] Means for collecting energy consumption information,

[0786] A means for detecting an anomaly using the aforementioned information,

[0787] A method to analyze multiple pricing plans and recommend the optimal price,

[0788] Means for notifying the user of the aforementioned anomaly and recommended charges,

[0789] A means of evaluating the user's emotional state,

[0790] Means for adjusting the content of the notification based on the aforementioned emotional state,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, wherein the aforementioned energy consumption information is obtained from a measuring device.

[0794] (Claim 3)

[0795] The system according to claim 1, wherein the detection of the anomaly uses a machine learning method for determining the consumption pattern.

[0796] "Application example 2 when combining with an emotional engine"

[0797] (Claim 1)

[0798] Means for collecting energy consumption data,

[0799] A means for detecting anomalies using the aforementioned data,

[0800] A method for analyzing multiple pricing plans and recommending the optimal plan,

[0801] A means of evaluating the user's emotional state,

[0802] Means for adjusting the content and method of notification based on the aforementioned emotional state,

[0803] Means for notifying the user of the aforementioned anomaly and recommended plan,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, wherein the energy consumption data is obtained from a metering device.

[0807] (Claim 3)

[0808] The system according to claim 1, wherein the detection of the anomaly uses a machine learning method for identifying fraudulent consumption patterns. [Explanation of symbols]

[0809] 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. Means for collecting energy consumption data, A means for detecting anomalies using the aforementioned data, A method for analyzing multiple pricing plans and recommending the optimal plan, Means for notifying the user of the aforementioned anomaly and recommended plan, A system that includes this.

2. The system according to claim 1, wherein the energy consumption data is obtained from a smart meter.

3. The system according to claim 1, wherein the detection of the anomaly uses a machine learning algorithm for identifying fraudulent consumption patterns.

Images