system

Abstract

We provide the system. [Solution] A means of acquiring consumption data in real time from an energy management device, A means for clustering consumption patterns by industry based on the aforementioned consumption data, A means of integrating external factor data and generating alerts, A means for notifying the aforementioned alert to an information display device and suggesting corrective measures, A means of proposing specific improvement measures to suppress peak consumption at specific times, A means of allowing a portable device or visual device to monitor the energy consumption efficiency status in real time, 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 method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Power consumption is closely related to economic activities in various industries and regions. However, it is difficult to grasp these consumption patterns in real time and accurately evaluate the activity level of economic activities by conventional methods. Further, an efficient and highly reproducible method is required to quickly analyze the impact of climate change and changes in social situations on power demand and propose countermeasures. Furthermore, it is necessary to realize a comprehensive energy management system including detection of abnormal consumption patterns and alert notifications considering economic impacts.

Means for Solving the Problems

[0005] This invention includes means for acquiring electricity consumption data in real time from an energy management device, and means for clustering consumption patterns by industry based on this consumption data. It also includes means for integrating external factor data such as climate information and social conditions information, thereby generating and notifying alerts when abnormal consumption patterns are detected. Furthermore, it has graph display means for visualizing the analysis results on a terminal, thereby also providing suggestions for improvement. By combining these means, it becomes possible to effectively analyze the relationship between electricity consumption and economic activity in real time and support economic decision-making.

[0006] An "energy management device" is a device that acquires and analyzes electricity consumption data in real time.

[0007] "Real-time" refers to processing or responding immediately without delay.

[0008] "Consumption data" refers to information about electricity usage, including details broken down by industry and region.

[0009] Clustering is an analytical technique that groups data sets based on their similarity.

[0010] "External factor data" refers to data related to the external environment that affects electricity consumption, such as climate information and social conditions.

[0011] An "alert" is a warning message that notifies you when an anomaly or important event occurs.

[0012] A "terminal" is a device or apparatus used for displaying or inputting information.

[0013] "Visualization" is a technique that visually represents information and data to make them easier to understand.

[0014] "Analysis results" refer to the outcomes and conclusions of an analysis based on the collected data.

[0015] "Improvement measures" are specific proposals or methods for overcoming current problems.

Brief Explanation of Drawings

[0016] [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 multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0017] 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.

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

[0019] In the following embodiments, a 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.

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

[0021] In the following embodiments, a 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.

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The system according to the present invention acquires electricity consumption data in real time from an energy management device and has multiple functions for analyzing consumption patterns by industry. This enables highly accurate evaluation of the level of economic activity and supports rapid decision-making.

[0038] First, the server acquires consumption data in real time from energy management devices. This data includes details specific to each industry and region, and the server standardizes the format and converts it into a form suitable for analysis.

[0039] Next, the server uses an AI agent to perform clustering based on the acquired data. This allows for the identification of consumption patterns by industry and region, and enables the immediate detection of unique or abnormal patterns.

[0040] Furthermore, the server acquires external factor data such as climate information and social conditions, and comprehensively analyzes power consumption data. This allows for an accurate understanding of the potential impacts that climate change and social events have on electricity demand.

[0041] Furthermore, if an abnormal consumption pattern is detected, the server generates an alert. The generated alert is immediately notified to the user's terminal through other systems and applications.

[0042] The terminal visually presents the user with analysis results sent from the server and the impact of external factors. Therefore, the terminal is equipped with graphing functions and dashboards to allow users to easily understand this data.

[0043] Furthermore, the device will present specific improvement measures for improving energy efficiency based on the analysis results. These improvement measures include suggestions for reducing peak consumption at specific times.

[0044] Finally, users develop energy management and business strategies based on the displayed information and improvement suggestions. This enables more efficient management of electricity consumption and improved economic effectiveness.

[0045] For example, if an automobile manufacturing company uses the system of the present invention, the server analyzes power consumption data based on the operating status of the manufacturing line. The terminal displays the results on a dashboard, and the user can adopt the provided improvement measures to contribute to cost reduction and productivity improvement.

[0046] Thus, the system of the present invention analyzes power consumption data from multiple perspectives and supports the efficiency of economic activities.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server acquires real-time power consumption data from energy management devices. This data includes detailed information such as date and time, industry, region, and consumption amount. After receiving the data, the format is standardized and stored in an analysis database.

[0050] Step 2:

[0051] The server performs data preprocessing. It checks the acquired consumption data for outliers and missing values, and performs interpolation or correction as necessary. This ensures the accuracy of the data.

[0052] Step 3:

[0053] The server runs an AI agent and performs cluster analysis. Specifically, it utilizes the k-means method to classify consumption patterns by industry and region into multiple clusters, thereby identifying groups with similar consumption characteristics.

[0054] Step 4:

[0055] The server acquires external factor data, including climate information and social conditions, which are integrated with electricity consumption data to perform impact analysis. This analysis makes it possible to more accurately predict the impact of temperature fluctuations on electricity demand.

[0056] Step 5:

[0057] The server generates an alert when it detects an abnormal consumption pattern. Abnormal patterns are determined based on pre-set thresholds, and the alert information is immediately transmitted to the terminal via the notification system.

[0058] Step 6:

[0059] The terminal receives analysis results from the server and visualizes them in a user-friendly format. The dashboard displays consumption pattern trends and abnormal patterns, making them easy for users to understand.

[0060] Step 7:

[0061] Based on the analysis results, the terminal will suggest improvements to optimize energy management. These improvements include proposals for shifting power peaks during specific time periods and developing efficient energy operation plans.

[0062] Step 8:

[0063] Based on the information provided, users can review their business operations and energy management policies, and develop new strategies. If necessary, they can adjust system settings to obtain more precise data.

[0064] (Example 1)

[0065] 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."

[0066] Modern energy management requires real-time acquisition of consumption data and highly accurate analysis of consumption patterns specific to particular industries and regions. However, conventional systems often fail to adequately format the acquired data or integrate it with external factors, making early detection of abnormal consumption patterns and the proposal of efficient improvement measures difficult. A solution to this problem is needed to further improve the efficiency of electricity consumption.

[0067] 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.

[0068] In this invention, the server includes means for acquiring usage data in real time from an information management device, means for formatting the usage data and integrating it into a consistent data format, and means for clustering usage patterns for each business category using artificial intelligence generated based on the usage data. This enables everything from real-time data acquisition to integrated analysis, anomaly detection, and the provision of specific improvement measures.

[0069] An "information management device" is a hardware or software system designed to collect, process, and manage data.

[0070] "Usage data" refers to information that shows consumption and usage patterns within a specific service or system, and is data that requires real-time collection and analysis.

[0071] "Generative artificial intelligence" refers to a program or algorithm that analyzes large amounts of data and identifies significant patterns or anomalies through self-learning.

[0072] "Business classification" refers to a classification used to distinguish specific industries or sectors, and in analysis, it is a category used to identify consumption patterns and economic behavior.

[0073] "External factor information" refers to data derived primarily from environments and circumstances other than the target system, and includes information such as weather data and economic indicators.

[0074] A "warning" is a notification or message used to inform users when an abnormal situation is detected, and is a means of prompting a quick response.

[0075] "Specific measures for efficiency improvement" refer to concrete actions or changes proposed based on the analysis results, and are measures aimed at optimizing resources and reducing costs.

[0076] "User equipment" refers to devices or equipment that receive information from servers and systems and provide it to users.

[0077] A "consistent data format" is a standardized format that integrates data from different sources and facilitates analysis and display.

[0078] This invention provides a system in which a server, terminal, and user work together to acquire and analyze power consumption data. Specifically, it is implemented as follows.

[0079] The server acquires usage data in real time from the information management device through an interface. The server uses a REST API to collect data from the device and stores it in a database in an appropriate format. Next, the server uses Python or R data processing libraries to format and unify the acquired data. After being converted to a consistent data format, the server uses a generative artificial intelligence model to cluster usage patterns by business segment. For clustering, for example, the k-means method of machine learning models is used. The server also acquires information on weather and social conditions from external data sources and analyzes this in conjunction with the power consumption data. If a unique pattern is detected from the analysis results, the server immediately generates an alert and sends notifications to other systems using technologies such as Webhooks.

[0080] The terminal is responsible for visualizing analysis results and warnings received from the server. Using the JavaScript® library D3.js, the terminal creates graphs and dashboards in a user-friendly format. Furthermore, the terminal provides users with specific measures for efficiency improvement based on suggestions from the generated artificial intelligence. This includes suggesting ways to reduce peak consumption during specified times.

[0081] Users formulate energy management and business strategies based on the data and improvement suggestions displayed on their devices. For example, a manufacturing user might input "Please propose energy efficiency improvement measures for our industry based on electricity consumption data" as a plutonium, and then use the generated AI model to formulate specific measures. This allows users to optimize electricity consumption and maximize economic benefits.

[0082] In this way, this invention enables the effective analysis and management of power consumption data, and supports user decision-making by providing necessary information quickly and accurately.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server acquires power consumption data in real time from the information management device. In this step, the server requests data via a REST API and receives usage data in JSON format. It receives raw data from the energy management device as input and stores it in the database. The server checks the data format and necessary metadata, and stores the data while supplementing any missing parts.

[0086] Step 2:

[0087] The server formats the acquired data into a format that is easy to analyze. Specifically, it uses Python to impute missing values, convert data types, and standardize timestamp formats. Using the raw data acquired in step 1 as input, it outputs cleaned data while maintaining data consistency.

[0088] Step 3:

[0089] The server uses a raw artificial intelligence model to analyze clean data and cluster usage patterns by industry and region. In this step, machine learning models such as k-means are used to process the input dataset and classify it into groups based on usage patterns. The output is a dataset showing the features of each cluster.

[0090] Step 4:

[0091] The server acquires external factor information and performs integrated analysis with the clustering results. It obtains weather data and social situation data from an external API as input and integrates this data with the clustering results from the previous step. The server uses a statistical model to evaluate the impact of the input data on power consumption and obtains the impact analysis results as output.

[0092] Step 5:

[0093] The server detects abnormal consumption patterns from the integrated analysis results and generates warnings as needed. In this step, an anomaly detection algorithm is used to detect usage patterns that differ from normal patterns from the results analysis. The input is integrated consumption and factor data, and the output is anomaly warnings and their background information.

[0094] Step 6:

[0095] The terminal visualizes warnings and analysis results received from the server and provides them to the user. Specifically, it uses D3.js to generate interactive graphs and dashboards, making it easy for users to understand the data. The input is warning information and analysis results from the server, and the output is graphically displayed information.

[0096] Step 7:

[0097] The terminal presents the user with specific measures for efficiency improvement based on the generated AI model. The terminal receives the prompt message proposed by the AI ​​model and presents it to the user, thereby providing practical operational improvement suggestions. As output, it displays the suggested measures to the user.

[0098] Step 8:

[0099] Users revise their energy management and strategies based on graphs and suggestions displayed on their devices. The input consists of visual information and suggestions from the device; based on this, they formulate and implement strategies for efficient energy consumption and cost reduction. The output is improved management methods and business strategies.

[0100] (Application Example 1)

[0101] 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."

[0102] Energy consumption in modern cities is constantly increasing, and solutions are needed to address this problem in order to achieve a sustainable society. Conventional energy management systems have not only failed to acquire energy consumption data, but also to adequately detect anomalies in actual consumption patterns and provide real-time improvement suggestions. Furthermore, there has been a lack of technology to provide concrete energy efficiency suggestions that users can intuitively understand and act upon. By solving these problems, it is necessary to improve the energy efficiency of cities as a whole and contribute to the realization of a sustainable society.

[0103] 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.

[0104] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for clustering consumption patterns by industry, integrating external factor data to generate alerts, and means for suggesting specific improvement measures to suppress consumption peaks at specific times, and for allowing portable devices or visual devices to monitor the energy consumption efficiency status in real time. This makes it possible to provide detailed monitoring and specific efficiency measures regarding energy consumption at the city level.

[0105] An "energy management device" is a device that acquires and manages electricity consumption data in real time.

[0106] "Consumption data" refers to numerical information that shows the amount and pattern of energy use over a specific period.

[0107] Clustering is an analytical method that groups data based on similarity and classifies consumption patterns.

[0108] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0109] An "alert" is a warning message that is generated and sent when an abnormal consumption pattern is detected.

[0110] An "information display device" is a device used to visually present consumption data and analysis results to the user.

[0111] "Improvement measures" refer to specific action plans proposed to improve the efficiency of energy consumption.

[0112] A "portable device" is a device that a user can carry with them and is primarily used for acquiring and manipulating information.

[0113] A "visual device" is a device that has the function of presenting data to the user visually.

[0114] "Peak consumption" refers to the period of time when energy consumption is at its highest.

[0115] The system for realizing this invention consists of multiple components and aims to improve energy consumption efficiency. First, the server acquires power consumption data in real time from the energy management device and performs data formatting and processing. This processing is carried out in real time on a cloud server using Python scripts and APIs.

[0116] Subsequently, the server uses Scikit-learn and TENSORFLOW® to perform industry-specific clustering based on the acquired consumption data. This enables immediate detection of abnormal consumption patterns and unusual movements. Furthermore, external factors such as climate information and social conditions are integrated into the data to perform a comprehensive analysis of consumption patterns. Based on this, an alert is generated if an anomaly is detected.

[0117] The generated alerts and analysis results are notified in real time to information display devices. Users can view this information through a visual dashboard in smartphone and smart glasses applications developed using Flutter® and React Native. Furthermore, specific improvement measures to reduce peak consumption during specific times are also presented.

[0118] For example, if electricity consumption increases during specific times in the summer, the app will notify the user with a message such as, "Please consider temporarily turning off the air conditioning between 2 PM and 4 PM and using a fan instead." This makes it possible to effectively suppress peak consumption while maintaining a comfortable living environment.

[0119] This system, which utilizes a generative AI model to improve the energy efficiency of the entire city, is effectively operated by the following prompt messages.

[0120] Example prompt: "Analyze today's electricity consumption data for a specific region, identify any unusual patterns, and propose specific energy-saving measures."

[0121] In this way, servers, information display devices, and users can work together to streamline energy management.

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The server acquires real-time power consumption data from energy management devices. The input is power consumption data from various industries and regions, and the output is analyzable data in a standardized format. This process uses a Python script to format the data on the cloud and save it to a database.

[0125] Step 2:

[0126] The server clusters consumption patterns by industry using Scikit-learn and TensorFlow based on unified consumption data. The input is organized power consumption data, and the output is cluster information separated by industry. Specifically, machine learning algorithms group correlated data and identify anomalous patterns.

[0127] Step 3:

[0128] The server integrates and analyzes consumption data and external factor data (such as climate information and social conditions). Inputs are cluster information and external data, and output is the integrated analysis result. This process identifies factors influencing consumption patterns and detects potential anomalies.

[0129] Step 4:

[0130] Based on the analysis results, the server generates an alert and notifies the information display device if an anomaly is detected. The input is the analyzed anomaly pattern, and the output is the alert notification to the user terminal. Specifically, a notification message is generated and immediately delivered to the user.

[0131] Step 5:

[0132] Based on alerts and analysis results received from the server, the terminal presents specific improvement measures to reduce peak consumption during specific times. At this stage, the terminal receives alert messages as input and displays a visual dashboard of improvement measures as output. It generates intuitively understandable graphs and charts using a user interface.

[0133] Step 6:

[0134] Users take action based on improvement suggestions displayed on their devices. Input is visualized data and improvement suggestions on the device, while output is the actual action taken to adjust energy consumption. For example, a user might follow instructions and take specific actions, such as refraining from using electrical appliances during certain time periods.

[0135] 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.

[0136] The system according to the present invention combines power consumption data acquired in real time from an energy management device with an emotion engine that analyzes the user's emotional state, thereby providing comprehensive energy management and decision-making support that takes into account both power consumption and the user's emotions.

[0137] First, the server acquires consumption data from energy management devices. This data includes detailed consumption information broken down by industry and region, and the server stores this data in a standard format in its database.

[0138] Next, the server uses an AI agent to analyze the data and classify consumption patterns using clustering techniques. Simultaneously, it acquires climate and social conditions information as external factors and analyzes how these factors affect power consumption.

[0139] Furthermore, the server runs an emotion engine to acquire emotion data from the user's device and evaluate how the user feels about the power consumption information. Emotion data is often acquired through image analysis and text analysis, and the emotion engine uses this data to determine the user's real-time emotional state.

[0140] If an abnormal consumption pattern is detected, the server creates an alert that takes the user's emotional state into account and notifies the device. For example, if it is determined that the user is stressed, it will provide customized solutions and suggestions to alleviate that stress.

[0141] The device displays analysis results, sentiment ratings, and customized alerts received from the server in dashboard and graph formats. This makes it easier for users to visually check their power consumption and their own emotional state.

[0142] Finally, based on the information provided, users determine improvement measures that are appropriate for their energy usage and personal feelings, and then strategically manage their energy accordingly. This allows for management that not only optimizes power consumption but also takes into account user satisfaction and stress levels.

[0143] In this way, this system takes into account the user's emotional state, thereby achieving a more human-centered and adaptable energy management system.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The server acquires real-time power consumption data from energy management devices. This data includes detailed information broken down by date, time, industry, and region, and the server formats this data and stores it in a database.

[0147] Step 2:

[0148] The server uses an AI agent to perform clustering on the acquired consumption data. Cluster analysis groups the consumption data based on similarity to discover anomalous and characteristic patterns.

[0149] Step 3:

[0150] The server acquires external factor data. This data includes climate information and social conditions information, and by analyzing it in combination with consumption data, the impact of external factors on electricity demand can be evaluated.

[0151] Step 4:

[0152] The server operates an emotion engine to acquire emotion data from the user's terminal. This emotion data is collected from the user's reactions, facial expressions, and entered text, and the server analyzes the user's emotional state in real time.

[0153] Step 5:

[0154] If an abnormal consumption pattern is detected, the server generates an alert based on the analysis results from the emotion engine. The alert is customized according to the user's emotional state and sent to the device along with specific corrective actions.

[0155] Step 6:

[0156] The device displays analysis results received from the server and customized alerts to the user in dashboard and graph format. The device integrates consumption data and sentiment data to allow the user to intuitively understand the situation.

[0157] Step 7:

[0158] Based on the information provided, users select improvement measures tailored to their power consumption and emotional state. They then optimize energy management according to the recommended strategy and adjust system settings as needed.

[0159] In this way, the present invention realizes energy management that takes user emotions into consideration, and supports more intuitive and human-centered decision-making.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0162] In recent years, while there has been a growing demand for more efficient energy consumption, existing energy management systems are limited to analyzing consumption data and struggle to implement comprehensive management that takes into account user emotions and external factors. Furthermore, warnings for abnormal consumption patterns are uniform, and the provision of appropriate improvement measures for individual users is insufficient. Therefore, in addition to optimizing energy consumption, flexible energy management that takes into account user satisfaction and emotional aspects is necessary.

[0163] 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.

[0164] In this invention, the server includes means for acquiring usage data in real time from an energy management mechanism, means for classifying usage patterns for each economic activity based on the usage data, and means for integrating external factor information and creating warnings. This enables comprehensive energy management that takes into account not only the analysis of usage data but also external factors and the emotional state of the user.

[0165] An "energy management system" is a device or system for monitoring energy usage in real time and for collecting and managing data.

[0166] "Usage data" refers to data that includes information about the consumption of electricity and other energy, showing when, where, and how it was used.

[0167] "Economic activity" refers to activities that indicate trends in energy consumption in specific industries or regions, and is information related to the analysis of consumption patterns.

[0168] "External factors information" refers to information about climate conditions and social circumstances that may affect energy consumption.

[0169] A "warning" is a message that notifies the user of an abnormal energy consumption pattern or the associated risks, and urges them to take action.

[0170] "Information equipment" refers to devices that allow users to receive and visually confirm information, and includes smartphones and computers.

[0171] An "emotion evaluation mechanism" is a technology for detecting and analyzing a user's emotional state, using image recognition and text analysis.

[0172] "Visual display means" refers to a function for displaying data in a visual format such as graphs and charts, and is intended to allow users to intuitively understand the information.

[0173] To implement this invention, it is necessary to construct a complex system that includes an energy management mechanism, a server, an emotion evaluation mechanism, and information equipment.

[0174] The server functions as the core of a system that acquires usage data from the energy management organization in real time. The server is equipped with an AI agent for data analysis and clustering, which is used to identify power consumption patterns and detect abnormal usage. Furthermore, it acquires weather and social information from the internet as external factor information and analyzes it comprehensively. This allows the server to understand the relationship between consumption patterns and external factors.

[0175] The terminal plays a crucial role in displaying the analysis results received from the server to the user. Desktop computers and smartphones are often used for this purpose, and the information is presented visually as dashboards and graphs. The terminal also sends information about the user's condition, such as sentiment data in the form of images and text, to the server.

[0176] Users can leverage the information provided through their devices to understand their energy consumption patterns and emotional state, and take concrete action. It is recommended that they adopt strategies aimed at both optimizing energy use and maintaining emotional well-being, taking into account the customized alerts generated by the system.

[0177] As a concrete example, the following prompt can be entered into the generative AI model.

[0178] Example of a prompt:

[0179] "Please provide an analysis of my recent increase in electricity consumption and its emotional impact on me. I would especially appreciate it if you could identify the times of day when I feel most stressed. Also, please suggest what actions I should take to address this."

[0180] By using this system, users can contribute not only to improving the efficiency of their power consumption but also to improving their overall lifestyle.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The server collects usage data in real time from the energy management organization. Specifically, it receives power usage information transmitted from each energy consumption point and applies a method to store it in a database. Industry-specific and regional consumption data is provided as input, which is converted into a standard format and organized into time-series data to form the output.

[0184] Step 2:

[0185] The server analyzes consumption data acquired using an AI agent and classifies usage patterns. Specifically, it groups similar consumption patterns using clustering techniques. The consumption data organized in the previous step is used as input, and the output is consumption patterns classified by cluster. Furthermore, external factor information (weather and social conditions related data) is integrated, and correlation and regression analyses are performed.

[0186] Step 3:

[0187] The server uses an emotion evaluation mechanism to analyze emotion data acquired from the terminal in order to evaluate the user's emotional state. Specifically, it analyzes image and text data from the user and uses an AI model to infer emotions. The input is the user's emotion data (images and text), and the output is an evaluation result of the user's real-time emotional state.

[0188] Step 4:

[0189] The server, upon detecting an abnormal consumption pattern, generates a customized warning based on the user's emotional state and sends it to the information device. Specifically, it activates an anomaly detection algorithm and creates a warning, including stress reduction measures, for users determined to be experiencing high stress levels. The input is the results of the consumption pattern analysis and emotional evaluation, and the output is a customized warning message.

[0190] Step 5:

[0191] The terminal visually presents the user with analysis results and customized warnings received from the server. Specifically, it displays information in graph and chart format through a dashboard, allowing users to easily check their energy consumption and emotional state. The input is analysis results from the server, and the output is information displayed on the terminal in a visually organized format.

[0192] Step 6:

[0193] Users develop plans to improve their energy consumption habits based on the information displayed on their devices. Specifically, they adjust their electricity usage patterns or engage in stress management activities based on the suggested improvements. The input is visual information from the device, and the output is concrete actions that users can take to review their energy management.

[0194] (Application Example 2)

[0195] 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".

[0196] In modern society, achieving both efficient energy management and user satisfaction is challenging. Furthermore, conventional energy management systems are limited to analyzing simple consumption patterns and do not consider individual user emotions or lifestyles, resulting in ineffective energy savings and reduced user comfort.

[0197] 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.

[0198] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for performing clustering based on the consumption data and integrating external factor data to analyze the user's emotional state, and means for generating emotionally conscious alerts based on the analysis results and notifying the terminal. This enables more human-centered and adaptable energy management that takes the user's psychological state into consideration during energy management.

[0199] An "energy management device" is a device used to monitor and control the consumption of energy, such as electricity.

[0200] "Means for acquiring consumption data in real time" refers to means that have the function of collecting electricity consumption information in real time.

[0201] A "clustering method" is a method of classifying data, such as consumption patterns, based on specific similarities.

[0202] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0203] "Means for analyzing a user's emotional state" refers to technologies and devices that analyze a user's psychological state and determine their emotions.

[0204] "Means of generating alerts and notifying terminals" refers to means of generating warnings based on abnormal consumption patterns or emotional states and transmitting them to the user's terminal.

[0205] An "emotion-sensitive alert" refers to a warning that takes into account the user's psychological state and provides specific actions or notifications accordingly.

[0206] "Energy management" refers to the process of planning and controlling the efficient use of energy, such as electricity.

[0207] One embodiment of this invention is a system that integrates energy management with the user's emotional state to achieve more human-centered and adaptable energy management.

[0208] The server acquires energy consumption data in real time from energy management devices. This makes it possible to capture the latest consumption patterns. The consumption data is classified into standard consumption patterns for each industry using specialized clustering techniques. Data analysis tools are often used in this process.

[0209] Furthermore, the server acquires external factor data, such as climate information and social conditions information, from external data sources and integrates it as an element that affects power consumption. Additionally, emotional data is collected from the user's terminal, and an emotional analysis engine processes this data to evaluate the user's real-time emotional state. Emotional data is typically acquired using image analysis and text analysis technologies.

[0210] The server comprehensively analyzes consumption and emotional data, and if abnormal consumption patterns are detected, it generates appropriate alerts that take into account the user's emotional state. For example, for a user experiencing stress, it will suggest customized improvement measures to reduce consumption while alleviating stress.

[0211] The device displays analysis results, sentiment evaluation results, and customized alerts sent from the server in a dashboard format. This allows users to visually check their power consumption status and helps them make appropriate decisions about their energy consumption behavior.

[0212] For example, if a user is worried because their electricity bill has been too high lately, the app will recognize this emotion and suggest energy-saving measures for their home. A concrete example of a prompt for the generating AI model would be: "User's emotional state is 'worried'. Electricity consumption data: 20% increase compared to last month. Suggested solution: Please suggest simple energy-saving methods for your home to alleviate your worry."

[0213] In this way, by implementing energy management tailored to each user's individual circumstances, it is possible to improve both user satisfaction and energy efficiency.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server acquires energy consumption data in real time from energy management devices. This data includes consumption information organized by industry and is stored in the server's database. The input is consumption information obtained from energy management devices, and the output is consumption data saved in the database.

[0217] Step 2:

[0218] The server uses an AI model to analyze consumption data and applies clustering techniques to classify consumption patterns by industry. This process uses organized consumption data as input and produces a cluster list of consumption patterns as output. This provides clues to discovering characteristics and anomalies in consumption.

[0219] Step 3:

[0220] The server collects external factor data, such as climate information and social conditions, from external data sources and integrates it with consumption data. This identifies factors that may affect electricity consumption. The input is climate and social information obtained from external data sources, and the output is an analyzable dataset integrated with consumption data.

[0221] Step 4:

[0222] The server acquires emotional data from the user's terminal and analyzes the emotional state using an emotional analysis engine. The input for this step is emotional data obtained from the terminal, and the output is a real-time emotional evaluation result of the user. Image analysis and text analysis techniques are used for the data.

[0223] Step 5:

[0224] Based on the emotion evaluation results and consumption patterns, the server generates alerts that take the user's emotional state into consideration and notifies the terminal. The input consists of anomaly detection data for consumption patterns and emotion evaluation data, while the output is customized improvement measures and warning messages that take the user's psychology into account.

[0225] Step 6:

[0226] The device displays received analysis results, sentiment ratings, and customized alerts in a dashboard format. Input is notification data from the server, and output is a visualized information display. This allows users to understand their situation and select appropriate actions.

[0227] Step 7:

[0228] Based on the information presented, users make energy management decisions tailored to their own lifestyles. In this process, user input is a reaction to the information presented by the server, and the output results in specific energy-saving actions and changes in lifestyle habits.

[0229] 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.

[0230] 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 those described above. 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 shown 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] The system according to the present invention acquires electricity consumption data in real time from an energy management device and has multiple functions for analyzing consumption patterns by industry. This enables highly accurate evaluation of the level of economic activity and supports rapid decision-making.

[0246] First, the server acquires consumption data in real time from energy management devices. This data includes details specific to each industry and region, and the server standardizes the format and converts it into a form suitable for analysis.

[0247] Next, the server uses an AI agent to perform clustering based on the acquired data. This allows for the identification of consumption patterns by industry and region, and enables the immediate detection of unique or abnormal patterns.

[0248] Furthermore, the server acquires external factor data such as climate information and social conditions, and comprehensively analyzes power consumption data. This allows for an accurate understanding of the potential impacts that climate change and social events have on electricity demand.

[0249] Furthermore, if an abnormal consumption pattern is detected, the server generates an alert. The generated alert is immediately notified to the user's terminal through other systems and applications.

[0250] The terminal visually presents the user with analysis results sent from the server and the impact of external factors. Therefore, the terminal is equipped with graphing functions and dashboards to allow users to easily understand this data.

[0251] Furthermore, the device will present specific improvement measures for improving energy efficiency based on the analysis results. These improvement measures include suggestions for reducing peak consumption at specific times.

[0252] Finally, users develop energy management and business strategies based on the displayed information and improvement suggestions. This enables more efficient management of electricity consumption and improved economic effectiveness.

[0253] For example, if an automobile manufacturing company uses the system of the present invention, the server analyzes power consumption data based on the operating status of the manufacturing line. The terminal displays the results on a dashboard, and the user can adopt the provided improvement measures to contribute to cost reduction and productivity improvement.

[0254] Thus, the system of the present invention analyzes power consumption data from multiple perspectives and supports the efficiency of economic activities.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server acquires real-time power consumption data from energy management devices. This data includes detailed information such as date and time, industry, region, and consumption amount. After receiving the data, the format is standardized and stored in an analysis database.

[0258] Step 2:

[0259] The server performs data preprocessing. It checks the acquired consumption data for outliers and missing values, and performs interpolation or correction as necessary. This ensures the accuracy of the data.

[0260] Step 3:

[0261] The server runs an AI agent and performs cluster analysis. Specifically, it utilizes the k-means method to classify consumption patterns by industry and region into multiple clusters, thereby identifying groups with similar consumption characteristics.

[0262] Step 4:

[0263] The server acquires external factor data, including climate information and social conditions, which are integrated with electricity consumption data to perform impact analysis. This analysis makes it possible to more accurately predict the impact of temperature fluctuations on electricity demand.

[0264] Step 5:

[0265] The server generates an alert when it detects an abnormal consumption pattern. Abnormal patterns are determined based on pre-set thresholds, and the alert information is immediately transmitted to the terminal via the notification system.

[0266] Step 6:

[0267] The terminal receives analysis results from the server and visualizes them in a user-friendly format. The dashboard displays consumption pattern trends and abnormal patterns, making them easy for users to understand.

[0268] Step 7:

[0269] Based on the analysis results, the terminal will suggest improvements to optimize energy management. These improvements include suggestions regarding shifting power peaks during specific time periods and developing efficient energy operation plans.

[0270] Step 8:

[0271] Based on the information provided, users can review their business operations and energy management policies, and develop new strategies. If necessary, they can adjust system settings to obtain more precise data.

[0272] (Example 1)

[0273] 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."

[0274] Modern energy management requires real-time acquisition of consumption data and highly accurate analysis of consumption patterns specific to particular industries and regions. However, conventional systems often fail to adequately format the acquired data or integrate it with external factors, making early detection of abnormal consumption patterns and the proposal of efficient improvement measures difficult. A solution to this problem is needed to further improve the efficiency of electricity consumption.

[0275] 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.

[0276] In this invention, the server includes means for acquiring usage data in real time from an information management device, means for formatting the usage data and integrating it into a consistent data format, and means for clustering usage patterns for each business category using artificial intelligence generated based on the usage data. This enables everything from real-time data acquisition to integrated analysis, anomaly detection, and the provision of specific improvement measures.

[0277] An "information management device" is a hardware or software system designed to collect, process, and manage data.

[0278] "Usage data" refers to information that shows consumption and usage patterns within a specific service or system, and is data that requires real-time collection and analysis.

[0279] "Generative artificial intelligence" refers to a program or algorithm that analyzes large amounts of data and identifies significant patterns or anomalies through self-learning.

[0280] "Business classification" refers to a classification used to distinguish specific industries or sectors, and in analysis, it is a category used to identify consumption patterns and economic behavior.

[0281] "External factor information" refers to data derived primarily from environments and circumstances other than the target system, and includes information such as weather data and economic indicators.

[0282] A "warning" is a notification or message used to inform users when an abnormal situation is detected, and is a means of prompting a quick response.

[0283] "Specific measures for efficiency improvement" refer to concrete actions or changes proposed based on the analysis results, and are measures aimed at optimizing resources and reducing costs.

[0284] The "user device" is a device or apparatus that receives information from a server or system and provides this information to the user.

[0285] The "consistent data format" is a format that integrates data obtained from different sources and standardizes it to facilitate analysis and display.

[0286] In this invention, a system is provided in which a server, a terminal, and a user cooperate to acquire and analyze power consumption data. Specifically, it is implemented as follows.

[0287] The server acquires usage data in real time from an information management device through an interface. The server uses the REST API to collect data from the device and stores the data in a database in an appropriate format. Next, the server uses data processing libraries such as Python and R to shape and unify the acquired data. After being converted into a consistent data format, the server uses a generated artificial intelligence model to perform clustering of usage patterns for each business segment. For clustering, for example, the k-means method of a machine learning model is used. Also, the server acquires information on weather and social situations from an external data source and integratively analyzes this with the power consumption data. If a specific pattern is detected from the analysis results, the server immediately generates a warning and uses technologies such as Webhooks to send notifications to other systems.

[0288] The terminal is responsible for visualizing the analysis results and warnings received from the server. The terminal uses the D3.js JavaScript library to create graphs and dashboards in a form that is easy for the user to understand. Also, the terminal provides the user with specific measures for efficiency improvement based on the suggestions from the generated artificial intelligence. This includes presenting methods for reducing the consumption peak at a specified time.

[0289] Users formulate energy management and business strategies based on the data and improvement suggestions displayed on their devices. For example, a manufacturing user might input "Please propose energy efficiency improvement measures for our industry based on electricity consumption data" as a plutonium, and then use the generated AI model to formulate specific measures. This allows users to optimize electricity consumption and maximize economic benefits.

[0290] In this way, this invention enables the effective analysis and management of power consumption data, and supports user decision-making by providing necessary information quickly and accurately.

[0291] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0292] Step 1:

[0293] The server acquires power consumption data in real time from the information management device. In this step, the server requests data via a REST API and receives usage data in JSON format. It receives raw data from the energy management device as input and stores it in the database. The server checks the data format and necessary metadata, and stores the data while supplementing any missing parts.

[0294] Step 2:

[0295] The server formats the acquired data into a format that is easy to analyze. Specifically, it uses Python to impute missing values, convert data types, and standardize timestamp formats. Using the raw data acquired in step 1 as input, it outputs cleaned data while maintaining data consistency.

[0296] Step 3:

[0297] The server uses a raw artificial intelligence model to analyze clean data and cluster usage patterns by industry and region. In this step, machine learning models such as k-means are used to process the input dataset and classify it into groups based on usage patterns. The output is a dataset showing the features of each cluster.

[0298] Step 4:

[0299] The server acquires external factor information and performs integrated analysis with the clustering results. It obtains weather data and social situation data from an external API as input and integrates this data with the clustering results from the previous step. The server uses a statistical model to evaluate the impact of the input data on power consumption and obtains the impact analysis results as output.

[0300] Step 5:

[0301] The server detects abnormal consumption patterns from the integrated analysis results and generates warnings as needed. In this step, an anomaly detection algorithm is used to detect usage patterns that differ from normal patterns from the results analysis. The input is integrated consumption and factor data, and the output is anomaly warnings and their background information.

[0302] Step 6:

[0303] The terminal visualizes warnings and analysis results received from the server and provides them to the user. Specifically, it uses D3.js to generate interactive graphs and dashboards, making it easy for users to understand the data. The input is warning information and analysis results from the server, and the output is graphically displayed information.

[0304] Step 7:

[0305] The terminal presents specific measures for efficiency improvement to the user based on the generative AI model. The terminal receives the prompt text proposed by the AI model and presents it to the user, thereby providing practical operation improvement plans. As output, proposals for countermeasures are displayed to the user.

[0306] Step 8:

[0307] Based on the graphs and proposals shown on the terminal, the user reviews energy management and strategies. The inputs are visual information and proposals from the terminal, and based on these, strategies such as efficient energy consumption and cost reduction are formulated and put into practice. The output is improved management methods and business strategies.

[0308] (Application Example 1)

[0309] Next, Application Example 1 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".

[0310] Energy consumption in modern cities is on the rise, and in aiming for a sustainable society, means to solve this problem are being sought. Conventional energy management systems have not sufficiently carried out not only the acquisition of energy consumption data, but also the detection of abnormalities in actual consumption patterns and real-time improvement proposals. Furthermore, there has also been a lack of technology to provide specific proposals for energy efficiency that users can intuitively understand and put into action. By solving these problems, it is required to improve the energy efficiency of the entire city and contribute to the realization of a sustainable society.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0312] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for clustering consumption patterns by industry, integrating external factor data to generate alerts, and means for suggesting specific improvement measures to suppress consumption peaks at specific times, and for allowing portable devices or visual devices to monitor the energy consumption efficiency status in real time. This makes it possible to provide detailed monitoring and specific efficiency measures regarding energy consumption at the city level.

[0313] An "energy management device" is a device that acquires and manages electricity consumption data in real time.

[0314] "Consumption data" refers to numerical information that shows the amount and pattern of energy use over a specific period.

[0315] Clustering is an analytical method that groups data based on similarity and classifies consumption patterns.

[0316] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0317] An "alert" is a warning message that is generated and sent when an abnormal consumption pattern is detected.

[0318] An "information display device" is a device used to visually present consumption data and analysis results to the user.

[0319] "Improvement measures" refer to specific action plans proposed to improve the efficiency of energy consumption.

[0320] A "portable device" is a device that a user can carry with them and is primarily used for acquiring and manipulating information.

[0321] A "visual device" is a device that has the function of presenting data to the user visually.

[0322] "Peak consumption" refers to the period of time when energy consumption is at its highest.

[0323] The system for realizing this invention consists of multiple components and aims to improve energy consumption efficiency. First, the server acquires power consumption data in real time from the energy management device and performs data formatting and processing. This processing is carried out in real time on a cloud server using Python scripts and APIs.

[0324] Subsequently, the server uses Scikit-learn and TensorFlow to perform industry-specific clustering based on the acquired consumption data. This enables immediate detection of abnormal consumption patterns and unusual movements. Furthermore, external factors such as climate information and social conditions are integrated into the data to perform a comprehensive analysis of consumption patterns. Based on this, an alert is generated if an anomaly is detected.

[0325] The generated alerts and analysis results are notified in real time to information display devices. Users can view this information through a visual dashboard in smartphone and smart glasses applications developed using Flutter and React Native. Furthermore, specific improvement measures to reduce peak consumption during specific times are also presented.

[0326] For example, if electricity consumption increases during specific times in the summer, the app will notify the user with a message such as, "Please consider temporarily turning off the air conditioning between 2 PM and 4 PM and using a fan instead." This makes it possible to effectively suppress peak consumption while maintaining a comfortable living environment.

[0327] This system, which utilizes a generative AI model to improve the energy efficiency of the entire city, is effectively operated by the following prompt messages.

[0328] Example prompt: "Analyze today's electricity consumption data for a specific region, identify any unusual patterns, and propose specific energy-saving measures."

[0329] In this way, servers, information display devices, and users can work together to streamline energy management.

[0330] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0331] Step 1:

[0332] The server acquires real-time power consumption data from energy management devices. The input is power consumption data from various industries and regions, and the output is analyzable data in a standardized format. This process uses a Python script to format the data on the cloud and save it to a database.

[0333] Step 2:

[0334] The server clusters consumption patterns by industry using Scikit-learn and TensorFlow based on unified consumption data. The input is organized power consumption data, and the output is cluster information separated by industry. Specifically, machine learning algorithms group correlated data and identify anomalous patterns.

[0335] Step 3:

[0336] The server integrates and analyzes consumption data and external factor data (such as climate information and social conditions). Inputs are cluster information and external data, and output is the integrated analysis result. This process identifies factors influencing consumption patterns and detects potential anomalies.

[0337] Step 4:

[0338] Based on the analysis results, the server generates an alert and notifies the information display device if an anomaly is detected. The input is the analyzed anomaly pattern, and the output is the alert notification to the user terminal. Specifically, a notification message is generated and immediately delivered to the user.

[0339] Step 5:

[0340] Based on alerts and analysis results received from the server, the terminal presents specific improvement measures to reduce peak consumption during specific times. At this stage, the terminal receives alert messages as input and displays a visual dashboard of improvement measures as output. It generates intuitively understandable graphs and charts using a user interface.

[0341] Step 6:

[0342] Users take action based on improvement suggestions displayed on their devices. The input is visualized data and improvement suggestions on the device, and the output is the actual action taken to adjust energy consumption. For example, users follow the instructions and take specific actions such as refraining from using electrical appliances during certain times of the day.

[0343] 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.

[0344] The system according to the present invention combines power consumption data acquired in real time from an energy management device with an emotion engine that analyzes the user's emotional state, thereby providing comprehensive energy management and decision-making support that takes into account both power consumption and the user's emotions.

[0345] First, the server acquires consumption data from energy management devices. This data includes detailed consumption information broken down by industry and region, and the server stores this data in a standard format in its database.

[0346] Next, the server uses an AI agent to analyze the data and classify consumption patterns using clustering techniques. Simultaneously, it acquires climate and social conditions information as external factors and analyzes how these factors affect power consumption.

[0347] Furthermore, the server runs an emotion engine to acquire emotion data from the user's device and evaluate how the user feels about the power consumption information. Emotion data is often acquired through image analysis and text analysis, and the emotion engine uses this data to determine the user's real-time emotional state.

[0348] If an abnormal consumption pattern is detected, the server creates an alert that takes the user's emotional state into account and notifies the device. For example, if it is determined that the user is stressed, it will provide customized solutions and suggestions to alleviate that stress.

[0349] The device displays analysis results, sentiment ratings, and customized alerts received from the server in dashboard and graph formats. This makes it easier for users to visually check their power consumption and their own emotional state.

[0350] Finally, based on the information provided, users determine improvement measures that are appropriate for their energy usage and personal feelings, and then strategically manage their energy accordingly. This allows for management that not only optimizes power consumption but also takes into account user satisfaction and stress levels.

[0351] In this way, this system takes into account the user's emotional state, thereby achieving a more human-centered and adaptable energy management system.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The server acquires real-time power consumption data from energy management devices. This data includes detailed information broken down by date, time, industry, and region, and the server formats this data and stores it in a database.

[0355] Step 2:

[0356] The server uses an AI agent to perform clustering on the acquired consumption data. Cluster analysis groups the consumption data based on similarity to discover anomalous and characteristic patterns.

[0357] Step 3:

[0358] The server acquires external factor data. This data includes climate information and social conditions information, and by analyzing it in combination with consumption data, the impact of external factors on electricity demand can be evaluated.

[0359] Step 4:

[0360] The server operates an emotion engine to acquire emotion data from the user's terminal. This emotion data is collected from the user's reactions, facial expressions, and entered text, and the server analyzes the user's emotional state in real time.

[0361] Step 5:

[0362] If an abnormal consumption pattern is detected, the server generates an alert based on the analysis results from the emotion engine. The alert is customized according to the user's emotional state and sent to the device along with specific corrective actions.

[0363] Step 6:

[0364] The device displays analysis results received from the server and customized alerts to the user in dashboard and graph format. The device integrates consumption data and sentiment data to allow the user to intuitively understand the situation.

[0365] Step 7:

[0366] Based on the information provided, users select improvement measures tailored to their power consumption and emotional state. They then optimize energy management according to the recommended strategy and adjust system settings as needed.

[0367] In this way, the present invention realizes energy management that takes user emotions into consideration, and supports more intuitive and human-centered decision-making.

[0368] (Example 2)

[0369] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0370] In recent years, while there has been a growing demand for more efficient energy consumption, existing energy management systems are limited to analyzing consumption data and struggle to implement comprehensive management that takes into account user emotions and external factors. Furthermore, warnings for abnormal consumption patterns are uniform, and the provision of appropriate improvement measures for individual users is insufficient. Therefore, in addition to optimizing energy consumption, flexible energy management that takes into account user satisfaction and emotional aspects is necessary.

[0371] 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.

[0372] In this invention, the server includes means for acquiring usage data in real time from an energy management mechanism, means for classifying usage patterns for each economic activity based on the usage data, and means for integrating external factor information and creating warnings. This enables comprehensive energy management that takes into account not only the analysis of usage data but also external factors and the emotional state of the user.

[0373] An "energy management system" is a device or system for monitoring energy usage in real time and for collecting and managing data.

[0374] "Usage data" refers to data that includes information about the consumption of electricity and other energy sources, showing when, where, and how they were used.

[0375] "Economic activity" refers to activities that indicate trends in energy consumption in specific industries or regions, and is information related to the analysis of consumption patterns.

[0376] "External factors information" refers to information about climate conditions and social circumstances that may affect energy consumption.

[0377] A "warning" is a message that notifies the user of an abnormal energy consumption pattern or the associated risks, and urges them to take action.

[0378] "Information equipment" refers to devices that allow users to receive and visually confirm information, and includes smartphones and computers.

[0379] An "emotion evaluation mechanism" is a technology for detecting and analyzing a user's emotional state, using image recognition and text analysis.

[0380] "Visual display means" refers to a function for displaying data in a visual format such as graphs and charts, and is intended to allow users to intuitively understand the information.

[0381] To implement this invention, it is necessary to construct a complex system that includes an energy management mechanism, a server, an emotion evaluation mechanism, and information equipment.

[0382] The server functions as the core of a system that acquires usage data from the energy management organization in real time. The server is equipped with an AI agent for data analysis and clustering, which is used to identify power consumption patterns and detect abnormal usage. Furthermore, it acquires weather and social information from the internet as external factor information and analyzes it comprehensively. This allows the server to understand the relationship between consumption patterns and external factors.

[0383] The terminal plays a crucial role in displaying the analysis results received from the server to the user. Desktop computers and smartphones are often used for this purpose, and the information is presented visually as dashboards and graphs. The terminal also sends information about the user's condition, such as sentiment data in the form of images and text, to the server.

[0384] Users can leverage the information provided through their devices to understand their energy consumption patterns and emotional state, and take concrete action. It is recommended that they adopt strategies aimed at both optimizing energy use and maintaining emotional well-being, taking into account the customized alerts generated by the system.

[0385] As a concrete example, the following prompt can be entered into the generative AI model.

[0386] Example of a prompt:

[0387] "Please provide an analysis of my recent increase in electricity consumption and its emotional impact on me. I would especially appreciate it if you could identify the times of day when I feel most stressed. Also, please suggest what actions I should take to address this."

[0388] By using this system, users can contribute not only to improving the efficiency of their power consumption but also to improving their overall lifestyle.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] The server collects usage data in real time from the energy management organization. Specifically, it receives power usage information transmitted from each energy consumption point and applies a method to store it in a database. Industry-specific and regional consumption data is provided as input, which is converted into a standard format and organized into time-series data to form the output.

[0392] Step 2:

[0393] The server analyzes consumption data acquired using an AI agent and classifies usage patterns. Specifically, it groups similar consumption patterns using clustering techniques. The consumption data organized in the previous step is used as input, and the output is consumption patterns classified by cluster. Furthermore, external factor information (weather and social conditions related data) is integrated, and correlation and regression analyses are performed.

[0394] Step 3:

[0395] The server uses an emotion evaluation mechanism to analyze emotion data acquired from the terminal in order to evaluate the user's emotional state. Specifically, it analyzes image and text data from the user and uses an AI model to infer emotions. The input is the user's emotion data (images and text), and the output is an evaluation result of the user's real-time emotional state.

[0396] Step 4:

[0397] The server, upon detecting an abnormal consumption pattern, generates a customized warning based on the user's emotional state and sends it to the information device. Specifically, it activates an anomaly detection algorithm and creates a warning, including stress reduction measures, for users determined to be experiencing high stress levels. The input is the results of the consumption pattern analysis and emotional evaluation, and the output is a customized warning message.

[0398] Step 5:

[0399] The terminal visually presents the user with analysis results and customized warnings received from the server. Specifically, it displays information in graph and chart format through a dashboard, allowing users to easily check their energy consumption and emotional state. The input is analysis results from the server, and the output is information displayed on the terminal in a visually organized format.

[0400] Step 6:

[0401] Users develop plans to improve their energy consumption habits based on the information displayed on their devices. Specifically, they adjust their electricity usage patterns or engage in stress management activities based on the suggested improvements. The input is visual information from the device, and the output is concrete actions that users can take to review their energy management.

[0402] (Application Example 2)

[0403] 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."

[0404] In modern society, achieving both efficient energy management and user satisfaction is challenging. Furthermore, conventional energy management systems are limited to analyzing simple consumption patterns and do not consider individual user emotions or lifestyles, resulting in ineffective energy savings and reduced user comfort.

[0405] 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.

[0406] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for performing clustering based on the consumption data and integrating external factor data to analyze the user's emotional state, and means for generating emotionally conscious alerts based on the analysis results and notifying the terminal. This enables more human-centered and adaptable energy management that takes the user's psychological state into consideration in energy management.

[0407] An "energy management device" is a device used to monitor and control the consumption of energy, such as electricity.

[0408] "Means for acquiring consumption data in real time" refers to means that have the function of collecting electricity consumption information in real time.

[0409] A "clustering method" is a method of classifying data, such as consumption patterns, based on specific similarities.

[0410] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0411] "Means for analyzing a user's emotional state" refers to technologies and devices that analyze a user's psychological state and determine their emotions.

[0412] "Means of generating alerts and notifying terminals" refers to means of generating warnings based on abnormal consumption patterns or emotional states and transmitting them to the user's terminal.

[0413] An "emotion-sensitive alert" refers to a warning that takes into account the user's psychological state and provides specific actions or notifications accordingly.

[0414] "Energy management" refers to the process of planning and controlling the efficient use of energy, such as electricity.

[0415] One embodiment of this invention is a system that integrates energy management with the user's emotional state to achieve more human-centered and adaptable energy management.

[0416] The server acquires energy consumption data in real time from energy management devices. This makes it possible to capture the latest consumption patterns. The consumption data is classified into standard consumption patterns for each industry using specialized clustering techniques. Data analysis tools are often used in this process.

[0417] Furthermore, the server acquires external factor data, such as climate information and social conditions information, from external data sources and integrates it as an element that affects power consumption. Additionally, emotional data is collected from the user's terminal, and an emotional analysis engine processes this data to evaluate the user's real-time emotional state. Emotional data is typically acquired using image analysis and text analysis technologies.

[0418] The server comprehensively analyzes consumption and emotional data, and if abnormal consumption patterns are detected, it generates appropriate alerts that take into account the user's emotional state. For example, for a user experiencing stress, it will suggest customized improvement measures to reduce consumption while alleviating stress.

[0419] The device displays analysis results, sentiment evaluation results, and customized alerts sent from the server in a dashboard format. This allows users to visually check their power consumption status and helps them make appropriate decisions about their energy consumption behavior.

[0420] For example, if a user is worried because their electricity bill has been too high lately, the app will recognize this emotion and suggest energy-saving measures for their home. A concrete example of a prompt for the generating AI model would be: "User's emotional state is 'worried'. Electricity consumption data: 20% increase compared to last month. Suggested solution: Please suggest simple energy-saving methods for your home to alleviate your worry."

[0421] In this way, by implementing energy management tailored to each user's individual circumstances, it is possible to improve both user satisfaction and energy efficiency.

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The server acquires energy consumption data in real time from energy management devices. This data includes consumption information organized by industry and is stored in the server's database. The input is consumption information obtained from energy management devices, and the output is consumption data saved in the database.

[0425] Step 2:

[0426] The server uses an AI model to analyze consumption data and applies clustering techniques to classify consumption patterns by industry. This process uses organized consumption data as input and produces a cluster list of consumption patterns as output. This provides clues to discovering characteristics and anomalies in consumption.

[0427] Step 3:

[0428] The server collects external factor data, such as climate information and social conditions, from external data sources and integrates it with consumption data. This identifies factors that may affect electricity consumption. The input is climate and social information obtained from external data sources, and the output is an analyzable dataset integrated with consumption data.

[0429] Step 4:

[0430] The server acquires emotional data from the user's terminal and analyzes the emotional state using an emotional analysis engine. The input for this step is emotional data obtained from the terminal, and the output is a real-time emotional evaluation result of the user. Image analysis and text analysis techniques are used for the data.

[0431] Step 5:

[0432] Based on the emotion evaluation results and consumption patterns, the server generates alerts that take the user's emotional state into consideration and notifies the terminal. The input consists of anomaly detection data for consumption patterns and emotion evaluation data, while the output is customized improvement measures and warning messages that take the user's psychology into account.

[0433] Step 6:

[0434] The device displays received analysis results, sentiment ratings, and customized alerts in a dashboard format. Input is notification data from the server, and output is a visualized information display. This allows users to understand their situation and select appropriate actions.

[0435] Step 7:

[0436] Based on the information presented, users make energy management decisions tailored to their own lifestyles. In this process, user input is a reaction to the information presented by the server, resulting in concrete energy-saving actions and changes in lifestyle habits.

[0437] 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.

[0438] 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 those described above. 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 shown 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.

[0439] 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.

[0440] [Third Embodiment]

[0441] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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".

[0453] The system according to the present invention acquires electricity consumption data in real time from an energy management device and has multiple functions for analyzing consumption patterns by industry. This enables highly accurate evaluation of the level of economic activity and supports rapid decision-making.

[0454] First, the server acquires consumption data in real time from energy management devices. This data includes details specific to each industry and region, and the server standardizes the format and converts it into a form suitable for analysis.

[0455] Next, the server uses an AI agent to perform clustering based on the acquired data. This allows for the identification of consumption patterns by industry and region, and enables the immediate detection of unique or abnormal patterns.

[0456] Furthermore, the server acquires external factor data such as climate information and social conditions, and comprehensively analyzes power consumption data. This allows for an accurate understanding of the potential impacts that climate change and social events have on electricity demand.

[0457] Furthermore, if an abnormal consumption pattern is detected, the server generates an alert. The generated alert is immediately notified to the user's terminal through other systems and applications.

[0458] The terminal visually presents the user with analysis results sent from the server and the impact of external factors. Therefore, the terminal is equipped with graphing functions and dashboards to allow users to easily understand this data.

[0459] Furthermore, the device will present specific improvement measures for improving energy efficiency based on the analysis results. These improvement measures include suggestions for reducing peak consumption at specific times.

[0460] Finally, users develop energy management and business strategies based on the displayed information and improvement suggestions. This enables more efficient management of electricity consumption and improved economic effectiveness.

[0461] For example, if an automobile manufacturing company uses the system of the present invention, the server analyzes power consumption data based on the operating status of the manufacturing line. The terminal displays the results on a dashboard, and the user can adopt the provided improvement measures to contribute to cost reduction and productivity improvement.

[0462] Thus, the system of the present invention analyzes power consumption data from multiple perspectives and supports the efficiency of economic activities.

[0463] The following describes the processing flow.

[0464] Step 1:

[0465] The server acquires real-time power consumption data from energy management devices. This data includes detailed information such as date and time, industry, region, and consumption amount. After receiving the data, the format is standardized and stored in an analysis database.

[0466] Step 2:

[0467] The server performs data preprocessing. It checks the acquired consumption data for outliers and missing values, and performs interpolation or correction as necessary. This ensures the accuracy of the data.

[0468] Step 3:

[0469] The server runs an AI agent and performs cluster analysis. Specifically, it utilizes the k-means method to classify consumption patterns by industry and region into multiple clusters, thereby identifying groups with similar consumption characteristics.

[0470] Step 4:

[0471] The server acquires external factor data, including climate information and social conditions, which are integrated with electricity consumption data to perform impact analysis. This analysis makes it possible to more accurately predict the impact of temperature fluctuations on electricity demand.

[0472] Step 5:

[0473] The server generates an alert when it detects an abnormal consumption pattern. Abnormal patterns are determined based on pre-set thresholds, and the alert information is immediately transmitted to the terminal via the notification system.

[0474] Step 6:

[0475] The terminal receives analysis results from the server and visualizes them in a user-friendly format. The dashboard displays consumption pattern trends and abnormal patterns, making them easy for users to understand.

[0476] Step 7:

[0477] Based on the analysis results, the terminal will suggest improvements to optimize energy management. These improvements include proposals for shifting power peaks during specific time periods and developing efficient energy operation plans.

[0478] Step 8:

[0479] Based on the information provided, users can review their business operations and energy management policies, and develop new strategies. If necessary, they can adjust system settings to obtain more precise data.

[0480] (Example 1)

[0481] 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."

[0482] Modern energy management requires real-time acquisition of consumption data and highly accurate analysis of consumption patterns specific to particular industries and regions. However, conventional systems often fail to adequately format the acquired data or integrate it with external factors, making early detection of abnormal consumption patterns and the proposal of efficient improvement measures difficult. A solution to this problem is needed to further improve the efficiency of electricity consumption.

[0483] 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.

[0484] In this invention, the server includes means for acquiring usage data in real time from an information management device, means for formatting the usage data and integrating it into a consistent data format, and means for clustering usage patterns for each business category using artificial intelligence generated based on the usage data. This enables everything from real-time data acquisition to integrated analysis, anomaly detection, and the provision of specific improvement measures.

[0485] An "information management device" is a hardware or software system designed to collect, process, and manage data.

[0486] "Usage data" refers to information that shows consumption and usage patterns within a specific service or system, and is data that requires real-time collection and analysis.

[0487] "Generative artificial intelligence" refers to a program or algorithm that analyzes large amounts of data and identifies significant patterns or anomalies through self-learning.

[0488] "Business classification" refers to a classification used to distinguish specific industries or sectors, and in analysis, it is a category used to identify consumption patterns and economic behavior.

[0489] "External factor information" refers to data derived primarily from environments and circumstances other than the target system, and includes information such as weather data and economic indicators.

[0490] A "warning" is a notification or message used to inform users when an abnormal situation is detected, and is a means of prompting a quick response.

[0491] "Specific measures for efficiency improvement" refer to concrete actions or changes proposed based on the analysis results, and are measures aimed at optimizing resources and reducing costs.

[0492] "User equipment" refers to devices or equipment that receive information from servers and systems and provide it to users.

[0493] A "consistent data format" is a standardized format that integrates data from different sources and facilitates analysis and display.

[0494] This invention provides a system in which a server, terminal, and user work together to acquire and analyze power consumption data. Specifically, it is implemented as follows.

[0495] The server acquires usage data in real time from the information management device through an interface. The server uses a REST API to collect data from the device and stores it in a database in an appropriate format. Next, the server uses Python or R data processing libraries to format and unify the acquired data. After being converted to a consistent data format, the server uses a generative artificial intelligence model to cluster usage patterns by business segment. For clustering, for example, the k-means method of machine learning models is used. The server also acquires information on weather and social conditions from external data sources and analyzes this in conjunction with the power consumption data. If a unique pattern is detected from the analysis results, the server immediately generates an alert and sends notifications to other systems using technologies such as Webhooks.

[0496] The terminal is responsible for visualizing analysis results and warnings received from the server. Using the JavaScript library D3.js, the terminal creates graphs and dashboards in a user-friendly format. Furthermore, the terminal provides users with specific measures for efficiency improvement based on suggestions from the generated artificial intelligence. This includes suggesting ways to reduce peak consumption during specified times.

[0497] Users formulate energy management and business strategies based on the data and improvement suggestions displayed on their devices. For example, a manufacturing user might input "Please propose energy efficiency improvement measures for our industry based on electricity consumption data" as a plutonium, and then use the generated AI model to formulate specific measures. This allows users to optimize electricity consumption and maximize economic benefits.

[0498] In this way, this invention enables the effective analysis and management of power consumption data, and supports user decision-making by providing necessary information quickly and accurately.

[0499] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0500] Step 1:

[0501] The server acquires power consumption data in real time from the information management device. In this step, the server requests data via a REST API and receives usage data in JSON format. It receives raw data from the energy management device as input and stores it in the database. The server checks the data format and necessary metadata, and stores the data while supplementing any missing parts.

[0502] Step 2:

[0503] The server formats the acquired data into a format that is easy to analyze. Specifically, it uses Python to impute missing values, convert data types, and standardize timestamp formats. Using the raw data acquired in step 1 as input, it outputs cleaned data while maintaining data consistency.

[0504] Step 3:

[0505] The server uses a raw artificial intelligence model to analyze clean data and cluster usage patterns by industry and region. In this step, machine learning models such as k-means are used to process the input dataset and classify it into groups based on usage patterns. The output is a dataset showing the features of each cluster.

[0506] Step 4:

[0507] The server acquires external factor information and performs integrated analysis with the clustering results. It obtains weather data and social situation data from an external API as input and integrates this data with the clustering results from the previous step. The server uses a statistical model to evaluate the impact of the input data on power consumption and obtains the impact analysis results as output.

[0508] Step 5:

[0509] The server detects abnormal consumption patterns from the integrated analysis results and generates warnings as needed. In this step, an anomaly detection algorithm is used to detect usage patterns that differ from normal patterns from the results analysis. The input is integrated consumption and factor data, and the output is anomaly warnings and their background information.

[0510] Step 6:

[0511] The terminal visualizes warnings and analysis results received from the server and provides them to the user. Specifically, it uses D3.js to generate interactive graphs and dashboards, making it easy for users to understand the data. The input is warning information and analysis results from the server, and the output is graphically displayed information.

[0512] Step 7:

[0513] The terminal presents the user with specific measures for efficiency improvement based on the generated AI model. The terminal receives the prompt message proposed by the AI ​​model and presents it to the user, thereby providing practical operational improvement suggestions. As output, it displays the suggested measures to the user.

[0514] Step 8:

[0515] Users revise their energy management and strategies based on graphs and suggestions displayed on their devices. The input consists of visual information and suggestions from the device; based on this, they formulate and implement strategies for efficient energy consumption and cost reduction. The output is improved management methods and business strategies.

[0516] (Application Example 1)

[0517] 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."

[0518] Energy consumption in modern cities is constantly increasing, and solutions are needed to address this problem in order to achieve a sustainable society. Conventional energy management systems have not only failed to acquire energy consumption data, but also to adequately detect anomalies in actual consumption patterns and provide real-time improvement suggestions. Furthermore, there has been a lack of technology to provide concrete energy efficiency suggestions that users can intuitively understand and act upon. By solving these problems, it is necessary to improve the energy efficiency of cities as a whole and contribute to the realization of a sustainable society.

[0519] 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.

[0520] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for clustering consumption patterns by industry, integrating external factor data to generate alerts, and means for suggesting specific improvement measures to suppress consumption peaks at specific times, and for allowing portable devices or visual devices to monitor the energy consumption efficiency status in real time. This makes it possible to provide detailed monitoring and specific efficiency measures regarding energy consumption at the city level.

[0521] An "energy management device" is a device that acquires and manages electricity consumption data in real time.

[0522] "Consumption data" refers to numerical information that shows the amount and pattern of energy use over a specific period.

[0523] Clustering is an analytical method that groups data based on similarity and classifies consumption patterns.

[0524] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0525] An "alert" is a warning message that is generated and sent when an abnormal consumption pattern is detected.

[0526] An "information display device" is a device used to visually present consumption data and analysis results to the user.

[0527] "Improvement measures" refer to specific action plans proposed to improve the efficiency of energy consumption.

[0528] A "portable device" is a device that a user can carry with them and is primarily used for acquiring and manipulating information.

[0529] A "visual device" is a device that has the function of presenting data to the user visually.

[0530] "Peak consumption" refers to the period of time when energy consumption is at its highest.

[0531] The system for realizing this invention consists of multiple components and aims to improve energy consumption efficiency. First, the server acquires power consumption data in real time from the energy management device and performs data formatting and processing. This processing is carried out in real time on a cloud server using Python scripts and APIs.

[0532] Subsequently, the server uses Scikit-learn and TensorFlow to perform industry-specific clustering based on the acquired consumption data. This enables immediate detection of abnormal consumption patterns and unusual movements. Furthermore, external factors such as climate information and social conditions are integrated into the data to perform a comprehensive analysis of consumption patterns. Based on this, an alert is generated if an anomaly is detected.

[0533] The generated alerts and analysis results are notified in real time to information display devices. Users can view this information through a visual dashboard in smartphone and smart glasses applications developed using Flutter and React Native. Furthermore, specific improvement measures to reduce peak consumption during specific times are also presented.

[0534] For example, if electricity consumption increases during specific times in the summer, the app will notify the user with a message such as, "Please consider temporarily turning off the air conditioning between 2 PM and 4 PM and using a fan instead." This makes it possible to effectively suppress peak consumption while maintaining a comfortable living environment.

[0535] This system, which utilizes a generative AI model to improve the energy efficiency of the entire city, is effectively operated by the following prompt messages.

[0536] Example prompt: "Analyze today's electricity consumption data for a specific region, identify any unusual patterns, and propose specific energy-saving measures."

[0537] In this way, servers, information display devices, and users can work together to streamline energy management.

[0538] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0539] Step 1:

[0540] The server acquires real-time power consumption data from energy management devices. The input is power consumption data from various industries and regions, and the output is analyzable data in a standardized format. This process uses a Python script to format the data on the cloud and save it to a database.

[0541] Step 2:

[0542] The server clusters consumption patterns by industry using Scikit-learn and TensorFlow based on unified consumption data. The input is organized power consumption data, and the output is cluster information separated by industry. Specifically, machine learning algorithms group correlated data and identify anomalous patterns.

[0543] Step 3:

[0544] The server integrates and analyzes consumption data and external factor data (such as climate information and social conditions). Inputs are cluster information and external data, and output is the integrated analysis result. This process identifies factors influencing consumption patterns and detects potential anomalies.

[0545] Step 4:

[0546] Based on the analysis results, the server generates an alert and notifies the information display device if an anomaly is detected. The input is the analyzed anomaly pattern, and the output is the alert notification to the user terminal. Specifically, a notification message is generated and immediately delivered to the user.

[0547] Step 5:

[0548] Based on alerts and analysis results received from the server, the terminal presents specific improvement measures to reduce peak consumption during specific times. At this stage, the terminal receives alert messages as input and displays a visual dashboard of improvement measures as output. It generates intuitively understandable graphs and charts using a user interface.

[0549] Step 6:

[0550] Users take action based on improvement suggestions displayed on their devices. Input is visualized data and improvement suggestions on the device, while output is the actual action taken to adjust energy consumption. For example, a user might follow instructions and take specific actions, such as refraining from using electrical appliances during certain time periods.

[0551] 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.

[0552] The system according to the present invention combines power consumption data acquired in real time from an energy management device with an emotion engine that analyzes the user's emotional state, thereby providing comprehensive energy management and decision-making support that takes into account both power consumption and the user's emotions.

[0553] First, the server acquires consumption data from energy management devices. This data includes detailed consumption information broken down by industry and region, and the server stores this data in a standard format in its database.

[0554] Next, the server uses an AI agent to analyze the data and classify consumption patterns using clustering techniques. Simultaneously, it acquires climate and social conditions information as external factors and analyzes how these factors affect power consumption.

[0555] Furthermore, the server runs an emotion engine to acquire emotion data from the user's device and evaluate how the user feels about the power consumption information. Emotion data is often acquired through image analysis and text analysis, and the emotion engine uses this data to determine the user's real-time emotional state.

[0556] If an abnormal consumption pattern is detected, the server creates an alert that takes the user's emotional state into account and notifies the device. For example, if it is determined that the user is stressed, it will provide customized solutions and suggestions to alleviate that stress.

[0557] The device displays analysis results, sentiment ratings, and customized alerts received from the server in dashboard and graph formats. This makes it easier for users to visually check their power consumption and their own emotional state.

[0558] Finally, based on the information provided, users determine improvement measures that are appropriate for their energy usage and personal feelings, and then strategically manage their energy accordingly. This allows for management that not only optimizes power consumption but also takes into account user satisfaction and stress levels.

[0559] In this way, this system takes into account the user's emotional state, thereby achieving a more human-centered and adaptable energy management system.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The server acquires real-time power consumption data from energy management devices. This data includes detailed information broken down by date, time, industry, and region, and the server formats this data and stores it in a database.

[0563] Step 2:

[0564] The server uses an AI agent to perform clustering on the acquired consumption data. Cluster analysis groups the consumption data based on similarity to discover anomalous and characteristic patterns.

[0565] Step 3:

[0566] The server acquires external factor data. This data includes climate information and social conditions information, and by analyzing it in combination with consumption data, the impact of external factors on electricity demand can be evaluated.

[0567] Step 4:

[0568] The server operates an emotion engine to acquire emotion data from the user's terminal. This emotion data is collected from the user's reactions, facial expressions, and entered text, and the server analyzes the user's emotional state in real time.

[0569] Step 5:

[0570] If an abnormal consumption pattern is detected, the server generates an alert based on the analysis results from the emotion engine. The alert is customized according to the user's emotional state and sent to the device along with specific corrective actions.

[0571] Step 6:

[0572] The device displays analysis results received from the server and customized alerts to the user in dashboard and graph format. The device integrates consumption data and sentiment data to allow the user to intuitively understand the situation.

[0573] Step 7:

[0574] Based on the information provided, users select improvement measures tailored to their power consumption and emotional state. They then optimize energy management according to the recommended strategy and adjust system settings as needed.

[0575] In this way, the present invention realizes energy management that takes user emotions into consideration, and supports more intuitive and human-centered decision-making.

[0576] (Example 2)

[0577] 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."

[0578] In recent years, while there has been a growing demand for more efficient energy consumption, existing energy management systems are limited to analyzing consumption data and struggle to implement comprehensive management that takes into account user emotions and external factors. Furthermore, warnings for abnormal consumption patterns are uniform, and the provision of appropriate improvement measures for individual users is insufficient. Therefore, in addition to optimizing energy consumption, flexible energy management that takes into account user satisfaction and emotional aspects is necessary.

[0579] 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.

[0580] In this invention, the server includes means for acquiring usage data in real time from an energy management mechanism, means for classifying usage patterns for each economic activity based on the usage data, and means for integrating external factor information and creating warnings. This enables comprehensive energy management that takes into account not only the analysis of usage data but also external factors and the emotional state of the user.

[0581] An "energy management system" is a device or system for monitoring energy usage in real time and for collecting and managing data.

[0582] "Usage data" refers to data that includes information about the consumption of electricity and other energy sources, showing when, where, and how they were used.

[0583] "Economic activity" refers to activities that indicate trends in energy consumption in specific industries or regions, and is information related to the analysis of consumption patterns.

[0584] "External factors information" refers to information about climate conditions and social circumstances that may affect energy consumption.

[0585] A "warning" is a message that notifies the user of an abnormal energy consumption pattern or the associated risks, and urges them to take action.

[0586] "Information equipment" refers to devices that allow users to receive and visually confirm information, and includes smartphones and computers.

[0587] An "emotion evaluation mechanism" is a technology for detecting and analyzing a user's emotional state, using image recognition and text analysis.

[0588] "Visual display means" refers to a function for displaying data in a visual format such as graphs or charts, and is intended to allow users to intuitively understand the information.

[0589] To implement this invention, it is necessary to construct a complex system that includes an energy management mechanism, a server, an emotion evaluation mechanism, and information equipment.

[0590] The server functions as the core of a system that acquires usage data from the energy management organization in real time. The server is equipped with an AI agent for data analysis and clustering, which is used to identify power consumption patterns and detect abnormal usage. Furthermore, it acquires weather and social information from the internet as external factor information and analyzes it comprehensively. This allows the server to understand the relationship between consumption patterns and external factors.

[0591] The terminal plays a crucial role in displaying the analysis results received from the server to the user. Desktop computers and smartphones are often used for this purpose, and the information is presented visually as dashboards and graphs. The terminal also sends information about the user's condition, such as sentiment data in the form of images and text, to the server.

[0592] Users can leverage the information provided through their devices to understand their energy consumption patterns and emotional state, and take concrete action. It is recommended that they adopt strategies aimed at both optimizing energy use and maintaining emotional well-being, taking into account the customized alerts generated by the system.

[0593] As a concrete example, the following prompt can be entered into the generative AI model.

[0594] Example of a prompt:

[0595] "Please provide an analysis of my recent increase in electricity consumption and its emotional impact on me. I would especially appreciate it if you could identify the times of day when I feel most stressed. Also, please suggest what actions I should take to address this."

[0596] By using this system, users can contribute not only to improving the efficiency of their power consumption but also to improving their overall lifestyle.

[0597] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0598] Step 1:

[0599] The server collects usage data in real time from the energy management organization. Specifically, it receives power usage information transmitted from each energy consumption point and applies a method to store it in a database. Industry-specific and regional consumption data is provided as input, which is converted into a standard format and organized into time-series data to form the output.

[0600] Step 2:

[0601] The server analyzes consumption data acquired using an AI agent and classifies usage patterns. Specifically, it groups similar consumption patterns using clustering techniques. The consumption data organized in the previous step is used as input, and the output is consumption patterns classified by cluster. Furthermore, external factor information (weather and social conditions related data) is integrated, and correlation and regression analyses are performed.

[0602] Step 3:

[0603] The server uses an emotion evaluation mechanism to analyze emotion data acquired from the terminal in order to evaluate the user's emotional state. Specifically, it analyzes image and text data from the user and uses an AI model to infer emotions. The input is the user's emotion data (images and text), and the output is an evaluation result of the user's real-time emotional state.

[0604] Step 4:

[0605] The server, upon detecting an abnormal consumption pattern, generates a customized warning based on the user's emotional state and sends it to the information device. Specifically, it activates an anomaly detection algorithm and creates a warning, including stress reduction measures, for users determined to be experiencing high stress levels. The input is the results of the consumption pattern analysis and emotional evaluation, and the output is a customized warning message.

[0606] Step 5:

[0607] The terminal visually presents the user with analysis results and customized warnings received from the server. Specifically, it displays information in graph and chart format through a dashboard, allowing users to easily check their energy consumption and emotional state. The input is analysis results from the server, and the output is information displayed on the terminal in a visually organized format.

[0608] Step 6:

[0609] Users develop plans to improve their energy consumption habits based on the information displayed on their devices. Specifically, they adjust their electricity usage patterns or engage in stress management activities based on the suggested improvements. The input is visual information from the device, and the output is concrete actions that users can take to review their energy management.

[0610] (Application Example 2)

[0611] 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."

[0612] In modern society, achieving both efficient energy management and user satisfaction is challenging. Furthermore, conventional energy management systems are limited to analyzing simple consumption patterns and do not consider individual user emotions or lifestyles, resulting in ineffective energy savings and reduced user comfort.

[0613] 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.

[0614] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for performing clustering based on the consumption data and integrating external factor data to analyze the user's emotional state, and means for generating emotionally conscious alerts based on the analysis results and notifying the terminal. This enables more human-centered and adaptable energy management that takes the user's psychological state into consideration during energy management.

[0615] An "energy management device" is a device used to monitor and control the consumption of energy, such as electricity.

[0616] "Means for acquiring consumption data in real time" refers to means that have the function of collecting electricity consumption information in real time.

[0617] A "clustering method" is a method of classifying data, such as consumption patterns, based on specific similarities.

[0618] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0619] "Means for analyzing a user's emotional state" refers to technologies and devices that analyze a user's psychological state and determine their emotions.

[0620] "Means of generating alerts and notifying terminals" refers to means of generating warnings based on abnormal consumption patterns or emotional states and transmitting them to the user's terminal.

[0621] An "emotion-sensitive alert" refers to a warning that takes into account the user's psychological state and provides specific actions or notifications accordingly.

[0622] "Energy management" refers to the process of planning and controlling the efficient use of energy, such as electricity.

[0623] One embodiment of this invention is a system that integrates energy management with the user's emotional state to achieve more human-centered and adaptable energy management.

[0624] The server acquires energy consumption data in real time from energy management devices. This makes it possible to capture the latest consumption patterns. The consumption data is classified into standard consumption patterns for each industry using specialized clustering techniques. Data analysis tools are often used in this process.

[0625] Furthermore, the server acquires external factor data, such as climate information and social conditions information, from external data sources and integrates it as an element that affects power consumption. Additionally, emotional data is collected from the user's terminal, and an emotional analysis engine processes this data to evaluate the user's real-time emotional state. Emotional data is typically acquired using image analysis and text analysis technologies.

[0626] The server comprehensively analyzes consumption and emotional data, and if abnormal consumption patterns are detected, it generates appropriate alerts that take into account the user's emotional state. For example, for a user experiencing stress, it will offer customized improvement measures to reduce consumption while alleviating stress.

[0627] The device displays analysis results, sentiment evaluation results, and customized alerts sent from the server in a dashboard format. This allows users to visually check their power consumption status and helps them make appropriate decisions about their energy consumption behavior.

[0628] For example, if a user is worried because their electricity bill has been too high lately, the app will recognize this emotion and suggest energy-saving measures for their home. A concrete example of a prompt for the generating AI model would be: "User's emotional state is 'worried'. Electricity consumption data: 20% increase compared to last month. Suggested solution: Please suggest simple energy-saving methods for your home to alleviate your worry."

[0629] In this way, by implementing energy management tailored to each user's individual circumstances, it is possible to improve both user satisfaction and energy efficiency.

[0630] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0631] Step 1:

[0632] The server acquires energy consumption data in real time from energy management devices. This data includes consumption information organized by industry and is stored in the server's database. The input is consumption information obtained from energy management devices, and the output is consumption data saved in the database.

[0633] Step 2:

[0634] The server uses an AI model to analyze consumption data and applies clustering techniques to classify consumption patterns by industry. This process uses organized consumption data as input and produces a cluster list of consumption patterns as output. This provides clues to discovering characteristics and anomalies in consumption.

[0635] Step 3:

[0636] The server collects external factor data, such as climate information and social conditions, from external data sources and integrates it with consumption data. This identifies factors that may affect electricity consumption. The input is climate and social information obtained from external data sources, and the output is an analyzable dataset integrated with consumption data.

[0637] Step 4:

[0638] The server acquires emotional data from the user's terminal and analyzes the emotional state using an emotional analysis engine. The input for this step is emotional data obtained from the terminal, and the output is a real-time emotional evaluation result of the user. Image analysis and text analysis techniques are used for the data.

[0639] Step 5:

[0640] Based on the emotion evaluation results and consumption patterns, the server generates alerts that take the user's emotional state into consideration and notifies the terminal. The input consists of anomaly detection data for consumption patterns and emotion evaluation data, while the output is customized improvement measures and warning messages that take the user's psychology into account.

[0641] Step 6:

[0642] The device displays received analysis results, sentiment ratings, and customized alerts in a dashboard format. Input is notification data from the server, and output is a visualized information display. This allows users to understand their situation and select appropriate actions.

[0643] Step 7:

[0644] Based on the information presented, users make energy management decisions tailored to their own lifestyles. In this process, user input is a reaction to the information presented by the server, resulting in concrete energy-saving actions and changes in lifestyle habits.

[0645] 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.

[0646] 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 those described above. 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 shown 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.

[0647] 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.

[0648] [Fourth Embodiment]

[0649] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0650] 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.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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).

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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".

[0662] The system according to the present invention acquires electricity consumption data in real time from an energy management device and has multiple functions for analyzing consumption patterns by industry. This enables highly accurate evaluation of the level of economic activity and supports rapid decision-making.

[0663] First, the server acquires consumption data in real time from energy management devices. This data includes details specific to each industry and region, and the server standardizes the format and converts it into a form suitable for analysis.

[0664] Next, the server uses an AI agent to perform clustering based on the acquired data. This allows for the identification of consumption patterns by industry and region, and enables the immediate detection of unique or abnormal patterns.

[0665] Furthermore, the server acquires external factor data such as climate information and social conditions, and comprehensively analyzes power consumption data. This allows for an accurate understanding of the potential impacts that climate change and social events have on electricity demand.

[0666] Furthermore, if an abnormal consumption pattern is detected, the server generates an alert. The generated alert is immediately notified to the user's terminal through other systems and applications.

[0667] The terminal visually presents the user with analysis results sent from the server and the impact of external factors. Therefore, the terminal is equipped with graphing functions and dashboards to allow users to easily understand this data.

[0668] Furthermore, the device will present specific improvement measures for improving energy efficiency based on the analysis results. These improvement measures include suggestions for reducing peak consumption at specific times.

[0669] Finally, users develop energy management and business strategies based on the displayed information and improvement suggestions. This enables more efficient management of electricity consumption and improved economic effectiveness.

[0670] For example, if an automobile manufacturing company uses the system of the present invention, the server analyzes power consumption data based on the operating status of the manufacturing line. The terminal displays the results on a dashboard, and the user can adopt the provided improvement measures to contribute to cost reduction and productivity improvement.

[0671] Thus, the system of the present invention analyzes power consumption data from multiple perspectives and supports the efficiency of economic activities.

[0672] The following describes the processing flow.

[0673] Step 1:

[0674] The server acquires real-time power consumption data from energy management devices. This data includes detailed information such as date and time, industry, region, and consumption amount. After receiving the data, the format is standardized and stored in an analysis database.

[0675] Step 2:

[0676] The server performs data preprocessing. It checks the acquired consumption data for outliers and missing values, and performs interpolation or correction as necessary. This ensures the accuracy of the data.

[0677] Step 3:

[0678] The server runs an AI agent and performs cluster analysis. Specifically, it utilizes the k-means method to classify consumption patterns by industry and region into multiple clusters, thereby identifying groups with similar consumption characteristics.

[0679] Step 4:

[0680] The server acquires external factor data, including climate information and social conditions, which are integrated with electricity consumption data to perform impact analysis. This analysis makes it possible to more accurately predict the impact of temperature fluctuations on electricity demand.

[0681] Step 5:

[0682] The server generates an alert when it detects an abnormal consumption pattern. Abnormal patterns are determined based on pre-set thresholds, and the alert information is immediately transmitted to the terminal via the notification system.

[0683] Step 6:

[0684] The terminal receives analysis results from the server and visualizes them in a user-friendly format. The dashboard displays consumption pattern trends and abnormal patterns, making them easy for users to understand.

[0685] Step 7:

[0686] Based on the analysis results, the terminal will suggest improvements to optimize energy management. These improvements include proposals for shifting power peaks during specific time periods and developing efficient energy operation plans.

[0687] Step 8:

[0688] Based on the information provided, users can review their business operations and energy management policies, and develop new strategies. If necessary, they can adjust system settings to obtain more precise data.

[0689] (Example 1)

[0690] 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".

[0691] Modern energy management requires real-time acquisition of consumption data and highly accurate analysis of consumption patterns specific to particular industries and regions. However, conventional systems often fail to adequately format the acquired data or integrate it with external factors, making early detection of abnormal consumption patterns and the proposal of efficient improvement measures difficult. A solution to this problem is needed to further improve the efficiency of electricity consumption.

[0692] 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.

[0693] In this invention, the server includes means for acquiring usage data in real time from an information management device, means for formatting the usage data and integrating it into a consistent data format, and means for clustering usage patterns for each business category using artificial intelligence generated based on the usage data. This enables everything from real-time data acquisition to integrated analysis, anomaly detection, and the provision of specific improvement measures.

[0694] An "information management device" is a hardware or software system designed to collect, process, and manage data.

[0695] "Usage data" refers to information that shows consumption and usage patterns within a specific service or system, and is data that requires real-time collection and analysis.

[0696] "Generative artificial intelligence" refers to a program or algorithm that analyzes large amounts of data and identifies significant patterns or anomalies through self-learning.

[0697] "Business classification" refers to a classification used to distinguish specific industries or sectors, and in analysis, it is a category used to identify consumption patterns and economic behavior.

[0698] "External factor information" refers to data derived primarily from environments and circumstances other than the target system, and includes information such as weather data and economic indicators.

[0699] A "warning" is a notification or message used to inform users when an abnormal situation is detected, and is a means of prompting a quick response.

[0700] "Specific measures for efficiency improvement" refer to concrete actions or changes proposed based on the analysis results, and are measures aimed at optimizing resources and reducing costs.

[0701] "User equipment" refers to devices or equipment that receive information from servers and systems and provide it to users.

[0702] A "consistent data format" is a standardized format that integrates data from different sources and facilitates analysis and display.

[0703] This invention provides a system in which a server, terminal, and user work together to acquire and analyze power consumption data. Specifically, it is implemented as follows.

[0704] The server acquires usage data in real time from the information management device through an interface. The server uses a REST API to collect data from the device and stores it in a database in an appropriate format. Next, the server uses Python or R data processing libraries to format and unify the acquired data. After being converted to a consistent data format, the server uses a generative artificial intelligence model to cluster usage patterns by business segment. For clustering, for example, the k-means method of machine learning models is used. The server also acquires information on weather and social conditions from external data sources and analyzes this in conjunction with the power consumption data. If a unique pattern is detected from the analysis results, the server immediately generates an alert and sends notifications to other systems using technologies such as Webhooks.

[0705] The terminal is responsible for visualizing analysis results and warnings received from the server. Using the JavaScript library D3.js, the terminal creates graphs and dashboards in a user-friendly format. Furthermore, the terminal provides users with specific measures for efficiency improvement based on suggestions from the generated artificial intelligence. This includes suggesting ways to reduce peak consumption during specified times.

[0706] Users formulate energy management and business strategies based on the data and improvement suggestions displayed on their devices. For example, a manufacturing user might input "Please propose energy efficiency improvement measures for our industry based on electricity consumption data" as a plutonium, and then use the generated AI model to formulate specific measures. This allows users to optimize electricity consumption and maximize economic benefits.

[0707] In this way, this invention enables the effective analysis and management of power consumption data, and supports user decision-making by providing necessary information quickly and accurately.

[0708] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0709] Step 1:

[0710] The server acquires power consumption data in real time from the information management device. In this step, the server requests data via a REST API and receives usage data in JSON format. It receives raw data from the energy management device as input and stores it in the database. The server checks the data format and necessary metadata, and stores the data while supplementing any missing parts.

[0711] Step 2:

[0712] The server formats the acquired data into a format that is easy to analyze. Specifically, it uses Python to impute missing values, convert data types, and standardize timestamp formats. Using the raw data acquired in step 1 as input, it outputs cleaned data while maintaining data consistency.

[0713] Step 3:

[0714] The server uses a raw artificial intelligence model to analyze clean data and cluster usage patterns by industry and region. In this step, machine learning models such as k-means are used to process the input dataset and classify it into groups based on usage patterns. The output is a dataset showing the features of each cluster.

[0715] Step 4:

[0716] The server acquires external factor information and performs integrated analysis with the clustering results. It obtains weather data and social situation data from an external API as input and integrates this data with the clustering results from the previous step. The server uses a statistical model to evaluate the impact of the input data on power consumption and obtains the impact analysis results as output.

[0717] Step 5:

[0718] The server detects abnormal consumption patterns from the integrated analysis results and generates warnings as needed. In this step, an anomaly detection algorithm is used to detect usage patterns that differ from normal patterns from the results analysis. The input is integrated consumption and factor data, and the output is anomaly warnings and their background information.

[0719] Step 6:

[0720] The terminal visualizes warnings and analysis results received from the server and provides them to the user. Specifically, it uses D3.js to generate interactive graphs and dashboards, making it easy for users to understand the data. The input is warning information and analysis results from the server, and the output is graphically displayed information.

[0721] Step 7:

[0722] The terminal presents the user with specific measures for efficiency improvement based on the generated AI model. The terminal receives the prompt message proposed by the AI ​​model and presents it to the user, thereby providing practical operational improvement suggestions. As output, it displays the suggested measures to the user.

[0723] Step 8:

[0724] Users revise their energy management and strategies based on graphs and suggestions displayed on their devices. The input consists of visual information and suggestions from the device; based on this, they formulate and implement strategies for efficient energy consumption and cost reduction. The output is improved management methods and business strategies.

[0725] (Application Example 1)

[0726] 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".

[0727] Energy consumption in modern cities is constantly increasing, and solutions are needed to address this problem in order to achieve a sustainable society. Conventional energy management systems have not only failed to acquire energy consumption data, but also to adequately detect anomalies in actual consumption patterns and provide real-time improvement suggestions. Furthermore, there has been a lack of technology to provide concrete energy efficiency suggestions that users can intuitively understand and act upon. By solving these problems, it is necessary to improve the energy efficiency of cities as a whole and contribute to the realization of a sustainable society.

[0728] 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.

[0729] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for clustering consumption patterns by industry, integrating external factor data to generate alerts, and means for suggesting specific improvement measures to suppress consumption peaks at specific times, and for allowing portable devices or visual devices to monitor the energy consumption efficiency status in real time. This makes it possible to provide detailed monitoring and specific efficiency measures regarding energy consumption at the city level.

[0730] An "energy management device" is a device that acquires and manages electricity consumption data in real time.

[0731] "Consumption data" refers to numerical information that shows the amount and pattern of energy use over a specific period.

[0732] Clustering is an analytical method that groups data based on similarity and classifies consumption patterns.

[0733] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0734] An "alert" is a warning message that is generated and sent when an abnormal consumption pattern is detected.

[0735] An "information display device" is a device used to visually present consumption data and analysis results to the user.

[0736] "Improvement measures" refer to specific action plans proposed to improve the efficiency of energy consumption.

[0737] A "portable device" is a device that a user can carry with them and is primarily used for acquiring and manipulating information.

[0738] A "visual device" is a device that has the function of presenting data to the user visually.

[0739] "Peak consumption" refers to the period of time when energy consumption is at its highest.

[0740] The system for realizing this invention consists of multiple components and aims to improve energy consumption efficiency. First, the server acquires power consumption data in real time from the energy management device and performs data formatting and processing. This processing is carried out in real time on a cloud server using Python scripts and APIs.

[0741] Subsequently, the server uses Scikit-learn and TensorFlow to perform industry-specific clustering based on the acquired consumption data. This enables immediate detection of abnormal consumption patterns and unusual movements. Furthermore, external factors such as climate information and social conditions are integrated into the data to perform a comprehensive analysis of consumption patterns. Based on this, an alert is generated if an anomaly is detected.

[0742] The generated alerts and analysis results are notified in real time to information display devices. Users can view this information through a visual dashboard in smartphone and smart glasses applications developed using Flutter and React Native. Furthermore, specific improvement measures to reduce peak consumption during specific times are also presented.

[0743] For example, if electricity consumption increases during specific times in the summer, the app will notify the user with a message such as, "Please consider temporarily turning off the air conditioning between 2 PM and 4 PM and using a fan instead." This makes it possible to effectively suppress peak consumption while maintaining a comfortable living environment.

[0744] This system, which utilizes a generative AI model to improve the energy efficiency of the entire city, is effectively operated by the following prompt messages.

[0745] Example prompt: "Analyze today's electricity consumption data for a specific region, identify any unusual patterns, and propose specific energy-saving measures."

[0746] In this way, servers, information display devices, and users can work together to streamline energy management.

[0747] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0748] Step 1:

[0749] The server acquires real-time power consumption data from energy management devices. The input is power consumption data from various industries and regions, and the output is analyzable data in a standardized format. This process uses a Python script to format the data on the cloud and save it to a database.

[0750] Step 2:

[0751] The server clusters consumption patterns by industry using Scikit-learn and TensorFlow based on unified consumption data. The input is organized power consumption data, and the output is cluster information separated by industry. Specifically, machine learning algorithms group correlated data and identify anomalous patterns.

[0752] Step 3:

[0753] The server integrates and analyzes consumption data and external factor data (such as climate information and social conditions). Inputs are cluster information and external data, and output is the integrated analysis result. This process identifies factors influencing consumption patterns and detects potential anomalies.

[0754] Step 4:

[0755] Based on the analysis results, the server generates an alert and notifies the information display device if an anomaly is detected. The input is the analyzed anomaly pattern, and the output is the alert notification to the user terminal. Specifically, a notification message is generated and immediately delivered to the user.

[0756] Step 5:

[0757] Based on alerts and analysis results received from the server, the terminal presents specific improvement measures to reduce peak consumption during specific times. At this stage, the terminal receives alert messages as input and displays a visual dashboard of improvement measures as output. It generates intuitively understandable graphs and charts using a user interface.

[0758] Step 6:

[0759] Users take action based on improvement suggestions displayed on their devices. Input is visualized data and improvement suggestions on the device, while output is the actual action taken to adjust energy consumption. For example, a user might follow instructions and take specific actions, such as refraining from using electrical appliances during certain time periods.

[0760] 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.

[0761] The system according to the present invention combines power consumption data acquired in real time from an energy management device with an emotion engine that analyzes the user's emotional state, thereby providing comprehensive energy management and decision-making support that takes into account both power consumption and the user's emotions.

[0762] First, the server acquires consumption data from energy management devices. This data includes detailed consumption information broken down by industry and region, and the server stores this data in a standard format in its database.

[0763] Next, the server uses an AI agent to analyze the data and classify consumption patterns using clustering techniques. Simultaneously, it acquires climate and social conditions information as external factors and analyzes how these factors affect power consumption.

[0764] Furthermore, the server runs an emotion engine to acquire emotion data from the user's device and evaluate how the user feels about the power consumption information. Emotion data is often acquired through image analysis and text analysis, and the emotion engine uses this data to determine the user's real-time emotional state.

[0765] If an abnormal consumption pattern is detected, the server creates an alert that takes the user's emotional state into account and notifies the device. For example, if it is determined that the user is stressed, it will provide customized solutions and suggestions to alleviate that stress.

[0766] The device displays analysis results, sentiment ratings, and customized alerts received from the server in dashboard and graph formats. This makes it easier for users to visually check their power consumption and their own emotional state.

[0767] Finally, based on the information provided, users determine improvement measures that are appropriate for their energy usage and personal feelings, and then strategically manage their energy accordingly. This allows for management that not only optimizes power consumption but also takes into account user satisfaction and stress levels.

[0768] In this way, this system takes into account the user's emotional state, thereby achieving a more human-centered and adaptable energy management system.

[0769] The following describes the processing flow.

[0770] Step 1:

[0771] The server acquires real-time power consumption data from energy management devices. This data includes detailed information broken down by date, time, industry, and region, and the server formats this data and stores it in a database.

[0772] Step 2:

[0773] The server uses an AI agent to perform clustering on the acquired consumption data. Cluster analysis groups the consumption data based on similarity to discover anomalous and characteristic patterns.

[0774] Step 3:

[0775] The server acquires external factor data. This data includes climate information and social conditions information, and by analyzing it in combination with consumption data, the impact of external factors on electricity demand can be evaluated.

[0776] Step 4:

[0777] The server operates an emotion engine to acquire emotion data from the user's terminal. This emotion data is collected from the user's reactions, facial expressions, and entered text, and the server analyzes the user's emotional state in real time.

[0778] Step 5:

[0779] If an abnormal consumption pattern is detected, the server generates an alert based on the analysis results from the emotion engine. The alert is customized according to the user's emotional state and sent to the device along with specific corrective actions.

[0780] Step 6:

[0781] The device displays analysis results received from the server and customized alerts to the user in dashboard and graph format. The device integrates consumption data and sentiment data to allow the user to intuitively understand the situation.

[0782] Step 7:

[0783] Based on the information provided, users select improvement measures tailored to their power consumption and emotional state. They then optimize energy management according to the recommended strategy and adjust system settings as needed.

[0784] In this way, the present invention realizes energy management that takes user emotions into consideration, and supports more intuitive and human-centered decision-making.

[0785] (Example 2)

[0786] 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".

[0787] In recent years, while there has been a growing demand for more efficient energy consumption, existing energy management systems are limited to analyzing consumption data and struggle to implement comprehensive management that takes into account user emotions and external factors. Furthermore, warnings for abnormal consumption patterns are uniform, and the provision of appropriate improvement measures for individual users is insufficient. Therefore, in addition to optimizing energy consumption, flexible energy management that takes into account user satisfaction and emotional aspects is necessary.

[0788] 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.

[0789] In this invention, the server includes means for acquiring usage data in real time from an energy management mechanism, means for classifying usage patterns for each economic activity based on the usage data, and means for integrating external factor information and creating warnings. This enables comprehensive energy management that takes into account not only the analysis of usage data but also external factors and the emotional state of the user.

[0790] An "energy management system" is a device or system for monitoring energy usage in real time and for collecting and managing data.

[0791] "Usage data" refers to data that includes information about the consumption of electricity and other energy sources, showing when, where, and how they were used.

[0792] "Economic activity" refers to activities that indicate trends in energy consumption in specific industries or regions, and is information related to the analysis of consumption patterns.

[0793] "External factors information" refers to information about climate conditions and social circumstances that may affect energy consumption.

[0794] A "warning" is a message that notifies the user of an abnormal energy consumption pattern or the associated risks, and urges them to take action.

[0795] "Information equipment" refers to devices that allow users to receive and visually confirm information, and includes smartphones and computers.

[0796] An "emotion evaluation mechanism" is a technology for detecting and analyzing a user's emotional state, using image recognition and text analysis.

[0797] "Visual display means" refers to a function for displaying data in a visual format such as graphs or charts, and is intended to allow users to intuitively understand the information.

[0798] To implement this invention, it is necessary to construct a complex system that includes an energy management mechanism, a server, an emotion evaluation mechanism, and information equipment.

[0799] The server functions as the core of a system that acquires usage data from the energy management organization in real time. The server is equipped with an AI agent for data analysis and clustering, which is used to identify power consumption patterns and detect abnormal usage. Furthermore, it acquires weather and social information from the internet as external factor information and analyzes it comprehensively. This allows the server to understand the relationship between consumption patterns and external factors.

[0800] The terminal plays a crucial role in displaying the analysis results received from the server to the user. Desktop computers and smartphones are often used for this purpose, and the information is presented visually as dashboards and graphs. The terminal also sends information about the user's condition, such as sentiment data in the form of images and text, to the server.

[0801] Users can leverage the information provided through their devices to understand their energy consumption patterns and emotional state, and take concrete action. It is recommended that they adopt strategies aimed at both optimizing energy use and maintaining emotional well-being, taking into account the customized alerts generated by the system.

[0802] As a concrete example, the following prompt can be entered into the generative AI model.

[0803] Example of a prompt:

[0804] "Please provide an analysis of my recent increase in electricity consumption and its emotional impact on me. I would especially appreciate it if you could identify the times of day when I feel most stressed. Also, please suggest what actions I should take to address this."

[0805] By using this system, users can contribute not only to improving the efficiency of their power consumption but also to improving their overall lifestyle.

[0806] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0807] Step 1:

[0808] The server collects usage data in real time from the energy management organization. Specifically, it receives power usage information transmitted from each energy consumption point and applies a method to store it in a database. Industry-specific and regional consumption data is provided as input, which is converted into a standard format and organized into time-series data to form the output.

[0809] Step 2:

[0810] The server analyzes consumption data acquired using an AI agent and classifies usage patterns. Specifically, it groups similar consumption patterns using clustering techniques. The consumption data organized in the previous step is used as input, and the output is consumption patterns classified by cluster. Furthermore, external factor information (weather and social conditions related data) is integrated, and correlation and regression analyses are performed.

[0811] Step 3:

[0812] The server uses an emotion evaluation mechanism to analyze emotion data acquired from the terminal in order to evaluate the user's emotional state. Specifically, it analyzes image and text data from the user and uses an AI model to infer emotions. The input is the user's emotion data (images and text), and the output is an evaluation result of the user's real-time emotional state.

[0813] Step 4:

[0814] The server, upon detecting an abnormal consumption pattern, generates a customized warning based on the user's emotional state and sends it to the information device. Specifically, it activates an anomaly detection algorithm and creates a warning, including stress reduction measures, for users determined to be experiencing high stress levels. The input is the results of the consumption pattern analysis and emotional evaluation, and the output is a customized warning message.

[0815] Step 5:

[0816] The terminal visually presents the user with analysis results and customized warnings received from the server. Specifically, it displays information in graph and chart format through a dashboard, allowing users to easily check their energy consumption and emotional state. The input is analysis results from the server, and the output is information displayed on the terminal in a visually organized format.

[0817] Step 6:

[0818] Users develop plans to improve their energy consumption habits based on the information displayed on their devices. Specifically, they adjust their electricity usage patterns or engage in stress management activities based on the suggested improvements. The input is visual information from the device, and the output is concrete actions that users can take to review their energy management.

[0819] (Application Example 2)

[0820] 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".

[0821] In modern society, achieving both efficient energy management and user satisfaction is challenging. Furthermore, conventional energy management systems are limited to analyzing simple consumption patterns and do not consider individual user emotions or lifestyles, resulting in ineffective energy savings and reduced user comfort.

[0822] 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.

[0823] In this invention, the server includes means for acquiring consumption data in real time from an energy management device, means for performing clustering based on the consumption data and integrating external factor data to analyze the user's emotional state, and means for generating emotionally conscious alerts based on the analysis results and notifying the terminal. This enables more human-centered and adaptable energy management that takes the user's psychological state into consideration during energy management.

[0824] An "energy management device" is a device used to monitor and control the consumption of energy, such as electricity.

[0825] "Means for acquiring consumption data in real time" refers to means that have the function of collecting electricity consumption information in real time.

[0826] A "clustering method" is a method of classifying data, such as consumption patterns, based on specific similarities.

[0827] "External factor data" refers to external information that affects electricity consumption, such as climate information and social conditions.

[0828] "Means for analyzing a user's emotional state" refers to technologies and devices that analyze a user's psychological state and determine their emotions.

[0829] "Means of generating alerts and notifying terminals" refers to means of generating warnings based on abnormal consumption patterns or emotional states and transmitting them to the user's terminal.

[0830] An "emotion-sensitive alert" refers to a warning that takes into account the user's psychological state and provides specific actions or notifications accordingly.

[0831] "Energy management" refers to the process of planning and controlling the efficient use of energy, such as electricity.

[0832] One embodiment of this invention is a system that integrates energy management with the user's emotional state to achieve more human-centered and adaptable energy management.

[0833] The server acquires energy consumption data in real time from energy management devices. This makes it possible to capture the latest consumption patterns. The consumption data is classified into standard consumption patterns for each industry using specialized clustering techniques. Data analysis tools are often used in this process.

[0834] Furthermore, the server acquires external factor data, such as climate information and social conditions information, from external data sources and integrates it as an element that affects power consumption. Additionally, emotional data is collected from the user's terminal, and an emotional analysis engine processes this data to evaluate the user's real-time emotional state. Emotional data is typically acquired using image analysis and text analysis technologies.

[0835] The server comprehensively analyzes consumption and emotional data, and if abnormal consumption patterns are detected, it generates appropriate alerts that take into account the user's emotional state. For example, for a user experiencing stress, it will offer customized improvement measures to reduce consumption while alleviating stress.

[0836] The device displays analysis results, sentiment evaluation results, and customized alerts sent from the server in a dashboard format. This allows users to visually check their power consumption status and helps them make appropriate decisions about their energy consumption behavior.

[0837] For example, if a user is worried because their electricity bill has been too high lately, the app will recognize this emotion and suggest energy-saving measures for their home. A concrete example of a prompt for the generating AI model would be: "User's emotional state is 'worried'. Electricity consumption data: 20% increase compared to last month. Suggested solution: Please suggest simple energy-saving methods for your home to alleviate your worry."

[0838] In this way, by implementing energy management tailored to each user's individual circumstances, it is possible to improve both user satisfaction and energy efficiency.

[0839] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0840] Step 1:

[0841] The server acquires energy consumption data in real time from energy management devices. This data includes consumption information organized by industry and is stored in the server's database. The input is consumption information obtained from energy management devices, and the output is consumption data saved in the database.

[0842] Step 2:

[0843] The server uses an AI model to analyze consumption data and applies clustering techniques to classify consumption patterns by industry. This process uses organized consumption data as input and produces a cluster list of consumption patterns as output. This provides clues to discovering characteristics and anomalies in consumption.

[0844] Step 3:

[0845] The server collects external factor data, such as climate information and social conditions, from external data sources and integrates it with consumption data. This identifies factors that may affect electricity consumption. The input is climate and social information obtained from external data sources, and the output is an analyzable dataset integrated with consumption data.

[0846] Step 4:

[0847] The server acquires emotional data from the user's terminal and analyzes the emotional state using an emotional analysis engine. The input for this step is emotional data obtained from the terminal, and the output is a real-time emotional evaluation result of the user. Image analysis and text analysis techniques are used for the data.

[0848] Step 5:

[0849] Based on the emotion evaluation results and consumption patterns, the server generates alerts that take the user's emotional state into consideration and notifies the terminal. The input consists of anomaly detection data for consumption patterns and emotion evaluation data, while the output is customized improvement measures and warning messages that take the user's psychology into account.

[0850] Step 6:

[0851] The device displays received analysis results, sentiment ratings, and customized alerts in a dashboard format. Input is notification data from the server, and output is a visualized information display. This allows users to understand their situation and select appropriate actions.

[0852] Step 7:

[0853] Based on the information presented, users make energy management decisions tailored to their own lifestyles. In this process, user input is a reaction to the information presented by the server, resulting in concrete energy-saving actions and changes in lifestyle habits.

[0854] 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.

[0855] 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 those described above. 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 shown 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0875] The following is further disclosed regarding the embodiments described above.

[0876] (Claim 1)

[0877] A means of acquiring consumption data in real time from an energy management device,

[0878] A means for clustering consumption patterns by industry based on the aforementioned consumption data,

[0879] A means of integrating external factor data and generating alerts,

[0880] A means of notifying the terminal of the aforementioned alert and suggesting corrective measures,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, which uses climate information and social conditions information as external factor data.

[0884] (Claim 3)

[0885] The system according to claim 1, further comprising a graph display means for visualizing the analysis results displayed on the terminal.

[0886] "Example 1"

[0887] (Claim 1)

[0888] A means of acquiring usage data in real time from an information management device,

[0889] A means for formatting the aforementioned usage data and integrating it into a consistent data format,

[0890] A means for clustering usage patterns for each business category using artificial intelligence generated based on the aforementioned usage data,

[0891] A means for integrating external factor information and analyzing the factors that affect the aforementioned usage data,

[0892] A means for detecting abnormal usage patterns and generating warnings based on them,

[0893] A means of notifying the user's device of the aforementioned warning and presenting specific measures for improving efficiency,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, which uses weather data and social conditions data as external factor information.

[0897] (Claim 3)

[0898] The system according to claim 1, further comprising visual display means for visualizing analysis results displayed on a user's device.

[0899] "Application Example 1"

[0900] (Claim 1)

[0901] A means of acquiring consumption data in real time from an energy management device,

[0902] A means for clustering consumption patterns by industry based on the aforementioned consumption data,

[0903] A means of integrating external factor data and generating alerts,

[0904] A means for notifying the aforementioned alert to an information display device and suggesting corrective measures,

[0905] A means of proposing specific improvement measures to suppress peak consumption at specific times,

[0906] A means of allowing a portable device or visual device to monitor the energy consumption efficiency status in real time,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, which uses climate information and social conditions information as external factor data.

[0910] (Claim 3)

[0911] The system according to claim 1, further comprising a graph display means for visualizing the analysis results displayed on an information display device.

[0912] "Example 2 of combining an emotion engine"

[0913] (Claim 1)

[0914] A means of obtaining real-time usage data from the energy management organization,

[0915] A means for classifying usage patterns for each economic activity based on the aforementioned usage data,

[0916] A means of integrating external factor information and creating a warning,

[0917] A means for notifying the aforementioned warning to an information device and suggesting corrective measures,

[0918] A means of acquiring and evaluating the emotional state of a user using an emotion evaluation mechanism,

[0919] A means of generating and notifying users of customized warnings that take into account their emotional state,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, which uses climate conditions and social conditions information as external factor information.

[0923] (Claim 3)

[0924] The system according to claim 1, further comprising a graphical display means for visualizing the analysis results displayed on an information device.

[0925] "Application example 2 when combining with an emotional engine"

[0926] (Claim 1)

[0927] A means of acquiring consumption data in real time from an energy management device,

[0928] A means for clustering consumption patterns by industry based on the aforementioned consumption data,

[0929] A means of integrating external factor data and analyzing the user's emotional state,

[0930] A means for generating an alert that takes emotional data into consideration based on the aforementioned analysis and notifying the terminal,

[0931] The aforementioned alerts and corrective measures are presented, and the means of supporting energy management that is suitable for the user's lifestyle are provided.

[0932] A means for visualizing the aforementioned analysis results and sentiment evaluations and displaying them so that the user can confirm them,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, which uses climate information and social conditions information as external factor data, as well as user sentiment data.

[0936] (Claim 3)

[0937] The system according to claim 1, further comprising a graph display means for visualizing the analysis results and sentiment evaluation displayed on the terminal. [Explanation of symbols]

[0938] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring consumption data in real time from an energy management device, A means for clustering consumption patterns by industry based on the aforementioned consumption data, A means of integrating external factor data and generating alerts, A means for notifying the aforementioned alert to an information display device and suggesting corrective measures, A means of proposing specific improvement measures to suppress peak consumption at specific times, A means of allowing a portable device or visual device to monitor the energy consumption efficiency status in real time, A system that includes this.

2. The system according to claim 1, which uses climate information and social conditions information as external factor data.

3. The system according to claim 1, further comprising a graph display means for visualizing the analysis results displayed on an information display device.

Images