System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting power consumption data; means for analyzing the collected power consumption data; means comprising a generative algorithm for interacting with a user and suggesting power saving measures; and means for remotely operating a power source or a breaker.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Improving energy efficiency and optimizing power consumption are important issues in modern large buildings and facilities. However, conventional systems have difficulty collecting and analyzing detailed power consumption patterns for each floor or room, making it difficult to implement effective power-saving measures. Furthermore, since manually operating power supplies and breakers is time-consuming and cumbersome for users, remote management is required. Furthermore, it is desirable for such systems to have the ability to provide effective power-saving measures tailored to individual situations through interactive dialogue with users. [Means for solving the problem]

[0005] To solve these problems, the present invention provides the following means. Specifically, it provides a system including a means for collecting power consumption data, a means for analyzing the collected power consumption data, a means including a generation algorithm that interacts with the user and proposes power-saving measures, and a means for remotely operating power supplies or breakers. This system makes it possible to grasp the power consumption status of each floor or room in real time and to generate and propose effective power-saving measures based on the analysis results. Furthermore, remote operation of power supplies and breakers enables fast and efficient energy management.

[0006] "Power consumption data" is information that records the amount of power consumed by each measurement point or device.

[0007] "Means for collection" refers to a device, system, or process for obtaining electricity consumption data in real time.

[0008] "Means for analysis" refers to software algorithms and processing methods used to analyze collected power consumption data and identify usage patterns and anomalies.

[0009] "User interaction" is the process of using generative algorithms to communicate with users, gather information, and provide advice.

[0010] A "generative algorithm" is a program or logic that automatically generates optimal results or suggestions based on input data.

[0011] "Remote operation" means controlling the status of equipment or systems from a remote location via a network.

[0012] "Operating a power source or breaker" is the act of turning on or off the power supply to a particular electrical circuit or device.

[0013] "System" is a collective term for a series of devices, software, and networks that function in combination with the above means. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[0036] Data collection

[0037] The server collects real-time electricity consumption data from smart meters in each building and on each floor, including the amount of power consumed (kWh) by each area and device, the duration of use, and peak consumption.

[0038] Data storage and analysis

[0039] The server stores the collected data in a database, which is then used for further analysis. The server then invokes an AI analysis module to identify power usage patterns and abnormal usage, enabling more efficient energy consumption and anomaly detection.

[0040] Dialogue with users and recommendations

[0041] The user accesses the system and asks for advice on power-saving measures. The server uses generative AI to interact with the user and proposes power-saving measures based on usage. The server compares past data with the current situation and generates optimal recommendations.

[0042] For example, if a user inputs, "I want to reduce electricity consumption after 6 p.m.", the generative AI will suggest, "Since electricity consumption peaks between 7 p.m. and 9 p.m., replacing lighting with LEDs would be highly effective."

[0043] Remote power / breaker operation

[0044] When a user instructs the power supply to be turned off in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which then turns off the power to the specified room or equipment.

[0045] For example, if a user inputs a command to the system to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in that room.

[0046] Specific examples of programs

[0047] Data collection flow

[0048] The server collects real-time electricity consumption data from each smart meter via an API.

[0049] The server stores the collected data in a database.

[0050] Data analysis flow

[0051] The server passes the stored data to an AI analysis module to detect power usage patterns and anomalies.

[0052] The server prepares data for generating proposals for power saving measures based on the analysis results.

[0053] User interaction and proposal flow

[0054] The user inputs their energy saving advice into the system.

[0055] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[0056] Remote operation flow

[0057] A user requests power / breaker operation for a specific room or device.

[0058] The server analyzes the instructions and instructs the corresponding smart meter to perform remote operation.

[0059] The terminal (smart meter) performs the specified operation.

[0060] The above is an embodiment of the present invention, which provides comprehensive power management and effective power saving measures to optimize energy efficiency.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[0064] Step 2:

[0065] The server stores the collected data in a database, where the data is structured by floor and device, and stored safely and efficiently.

[0066] Step 3:

[0067] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[0068] Step 4:

[0069] The server calls the AI ​​based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generates the most effective energy-saving method for the user based on past data and current usage.

[0070] Step 5:

[0071] A user accesses the system and inputs a request for power saving measures, for example, inputting a specific request such as "I want to reduce power consumption after 6 PM."

[0072] Step 6:

[0073] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[0074] Step 7:

[0075] If the user accepts the suggestion and instructs the power to be turned off in a specific room, the user inputs a remote command to the system, such as "Turn off the power in the conference room."

[0076] Step 8:

[0077] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meters. In this step, the server sends control signals to perform specific operations to turn on or off the power to the specified rooms or devices.

[0078] Step 9:

[0079] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[0080] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and achieving efficient energy management.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Conventional power management systems only collect power consumption data, making it difficult to pinpoint abnormal power usage or specific power-saving measures. Furthermore, the ability to remotely control power was limited, preventing flexible power management. Furthermore, it was difficult to provide appropriate recommendations based on user interaction. This led to problems such as inappropriate suggestions for efficient power usage and power-saving measures.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes a means for collecting power consumption data, a means for analyzing the collected power consumption data, a means including a generation algorithm for interacting with a user and proposing power-saving measures, a means for remotely operating a power supply or a breaker, a means for detecting anomalies in the power consumption data, and a means for pre-processing the power consumption data. This enables comprehensive power collection, analysis, interaction, and remote operation, enabling efficient use of power and the proposal of appropriate power-saving measures.

[0086] "Power consumption data" includes various information related to the amount of power, usage time, and peak consumption.

[0087] "Means for collection" refers to devices or software that communicate with smart meters and various sensors to obtain electricity consumption data.

[0088] A "database" is a collection of information that stores and manages collected electricity consumption data and can be used for analysis.

[0089] "Means for analyzing" refers to devices or software for analyzing power consumption data and detecting usage patterns or anomalies.

[0090] A "generative algorithm" is a program that interacts with users based on their input and suggests appropriate energy-saving measures.

[0091] "Remote operation means" means a device or software for operating a power supply or breaker from a remote location.

[0092] An "anomaly detection means" is a device or software that detects unusual patterns or unauthorized usage in power consumption data.

[0093] "Preprocessing means" means equipment or software that appropriately formats and cleans collected electricity consumption data before analysis and storage.

[0094] "Recommendations" are suggestions for energy-saving measures provided based on the user's power usage patterns.

[0095] "Generative AI" is an artificial intelligence technology that creates appropriate suggestions based on dialogue with users.

[0096] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[0097] Hardware and software used

[0098] Server: Oversees the collection, analysis, storage, remote operation, and collaboration with generative AI of power consumption data. Specifically, it uses general server hardware and the following software:

[0099] Database management system: MySQL (registered trademark), PostgreSQL, etc.

[0100] AI analysis module: Python scikit-learn library.

[0101] Generative AI models: such as OpenAI's (registered trademark) GPT-3 (registered trademark).

[0102] Terminal (smart meter): Installed in each building and on each floor, it collects electricity consumption data and sends it to a server.

[0103] Data collection

[0104] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, the smart meters send the data to the server via an API. This data includes the power consumption (kWh) of each area and device, the time of use, and peak consumption.

[0105] Data storage and preprocessing

[0106] The server stores the collected power consumption data in a database. Before storing the data, a Python data processing library (e.g., pandas) is used to preprocess the data and filter incomplete data and outliers.

[0107] Data analysis

[0108] The server passes the stored data to an AI analysis module (Python's scikit-learn library) to identify power usage patterns and anomalies, enabling more efficient energy consumption and anomaly detection.

[0109] User interaction

[0110] When a user accesses the system and asks for advice on energy-saving measures, the server uses generative AI (e.g., OpenAI's GPT-3) to converse with the user. For example, if the user inputs, "I want to reduce power consumption after 6 p.m.," the generative AI will suggest, "Power consumption peaks between 7 p.m. and 9 p.m., so replacing the lighting with LEDs would be highly effective."

[0111] Remote Operation

[0112] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter. The terminal (smart meter) follows the instruction and turns off the power in the specified room or equipment. For example, if a user enters the command "Turn off the power in the conference room," the server analyzes the instruction and the smart meter turns off the power in the conference room.

[0113] Examples of concrete examples and prompts

[0114] For example, if a user inputs "I want to reduce power consumption after 6 PM," the generative AI will suggest, "Power consumption peaks between 7 PM and 9 PM, so replacing the lighting with LEDs would be highly effective." In response to the command "Turn off the power in the conference room," the server will send an instruction to the corresponding smart meter to turn off the power in the conference room.

[0115] This will enable comprehensive power collection, analysis, interaction, and remote operation, enabling efficient power use and the proposal of appropriate power-saving measures.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Power management system program processing flow

[0118] Step 1: Data collection

[0119] The server collects real-time electricity consumption data from smart meters in each building and floor. The input is data such as the amount of electricity measured by the smart meters, usage time, and peak consumption. The output is the collected electricity consumption data.

[0120] Specific behavior:

[0121] The server sends API requests to each smart meter at regular intervals.

[0122] The server receives the power consumption data from the smart meter and temporarily stores it in memory.

[0123] Step 2: Data storage and preprocessing

[0124] The server preprocesses the collected power consumption data before storing it in the database. The input is the power consumption data collected in step 1. The output is the preprocessed data with outliers filtered out.

[0125] Specific behavior:

[0126] The server uses Python data processing libraries (e.g., pandas) to shape the data and filter out incomplete data and outliers.

[0127] The server generates SQL statements and stores the pre-processed data in a database (e.g. MySQL or PostgreSQL).

[0128] Step 3: Data analysis

[0129] The server passes the stored data to an AI analysis module to identify power usage patterns and anomalies. The input is pre-processed power consumption data stored in a database. The output is the analysis results.

[0130] Specific behavior:

[0131] The server executes a query to retrieve the required data from the database.

[0132] The server passes the acquired data to an AI analysis module using Python's scikit-learn library to detect power usage patterns and anomalies.

[0133] The server stores the analysis results in the database again.

[0134] Step 4: User interaction

[0135] When a user accesses the system and asks for advice on power-saving measures, the server uses generative AI to interact with the user. The input is the prompt the user enters into the system. The output is a power-saving measure proposal generated by the AI.

[0136] Specific behavior:

[0137] The user inputs a prompt statement into the system (e.g., "I want to reduce power consumption after 6 p.m.").

[0138] The server sends a prompt to the generative AI (e.g., OpenAI's GPT-3) and receives a response from the AI.

[0139] The server returns AI-generated suggestions to the user (e.g., "Electricity consumption peaks between 7:00 and 9:00 p.m., so replacing your lighting with LEDs would be highly effective").

[0140] Step 5: Remote Operation

[0141] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation instruction to the corresponding smart meter. The input is the remote operation command that the user inputs to the system. The output is that the power of the specified equipment is turned off.

[0142] Specific behavior:

[0143] The user enters the command "Turn off the power in the conference room."

[0144] The server analyzes the command and sends a request to the corresponding smart meter API.

[0145] The terminal (smart meter) receives the request and turns off the power in the designated conference room.

[0146] The above are the program processing steps and their specific operations in the power management system. This enables comprehensive power collection, analysis, interaction, and remote operation, making it possible to use power efficiently and propose appropriate power-saving measures.

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] There is a demand for more efficient power consumption and energy-saving measures in factories, but conventional systems do not adequately monitor and analyze power consumption in real time, and they also do not adequately propose effective power-saving measures through dialogue with users.To solve this problem, a system is needed that can collect and analyze power consumption data in detail, operate devices remotely, and propose optimal power-saving measures to users.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with a user and proposing power-saving measures, means for remotely operating a power supply or breaker, means for monitoring the power consumption of work equipment in a factory and collecting data in real time, means for saving the data collected in real time in the server, means for analyzing the saved data with an AI analysis module, means for generating and proposing optimal power-saving measures in response to user input using generative AI, and means for enabling remote power control of specific areas or devices. This makes it possible to monitor and optimize power consumption in a factory, and to propose and remotely operate efficient power-saving measures.

[0152] "Power consumption data" is numerical information about the amount of power consumed in a specific area or device, usage time, peak consumption, etc.

[0153] "Collection means" refers to a device or software that has the function of acquiring electricity consumption data from each smart meter or measuring device.

[0154] The "analyzing means" is a device or software that has the function of analyzing collected power consumption data and detecting usage patterns and anomalies.

[0155] The "means for interacting with the user" refers to a device or software that has the function of proposing appropriate power saving measures using a generative algorithm in response to user input.

[0156] A "generative algorithm" is an algorithm that includes calculation methods and procedures for providing optimal recommendations and advice to users based on collected and analyzed data.

[0157] "Means for remotely operating power or breakers" refers to devices or software that have the function of turning on and off the power or breakers of specific equipment or areas from a remote location.

[0158] The "monitoring means" refers to a device or software that has the function of monitoring the power consumption of work equipment in a factory and acquiring data in real time.

[0159] A "server" is a computer system capable of collecting, storing, analyzing, and interacting with users.

[0160] An "AI analysis module" is a software module that uses artificial intelligence to analyze acquired data and detect usage patterns and anomalies.

[0161] "Means for enabling remote power control of a device" refers to a device or software that has the function of turning the power of a specific device on or off from a remote location.

[0162] The "means for generating and proposing optimal energy-saving measures" refers to a device or software that has the function of proposing specific action plans to users for reducing energy consumption based on collected and analyzed data.

[0163] This invention relates to a system for optimizing power consumption in factories and proposing efficient power-saving measures. This system has the function of collecting and analyzing detailed power consumption data and remotely operating power supplies and breakers.

[0164] Data collection

[0165] The server collects real-time power consumption data from smart meters and various measuring devices installed within the factory. This data includes the power consumption of each work area and device, usage time, and peak consumption. This allows for an accurate understanding of the energy consumption situation throughout the factory.

[0166] Data storage and analysis

[0167] The server securely stores the collected data in a database for later detailed analysis. The stored data is then analyzed by an AI analysis module to identify power usage patterns and anomalous usage. The analysis results can be used to improve energy efficiency and detect anomalies.

[0168] Dialogue with users and recommendations

[0169] When a user accesses the system to inquire about power-saving measures, the server uses generative AI to converse with the user and propose power-saving measures based on usage. For example, if a user inputs, "I want to reduce power consumption during the day," the generative AI will generate specific suggestions based on collected data and analysis results, such as, "Consumption is high during certain times of the day, so shift the operating hours of some devices."

[0170] Remote power / breaker operation

[0171] When a user instructs a specific room or device to be turned off, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which results in the power being turned off for the designated work area or equipment. For example, if a user instructs the server to "turn off the power in the conference room," the server analyzes the instruction and the corresponding device turns off the power in the conference room.

[0172] Hardware and software used

[0173] Hardware: Smart meters, servers, database servers, and smartphones used by users.

[0174] Software: Python API, database management system, AI analysis module, generative AI.

[0175] For example, if a factory manager inputs "I want to reduce electricity consumption during the day," the system will use past data to suggest "Since usage is high during certain times of the day, we should spread out the use of heavy machinery." A specific example of a prompt for the generative AI model is as follows:

[0176] "I want to reduce electricity consumption during the day."

[0177] In this way, the server can streamline power management within the factory and optimize overall energy consumption.

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The server collects power consumption data in real time from smart meters and various measuring devices installed within the factory. The input is data from the smart meters (power consumption, usage time, peak consumption, etc.), and the output is the collected data. This allows the server to accurately grasp the energy consumption status of the entire factory.

[0181] Step 2:

[0182] The server stores the collected power consumption data in a database. The input is the data collected in step 1, and the output is the stored data. This storage process lays the foundation for further analysis later.

[0183] Step 3:

[0184] The server passes the stored data to an AI analysis module, which analyzes power usage patterns and abnormal usage. The input is the data stored in the database, and the output is the analysis results. This analysis makes it possible to improve energy efficiency and detect abnormalities.

[0185] Step 4:

[0186] The user accesses the system and asks for advice on power-saving measures. The input is the user's request (prompt), such as "I want to reduce power consumption during the day." The server uses generative AI to advance the dialogue with the user.

[0187] Step 5:

[0188] The server uses generative AI to propose optimal power-saving measures based on the analysis results of the AI ​​analysis module and user requests. The inputs are the analysis results and user requests, and the output is the generated power-saving measure proposal. For example, a proposal may be generated such as, "Consumption is high during certain time periods, so shift the operating hours of some devices."

[0189] Step 6:

[0190] A user remotely commands a specific room or device to be turned off. The input is the user's specific command (e.g., "Turn off the power in the conference room"), and the server receives the command.

[0191] Step 7:

[0192] The server analyzes the user's instructions and sends remote operation instructions to the corresponding smart meter. The input is the user's instructions, and the output is the specific remote operation instructions. This will turn off the power to the designated work area or equipment.

[0193] In this way, the server, terminals, and users work together to make power management within the factory more efficient and optimize overall energy consumption.

[0194] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0195] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with the user, and combines an emotion engine to take optimal action according to the user's emotions. The following describes in detail an embodiment of the present invention.

[0196] Data collection

[0197] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it obtains data such as power consumption (kWh), usage time, and peak consumption through the API of each smart meter.

[0198] Data storage and analysis

[0199] The server stores the collected data in a database, where data collected from each floor and device is structured, securely, and efficiently stored. The stored data is then passed to an AI analysis module, where it is analyzed to identify power usage patterns and anomalies, enabling efficient energy management.

[0200] Dialogue with users and recommendations

[0201] The user accesses the system and asks for advice on energy-saving measures. Specifically, the user inputs a request such as "I want to reduce power consumption after 6 PM." The server then uses generative AI to suggest specific energy-saving measures in a dialogue with the user. For example, the server might suggest, "Since power consumption peaks between 7 PM and 9 PM, we should replace the lighting with LEDs."

[0202] Emotion engine integration

[0203] The server calls the emotion engine during a dialogue with the user and recognizes their emotions by analyzing their voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied, and passes corresponding suggestions to the generative AI. For example, if the user is feeling stressed, the emotion engine will recognize this and suggest simple and easy-to-implement energy-saving measures to the generative AI.

[0204] Remote power / breaker operation

[0205] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the smart meter. For example, if a user inputs a command to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in the conference room based on the instruction.

[0206] Specific examples of programs

[0207] Data collection flow

[0208] The server collects real-time electricity consumption data from each smart meter via an API.

[0209] The server stores the collected data in a database.

[0210] Data analysis flow

[0211] The server passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[0212] The server prepares data to propose energy-saving measures based on the analysis results.

[0213] User interaction and proposal flow

[0214] The user inputs a request for advice on power saving measures.

[0215] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[0216] Flow of emotion engine integration

[0217] The server uses an emotion engine during dialogue with the user to analyze voice and text data and recognize the user's emotions.

[0218] Based on the results of the emotion engine, the server has the generative AI make suggestions based on the user's emotions.

[0219] Remote operation flow

[0220] A user requests power / breaker operation for a specific room or device.

[0221] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meter.

[0222] The terminal (smart meter) performs the specified operation.

[0223] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[0224] The processing flow will be explained below.

[0225] Step 1:

[0226] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[0227] Step 2:

[0228] The server stores the collected power consumption data in a database, which stores the information collected from each floor and device in a structured manner.

[0229] Step 3:

[0230] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[0231] Step 4:

[0232] The server calls the AI ​​generator based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generator generates effective energy-saving methods by taking into account past data and current usage conditions.

[0233] Step 5:

[0234] A user accesses the system and inputs a request for power saving measures. For example, the user inputs a request such as "I want to reduce power consumption after 6 PM."

[0235] Step 6:

[0236] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[0237] Step 7:

[0238] The server activates an emotion engine during a dialogue with the user and recognizes emotions by analyzing the voice and text data entered by the user. The emotion engine determines the user's stress and satisfaction levels and sends corresponding suggestions to the generative AI.

[0239] Step 8:

[0240] When a user issues a command to turn off the power in a specific room, the server analyzes the command and sends a remote operation command to the smart meter. For example, a user might enter a command such as "Turn off the power in the conference room."

[0241] Step 9:

[0242] The server sends specific operational instructions to the smart meter to power on or off designated rooms or devices.

[0243] Step 10:

[0244] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[0245] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and providing effective power saving measures according to the user's emotions.

[0246] Example 2

[0247] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0248] In modern society, efficient management of power consumption and energy-saving measures are important issues. Conventional power management systems can collect and analyze data on power consumption, but in many cases, it is difficult to provide users with appropriate energy-saving measures. In addition, they are unable to respond to users' emotions, which means they are unable to make suggestions that take into account users' satisfaction and willingness to implement them.

[0249] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0250] In this invention, the server includes means for collecting power consumption data, means for saving the collected power consumption data, means for analyzing the saved power consumption data, means including a generative algorithm for interacting with the user and proposing power saving measures, means including an emotion engine for analyzing the user's emotions, and means for remotely operating the power supply or breaker. This not only enables efficient power saving measures to be proposed based on the collected power consumption data, but also enables flexible responses according to the user's emotions.

[0251] "Power consumption data" refers to information such as the amount of power consumed, usage time, and peak consumption at each measurement point within a building or facility.

[0252] The "means of collection" refers to interface devices such as APIs and sensors for obtaining electricity consumption data from each smart meter.

[0253] The "storage means" is a database management system for structuring, efficiently and securely storing collected electricity consumption data.

[0254] The "analysis means" is an AI analysis module that uses stored power consumption data to detect power usage patterns and anomalies and support efficient energy management.

[0255] A "generative algorithm" is an artificial intelligence technology that proposes optimal energy-saving measures based on data collected through dialogue with users.

[0256] The "emotion engine" is a technology that analyzes the user's voice and text data to recognize their emotions. It can determine whether the user is feeling stressed or satisfied.

[0257] "Means for remote operation" refers to a mechanism for sending remote operation instructions to devices such as smart meters based on user instructions, and actually operating power supplies and breakers.

[0258] "User" refers to an individual or corporation that uses the system to manage power consumption and take measures to save power.

[0259] This invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power-saving measures through dialogue with the user, and combines an emotion engine to provide optimal responses according to the user's emotions.

[0260] Data collection

[0261] The server collects real-time power consumption data from smart meters in each building and floor via API. This collected data includes power consumption (kWh), usage time, peak consumption, etc. For example, when the server sends a request such as "GET / api / v1 / power-usage?floor=3", the smart meter returns JSON-formatted data such as "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}".

[0262] Data storage and analysis

[0263] The server stores the collected power consumption data in a database. This database uses an RDBMS such as MySQL. The stored data is passed to an AI analysis module, which uses Python's TENSORFLOW® library to perform analysis to identify power usage patterns and anomalies. For example, the server executes the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN® '2023-10-01' AND '2023-10-02'", converts the acquired data into JSON, and sends it to the AI ​​analysis module.

[0264] Dialogue with users and recommendations

[0265] Users access the system and use a chat interface to discuss energy-saving measures. For example, they input a request such as, "I want to reduce power consumption after 6 p.m." The server then uses a generative AI model to suggest specific energy-saving measures through a dialogue with the user. Specifically, the server suggests, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs." An example of a prompt statement is, "I want to reduce power consumption after 6 p.m."

[0266] Emotion engine integration

[0267] While interacting with the user, the server calls the emotion engine and analyzes the user's emotions from voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied. For example, voice data is sent to the emotion analysis API and results such as "Stress: 70%" and "Satisfaction: 20%" are received. Based on this, the generative AI model makes suggestions that take emotions into consideration. As a specific example, if the user is feeling stressed, it suggests "securely closing doors at night to increase heating and cooling efficiency" as a simple and easy-to-implement energy-saving measure.

[0268] Remote power / breaker operation

[0269] When a user requests a power control for a specific room, the server analyzes the request and sends a remote operation instruction to the smart meter. For example, if a user inputs "Turn off the power in the conference room," the server sends a "POST / api / v1 / control-power" request to the smart meter API, passing the data "room: conference_room, action: off." The device (smart meter) receives this instruction and turns off the power to the conference room.

[0270] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[0271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0272] Step 1:

[0273] The server collects data from the smart meters.

[0274] The server periodically sends API requests to the smart meters in each building and floor. Specifically, it sends the request "GET / api / v1 / power-usage." This input returns power consumption data such as power consumption, usage time, and peak consumption from the smart meter. For example, requesting "GET / api / v1 / power-usage?floor=3" will return the output "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}."

[0275] Step 2:

[0276] The server stores the collected data in a database

[0277] The server stores the acquired power consumption data in a MySQL database. The data input is the JSON format data returned from the smart meter. The data is structured and stored using the SQL query "INSERT INTO power_usage (timestamp, kWh, peak_usage, floor) VALUES ('2023-10-04T10:00:00Z', 50, 15, 3)".

[0278] Step 3:

[0279] The server passes the data to the AI ​​analysis module

[0280] The server retrieves power consumption data for a specific period from the database and sends it to the AI ​​analysis module. The input is the result of an SQL query from the database, and the output is formatted JSON data. Specifically, the data is retrieved using the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'".

[0281] Step 4:

[0282] The server receives the analysis results from the AI ​​analysis module

[0283] The AI ​​analysis module uses the input data to identify power usage patterns and anomalies. Based on this, it generates the data necessary to propose specific power-saving measures. For example, the AI ​​analysis module outputs "{"pattern":"high_usage","suggestion":"switch to LED lights"}", which is received by the server.

[0284] Step 5:

[0285] User consults about power saving measures

[0286] Users access the system and discuss energy-saving measures through a chat interface. For example, they input a request such as "I want to reduce power consumption after 6 p.m." The output is a response from the server based on that request.

[0287] Step 6:

[0288] The server interacts with the user using generative AI

[0289] The server passes the user's request to a generative AI model, which then interactively proposes specific energy-saving measures. The input is the user's request and the analysis results from the AI ​​analysis module, and the output is a specific energy-saving proposal. For example, it might suggest, "Since power consumption peaks between 7:00 and 9:00 p.m., replace the lighting with LEDs."

[0290] Step 7:

[0291] The server uses an emotion engine to recognize the user's emotions.

[0292] The server analyzes the user's voice and text data using an emotion engine. The input is the user's dialogue data, and the output is the emotion analysis results. For example, analyzing voice data yields results such as "Stress: 70%" and "Satisfaction: 20%."

[0293] Step 8:

[0294] The server uses generative AI to make suggestions based on emotions.

[0295] Based on the emotion analysis results, the server provides the generative AI model with suggestions that correspond to the user's emotions. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes the user's emotions into consideration. For example, if the user is feeling stressed, the server will make a suggestion such as "As a specific and easy-to-implement energy-saving measure, we suggest closing the doors at night to improve heating and cooling efficiency."

[0296] Step 9:

[0297] A user requests a remote operation

[0298] The user requests the system to operate the power / breaker for a specific room or device, for example, by inputting "Turn off the power to the conference room."

[0299] Step 10:

[0300] The server sends remote operation instructions to the smart meter

[0301] The server analyzes the user's request and sends remote operation instructions to the corresponding smart meter. The input is the user's request, and the output is the specific operation instruction to the smart meter. For example, send a "POST / api / v1 / control-power" request and pass the data "room: conference_room, action: off".

[0302] Step 11:

[0303] The terminal (smart meter) performs remote operations

[0304] The terminal (smart meter) turns off the power in a specific room based on instructions sent from the server. The input is the operation instruction from the server, and the output is the result of the operation. Specifically, it executes the command "to turn off the power in the conference room" using a relay operation or other means.

[0305] These are the processing steps of this system. This process makes it possible to efficiently manage the user's power consumption and provide optimal power saving measures.

[0306] (Application example 2)

[0307] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] In addition to optimizing power consumption and implementing effective energy-saving measures in industrial facilities, it has been difficult to manage energy consumption while taking into account the emotions of workers. Furthermore, there is a lack of systems that can collect real-time power consumption data from each facility and make effective energy-saving proposals.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with the user and proposing power-saving measures, means for analyzing emotion data and making suggestions according to the user's emotions, means for collecting power consumption data of industrial equipment in real time, and means for remotely operating the power supplies or breakers of specific work areas or equipment. This enables comprehensive energy management and effective power-saving measures tailored to the user.

[0310] "Power consumption data" refers to detailed data such as the amount of power used by each power device or facility, the duration of use, and peak consumption.

[0311] "Analysis means" refers to algorithms or software used to process collected power consumption data and identify power usage patterns and anomalies.

[0312] "Generative algorithms" are artificial intelligence technologies that interact with users based on collected and analyzed data and suggest specific energy-saving measures.

[0313] "Emotion data" is emotional data analyzed based on the user's voice and text data, and is information indicating whether the user is feeling stressed or satisfied.

[0314] "Emotion analysis means" is a technology for analyzing emotion data and recognizing the user's emotional state.

[0315] The "real-time collection means" is a function that collects power consumption data from each power device or facility in real time.

[0316] "Remote operation means" refers to technology for remotely controlling the power supply or breaker of a specific work area or equipment.

[0317] System Configuration

[0318] The present invention is embodied as a power management system within an industrial facility. The system includes the following main components:

[0319] 1. Server

[0320] Data collection: The server collects electricity consumption data in real time from the smart meters of each industrial facility via API.

[0321] Data storage: Collected data is stored in a cloud database (e.g., AWS (registered trademark) RDS).

[0322] Data analysis: The stored data is passed to an AI analysis module (e.g., TensorFlow) for analysis to identify power usage patterns and anomalies.

[0323] Generative algorithm: Using generative AI (e.g., OpenAI GPT-4 (registered trademark)), we interact with users and suggest specific energy-saving measures.

[0324] Emotion analysis: Using an emotion engine (e.g., IBM Watson (registered trademark) Tone Analyzer), emotions are analyzed from the user's voice and text data, and suggestions are made based on the user's emotions.

[0325] 2. Terminal

[0326] Real-time power collection: Each smart meter collects the power consumption data of the equipment in real time and transmits it to the server.

[0327] Remote Operation: Remotely operate power or breakers for specific work areas or equipment.

[0328] 3. Users

[0329] Dialogue and requests: Users access the system via smartphones or robots to discuss energy-saving measures. In response to the user's requests, the server uses generative AI to propose specific measures.

[0330] Emotion data provision: The voice and text data collected during the conversation is analyzed by the emotion engine to recognize the user's emotional state.

[0331] Program processing explanation

[0332] Below is a natural language description of how the components of the system work together:

[0333] 1. Data Collection and Storage

[0334] The server collects real-time electricity consumption data from each smart meter via API and stores it in a cloud database, including the amount of electricity consumed, the duration of use, and peak consumption.

[0335] 2. Data Analysis

[0336] The server periodically passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[0337] 3. Dialogue with users and proposals for energy-saving measures

[0338] When a user consults the system about energy-saving measures, the generative AI will suggest specific energy-saving measures in an interactive format. For example, if a user requests, "I want to reduce energy consumption after 6 p.m.", the generative AI will suggest, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs."

[0339] 4. Emotion analysis

[0340] The emotion engine analyzes the user's voice and text data to determine whether they are feeling stressed or satisfied. Based on the results of the emotion engine, the generative AI makes suggestions based on the user's emotions.

[0341] 5. Remote Operation

[0342] When a user requests a power control for a specific work area or device, the server analyzes the request and sends a remote control instruction to the corresponding smart meter, which then turns off the power accordingly.

[0343] Examples of concrete examples and prompts

[0344] For example, the following prompt sentences are used:

[0345] "What's the best way to reduce energy consumption after 6pm?"

[0346] Please tell me your current electricity usage.

[0347] "Please tell me about the energy savings that can be achieved by replacing lighting with LEDs."

[0348] "Please suggest some simple energy-saving measures for stressed workers."

[0349] "Please turn off the power to the conference room remotely."

[0350] In this way, the system achieves comprehensive energy management and effective power saving measures tailored to the user.

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] The server collects real-time electricity consumption data from the smart meters of each industrial facility. In this step, electricity consumption data (power consumption, usage time, peak consumption, etc.) is obtained from the smart meters via API and stored in a cloud database. The input is the electricity consumption data from each smart meter, and the output is the data stored in the cloud database.

[0354] Step 2:

[0355] The server passes the collected data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies. In this step, data is read from the cloud database and analyzed by the AI ​​analysis module (e.g., TensorFlow). The input is the stored power consumption data, and the output is the analysis results (identification of power usage patterns and anomalies).

[0356] Step 3:

[0357] A user consults the system about energy-saving measures. The user inputs a request to the system via a smartphone or robot. For example, the user inputs a prompt such as, "What is the best way to reduce energy consumption after 6 p.m." The input is the request from the user, and the output is the request data to the server.

[0358] Step 4:

[0359] The server uses generative AI (e.g., OpenAI GPT-4) to interactively propose specific power-saving measures. In this step, optimal power-saving measures are generated based on the user's request and the results of the AI ​​analysis module. The input is the user's request and the analysis results, and the output is a proposed power-saving measure.

[0360] Step 5:

[0361] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. In this step, the user's dialogue data is passed to the emotion engine for analysis. The input is the user's voice and text data, and the output is the emotion analysis result.

[0362] Step 6:

[0363] Based on the results of the emotion analysis, the server passes suggestions based on the user's emotions to the generative AI and engages in a dialogue. In this step, the results of the emotion analysis are taken into account to generate suggestions suitable for the user. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes emotions into consideration.

[0364] Step 7:

[0365] A user requests power control for a specific work area or device. The user enters a command such as "Please turn off the power to the conference room remotely." The input is the user's request, and the output is the operation instruction data sent to the server.

[0366] Step 8:

[0367] The server receives the remote operation instruction and sends it to the corresponding smart meter. In this step, the server analyzes the operation instruction and sends a power operation command to the specific smart meter. The input is the operation instruction data, and the output is a control signal to the smart meter.

[0368] Step 9:

[0369] The smart meter of the terminal performs the specified operation and turns off the power of the device. In this step, the smart meter controls the power of the device based on the instruction received. The input is the control signal, and the output is the state in which the device is powered off.

[0370] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0376] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0377] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0378] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0379] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0380] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0381] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0382] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0383] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0384] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0385] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0386] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[0387] Data collection

[0388] The server collects real-time electricity consumption data from smart meters in each building and on each floor, including the amount of power consumed (kWh) by each area and device, the duration of use, and peak consumption.

[0389] Data storage and analysis

[0390] The server stores the collected data in a database, which is then used for further analysis. The server then invokes an AI analysis module to identify power usage patterns and abnormal usage, enabling more efficient energy consumption and anomaly detection.

[0391] Dialogue with users and recommendations

[0392] The user accesses the system and asks for advice on power-saving measures. The server uses generative AI to interact with the user and proposes power-saving measures based on usage. The server compares past data with the current situation and generates optimal recommendations.

[0393] For example, if a user inputs, "I want to reduce electricity consumption after 6 p.m.", the generative AI will suggest, "Since electricity consumption peaks between 7 p.m. and 9 p.m., replacing lighting with LEDs would be highly effective."

[0394] Remote power / breaker operation

[0395] When a user instructs the power supply to be turned off in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which then turns off the power to the specified room or equipment.

[0396] For example, if a user inputs a command to the system to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in that room.

[0397] Specific examples of programs

[0398] Data collection flow

[0399] The server collects real-time electricity consumption data from each smart meter via an API.

[0400] The server stores the collected data in a database.

[0401] Data analysis flow

[0402] The server passes the stored data to an AI analysis module to detect power usage patterns and anomalies.

[0403] The server prepares data for generating proposals for power saving measures based on the analysis results.

[0404] User interaction and proposal flow

[0405] The user inputs their energy saving advice into the system.

[0406] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[0407] Remote operation flow

[0408] A user requests power / breaker operation for a specific room or device.

[0409] The server analyzes the instructions and instructs the corresponding smart meter to perform remote operation.

[0410] The terminal (smart meter) performs the specified operation.

[0411] The above is an embodiment of the present invention, which provides comprehensive power management and effective power saving measures to optimize energy efficiency.

[0412] The processing flow will be explained below.

[0413] Step 1:

[0414] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[0415] Step 2:

[0416] The server stores the collected data in a database, where the data is structured by floor and device, and stored safely and efficiently.

[0417] Step 3:

[0418] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[0419] Step 4:

[0420] The server calls the AI ​​based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generates the most effective energy-saving method for the user based on past data and current usage.

[0421] Step 5:

[0422] A user accesses the system and inputs a request for power saving measures, for example, inputting a specific request such as "I want to reduce power consumption after 6 PM."

[0423] Step 6:

[0424] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[0425] Step 7:

[0426] If the user accepts the suggestion and instructs the power to be turned off in a specific room, the user inputs a remote command to the system, such as "Turn off the power in the conference room."

[0427] Step 8:

[0428] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meters. In this step, the server sends control signals to perform specific operations to turn on or off the power to the specified rooms or devices.

[0429] Step 9:

[0430] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[0431] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and achieving efficient energy management.

[0432] Example 1

[0433] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0434] Conventional power management systems only collect power consumption data, making it difficult to pinpoint abnormal power usage or specific power-saving measures. Furthermore, the ability to remotely control power was limited, preventing flexible power management. Furthermore, it was difficult to provide appropriate recommendations based on user interaction. This led to problems such as inappropriate suggestions for efficient power usage and power-saving measures.

[0435] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0436] In this invention, the server includes a means for collecting power consumption data, a means for analyzing the collected power consumption data, a means including a generation algorithm for interacting with a user and proposing power-saving measures, a means for remotely operating a power supply or a breaker, a means for detecting anomalies in the power consumption data, and a means for pre-processing the power consumption data. This enables comprehensive power collection, analysis, interaction, and remote operation, enabling efficient use of power and the proposal of appropriate power-saving measures.

[0437] "Power consumption data" includes various information related to the amount of power, usage time, and peak consumption.

[0438] "Means for collection" refers to devices or software that communicate with smart meters and various sensors to obtain electricity consumption data.

[0439] A "database" is a collection of information that stores and manages collected electricity consumption data and can be used for analysis.

[0440] "Means for analyzing" refers to devices or software for analyzing power consumption data and detecting usage patterns or anomalies.

[0441] A "generative algorithm" is a program that interacts with users based on their input and suggests appropriate energy-saving measures.

[0442] "Remote operation means" means a device or software for operating a power supply or breaker from a remote location.

[0443] An "anomaly detection means" is a device or software that detects unusual patterns or unauthorized usage in power consumption data.

[0444] "Preprocessing means" means equipment or software that appropriately formats and cleans collected electricity consumption data before analysis and storage.

[0445] "Recommendations" are suggestions for energy-saving measures provided based on the user's power usage patterns.

[0446] "Generative AI" is an artificial intelligence technology that creates appropriate suggestions based on dialogue with users.

[0447] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[0448] Hardware and software used

[0449] Server: Oversees the collection, analysis, storage, remote operation, and collaboration with generative AI of power consumption data. Specifically, it uses general server hardware and the following software:

[0450] Database management system: MySQL, PostgreSQL, etc.

[0451] AI analysis module: Python scikit-learn library.

[0452] Generative AI models: such as OpenAI's GPT-3.

[0453] Terminal (smart meter): Installed in each building and on each floor, it collects electricity consumption data and sends it to a server.

[0454] Data collection

[0455] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, the smart meters send the data to the server via an API. This data includes the power consumption (kWh) of each area and device, the time of use, and peak consumption.

[0456] Data storage and preprocessing

[0457] The server stores the collected power consumption data in a database. Before storing the data, a Python data processing library (e.g., pandas) is used to preprocess the data and filter incomplete data and outliers.

[0458] Data analysis

[0459] The server passes the stored data to an AI analysis module (Python's scikit-learn library) to identify power usage patterns and anomalies, enabling more efficient energy consumption and anomaly detection.

[0460] User interaction

[0461] When a user accesses the system and asks for advice on energy-saving measures, the server uses generative AI (e.g., OpenAI's GPT-3) to converse with the user. For example, if the user inputs, "I want to reduce power consumption after 6 p.m.," the generative AI will suggest, "Power consumption peaks between 7 p.m. and 9 p.m., so replacing the lighting with LEDs would be highly effective."

[0462] Remote Operation

[0463] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter. The terminal (smart meter) follows the instruction and turns off the power in the specified room or equipment. For example, if a user enters the command "Turn off the power in the conference room," the server analyzes the instruction and the smart meter turns off the power in the conference room.

[0464] Examples of concrete examples and prompts

[0465] For example, if a user inputs "I want to reduce power consumption after 6 PM," the generative AI will suggest, "Power consumption peaks between 7 PM and 9 PM, so replacing the lighting with LEDs would be highly effective." In response to the command "Turn off the power in the conference room," the server will send an instruction to the corresponding smart meter to turn off the power in the conference room.

[0466] This will enable comprehensive power collection, analysis, interaction, and remote operation, enabling efficient power use and the proposal of appropriate power-saving measures.

[0467] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0468] Power management system program processing flow

[0469] Step 1: Data collection

[0470] The server collects real-time electricity consumption data from smart meters in each building and floor. The input is data such as the amount of electricity measured by the smart meters, usage time, and peak consumption. The output is the collected electricity consumption data.

[0471] Specific behavior:

[0472] The server sends API requests to each smart meter at regular intervals.

[0473] The server receives the power consumption data from the smart meter and temporarily stores it in memory.

[0474] Step 2: Data storage and preprocessing

[0475] The server preprocesses the collected power consumption data before storing it in the database. The input is the power consumption data collected in step 1. The output is the preprocessed data with outliers filtered out.

[0476] Specific behavior:

[0477] The server uses Python data processing libraries (e.g., pandas) to shape the data and filter out incomplete data and outliers.

[0478] The server generates SQL statements and stores the pre-processed data in a database (e.g. MySQL or PostgreSQL).

[0479] Step 3: Data analysis

[0480] The server passes the stored data to an AI analysis module to identify power usage patterns and anomalies. The input is pre-processed power consumption data stored in a database. The output is the analysis results.

[0481] Specific behavior:

[0482] The server executes a query to retrieve the required data from the database.

[0483] The server passes the acquired data to an AI analysis module using Python's scikit-learn library to detect power usage patterns and anomalies.

[0484] The server stores the analysis results in the database again.

[0485] Step 4: User interaction

[0486] When a user accesses the system and asks for advice on power-saving measures, the server uses generative AI to interact with the user. The input is the prompt the user enters into the system. The output is a power-saving measure proposal generated by the AI.

[0487] Specific behavior:

[0488] The user inputs a prompt statement into the system (e.g., "I want to reduce power consumption after 6 p.m.").

[0489] The server sends a prompt to the generative AI (e.g., OpenAI's GPT-3) and receives a response from the AI.

[0490] The server returns AI-generated suggestions to the user (e.g., "Electricity consumption peaks between 7:00 and 9:00 p.m., so replacing your lighting with LEDs would be highly effective").

[0491] Step 5: Remote Operation

[0492] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation instruction to the corresponding smart meter. The input is the remote operation command that the user inputs to the system. The output is that the power of the specified equipment is turned off.

[0493] Specific behavior:

[0494] The user enters the command "Turn off the power in the conference room."

[0495] The server analyzes the command and sends a request to the corresponding smart meter API.

[0496] The terminal (smart meter) receives the request and turns off the power in the designated conference room.

[0497] The above are the program processing steps and their specific operations in the power management system. This enables comprehensive power collection, analysis, interaction, and remote operation, making it possible to use power efficiently and propose appropriate power-saving measures.

[0498] (Application example 1)

[0499] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0500] There is a demand for more efficient power consumption and energy-saving measures in factories, but conventional systems do not adequately monitor and analyze power consumption in real time, and they also do not adequately propose effective power-saving measures through dialogue with users.To solve this problem, a system is needed that can collect and analyze power consumption data in detail, operate devices remotely, and propose optimal power-saving measures to users.

[0501] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0502] In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with a user and proposing power-saving measures, means for remotely operating a power supply or breaker, means for monitoring the power consumption of work equipment in a factory and collecting data in real time, means for saving the data collected in real time in the server, means for analyzing the saved data with an AI analysis module, means for generating and proposing optimal power-saving measures in response to user input using generative AI, and means for enabling remote power control of specific areas or devices. This makes it possible to monitor and optimize power consumption in a factory, and to propose and remotely operate efficient power-saving measures.

[0503] "Power consumption data" is numerical information about the amount of power consumed in a specific area or device, usage time, peak consumption, etc.

[0504] "Collection means" refers to a device or software that has the function of acquiring electricity consumption data from each smart meter or measuring device.

[0505] The "analyzing means" is a device or software that has the function of analyzing collected power consumption data and detecting usage patterns and anomalies.

[0506] The "means for interacting with the user" refers to a device or software that has the function of proposing appropriate power saving measures using a generative algorithm in response to user input.

[0507] A "generative algorithm" is an algorithm that includes calculation methods and procedures for providing optimal recommendations and advice to users based on collected and analyzed data.

[0508] "Means for remotely operating power or breakers" refers to devices or software that have the function of turning on and off the power or breakers of specific equipment or areas from a remote location.

[0509] The "monitoring means" refers to a device or software that has the function of monitoring the power consumption of work equipment in a factory and acquiring data in real time.

[0510] A "server" is a computer system capable of collecting, storing, analyzing, and interacting with users.

[0511] An "AI analysis module" is a software module that uses artificial intelligence to analyze acquired data and detect usage patterns and anomalies.

[0512] "Means for enabling remote power control of a device" refers to a device or software that has the function of turning the power of a specific device on or off from a remote location.

[0513] The "means for generating and proposing optimal energy-saving measures" refers to a device or software that has the function of proposing specific action plans to users for reducing energy consumption based on collected and analyzed data.

[0514] This invention relates to a system for optimizing power consumption in factories and proposing efficient power-saving measures. This system has the function of collecting and analyzing detailed power consumption data and remotely operating power supplies and breakers.

[0515] Data collection

[0516] The server collects real-time power consumption data from smart meters and various measuring devices installed within the factory. This data includes the power consumption of each work area and device, usage time, and peak consumption. This allows for an accurate understanding of the energy consumption situation throughout the factory.

[0517] Data storage and analysis

[0518] The server securely stores the collected data in a database for later detailed analysis. The stored data is then analyzed by an AI analysis module to identify power usage patterns and anomalous usage. The analysis results can be used to improve energy efficiency and detect anomalies.

[0519] Dialogue with users and recommendations

[0520] When a user accesses the system to inquire about power-saving measures, the server uses generative AI to converse with the user and propose power-saving measures based on usage. For example, if a user inputs, "I want to reduce power consumption during the day," the generative AI will generate specific suggestions based on collected data and analysis results, such as, "Consumption is high during certain times of the day, so shift the operating hours of some devices."

[0521] Remote power / breaker operation

[0522] When a user instructs a specific room or device to be turned off, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which results in the power being turned off for the designated work area or equipment. For example, if a user instructs the server to "turn off the power in the conference room," the server analyzes the instruction and the corresponding device turns off the power in the conference room.

[0523] Hardware and software used

[0524] Hardware: Smart meters, servers, database servers, and smartphones used by users.

[0525] Software: Python API, database management system, AI analysis module, generative AI.

[0526] For example, if a factory manager inputs "I want to reduce electricity consumption during the day," the system will use past data to suggest "Since usage is high during certain times of the day, we should spread out the use of heavy machinery." A specific example of a prompt for the generative AI model is as follows:

[0527] "I want to reduce electricity consumption during the day."

[0528] In this way, the server can streamline power management within the factory and optimize overall energy consumption.

[0529] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0530] Step 1:

[0531] The server collects power consumption data in real time from smart meters and various measuring devices installed within the factory. The input is data from the smart meters (power consumption, usage time, peak consumption, etc.), and the output is the collected data. This allows the server to accurately grasp the energy consumption status of the entire factory.

[0532] Step 2:

[0533] The server stores the collected power consumption data in a database. The input is the data collected in step 1, and the output is the stored data. This storage process lays the foundation for further analysis later.

[0534] Step 3:

[0535] The server passes the stored data to an AI analysis module, which analyzes power usage patterns and abnormal usage. The input is the data stored in the database, and the output is the analysis results. This analysis makes it possible to improve energy efficiency and detect abnormalities.

[0536] Step 4:

[0537] The user accesses the system and asks for advice on power-saving measures. The input is the user's request (prompt), such as "I want to reduce power consumption during the day." The server uses generative AI to advance the dialogue with the user.

[0538] Step 5:

[0539] The server uses generative AI to propose optimal power-saving measures based on the analysis results of the AI ​​analysis module and user requests. The inputs are the analysis results and user requests, and the output is the generated power-saving measure proposal. For example, a proposal may be generated such as, "Consumption is high during certain time periods, so shift the operating hours of some devices."

[0540] Step 6:

[0541] A user remotely commands a specific room or device to be turned off. The input is the user's specific command (e.g., "Turn off the power in the conference room"), and the server receives the command.

[0542] Step 7:

[0543] The server analyzes the user's instructions and sends remote operation instructions to the corresponding smart meter. The input is the user's instructions, and the output is the specific remote operation instructions. This will turn off the power to the designated work area or equipment.

[0544] In this way, the server, terminals, and users work together to make power management within the factory more efficient and optimize overall energy consumption.

[0545] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0546] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with the user, and combines an emotion engine to take optimal action according to the user's emotions. The following describes in detail an embodiment of the present invention.

[0547] Data collection

[0548] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it obtains data such as power consumption (kWh), usage time, and peak consumption through the API of each smart meter.

[0549] Data storage and analysis

[0550] The server stores the collected data in a database, where data collected from each floor and device is structured, securely, and efficiently stored. The stored data is then passed to an AI analysis module, where it is analyzed to identify power usage patterns and anomalies, enabling efficient energy management.

[0551] Dialogue with users and recommendations

[0552] The user accesses the system and asks for advice on energy-saving measures. Specifically, the user inputs a request such as "I want to reduce power consumption after 6 PM." The server then uses generative AI to suggest specific energy-saving measures in a dialogue with the user. For example, the server might suggest, "Since power consumption peaks between 7 PM and 9 PM, we should replace the lighting with LEDs."

[0553] Emotion engine integration

[0554] The server calls the emotion engine during a dialogue with the user and recognizes their emotions by analyzing their voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied, and passes corresponding suggestions to the generative AI. For example, if the user is feeling stressed, the emotion engine will recognize this and suggest simple and easy-to-implement energy-saving measures to the generative AI.

[0555] Remote power / breaker operation

[0556] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the smart meter. For example, if a user inputs a command to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in the conference room based on the instruction.

[0557] Specific examples of programs

[0558] Data collection flow

[0559] The server collects real-time electricity consumption data from each smart meter via an API.

[0560] The server stores the collected data in a database.

[0561] Data analysis flow

[0562] The server passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[0563] The server prepares data to propose energy-saving measures based on the analysis results.

[0564] User interaction and proposal flow

[0565] The user inputs a request for advice on power saving measures.

[0566] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[0567] Flow of emotion engine integration

[0568] The server uses an emotion engine during dialogue with the user to analyze voice and text data and recognize the user's emotions.

[0569] Based on the results of the emotion engine, the server has the generative AI make suggestions based on the user's emotions.

[0570] Remote operation flow

[0571] A user requests power / breaker operation for a specific room or device.

[0572] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meter.

[0573] The terminal (smart meter) performs the specified operation.

[0574] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[0575] The processing flow will be explained below.

[0576] Step 1:

[0577] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[0578] Step 2:

[0579] The server stores the collected power consumption data in a database, which stores the information collected from each floor and device in a structured manner.

[0580] Step 3:

[0581] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[0582] Step 4:

[0583] The server calls the AI ​​generator based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generator generates effective energy-saving methods by taking into account past data and current usage conditions.

[0584] Step 5:

[0585] A user accesses the system and inputs a request for power saving measures. For example, the user inputs a request such as "I want to reduce power consumption after 6 PM."

[0586] Step 6:

[0587] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[0588] Step 7:

[0589] The server activates an emotion engine during a dialogue with the user and recognizes emotions by analyzing the voice and text data entered by the user. The emotion engine determines the user's stress and satisfaction levels and sends corresponding suggestions to the generative AI.

[0590] Step 8:

[0591] When a user issues a command to turn off the power in a specific room, the server analyzes the command and sends a remote operation command to the smart meter. For example, a user might enter a command such as "Turn off the power in the conference room."

[0592] Step 9:

[0593] The server sends specific operational instructions to the smart meter to power on or off designated rooms or devices.

[0594] Step 10:

[0595] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[0596] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and providing effective power saving measures according to the user's emotions.

[0597] Example 2

[0598] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0599] In modern society, efficient management of power consumption and energy-saving measures are important issues. Conventional power management systems can collect and analyze data on power consumption, but in many cases, it is difficult to provide users with appropriate energy-saving measures. In addition, they are unable to respond to users' emotions, which means they are unable to make suggestions that take into account users' satisfaction and willingness to implement them.

[0600] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0601] In this invention, the server includes means for collecting power consumption data, means for saving the collected power consumption data, means for analyzing the saved power consumption data, means including a generative algorithm for interacting with the user and proposing power saving measures, means including an emotion engine for analyzing the user's emotions, and means for remotely operating the power supply or breaker. This not only enables efficient power saving measures to be proposed based on the collected power consumption data, but also enables flexible responses according to the user's emotions.

[0602] "Power consumption data" refers to information such as the amount of power consumed, usage time, and peak consumption at each measurement point within a building or facility.

[0603] The "means of collection" refers to interface devices such as APIs and sensors for obtaining electricity consumption data from each smart meter.

[0604] The "storage means" is a database management system for structuring, efficiently and securely storing collected electricity consumption data.

[0605] The "analysis means" is an AI analysis module that uses stored power consumption data to detect power usage patterns and anomalies and support efficient energy management.

[0606] A "generative algorithm" is an artificial intelligence technology that proposes optimal energy-saving measures based on data collected through dialogue with users.

[0607] The "emotion engine" is a technology that analyzes the user's voice and text data to recognize their emotions. It can determine whether the user is feeling stressed or satisfied.

[0608] "Means for remote operation" refers to a mechanism for sending remote operation instructions to devices such as smart meters based on user instructions, and actually operating power supplies and breakers.

[0609] "User" refers to an individual or corporation that uses the system to manage power consumption and take measures to save power.

[0610] This invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power-saving measures through dialogue with the user, and combines an emotion engine to provide optimal responses according to the user's emotions.

[0611] Data collection

[0612] The server collects real-time power consumption data from smart meters in each building and floor via API. This collected data includes power consumption (kWh), usage time, peak consumption, etc. For example, when the server sends a request such as "GET / api / v1 / power-usage?floor=3", the smart meter returns JSON-formatted data such as "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}".

[0613] Data storage and analysis

[0614] The server stores the collected power consumption data in a database. This database uses an RDBMS such as MySQL. The stored data is passed to an AI analysis module, which uses Python's TensorFlow library to perform analysis to identify power usage patterns and anomalies. For example, the server executes the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'", converts the obtained data into JSON, and sends it to the AI ​​analysis module.

[0615] Dialogue with users and recommendations

[0616] Users access the system and use a chat interface to discuss energy-saving measures. For example, they input a request such as, "I want to reduce power consumption after 6 p.m." The server then uses a generative AI model to suggest specific energy-saving measures through a dialogue with the user. Specifically, the server suggests, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs." An example of a prompt statement is, "I want to reduce power consumption after 6 p.m."

[0617] Emotion engine integration

[0618] While interacting with the user, the server calls the emotion engine and analyzes the user's emotions from voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied. For example, voice data is sent to the emotion analysis API and results such as "Stress: 70%" and "Satisfaction: 20%" are received. Based on this, the generative AI model makes suggestions that take emotions into consideration. As a specific example, if the user is feeling stressed, it suggests "securely closing doors at night to increase heating and cooling efficiency" as a simple and easy-to-implement energy-saving measure.

[0619] Remote power / breaker operation

[0620] When a user requests a power control for a specific room, the server analyzes the request and sends a remote operation instruction to the smart meter. For example, if a user inputs "Turn off the power in the conference room," the server sends a "POST / api / v1 / control-power" request to the smart meter API, passing the data "room: conference_room, action: off." The device (smart meter) receives this instruction and turns off the power to the conference room.

[0621] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[0622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0623] Step 1:

[0624] The server collects data from the smart meters.

[0625] The server periodically sends API requests to the smart meters in each building and floor. Specifically, it sends the request "GET / api / v1 / power-usage." This input returns power consumption data such as power consumption, usage time, and peak consumption from the smart meter. For example, requesting "GET / api / v1 / power-usage?floor=3" will return the output "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}."

[0626] Step 2:

[0627] The server stores the collected data in a database

[0628] The server stores the acquired power consumption data in a MySQL database. The data input is the JSON format data returned from the smart meter. The data is structured and stored using the SQL query "INSERT INTO power_usage (timestamp, kWh, peak_usage, floor) VALUES ('2023-10-04T10:00:00Z', 50, 15, 3)".

[0629] Step 3:

[0630] The server passes the data to the AI ​​analysis module

[0631] The server retrieves power consumption data for a specific period from the database and sends it to the AI ​​analysis module. The input is the result of an SQL query from the database, and the output is formatted JSON data. Specifically, the data is retrieved using the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'".

[0632] Step 4:

[0633] The server receives the analysis results from the AI ​​analysis module

[0634] The AI ​​analysis module uses the input data to identify power usage patterns and anomalies. Based on this, it generates the data necessary to propose specific power-saving measures. For example, the AI ​​analysis module outputs "{"pattern":"high_usage","suggestion":"switch to LED lights"}", which is received by the server.

[0635] Step 5:

[0636] User consults about power saving measures

[0637] Users access the system and discuss energy-saving measures through a chat interface. For example, they input a request such as "I want to reduce power consumption after 6 p.m." The output is a response from the server based on that request.

[0638] Step 6:

[0639] The server interacts with the user using generative AI

[0640] The server passes the user's request to a generative AI model, which then interactively proposes specific energy-saving measures. The input is the user's request and the analysis results from the AI ​​analysis module, and the output is a specific energy-saving proposal. For example, it might suggest, "Since power consumption peaks between 7:00 and 9:00 p.m., replace the lighting with LEDs."

[0641] Step 7:

[0642] The server uses an emotion engine to recognize the user's emotions.

[0643] The server analyzes the user's voice and text data using an emotion engine. The input is the user's dialogue data, and the output is the emotion analysis results. For example, analyzing voice data yields results such as "Stress: 70%" and "Satisfaction: 20%."

[0644] Step 8:

[0645] The server uses generative AI to make suggestions based on emotions.

[0646] Based on the emotion analysis results, the server provides the generative AI model with suggestions that correspond to the user's emotions. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes the user's emotions into consideration. For example, if the user is feeling stressed, the server will make a suggestion such as "As a specific and easy-to-implement energy-saving measure, we suggest closing the doors at night to improve heating and cooling efficiency."

[0647] Step 9:

[0648] A user requests a remote operation

[0649] The user requests the system to operate the power / breaker for a specific room or device, for example, by inputting "Turn off the power to the conference room."

[0650] Step 10:

[0651] The server sends remote operation instructions to the smart meter

[0652] The server analyzes the user's request and sends remote operation instructions to the corresponding smart meter. The input is the user's request, and the output is the specific operation instruction to the smart meter. For example, send a "POST / api / v1 / control-power" request and pass the data "room: conference_room, action: off".

[0653] Step 11:

[0654] The terminal (smart meter) performs remote operations

[0655] The terminal (smart meter) turns off the power in a specific room based on instructions sent from the server. The input is the operation instruction from the server, and the output is the result of the operation. Specifically, it executes the command "to turn off the power in the conference room" using a relay operation or other means.

[0656] These are the processing steps of this system. This process makes it possible to efficiently manage the user's power consumption and provide optimal power saving measures.

[0657] (Application example 2)

[0658] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0659] In addition to optimizing power consumption and implementing effective energy-saving measures in industrial facilities, it has been difficult to manage energy consumption while taking into account the emotions of workers. Furthermore, there is a lack of systems that can collect real-time power consumption data from each facility and make effective energy-saving proposals.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with the user and proposing power-saving measures, means for analyzing emotion data and making suggestions according to the user's emotions, means for collecting power consumption data of industrial equipment in real time, and means for remotely operating the power supplies or breakers of specific work areas or equipment. This enables comprehensive energy management and effective power-saving measures tailored to the user.

[0661] "Power consumption data" refers to detailed data such as the amount of power used by each power device or facility, the duration of use, and peak consumption.

[0662] "Analysis means" refers to algorithms or software used to process collected power consumption data and identify power usage patterns and anomalies.

[0663] "Generative algorithms" are artificial intelligence technologies that interact with users based on collected and analyzed data and suggest specific energy-saving measures.

[0664] "Emotion data" is emotional data analyzed based on the user's voice and text data, and is information indicating whether the user is feeling stressed or satisfied.

[0665] "Emotion analysis means" is a technology for analyzing emotion data and recognizing the user's emotional state.

[0666] The "real-time collection means" is a function that collects power consumption data from each power device or facility in real time.

[0667] "Remote operation means" refers to technology for remotely controlling the power supply or breaker of a specific work area or equipment.

[0668] System Configuration

[0669] The present invention is embodied as a power management system within an industrial facility. The system includes the following main components:

[0670] 1. Server

[0671] Data collection: The server collects electricity consumption data in real time from the smart meters of each industrial facility via API.

[0672] Data storage: Collected data is stored in a cloud database (e.g., AWS RDS).

[0673] Data analysis: The stored data is passed to an AI analysis module (e.g., TensorFlow) for analysis to identify power usage patterns and anomalies.

[0674] Generative algorithm: Using generative AI (e.g., OpenAI GPT-4), we interact with users and suggest specific energy-saving measures.

[0675] Emotion analysis: Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions are analyzed from the user's voice and text data, and suggestions are made based on the user's emotions.

[0676] 2. Terminal

[0677] Real-time power collection: Each smart meter collects the power consumption data of the equipment in real time and transmits it to the server.

[0678] Remote Operation: Remotely operate power or breakers for specific work areas or equipment.

[0679] 3. Users

[0680] Dialogue and requests: Users access the system via smartphones or robots to discuss energy-saving measures. In response to the user's requests, the server uses generative AI to propose specific measures.

[0681] Emotion data provision: The voice and text data collected during the conversation is analyzed by the emotion engine to recognize the user's emotional state.

[0682] Program processing explanation

[0683] Below is a natural language description of how the components of the system work together:

[0684] 1. Data Collection and Storage

[0685] The server collects real-time electricity consumption data from each smart meter via API and stores it in a cloud database, including the amount of electricity consumed, the duration of use, and peak consumption.

[0686] 2. Data Analysis

[0687] The server periodically passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[0688] 3. Dialogue with users and proposals for energy-saving measures

[0689] When a user consults the system about energy-saving measures, the generative AI will suggest specific energy-saving measures in an interactive format. For example, if a user requests, "I want to reduce energy consumption after 6 p.m.", the generative AI will suggest, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs."

[0690] 4. Emotion analysis

[0691] The emotion engine analyzes the user's voice and text data to determine whether they are feeling stressed or satisfied. Based on the results of the emotion engine, the generative AI makes suggestions based on the user's emotions.

[0692] 5. Remote Operation

[0693] When a user requests a power control for a specific work area or device, the server analyzes the request and sends a remote control instruction to the corresponding smart meter, which then turns off the power accordingly.

[0694] Examples of concrete examples and prompts

[0695] For example, the following prompt sentences are used:

[0696] "What's the best way to reduce energy consumption after 6pm?"

[0697] Please tell me your current electricity usage.

[0698] "Please tell me about the energy savings that can be achieved by replacing lighting with LEDs."

[0699] "Please suggest some simple energy-saving measures for stressed workers."

[0700] "Please turn off the power to the conference room remotely."

[0701] In this way, the system achieves comprehensive energy management and effective power saving measures tailored to the user.

[0702] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0703] Step 1:

[0704] The server collects real-time electricity consumption data from the smart meters of each industrial facility. In this step, electricity consumption data (power consumption, usage time, peak consumption, etc.) is obtained from the smart meters via API and stored in a cloud database. The input is the electricity consumption data from each smart meter, and the output is the data stored in the cloud database.

[0705] Step 2:

[0706] The server passes the collected data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies. In this step, data is read from the cloud database and analyzed by the AI ​​analysis module (e.g., TensorFlow). The input is the stored power consumption data, and the output is the analysis results (identification of power usage patterns and anomalies).

[0707] Step 3:

[0708] A user consults the system about energy-saving measures. The user inputs a request to the system via a smartphone or robot. For example, the user inputs a prompt such as, "What is the best way to reduce energy consumption after 6 p.m." The input is the request from the user, and the output is the request data to the server.

[0709] Step 4:

[0710] The server uses generative AI (e.g., OpenAI GPT-4) to interactively propose specific power-saving measures. In this step, optimal power-saving measures are generated based on the user's request and the results of the AI ​​analysis module. The input is the user's request and the analysis results, and the output is a proposed power-saving measure.

[0711] Step 5:

[0712] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. In this step, the user's dialogue data is passed to the emotion engine for analysis. The input is the user's voice and text data, and the output is the emotion analysis result.

[0713] Step 6:

[0714] Based on the results of the emotion analysis, the server passes suggestions based on the user's emotions to the generative AI and engages in a dialogue. In this step, the results of the emotion analysis are taken into account to generate suggestions suitable for the user. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes emotions into consideration.

[0715] Step 7:

[0716] A user requests power control for a specific work area or device. The user enters a command such as "Please turn off the power to the conference room remotely." The input is the user's request, and the output is the operation instruction data sent to the server.

[0717] Step 8:

[0718] The server receives the remote operation instruction and sends it to the corresponding smart meter. In this step, the server analyzes the operation instruction and sends a power operation command to the specific smart meter. The input is the operation instruction data, and the output is a control signal to the smart meter.

[0719] Step 9:

[0720] The smart meter of the terminal performs the specified operation and turns off the power of the device. In this step, the smart meter controls the power of the device based on the instruction received. The input is the control signal, and the output is the state in which the device is powered off.

[0721] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0722] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0723] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0724] [Third embodiment]

[0725] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0726] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0727] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0728] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0729] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0730] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0731] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0732] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0733] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0734] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0735] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0736] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0737] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[0738] Data collection

[0739] The server collects real-time electricity consumption data from smart meters in each building and on each floor, including the amount of power consumed (kWh) by each area and device, the duration of use, and peak consumption.

[0740] Data storage and analysis

[0741] The server stores the collected data in a database, which is then used for further analysis. The server then invokes an AI analysis module to identify power usage patterns and abnormal usage, enabling more efficient energy consumption and anomaly detection.

[0742] Dialogue with users and recommendations

[0743] The user accesses the system and asks for advice on power-saving measures. The server uses generative AI to interact with the user and proposes power-saving measures based on usage. The server compares past data with the current situation and generates optimal recommendations.

[0744] For example, if a user inputs, "I want to reduce electricity consumption after 6 p.m.", the generative AI will suggest, "Since electricity consumption peaks between 7 p.m. and 9 p.m., replacing lighting with LEDs would be highly effective."

[0745] Remote power / breaker operation

[0746] When a user instructs the power supply to be turned off in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which then turns off the power to the specified room or equipment.

[0747] For example, if a user inputs a command to the system to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in that room.

[0748] Specific examples of programs

[0749] Data collection flow

[0750] The server collects real-time electricity consumption data from each smart meter via an API.

[0751] The server stores the collected data in a database.

[0752] Data analysis flow

[0753] The server passes the stored data to an AI analysis module to detect power usage patterns and anomalies.

[0754] The server prepares data for generating proposals for power saving measures based on the analysis results.

[0755] User interaction and proposal flow

[0756] The user inputs their energy saving advice into the system.

[0757] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[0758] Remote operation flow

[0759] A user requests power / breaker operation for a specific room or device.

[0760] The server analyzes the instructions and instructs the corresponding smart meter to perform remote operation.

[0761] The terminal (smart meter) performs the specified operation.

[0762] The above is an embodiment of the present invention, which provides comprehensive power management and effective power saving measures to optimize energy efficiency.

[0763] The processing flow will be explained below.

[0764] Step 1:

[0765] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[0766] Step 2:

[0767] The server stores the collected data in a database, where the data is structured by floor and device, and stored safely and efficiently.

[0768] Step 3:

[0769] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[0770] Step 4:

[0771] The server calls the AI ​​based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generates the most effective energy-saving method for the user based on past data and current usage.

[0772] Step 5:

[0773] A user accesses the system and inputs a request for power saving measures, for example, inputting a specific request such as "I want to reduce power consumption after 6 PM."

[0774] Step 6:

[0775] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[0776] Step 7:

[0777] If the user accepts the suggestion and instructs the power to be turned off in a specific room, the user inputs a remote command to the system, such as "Turn off the power in the conference room."

[0778] Step 8:

[0779] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meters. In this step, the server sends control signals to perform specific operations to turn on or off the power to the specified rooms or devices.

[0780] Step 9:

[0781] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[0782] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and achieving efficient energy management.

[0783] Example 1

[0784] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0785] Conventional power management systems only collect power consumption data, making it difficult to pinpoint abnormal power usage or specific power-saving measures. Furthermore, the ability to remotely control power was limited, preventing flexible power management. Furthermore, it was difficult to provide appropriate recommendations based on user interaction. This led to problems such as inappropriate suggestions for efficient power usage and power-saving measures.

[0786] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0787] In this invention, the server includes a means for collecting power consumption data, a means for analyzing the collected power consumption data, a means including a generation algorithm for interacting with a user and proposing power-saving measures, a means for remotely operating a power supply or a breaker, a means for detecting anomalies in the power consumption data, and a means for pre-processing the power consumption data. This enables comprehensive power collection, analysis, interaction, and remote operation, enabling efficient use of power and the proposal of appropriate power-saving measures.

[0788] "Power consumption data" includes various information related to the amount of power, usage time, and peak consumption.

[0789] "Means for collection" refers to devices or software that communicate with smart meters and various sensors to obtain electricity consumption data.

[0790] A "database" is a collection of information that stores and manages collected electricity consumption data and can be used for analysis.

[0791] "Means for analyzing" refers to devices or software for analyzing power consumption data and detecting usage patterns or anomalies.

[0792] A "generative algorithm" is a program that interacts with users based on their input and suggests appropriate energy-saving measures.

[0793] "Remote operation means" means a device or software for operating a power supply or breaker from a remote location.

[0794] An "anomaly detection means" is a device or software that detects unusual patterns or unauthorized usage in power consumption data.

[0795] "Preprocessing means" means equipment or software that appropriately formats and cleans collected electricity consumption data before analysis and storage.

[0796] "Recommendations" are suggestions for energy-saving measures provided based on the user's power usage patterns.

[0797] "Generative AI" is an artificial intelligence technology that creates appropriate suggestions based on dialogue with users.

[0798] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[0799] Hardware and software used

[0800] Server: Oversees the collection, analysis, storage, remote operation, and collaboration with generative AI of power consumption data. Specifically, it uses general server hardware and the following software:

[0801] Database management system: MySQL, PostgreSQL, etc.

[0802] AI analysis module: Python scikit-learn library.

[0803] Generative AI models: such as OpenAI's GPT-3.

[0804] Terminal (smart meter): Installed in each building and on each floor, it collects electricity consumption data and sends it to a server.

[0805] Data collection

[0806] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, the smart meters send the data to the server via an API. This data includes the power consumption (kWh) of each area and device, the time of use, and peak consumption.

[0807] Data storage and preprocessing

[0808] The server stores the collected power consumption data in a database. Before storing the data, a Python data processing library (e.g., pandas) is used to preprocess the data and filter incomplete data and outliers.

[0809] Data analysis

[0810] The server passes the stored data to an AI analysis module (Python's scikit-learn library) to identify power usage patterns and anomalies, enabling more efficient energy consumption and anomaly detection.

[0811] User interaction

[0812] When a user accesses the system and asks for advice on energy-saving measures, the server uses generative AI (e.g., OpenAI's GPT-3) to converse with the user. For example, if the user inputs, "I want to reduce power consumption after 6 p.m.," the generative AI will suggest, "Power consumption peaks between 7 p.m. and 9 p.m., so replacing the lighting with LEDs would be highly effective."

[0813] Remote Operation

[0814] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter. The terminal (smart meter) follows the instruction and turns off the power in the specified room or equipment. For example, if a user enters the command "Turn off the power in the conference room," the server analyzes the instruction and the smart meter turns off the power in the conference room.

[0815] Examples of concrete examples and prompts

[0816] For example, if a user inputs "I want to reduce power consumption after 6 PM," the generative AI will suggest, "Power consumption peaks between 7 PM and 9 PM, so replacing the lighting with LEDs would be highly effective." In response to the command "Turn off the power in the conference room," the server will send an instruction to the corresponding smart meter to turn off the power in the conference room.

[0817] This will enable comprehensive power collection, analysis, interaction, and remote operation, enabling efficient power use and the proposal of appropriate power-saving measures.

[0818] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0819] Power management system program processing flow

[0820] Step 1: Data collection

[0821] The server collects real-time electricity consumption data from smart meters in each building and floor. The input is data such as the amount of electricity measured by the smart meters, usage time, and peak consumption. The output is the collected electricity consumption data.

[0822] Specific behavior:

[0823] The server sends API requests to each smart meter at regular intervals.

[0824] The server receives the power consumption data from the smart meter and temporarily stores it in memory.

[0825] Step 2: Data storage and preprocessing

[0826] The server preprocesses the collected power consumption data before storing it in the database. The input is the power consumption data collected in step 1. The output is the preprocessed data with outliers filtered out.

[0827] Specific behavior:

[0828] The server uses Python data processing libraries (e.g., pandas) to shape the data and filter out incomplete data and outliers.

[0829] The server generates SQL statements and stores the pre-processed data in a database (e.g. MySQL or PostgreSQL).

[0830] Step 3: Data analysis

[0831] The server passes the stored data to an AI analysis module to identify power usage patterns and anomalies. The input is pre-processed power consumption data stored in a database. The output is the analysis results.

[0832] Specific behavior:

[0833] The server executes a query to retrieve the required data from the database.

[0834] The server passes the acquired data to an AI analysis module using Python's scikit-learn library to detect power usage patterns and anomalies.

[0835] The server stores the analysis results in the database again.

[0836] Step 4: User interaction

[0837] When a user accesses the system and asks for advice on power-saving measures, the server uses generative AI to interact with the user. The input is the prompt the user enters into the system. The output is a power-saving measure proposal generated by the AI.

[0838] Specific behavior:

[0839] The user inputs a prompt statement into the system (e.g., "I want to reduce power consumption after 6 p.m.").

[0840] The server sends a prompt to the generative AI (e.g., OpenAI's GPT-3) and receives a response from the AI.

[0841] The server returns AI-generated suggestions to the user (e.g., "Electricity consumption peaks between 7:00 and 9:00 p.m., so replacing your lighting with LEDs would be highly effective").

[0842] Step 5: Remote Operation

[0843] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation instruction to the corresponding smart meter. The input is the remote operation command that the user inputs to the system. The output is that the power of the specified equipment is turned off.

[0844] Specific behavior:

[0845] The user enters the command "Turn off the power in the conference room."

[0846] The server analyzes the command and sends a request to the corresponding smart meter API.

[0847] The terminal (smart meter) receives the request and turns off the power in the designated conference room.

[0848] The above are the program processing steps and their specific operations in the power management system. This enables comprehensive power collection, analysis, interaction, and remote operation, making it possible to use power efficiently and propose appropriate power-saving measures.

[0849] (Application example 1)

[0850] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0851] There is a demand for more efficient power consumption and energy-saving measures in factories, but conventional systems do not adequately monitor and analyze power consumption in real time, and they also do not adequately propose effective power-saving measures through dialogue with users.To solve this problem, a system is needed that can collect and analyze power consumption data in detail, operate devices remotely, and propose optimal power-saving measures to users.

[0852] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0853] In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with a user and proposing power-saving measures, means for remotely operating a power supply or breaker, means for monitoring the power consumption of work equipment in a factory and collecting data in real time, means for saving the data collected in real time in the server, means for analyzing the saved data with an AI analysis module, means for generating and proposing optimal power-saving measures in response to user input using generative AI, and means for enabling remote power control of specific areas or devices. This makes it possible to monitor and optimize power consumption in a factory, and to propose and remotely operate efficient power-saving measures.

[0854] "Power consumption data" is numerical information about the amount of power consumed in a specific area or device, usage time, peak consumption, etc.

[0855] "Collection means" refers to a device or software that has the function of acquiring electricity consumption data from each smart meter or measuring device.

[0856] The "analyzing means" is a device or software that has the function of analyzing collected power consumption data and detecting usage patterns and anomalies.

[0857] The "means for interacting with the user" refers to a device or software that has the function of proposing appropriate power saving measures using a generative algorithm in response to user input.

[0858] A "generative algorithm" is an algorithm that includes calculation methods and procedures for providing optimal recommendations and advice to users based on collected and analyzed data.

[0859] "Means for remotely operating power or breakers" refers to devices or software that have the function of turning on and off the power or breakers of specific equipment or areas from a remote location.

[0860] The "monitoring means" refers to a device or software that has the function of monitoring the power consumption of work equipment in a factory and acquiring data in real time.

[0861] A "server" is a computer system capable of collecting, storing, analyzing, and interacting with users.

[0862] An "AI analysis module" is a software module that uses artificial intelligence to analyze acquired data and detect usage patterns and anomalies.

[0863] "Means for enabling remote power control of a device" refers to a device or software that has the function of turning the power of a specific device on or off from a remote location.

[0864] The "means for generating and proposing optimal energy-saving measures" refers to a device or software that has the function of proposing specific action plans to users for reducing energy consumption based on collected and analyzed data.

[0865] This invention relates to a system for optimizing power consumption in factories and proposing efficient power-saving measures. This system has the function of collecting and analyzing detailed power consumption data and remotely operating power supplies and breakers.

[0866] Data collection

[0867] The server collects real-time power consumption data from smart meters and various measuring devices installed within the factory. This data includes the power consumption of each work area and device, usage time, and peak consumption. This allows for an accurate understanding of the energy consumption situation throughout the factory.

[0868] Data storage and analysis

[0869] The server securely stores the collected data in a database for later detailed analysis. The stored data is then analyzed by an AI analysis module to identify power usage patterns and anomalous usage. The analysis results can be used to improve energy efficiency and detect anomalies.

[0870] Dialogue with users and recommendations

[0871] When a user accesses the system to inquire about power-saving measures, the server uses generative AI to converse with the user and propose power-saving measures based on usage. For example, if a user inputs, "I want to reduce power consumption during the day," the generative AI will generate specific suggestions based on collected data and analysis results, such as, "Consumption is high during certain times of the day, so shift the operating hours of some devices."

[0872] Remote power / breaker operation

[0873] When a user instructs a specific room or device to be turned off, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which results in the power being turned off for the designated work area or equipment. For example, if a user instructs the server to "turn off the power in the conference room," the server analyzes the instruction and the corresponding device turns off the power in the conference room.

[0874] Hardware and software used

[0875] Hardware: Smart meters, servers, database servers, and smartphones used by users.

[0876] Software: Python API, database management system, AI analysis module, generative AI.

[0877] For example, if a factory manager inputs "I want to reduce electricity consumption during the day," the system will use past data to suggest "Since usage is high during certain times of the day, we should spread out the use of heavy machinery." A specific example of a prompt for the generative AI model is as follows:

[0878] "I want to reduce electricity consumption during the day."

[0879] In this way, the server can streamline power management within the factory and optimize overall energy consumption.

[0880] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0881] Step 1:

[0882] The server collects power consumption data in real time from smart meters and various measuring devices installed within the factory. The input is data from the smart meters (power consumption, usage time, peak consumption, etc.), and the output is the collected data. This allows the server to accurately grasp the energy consumption status of the entire factory.

[0883] Step 2:

[0884] The server stores the collected power consumption data in a database. The input is the data collected in step 1, and the output is the stored data. This storage process lays the foundation for further analysis later.

[0885] Step 3:

[0886] The server passes the stored data to an AI analysis module, which analyzes power usage patterns and abnormal usage. The input is the data stored in the database, and the output is the analysis results. This analysis makes it possible to improve energy efficiency and detect abnormalities.

[0887] Step 4:

[0888] The user accesses the system and asks for advice on power-saving measures. The input is the user's request (prompt), such as "I want to reduce power consumption during the day." The server uses generative AI to advance the dialogue with the user.

[0889] Step 5:

[0890] The server uses generative AI to propose optimal power-saving measures based on the analysis results of the AI ​​analysis module and user requests. The inputs are the analysis results and user requests, and the output is the generated power-saving measure proposal. For example, a proposal may be generated such as, "Consumption is high during certain time periods, so shift the operating hours of some devices."

[0891] Step 6:

[0892] A user remotely commands a specific room or device to be turned off. The input is the user's specific command (e.g., "Turn off the power in the conference room"), and the server receives the command.

[0893] Step 7:

[0894] The server analyzes the user's instructions and sends remote operation instructions to the corresponding smart meter. The input is the user's instructions, and the output is the specific remote operation instructions. This will turn off the power to the designated work area or equipment.

[0895] In this way, the server, terminals, and users work together to make power management within the factory more efficient and optimize overall energy consumption.

[0896] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0897] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with the user, and combines an emotion engine to take optimal action according to the user's emotions. The following describes in detail an embodiment of the present invention.

[0898] Data collection

[0899] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it obtains data such as power consumption (kWh), usage time, and peak consumption through the API of each smart meter.

[0900] Data storage and analysis

[0901] The server stores the collected data in a database, where data collected from each floor and device is structured, securely, and efficiently stored. The stored data is then passed to an AI analysis module, where it is analyzed to identify power usage patterns and anomalies, enabling efficient energy management.

[0902] Dialogue with users and recommendations

[0903] The user accesses the system and asks for advice on energy-saving measures. Specifically, the user inputs a request such as "I want to reduce power consumption after 6 PM." The server then uses generative AI to suggest specific energy-saving measures in a dialogue with the user. For example, the server might suggest, "Since power consumption peaks between 7 PM and 9 PM, we should replace the lighting with LEDs."

[0904] Emotion engine integration

[0905] The server calls the emotion engine during a dialogue with the user and recognizes their emotions by analyzing their voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied, and passes corresponding suggestions to the generative AI. For example, if the user is feeling stressed, the emotion engine will recognize this and suggest simple and easy-to-implement energy-saving measures to the generative AI.

[0906] Remote power / breaker operation

[0907] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the smart meter. For example, if a user inputs a command to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in the conference room based on the instruction.

[0908] Specific examples of programs

[0909] Data collection flow

[0910] The server collects real-time electricity consumption data from each smart meter via an API.

[0911] The server stores the collected data in a database.

[0912] Data analysis flow

[0913] The server passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[0914] The server prepares data to propose energy-saving measures based on the analysis results.

[0915] User interaction and proposal flow

[0916] The user inputs a request for advice on power saving measures.

[0917] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[0918] Flow of emotion engine integration

[0919] The server uses an emotion engine during dialogue with the user to analyze voice and text data and recognize the user's emotions.

[0920] Based on the results of the emotion engine, the server has the generative AI make suggestions based on the user's emotions.

[0921] Remote operation flow

[0922] A user requests power / breaker operation for a specific room or device.

[0923] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meter.

[0924] The terminal (smart meter) performs the specified operation.

[0925] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[0929] Step 2:

[0930] The server stores the collected power consumption data in a database, which stores the information collected from each floor and device in a structured manner.

[0931] Step 3:

[0932] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[0933] Step 4:

[0934] The server calls the AI ​​generator based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generator generates effective energy-saving methods by taking into account past data and current usage conditions.

[0935] Step 5:

[0936] A user accesses the system and inputs a request for power saving measures. For example, the user inputs a request such as "I want to reduce power consumption after 6 PM."

[0937] Step 6:

[0938] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[0939] Step 7:

[0940] The server activates an emotion engine during a dialogue with the user and recognizes emotions by analyzing the voice and text data entered by the user. The emotion engine determines the user's stress and satisfaction levels and sends corresponding suggestions to the generative AI.

[0941] Step 8:

[0942] When a user issues a command to turn off the power in a specific room, the server analyzes the command and sends a remote operation command to the smart meter. For example, a user might enter a command such as "Turn off the power in the conference room."

[0943] Step 9:

[0944] The server sends specific operational instructions to the smart meter to power on or off designated rooms or devices.

[0945] Step 10:

[0946] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[0947] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and providing effective power saving measures according to the user's emotions.

[0948] Example 2

[0949] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0950] In modern society, efficient management of power consumption and energy-saving measures are important issues. Conventional power management systems can collect and analyze data on power consumption, but in many cases, it is difficult to provide users with appropriate energy-saving measures. In addition, they are unable to respond to users' emotions, which means they are unable to make suggestions that take into account users' satisfaction and willingness to implement them.

[0951] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0952] In this invention, the server includes means for collecting power consumption data, means for saving the collected power consumption data, means for analyzing the saved power consumption data, means including a generative algorithm for interacting with the user and proposing power saving measures, means including an emotion engine for analyzing the user's emotions, and means for remotely operating the power supply or breaker. This not only enables efficient power saving measures to be proposed based on the collected power consumption data, but also enables flexible responses according to the user's emotions.

[0953] "Power consumption data" refers to information such as the amount of power consumed, usage time, and peak consumption at each measurement point within a building or facility.

[0954] The "means of collection" refers to interface devices such as APIs and sensors for obtaining electricity consumption data from each smart meter.

[0955] The "storage means" is a database management system for structuring, efficiently and securely storing collected electricity consumption data.

[0956] The "analysis means" is an AI analysis module that uses stored power consumption data to detect power usage patterns and anomalies and support efficient energy management.

[0957] A "generative algorithm" is an artificial intelligence technology that proposes optimal energy-saving measures based on data collected through dialogue with users.

[0958] The "emotion engine" is a technology that analyzes the user's voice and text data to recognize their emotions. It can determine whether the user is feeling stressed or satisfied.

[0959] "Means for remote operation" refers to a mechanism for sending remote operation instructions to devices such as smart meters based on user instructions, and actually operating power supplies and breakers.

[0960] "User" refers to an individual or corporation that uses the system to manage power consumption and take measures to save power.

[0961] This invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power-saving measures through dialogue with the user, and combines an emotion engine to provide optimal responses according to the user's emotions.

[0962] Data collection

[0963] The server collects real-time power consumption data from smart meters in each building and floor via API. This collected data includes power consumption (kWh), usage time, peak consumption, etc. For example, when the server sends a request such as "GET / api / v1 / power-usage?floor=3", the smart meter returns JSON-formatted data such as "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}".

[0964] Data storage and analysis

[0965] The server stores the collected power consumption data in a database. This database uses an RDBMS such as MySQL. The stored data is passed to an AI analysis module, which uses Python's TensorFlow library to perform analysis to identify power usage patterns and anomalies. For example, the server executes the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'", converts the obtained data into JSON, and sends it to the AI ​​analysis module.

[0966] Dialogue with users and recommendations

[0967] Users access the system and use a chat interface to discuss energy-saving measures. For example, they input a request such as, "I want to reduce power consumption after 6 p.m." The server then uses a generative AI model to suggest specific energy-saving measures through a dialogue with the user. Specifically, the server suggests, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs." An example of a prompt statement is, "I want to reduce power consumption after 6 p.m."

[0968] Emotion engine integration

[0969] While interacting with the user, the server calls the emotion engine and analyzes the user's emotions from voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied. For example, voice data is sent to the emotion analysis API and results such as "Stress: 70%" and "Satisfaction: 20%" are received. Based on this, the generative AI model makes suggestions that take emotions into consideration. As a specific example, if the user is feeling stressed, it suggests "securely closing doors at night to increase heating and cooling efficiency" as a simple and easy-to-implement energy-saving measure.

[0970] Remote power / breaker operation

[0971] When a user requests a power control for a specific room, the server analyzes the request and sends a remote operation instruction to the smart meter. For example, if a user inputs "Turn off the power in the conference room," the server sends a "POST / api / v1 / control-power" request to the smart meter API, passing the data "room: conference_room, action: off." The device (smart meter) receives this instruction and turns off the power to the conference room.

[0972] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[0973] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0974] Step 1:

[0975] The server collects data from the smart meters.

[0976] The server periodically sends API requests to the smart meters in each building and floor. Specifically, it sends the request "GET / api / v1 / power-usage." This input returns power consumption data such as power consumption, usage time, and peak consumption from the smart meter. For example, requesting "GET / api / v1 / power-usage?floor=3" will return the output "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}."

[0977] Step 2:

[0978] The server stores the collected data in a database

[0979] The server stores the acquired power consumption data in a MySQL database. The data input is the JSON format data returned from the smart meter. The data is structured and stored using the SQL query "INSERT INTO power_usage (timestamp, kWh, peak_usage, floor) VALUES ('2023-10-04T10:00:00Z', 50, 15, 3)".

[0980] Step 3:

[0981] The server passes the data to the AI ​​analysis module

[0982] The server retrieves power consumption data for a specific period from the database and sends it to the AI ​​analysis module. The input is the result of an SQL query from the database, and the output is formatted JSON data. Specifically, the data is retrieved using the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'".

[0983] Step 4:

[0984] The server receives the analysis results from the AI ​​analysis module

[0985] The AI ​​analysis module uses the input data to identify power usage patterns and anomalies. Based on this, it generates the data necessary to propose specific power-saving measures. For example, the AI ​​analysis module outputs "{"pattern":"high_usage","suggestion":"switch to LED lights"}", which is received by the server.

[0986] Step 5:

[0987] User consults about power saving measures

[0988] Users access the system and discuss energy-saving measures through a chat interface. For example, they input a request such as "I want to reduce power consumption after 6 p.m." The output is a response from the server based on that request.

[0989] Step 6:

[0990] The server interacts with the user using generative AI

[0991] The server passes the user's request to a generative AI model, which then interactively proposes specific energy-saving measures. The input is the user's request and the analysis results from the AI ​​analysis module, and the output is a specific energy-saving proposal. For example, it might suggest, "Since power consumption peaks between 7:00 and 9:00 p.m., replace the lighting with LEDs."

[0992] Step 7:

[0993] The server uses an emotion engine to recognize the user's emotions.

[0994] The server analyzes the user's voice and text data using an emotion engine. The input is the user's dialogue data, and the output is the emotion analysis results. For example, analyzing voice data yields results such as "Stress: 70%" and "Satisfaction: 20%."

[0995] Step 8:

[0996] The server uses generative AI to make suggestions based on emotions.

[0997] Based on the emotion analysis results, the server provides the generative AI model with suggestions that correspond to the user's emotions. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes the user's emotions into consideration. For example, if the user is feeling stressed, the server will make a suggestion such as "As a specific and easy-to-implement energy-saving measure, we suggest closing the doors at night to improve heating and cooling efficiency."

[0998] Step 9:

[0999] A user requests a remote operation

[1000] The user requests the system to operate the power / breaker for a specific room or device, for example, by inputting "Turn off the power to the conference room."

[1001] Step 10:

[1002] The server sends remote operation instructions to the smart meter

[1003] The server analyzes the user's request and sends remote operation instructions to the corresponding smart meter. The input is the user's request, and the output is the specific operation instruction to the smart meter. For example, send a "POST / api / v1 / control-power" request and pass the data "room: conference_room, action: off".

[1004] Step 11:

[1005] The terminal (smart meter) performs remote operations

[1006] The terminal (smart meter) turns off the power in a specific room based on instructions sent from the server. The input is the operation instruction from the server, and the output is the result of the operation. Specifically, it executes the command "to turn off the power in the conference room" using a relay operation or other means.

[1007] These are the processing steps of this system. This process makes it possible to efficiently manage the user's power consumption and provide optimal power saving measures.

[1008] (Application example 2)

[1009] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1010] In addition to optimizing power consumption and implementing effective energy-saving measures in industrial facilities, it has been difficult to manage energy consumption while taking into account the emotions of workers. Furthermore, there is a lack of systems that can collect real-time power consumption data from each facility and make effective energy-saving proposals.

[1011] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with the user and proposing power-saving measures, means for analyzing emotion data and making suggestions according to the user's emotions, means for collecting power consumption data of industrial equipment in real time, and means for remotely operating the power supplies or breakers of specific work areas or equipment. This enables comprehensive energy management and effective power-saving measures tailored to the user.

[1012] "Power consumption data" refers to detailed data such as the amount of power used by each power device or facility, the duration of use, and peak consumption.

[1013] "Analysis means" refers to algorithms or software used to process collected power consumption data and identify power usage patterns and anomalies.

[1014] "Generative algorithms" are artificial intelligence technologies that interact with users based on collected and analyzed data and suggest specific energy-saving measures.

[1015] "Emotion data" is emotional data analyzed based on the user's voice and text data, and is information indicating whether the user is feeling stressed or satisfied.

[1016] "Emotion analysis means" is a technology for analyzing emotion data and recognizing the user's emotional state.

[1017] The "real-time collection means" is a function that collects power consumption data from each power device or facility in real time.

[1018] "Remote operation means" refers to technology for remotely controlling the power supply or breaker of a specific work area or equipment.

[1019] System Configuration

[1020] The present invention is embodied as a power management system within an industrial facility. The system includes the following main components:

[1021] 1. Server

[1022] Data collection: The server collects electricity consumption data in real time from the smart meters of each industrial facility via API.

[1023] Data storage: Collected data is stored in a cloud database (e.g., AWS RDS).

[1024] Data analysis: The stored data is passed to an AI analysis module (e.g., TensorFlow) for analysis to identify power usage patterns and anomalies.

[1025] Generative algorithm: Using generative AI (e.g., OpenAI GPT-4), we interact with users and suggest specific energy-saving measures.

[1026] Emotion analysis: Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions are analyzed from the user's voice and text data, and suggestions are made based on the user's emotions.

[1027] 2. Terminal

[1028] Real-time power collection: Each smart meter collects the power consumption data of the equipment in real time and transmits it to the server.

[1029] Remote Operation: Remotely operate power or breakers for specific work areas or equipment.

[1030] 3. Users

[1031] Dialogue and requests: Users access the system via smartphones or robots to discuss energy-saving measures. In response to the user's requests, the server uses generative AI to propose specific measures.

[1032] Emotion data provision: The voice and text data collected during the conversation is analyzed by the emotion engine to recognize the user's emotional state.

[1033] Program processing explanation

[1034] Below is a natural language description of how the components of the system work together:

[1035] 1. Data Collection and Storage

[1036] The server collects real-time electricity consumption data from each smart meter via API and stores it in a cloud database, including the amount of electricity consumed, the duration of use, and peak consumption.

[1037] 2. Data Analysis

[1038] The server periodically passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[1039] 3. Dialogue with users and proposals for energy-saving measures

[1040] When a user consults the system about energy-saving measures, the generative AI will suggest specific energy-saving measures in an interactive format. For example, if a user requests, "I want to reduce energy consumption after 6 p.m.", the generative AI will suggest, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs."

[1041] 4. Emotion analysis

[1042] The emotion engine analyzes the user's voice and text data to determine whether they are feeling stressed or satisfied. Based on the results of the emotion engine, the generative AI makes suggestions based on the user's emotions.

[1043] 5. Remote Operation

[1044] When a user requests a power control for a specific work area or device, the server analyzes the request and sends a remote control instruction to the corresponding smart meter, which then turns off the power accordingly.

[1045] Examples of concrete examples and prompts

[1046] For example, the following prompt sentences are used:

[1047] "What's the best way to reduce energy consumption after 6pm?"

[1048] Please tell me your current electricity usage.

[1049] "Please tell me about the energy savings that can be achieved by replacing lighting with LEDs."

[1050] "Please suggest some simple energy-saving measures for stressed workers."

[1051] "Please turn off the power to the conference room remotely."

[1052] In this way, the system achieves comprehensive energy management and effective power saving measures tailored to the user.

[1053] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1054] Step 1:

[1055] The server collects real-time electricity consumption data from the smart meters of each industrial facility. In this step, electricity consumption data (power consumption, usage time, peak consumption, etc.) is obtained from the smart meters via API and stored in a cloud database. The input is the electricity consumption data from each smart meter, and the output is the data stored in the cloud database.

[1056] Step 2:

[1057] The server passes the collected data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies. In this step, data is read from the cloud database and analyzed by the AI ​​analysis module (e.g., TensorFlow). The input is the stored power consumption data, and the output is the analysis results (identification of power usage patterns and anomalies).

[1058] Step 3:

[1059] A user consults the system about energy-saving measures. The user inputs a request to the system via a smartphone or robot. For example, the user inputs a prompt such as, "What is the best way to reduce energy consumption after 6 p.m." The input is the request from the user, and the output is the request data to the server.

[1060] Step 4:

[1061] The server uses generative AI (e.g., OpenAI GPT-4) to interactively propose specific power-saving measures. In this step, optimal power-saving measures are generated based on the user's request and the results of the AI ​​analysis module. The input is the user's request and the analysis results, and the output is a proposed power-saving measure.

[1062] Step 5:

[1063] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. In this step, the user's dialogue data is passed to the emotion engine for analysis. The input is the user's voice and text data, and the output is the emotion analysis result.

[1064] Step 6:

[1065] Based on the results of the emotion analysis, the server passes suggestions based on the user's emotions to the generative AI and engages in a dialogue. In this step, the results of the emotion analysis are taken into account to generate suggestions suitable for the user. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes emotions into consideration.

[1066] Step 7:

[1067] A user requests power control for a specific work area or device. The user enters a command such as "Please turn off the power to the conference room remotely." The input is the user's request, and the output is the operation instruction data sent to the server.

[1068] Step 8:

[1069] The server receives the remote operation instruction and sends it to the corresponding smart meter. In this step, the server analyzes the operation instruction and sends a power operation command to the specific smart meter. The input is the operation instruction data, and the output is a control signal to the smart meter.

[1070] Step 9:

[1071] The smart meter of the terminal performs the specified operation and turns off the power of the device. In this step, the smart meter controls the power of the device based on the instruction received. The input is the control signal, and the output is the state in which the device is powered off.

[1072] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1073] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1074] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1075] [Fourth embodiment]

[1076] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1077] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1078] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1079] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1080] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1081] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1082] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1083] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1084] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1085] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1086] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1087] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1088] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1089] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[1090] Data collection

[1091] The server collects real-time electricity consumption data from smart meters in each building and on each floor, including the amount of power consumed (kWh) by each area and device, the duration of use, and peak consumption.

[1092] Data storage and analysis

[1093] The server stores the collected data in a database, which is then used for further analysis. The server then invokes an AI analysis module to identify power usage patterns and abnormal usage, enabling more efficient energy consumption and anomaly detection.

[1094] Dialogue with users and recommendations

[1095] The user accesses the system and asks for advice on power-saving measures. The server uses generative AI to interact with the user and proposes power-saving measures based on usage. The server compares past data with the current situation and generates optimal recommendations.

[1096] For example, if a user inputs, "I want to reduce electricity consumption after 6 p.m.", the generative AI will suggest, "Since electricity consumption peaks between 7 p.m. and 9 p.m., replacing lighting with LEDs would be highly effective."

[1097] Remote power / breaker operation

[1098] When a user instructs the power supply to be turned off in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which then turns off the power to the specified room or equipment.

[1099] For example, if a user inputs a command to the system to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in that room.

[1100] Specific examples of programs

[1101] Data collection flow

[1102] The server collects real-time electricity consumption data from each smart meter via an API.

[1103] The server stores the collected data in a database.

[1104] Data analysis flow

[1105] The server passes the stored data to an AI analysis module to detect power usage patterns and anomalies.

[1106] The server prepares data for generating proposals for power saving measures based on the analysis results.

[1107] User interaction and proposal flow

[1108] The user inputs their energy saving advice into the system.

[1109] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[1110] Remote operation flow

[1111] A user requests power / breaker operation for a specific room or device.

[1112] The server analyzes the instructions and instructs the corresponding smart meter to perform remote operation.

[1113] The terminal (smart meter) performs the specified operation.

[1114] The above is an embodiment of the present invention, which provides comprehensive power management and effective power saving measures to optimize energy efficiency.

[1115] The processing flow will be explained below.

[1116] Step 1:

[1117] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[1118] Step 2:

[1119] The server stores the collected data in a database, where the data is structured by floor and device, and stored safely and efficiently.

[1120] Step 3:

[1121] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[1122] Step 4:

[1123] The server calls the AI ​​based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generates the most effective energy-saving method for the user based on past data and current usage.

[1124] Step 5:

[1125] A user accesses the system and inputs a request for power saving measures, for example, inputting a specific request such as "I want to reduce power consumption after 6 PM."

[1126] Step 6:

[1127] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[1128] Step 7:

[1129] If the user accepts the suggestion and instructs the power to be turned off in a specific room, the user inputs a remote command to the system, such as "Turn off the power in the conference room."

[1130] Step 8:

[1131] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meters. In this step, the server sends control signals to perform specific operations to turn on or off the power to the specified rooms or devices.

[1132] Step 9:

[1133] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[1134] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and achieving efficient energy management.

[1135] Example 1

[1136] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1137] Conventional power management systems only collect power consumption data, making it difficult to pinpoint abnormal power usage or specific power-saving measures. Furthermore, the ability to remotely control power was limited, preventing flexible power management. Furthermore, it was difficult to provide appropriate recommendations based on user interaction. This led to problems such as inappropriate suggestions for efficient power usage and power-saving measures.

[1138] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1139] In this invention, the server includes a means for collecting power consumption data, a means for analyzing the collected power consumption data, a means including a generation algorithm for interacting with a user and proposing power-saving measures, a means for remotely operating a power supply or a breaker, a means for detecting anomalies in the power consumption data, and a means for pre-processing the power consumption data. This enables comprehensive power collection, analysis, interaction, and remote operation, enabling efficient use of power and the proposal of appropriate power-saving measures.

[1140] "Power consumption data" includes various information related to the amount of power, usage time, and peak consumption.

[1141] "Means for collection" refers to devices or software that communicate with smart meters and various sensors to obtain electricity consumption data.

[1142] A "database" is a collection of information that stores and manages collected electricity consumption data and can be used for analysis.

[1143] "Means for analyzing" refers to devices or software for analyzing power consumption data and detecting usage patterns or anomalies.

[1144] A "generative algorithm" is a program that interacts with users based on their input and suggests appropriate energy-saving measures.

[1145] "Remote operation means" means a device or software for operating a power supply or breaker from a remote location.

[1146] An "anomaly detection means" is a device or software that detects unusual patterns or unauthorized usage in power consumption data.

[1147] "Preprocessing means" means equipment or software that appropriately formats and cleans collected electricity consumption data before analysis and storage.

[1148] "Recommendations" are suggestions for energy-saving measures provided based on the user's power usage patterns.

[1149] "Generative AI" is an artificial intelligence technology that creates appropriate suggestions based on dialogue with users.

[1150] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with users, and remotely controls power supplies and breakers. The following describes in detail an embodiment of the present invention.

[1151] Hardware and software used

[1152] Server: Oversees the collection, analysis, storage, remote operation, and collaboration with generative AI of power consumption data. Specifically, it uses general server hardware and the following software:

[1153] Database management system: MySQL, PostgreSQL, etc.

[1154] AI analysis module: Python scikit-learn library.

[1155] Generative AI models: such as OpenAI's GPT-3.

[1156] Terminal (smart meter): Installed in each building and on each floor, it collects electricity consumption data and sends it to a server.

[1157] Data collection

[1158] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, the smart meters send the data to the server via an API. This data includes the power consumption (kWh) of each area and device, the time of use, and peak consumption.

[1159] Data storage and preprocessing

[1160] The server stores the collected power consumption data in a database. Before storing the data, a Python data processing library (e.g., pandas) is used to preprocess the data and filter incomplete data and outliers.

[1161] Data analysis

[1162] The server passes the stored data to an AI analysis module (Python's scikit-learn library) to identify power usage patterns and anomalies, enabling more efficient energy consumption and anomaly detection.

[1163] User interaction

[1164] When a user accesses the system and asks for advice on energy-saving measures, the server uses generative AI (e.g., OpenAI's GPT-3) to converse with the user. For example, if the user inputs, "I want to reduce power consumption after 6 p.m.," the generative AI will suggest, "Power consumption peaks between 7 p.m. and 9 p.m., so replacing the lighting with LEDs would be highly effective."

[1165] Remote Operation

[1166] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter. The terminal (smart meter) follows the instruction and turns off the power in the specified room or equipment. For example, if a user enters the command "Turn off the power in the conference room," the server analyzes the instruction and the smart meter turns off the power in the conference room.

[1167] Examples of concrete examples and prompts

[1168] For example, if a user inputs "I want to reduce power consumption after 6 PM," the generative AI will suggest, "Power consumption peaks between 7 PM and 9 PM, so replacing the lighting with LEDs would be highly effective." In response to the command "Turn off the power in the conference room," the server will send an instruction to the corresponding smart meter to turn off the power in the conference room.

[1169] This will enable comprehensive power collection, analysis, interaction, and remote operation, enabling efficient power use and the proposal of appropriate power-saving measures.

[1170] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1171] Power management system program processing flow

[1172] Step 1: Data collection

[1173] The server collects real-time electricity consumption data from smart meters in each building and floor. The input is data such as the amount of electricity measured by the smart meters, usage time, and peak consumption. The output is the collected electricity consumption data.

[1174] Specific behavior:

[1175] The server sends API requests to each smart meter at regular intervals.

[1176] The server receives the power consumption data from the smart meter and temporarily stores it in memory.

[1177] Step 2: Data storage and preprocessing

[1178] The server preprocesses the collected power consumption data before storing it in the database. The input is the power consumption data collected in step 1. The output is the preprocessed data with outliers filtered out.

[1179] Specific behavior:

[1180] The server uses Python data processing libraries (e.g., pandas) to shape the data and filter out incomplete data and outliers.

[1181] The server generates SQL statements and stores the pre-processed data in a database (e.g. MySQL or PostgreSQL).

[1182] Step 3: Data analysis

[1183] The server passes the stored data to an AI analysis module to identify power usage patterns and anomalies. The input is pre-processed power consumption data stored in a database. The output is the analysis results.

[1184] Specific behavior:

[1185] The server executes a query to retrieve the required data from the database.

[1186] The server passes the acquired data to an AI analysis module using Python's scikit-learn library to detect power usage patterns and anomalies.

[1187] The server stores the analysis results in the database again.

[1188] Step 4: User interaction

[1189] When a user accesses the system and asks for advice on power-saving measures, the server uses generative AI to interact with the user. The input is the prompt the user enters into the system. The output is a power-saving measure proposal generated by the AI.

[1190] Specific behavior:

[1191] The user inputs a prompt statement into the system (e.g., "I want to reduce power consumption after 6 p.m.").

[1192] The server sends a prompt to the generative AI (e.g., OpenAI's GPT-3) and receives a response from the AI.

[1193] The server returns AI-generated suggestions to the user (e.g., "Electricity consumption peaks between 7:00 and 9:00 p.m., so replacing your lighting with LEDs would be highly effective").

[1194] Step 5: Remote Operation

[1195] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation instruction to the corresponding smart meter. The input is the remote operation command that the user inputs to the system. The output is that the power of the specified equipment is turned off.

[1196] Specific behavior:

[1197] The user enters the command "Turn off the power in the conference room."

[1198] The server analyzes the command and sends a request to the corresponding smart meter API.

[1199] The terminal (smart meter) receives the request and turns off the power in the designated conference room.

[1200] The above are the program processing steps and their specific operations in the power management system. This enables comprehensive power collection, analysis, interaction, and remote operation, making it possible to use power efficiently and propose appropriate power-saving measures.

[1201] (Application example 1)

[1202] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1203] There is a demand for more efficient power consumption and energy-saving measures in factories, but conventional systems do not adequately monitor and analyze power consumption in real time, and they also do not adequately propose effective power-saving measures through dialogue with users.To solve this problem, a system is needed that can collect and analyze power consumption data in detail, operate devices remotely, and propose optimal power-saving measures to users.

[1204] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1205] In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with a user and proposing power-saving measures, means for remotely operating a power supply or breaker, means for monitoring the power consumption of work equipment in a factory and collecting data in real time, means for saving the data collected in real time in the server, means for analyzing the saved data with an AI analysis module, means for generating and proposing optimal power-saving measures in response to user input using generative AI, and means for enabling remote power control of specific areas or devices. This makes it possible to monitor and optimize power consumption in a factory, and to propose and remotely operate efficient power-saving measures.

[1206] "Power consumption data" is numerical information about the amount of power consumed in a specific area or device, usage time, peak consumption, etc.

[1207] "Collection means" refers to a device or software that has the function of acquiring electricity consumption data from each smart meter or measuring device.

[1208] The "analyzing means" is a device or software that has the function of analyzing collected power consumption data and detecting usage patterns and anomalies.

[1209] The "means for interacting with the user" refers to a device or software that has the function of proposing appropriate power saving measures using a generative algorithm in response to user input.

[1210] A "generative algorithm" is an algorithm that includes calculation methods and procedures for providing optimal recommendations and advice to users based on collected and analyzed data.

[1211] "Means for remotely operating power or breakers" refers to devices or software that have the function of turning on and off the power or breakers of specific equipment or areas from a remote location.

[1212] The "monitoring means" refers to a device or software that has the function of monitoring the power consumption of work equipment in a factory and acquiring data in real time.

[1213] A "server" is a computer system capable of collecting, storing, analyzing, and interacting with users.

[1214] An "AI analysis module" is a software module that uses artificial intelligence to analyze acquired data and detect usage patterns and anomalies.

[1215] "Means for enabling remote power control of a device" refers to a device or software that has the function of turning the power of a specific device on or off from a remote location.

[1216] The "means for generating and proposing optimal energy-saving measures" refers to a device or software that has the function of proposing specific action plans to users for reducing energy consumption based on collected and analyzed data.

[1217] This invention relates to a system for optimizing power consumption in factories and proposing efficient power-saving measures. This system has the function of collecting and analyzing detailed power consumption data and remotely operating power supplies and breakers.

[1218] Data collection

[1219] The server collects real-time power consumption data from smart meters and various measuring devices installed within the factory. This data includes the power consumption of each work area and device, usage time, and peak consumption. This allows for an accurate understanding of the energy consumption situation throughout the factory.

[1220] Data storage and analysis

[1221] The server securely stores the collected data in a database for later detailed analysis. The stored data is then analyzed by an AI analysis module to identify power usage patterns and anomalous usage. The analysis results can be used to improve energy efficiency and detect anomalies.

[1222] Dialogue with users and recommendations

[1223] When a user accesses the system to inquire about power-saving measures, the server uses generative AI to converse with the user and propose power-saving measures based on usage. For example, if a user inputs, "I want to reduce power consumption during the day," the generative AI will generate specific suggestions based on collected data and analysis results, such as, "Consumption is high during certain times of the day, so shift the operating hours of some devices."

[1224] Remote power / breaker operation

[1225] When a user instructs a specific room or device to be turned off, the server analyzes the instruction and sends a remote operation command to the corresponding smart meter, which results in the power being turned off for the designated work area or equipment. For example, if a user instructs the server to "turn off the power in the conference room," the server analyzes the instruction and the corresponding device turns off the power in the conference room.

[1226] Hardware and software used

[1227] Hardware: Smart meters, servers, database servers, and smartphones used by users.

[1228] Software: Python API, database management system, AI analysis module, generative AI.

[1229] For example, if a factory manager inputs "I want to reduce electricity consumption during the day," the system will use past data to suggest "Since usage is high during certain times of the day, we should spread out the use of heavy machinery." A specific example of a prompt for the generative AI model is as follows:

[1230] "I want to reduce electricity consumption during the day."

[1231] In this way, the server can streamline power management within the factory and optimize overall energy consumption.

[1232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1233] Step 1:

[1234] The server collects power consumption data in real time from smart meters and various measuring devices installed within the factory. The input is data from the smart meters (power consumption, usage time, peak consumption, etc.), and the output is the collected data. This allows the server to accurately grasp the energy consumption status of the entire factory.

[1235] Step 2:

[1236] The server stores the collected power consumption data in a database. The input is the data collected in step 1, and the output is the stored data. This storage process lays the foundation for further analysis later.

[1237] Step 3:

[1238] The server passes the stored data to an AI analysis module, which analyzes power usage patterns and abnormal usage. The input is the data stored in the database, and the output is the analysis results. This analysis makes it possible to improve energy efficiency and detect abnormalities.

[1239] Step 4:

[1240] The user accesses the system and asks for advice on power-saving measures. The input is the user's request (prompt), such as "I want to reduce power consumption during the day." The server uses generative AI to advance the dialogue with the user.

[1241] Step 5:

[1242] The server uses generative AI to propose optimal power-saving measures based on the analysis results of the AI ​​analysis module and user requests. The inputs are the analysis results and user requests, and the output is the generated power-saving measure proposal. For example, a proposal may be generated such as, "Consumption is high during certain time periods, so shift the operating hours of some devices."

[1243] Step 6:

[1244] A user remotely commands a specific room or device to be turned off. The input is the user's specific command (e.g., "Turn off the power in the conference room"), and the server receives the command.

[1245] Step 7:

[1246] The server analyzes the user's instructions and sends remote operation instructions to the corresponding smart meter. The input is the user's instructions, and the output is the specific remote operation instructions. This will turn off the power to the designated work area or equipment.

[1247] In this way, the server, terminals, and users work together to make power management within the factory more efficient and optimize overall energy consumption.

[1248] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1249] The present invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power saving measures through dialogue with the user, and combines an emotion engine to take optimal action according to the user's emotions. The following describes in detail an embodiment of the present invention.

[1250] Data collection

[1251] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it obtains data such as power consumption (kWh), usage time, and peak consumption through the API of each smart meter.

[1252] Data storage and analysis

[1253] The server stores the collected data in a database, where data collected from each floor and device is structured, securely, and efficiently stored. The stored data is then passed to an AI analysis module, where it is analyzed to identify power usage patterns and anomalies, enabling efficient energy management.

[1254] Dialogue with users and recommendations

[1255] The user accesses the system and asks for advice on energy-saving measures. Specifically, the user inputs a request such as "I want to reduce power consumption after 6 PM." The server then uses generative AI to suggest specific energy-saving measures in a dialogue with the user. For example, the server might suggest, "Since power consumption peaks between 7 PM and 9 PM, we should replace the lighting with LEDs."

[1256] Emotion engine integration

[1257] The server calls the emotion engine during a dialogue with the user and recognizes their emotions by analyzing their voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied, and passes corresponding suggestions to the generative AI. For example, if the user is feeling stressed, the emotion engine will recognize this and suggest simple and easy-to-implement energy-saving measures to the generative AI.

[1258] Remote power / breaker operation

[1259] When a user instructs the system to turn off the power in a specific room, the server analyzes the instruction and sends a remote operation command to the smart meter. For example, if a user inputs a command to "turn off the power in the conference room," the server analyzes the instruction and the terminal (smart meter) turns off the power in the conference room based on the instruction.

[1260] Specific examples of programs

[1261] Data collection flow

[1262] The server collects real-time electricity consumption data from each smart meter via an API.

[1263] The server stores the collected data in a database.

[1264] Data analysis flow

[1265] The server passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[1266] The server prepares data to propose energy-saving measures based on the analysis results.

[1267] User interaction and proposal flow

[1268] The user inputs a request for advice on power saving measures.

[1269] The server uses generative AI to interact with users and propose optimal power-saving measures based on usage.

[1270] Flow of emotion engine integration

[1271] The server uses an emotion engine during dialogue with the user to analyze voice and text data and recognize the user's emotions.

[1272] Based on the results of the emotion engine, the server has the generative AI make suggestions based on the user's emotions.

[1273] Remote operation flow

[1274] A user requests power / breaker operation for a specific room or device.

[1275] The server analyzes the instructions and sends remote operation instructions to the corresponding smart meter.

[1276] The terminal (smart meter) performs the specified operation.

[1277] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] The server collects real-time electricity consumption data from smart meters in each building and on each floor. Specifically, it sends requests to each smart meter via API to obtain data such as power consumption (kWh), usage time, and peak consumption.

[1281] Step 2:

[1282] The server stores the collected power consumption data in a database, which stores the information collected from each floor and device in a structured manner.

[1283] Step 3:

[1284] The server then passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies, including peak consumption times, abnormal consumption pattern detection, and predicted consumption.

[1285] Step 4:

[1286] The server calls the AI ​​generator based on the analysis results and prepares data to propose optimal energy-saving measures to the user. The AI ​​generator generates effective energy-saving methods by taking into account past data and current usage conditions.

[1287] Step 5:

[1288] A user accesses the system and inputs a request for power saving measures. For example, the user inputs a request such as "I want to reduce power consumption after 6 PM."

[1289] Step 6:

[1290] The server operates a generative AI based on this input and proposes specific energy-saving measures through a dialogue with the user, such as "Since power consumption peaks between 7:00 PM and 9:00 PM, replace the lighting with LEDs."

[1291] Step 7:

[1292] The server activates an emotion engine during a dialogue with the user and recognizes emotions by analyzing the voice and text data entered by the user. The emotion engine determines the user's stress and satisfaction levels and sends corresponding suggestions to the generative AI.

[1293] Step 8:

[1294] When a user issues a command to turn off the power in a specific room, the server analyzes the command and sends a remote operation command to the smart meter. For example, a user might enter a command such as "Turn off the power in the conference room."

[1295] Step 9:

[1296] The server sends specific operational instructions to the smart meter to power on or off designated rooms or devices.

[1297] Step 10:

[1298] The terminal (smart meter) follows the received remote operation instructions and turns off the power to the specified room or device, allowing the user to manage power remotely without being physically present at the site.

[1299] The above is the specific processing flow of this system, which provides a multifunctional means for optimizing power consumption and providing effective power saving measures according to the user's emotions.

[1300] Example 2

[1301] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1302] In modern society, efficient management of power consumption and energy-saving measures are important issues. Conventional power management systems can collect and analyze data on power consumption, but in many cases, it is difficult to provide users with appropriate energy-saving measures. In addition, they are unable to respond to users' emotions, which means they are unable to make suggestions that take into account users' satisfaction and willingness to implement them.

[1303] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1304] In this invention, the server includes means for collecting power consumption data, means for saving the collected power consumption data, means for analyzing the saved power consumption data, means including a generative algorithm for interacting with the user and proposing power saving measures, means including an emotion engine for analyzing the user's emotions, and means for remotely operating the power supply or breaker. This not only enables efficient power saving measures to be proposed based on the collected power consumption data, but also enables flexible responses according to the user's emotions.

[1305] "Power consumption data" refers to information such as the amount of power consumed, usage time, and peak consumption at each measurement point within a building or facility.

[1306] The "means of collection" refers to interface devices such as APIs and sensors for obtaining electricity consumption data from each smart meter.

[1307] The "storage means" is a database management system for structuring, efficiently and securely storing collected electricity consumption data.

[1308] The "analysis means" is an AI analysis module that uses stored power consumption data to detect power usage patterns and anomalies and support efficient energy management.

[1309] A "generative algorithm" is an artificial intelligence technology that proposes optimal energy-saving measures based on data collected through dialogue with users.

[1310] The "emotion engine" is a technology that analyzes the user's voice and text data to recognize their emotions. It can determine whether the user is feeling stressed or satisfied.

[1311] "Means for remote operation" refers to a mechanism for sending remote operation instructions to devices such as smart meters based on user instructions, and actually operating power supplies and breakers.

[1312] "User" refers to an individual or corporation that uses the system to manage power consumption and take measures to save power.

[1313] This invention relates to a power management system that collects and analyzes power consumption data in detail, proposes effective power-saving measures through dialogue with the user, and combines an emotion engine to provide optimal responses according to the user's emotions.

[1314] Data collection

[1315] The server collects real-time power consumption data from smart meters in each building and floor via API. This collected data includes power consumption (kWh), usage time, peak consumption, etc. For example, when the server sends a request such as "GET / api / v1 / power-usage?floor=3", the smart meter returns JSON-formatted data such as "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}".

[1316] Data storage and analysis

[1317] The server stores the collected power consumption data in a database. This database uses an RDBMS such as MySQL. The stored data is passed to an AI analysis module, which uses Python's TensorFlow library to perform analysis to identify power usage patterns and anomalies. For example, the server executes the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'", converts the obtained data into JSON, and sends it to the AI ​​analysis module.

[1318] Dialogue with users and recommendations

[1319] Users access the system and use a chat interface to discuss energy-saving measures. For example, they input a request such as, "I want to reduce power consumption after 6 p.m." The server then uses a generative AI model to suggest specific energy-saving measures through a dialogue with the user. Specifically, the server suggests, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs." An example of a prompt statement is, "I want to reduce power consumption after 6 p.m."

[1320] Emotion engine integration

[1321] While interacting with the user, the server calls the emotion engine and analyzes the user's emotions from voice and text data. The emotion engine determines whether the user is feeling stressed or satisfied. For example, voice data is sent to the emotion analysis API and results such as "Stress: 70%" and "Satisfaction: 20%" are received. Based on this, the generative AI model makes suggestions that take emotions into consideration. As a specific example, if the user is feeling stressed, it suggests "securely closing doors at night to increase heating and cooling efficiency" as a simple and easy-to-implement energy-saving measure.

[1322] Remote power / breaker operation

[1323] When a user requests a power control for a specific room, the server analyzes the request and sends a remote operation instruction to the smart meter. For example, if a user inputs "Turn off the power in the conference room," the server sends a "POST / api / v1 / control-power" request to the smart meter API, passing the data "room: conference_room, action: off." The device (smart meter) receives this instruction and turns off the power to the conference room.

[1324] The above is an embodiment of the present invention. This system realizes comprehensive power management and effective power saving measures tailored to the user, thereby optimizing energy efficiency.

[1325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1326] Step 1:

[1327] The server collects data from the smart meters.

[1328] The server periodically sends API requests to the smart meters in each building and floor. Specifically, it sends the request "GET / api / v1 / power-usage." This input returns power consumption data such as power consumption, usage time, and peak consumption from the smart meter. For example, requesting "GET / api / v1 / power-usage?floor=3" will return the output "{"timestamp":"2023-10-04T10:00:00Z","kWh":50,"peak_usage":15}."

[1329] Step 2:

[1330] The server stores the collected data in a database

[1331] The server stores the acquired power consumption data in a MySQL database. The data input is the JSON format data returned from the smart meter. The data is structured and stored using the SQL query "INSERT INTO power_usage (timestamp, kWh, peak_usage, floor) VALUES ('2023-10-04T10:00:00Z', 50, 15, 3)".

[1332] Step 3:

[1333] The server passes the data to the AI ​​analysis module

[1334] The server retrieves power consumption data for a specific period from the database and sends it to the AI ​​analysis module. The input is the result of an SQL query from the database, and the output is formatted JSON data. Specifically, the data is retrieved using the query "SELECT timestamp, kWh, peak_usage FROM power_usage WHERE floor=3 AND timestamp BETWEEN '2023-10-01' AND '2023-10-02'".

[1335] Step 4:

[1336] The server receives the analysis results from the AI ​​analysis module

[1337] The AI ​​analysis module uses the input data to identify power usage patterns and anomalies. Based on this, it generates the data necessary to propose specific power-saving measures. For example, the AI ​​analysis module outputs "{"pattern":"high_usage","suggestion":"switch to LED lights"}", which is received by the server.

[1338] Step 5:

[1339] User consults about power saving measures

[1340] Users access the system and discuss energy-saving measures through a chat interface. For example, they input a request such as "I want to reduce power consumption after 6 p.m." The output is a response from the server based on that request.

[1341] Step 6:

[1342] The server interacts with the user using generative AI

[1343] The server passes the user's request to a generative AI model, which then interactively proposes specific energy-saving measures. The input is the user's request and the analysis results from the AI ​​analysis module, and the output is a specific energy-saving proposal. For example, it might suggest, "Since power consumption peaks between 7:00 and 9:00 p.m., replace the lighting with LEDs."

[1344] Step 7:

[1345] The server uses an emotion engine to recognize the user's emotions.

[1346] The server analyzes the user's voice and text data using an emotion engine. The input is the user's dialogue data, and the output is the emotion analysis results. For example, analyzing voice data yields results such as "Stress: 70%" and "Satisfaction: 20%."

[1347] Step 8:

[1348] The server uses generative AI to make suggestions based on emotions.

[1349] Based on the emotion analysis results, the server provides the generative AI model with suggestions that correspond to the user's emotions. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes the user's emotions into consideration. For example, if the user is feeling stressed, the server will make a suggestion such as "As a specific and easy-to-implement energy-saving measure, we suggest closing the doors at night to improve heating and cooling efficiency."

[1350] Step 9:

[1351] A user requests a remote operation

[1352] The user requests the system to operate the power / breaker for a specific room or device, for example, by inputting "Turn off the power to the conference room."

[1353] Step 10:

[1354] The server sends remote operation instructions to the smart meter

[1355] The server analyzes the user's request and sends remote operation instructions to the corresponding smart meter. The input is the user's request, and the output is the specific operation instruction to the smart meter. For example, send a "POST / api / v1 / control-power" request and pass the data "room: conference_room, action: off".

[1356] Step 11:

[1357] The terminal (smart meter) performs remote operations

[1358] The terminal (smart meter) turns off the power in a specific room based on instructions sent from the server. The input is the operation instruction from the server, and the output is the result of the operation. Specifically, it executes the command "to turn off the power in the conference room" using a relay operation or other means.

[1359] These are the processing steps of this system. This process makes it possible to efficiently manage the user's power consumption and provide optimal power saving measures.

[1360] (Application example 2)

[1361] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1362] In addition to optimizing power consumption and implementing effective energy-saving measures in industrial facilities, it has been difficult to manage energy consumption while taking into account the emotions of workers. Furthermore, there is a lack of systems that can collect real-time power consumption data from each facility and make effective energy-saving proposals.

[1363] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting power consumption data, means for analyzing the collected power consumption data, means including a generative algorithm for interacting with the user and proposing power-saving measures, means for analyzing emotion data and making suggestions according to the user's emotions, means for collecting power consumption data of industrial equipment in real time, and means for remotely operating the power supplies or breakers of specific work areas or equipment. This enables comprehensive energy management and effective power-saving measures tailored to the user.

[1364] "Power consumption data" refers to detailed data such as the amount of power used by each power device or facility, the duration of use, and peak consumption.

[1365] "Analysis means" refers to algorithms or software used to process collected power consumption data and identify power usage patterns and anomalies.

[1366] "Generative algorithms" are artificial intelligence technologies that interact with users based on collected and analyzed data and suggest specific energy-saving measures.

[1367] "Emotion data" is emotional data analyzed based on the user's voice and text data, and is information indicating whether the user is feeling stressed or satisfied.

[1368] "Emotion analysis means" is a technology for analyzing emotion data and recognizing the user's emotional state.

[1369] The "real-time collection means" is a function that collects power consumption data from each power device or facility in real time.

[1370] "Remote operation means" refers to technology for remotely controlling the power supply or breaker of a specific work area or equipment.

[1371] System Configuration

[1372] The present invention is embodied as a power management system within an industrial facility. The system includes the following main components:

[1373] 1. Server

[1374] Data collection: The server collects electricity consumption data in real time from the smart meters of each industrial facility via API.

[1375] Data storage: Collected data is stored in a cloud database (e.g., AWS RDS).

[1376] Data analysis: The stored data is passed to an AI analysis module (e.g., TensorFlow) for analysis to identify power usage patterns and anomalies.

[1377] Generative algorithm: Using generative AI (e.g., OpenAI GPT-4), we interact with users and suggest specific energy-saving measures.

[1378] Emotion analysis: Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions are analyzed from the user's voice and text data, and suggestions are made based on the user's emotions.

[1379] 2. Terminal

[1380] Real-time power collection: Each smart meter collects the power consumption data of the equipment in real time and transmits it to the server.

[1381] Remote Operation: Remotely operate power or breakers for specific work areas or equipment.

[1382] 3. Users

[1383] Dialogue and requests: Users access the system via smartphones or robots to discuss energy-saving measures. In response to the user's requests, the server uses generative AI to propose specific measures.

[1384] Emotion data provision: The voice and text data collected during the conversation is analyzed by the emotion engine to recognize the user's emotional state.

[1385] Program processing explanation

[1386] Below is a natural language description of how the components of the system work together:

[1387] 1. Data Collection and Storage

[1388] The server collects real-time electricity consumption data from each smart meter via API and stores it in a cloud database, including the amount of electricity consumed, the duration of use, and peak consumption.

[1389] 2. Data Analysis

[1390] The server periodically passes the stored data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies.

[1391] 3. Dialogue with users and proposals for energy-saving measures

[1392] When a user consults the system about energy-saving measures, the generative AI will suggest specific energy-saving measures in an interactive format. For example, if a user requests, "I want to reduce energy consumption after 6 p.m.", the generative AI will suggest, "Since power consumption peaks between 7 p.m. and 9 p.m., replace the lighting with LEDs."

[1393] 4. Emotion analysis

[1394] The emotion engine analyzes the user's voice and text data to determine whether they are feeling stressed or satisfied. Based on the results of the emotion engine, the generative AI makes suggestions based on the user's emotions.

[1395] 5. Remote Operation

[1396] When a user requests a power control for a specific work area or device, the server analyzes the request and sends a remote control instruction to the corresponding smart meter, which then turns off the power accordingly.

[1397] Examples of concrete examples and prompts

[1398] For example, the following prompt sentences are used:

[1399] "What's the best way to reduce energy consumption after 6pm?"

[1400] Please tell me your current electricity usage.

[1401] "Please tell me about the energy savings that can be achieved by replacing lighting with LEDs."

[1402] "Please suggest some simple energy-saving measures for stressed workers."

[1403] "Please turn off the power to the conference room remotely."

[1404] In this way, the system achieves comprehensive energy management and effective power saving measures tailored to the user.

[1405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1406] Step 1:

[1407] The server collects real-time electricity consumption data from the smart meters of each industrial facility. In this step, electricity consumption data (power consumption, usage time, peak consumption, etc.) is obtained from the smart meters via API and stored in a cloud database. The input is the electricity consumption data from each smart meter, and the output is the data stored in the cloud database.

[1408] Step 2:

[1409] The server passes the collected data to an AI analysis module, which analyzes it to identify power usage patterns and anomalies. In this step, data is read from the cloud database and analyzed by the AI ​​analysis module (e.g., TensorFlow). The input is the stored power consumption data, and the output is the analysis results (identification of power usage patterns and anomalies).

[1410] Step 3:

[1411] A user consults the system about energy-saving measures. The user inputs a request to the system via a smartphone or robot. For example, the user inputs a prompt such as, "What is the best way to reduce energy consumption after 6 p.m." The input is the request from the user, and the output is the request data to the server.

[1412] Step 4:

[1413] The server uses generative AI (e.g., OpenAI GPT-4) to interactively propose specific power-saving measures. In this step, optimal power-saving measures are generated based on the user's request and the results of the AI ​​analysis module. The input is the user's request and the analysis results, and the output is a proposed power-saving measure.

[1414] Step 5:

[1415] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. In this step, the user's dialogue data is passed to the emotion engine for analysis. The input is the user's voice and text data, and the output is the emotion analysis result.

[1416] Step 6:

[1417] Based on the results of the emotion analysis, the server passes suggestions based on the user's emotions to the generative AI and engages in a dialogue. In this step, the results of the emotion analysis are taken into account to generate suggestions suitable for the user. The input is the emotion analysis results, and the output is a proposal for energy-saving measures that takes emotions into consideration.

[1418] Step 7:

[1419] A user requests power control for a specific work area or device. The user enters a command such as "Please turn off the power to the conference room remotely." The input is the user's request, and the output is the operation instruction data sent to the server.

[1420] Step 8:

[1421] The server receives the remote operation instruction and sends it to the corresponding smart meter. In this step, the server analyzes the operation instruction and sends a power operation command to the specific smart meter. The input is the operation instruction data, and the output is a control signal to the smart meter.

[1422] Step 9:

[1423] The smart meter of the terminal performs the specified operation and turns off the power of the device. In this step, the smart meter controls the power of the device based on the instruction received. The input is the control signal, and the output is the state in which the device is powered off.

[1424] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1425] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1426] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1427] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1428] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1429] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1430] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1431] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1432] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1433] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1434] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1435] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1436] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1437] 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.

[1438] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1439] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1440] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1441] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1442] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1443] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1444] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1445] The following is further disclosed regarding the above embodiment.

[1446] (Claim 1)

[1447] means for collecting electricity consumption data;

[1448] means for analyzing the collected power consumption data;

[1449] means for interacting with a user and including a generative algorithm for suggesting power saving measures;

[1450] a means for remotely operating power or breakers;

[1451] A system including:

[1452] (Claim 2)

[1453] 10. The system of claim 1, wherein the power consumption data is collected in real time for each measurement location.

[1454] (Claim 3)

[1455] The system of claim 1, wherein the generative algorithm provides recommendations to the user based on the analysis results.

[1456] "Example 1"

[1457] (Claim 1)

[1458] means for collecting electricity consumption data;

[1459] means for analyzing the collected power consumption data;

[1460] means for interacting with a user and including a generative algorithm for suggesting power saving measures;

[1461] a means for remotely operating power or breakers;

[1462] means for detecting anomalies in power consumption data;

[1463] means for pre-processing the power consumption data;

[1464] A system including:

[1465] (Claim 2)

[1466] 10. The system of claim 1, wherein the power consumption data is collected in real time for each measurement location.

[1467] (Claim 3)

[1468] The system of claim 1, wherein the generative algorithm provides recommendations to the user based on the analysis results.

[1469] "Application Example 1"

[1470] (Claim 1)

[1471] means for collecting electricity consumption data;

[1472] means for analyzing the collected power consumption data;

[1473] means for interacting with a user and including a generative algorithm for suggesting power saving measures;

[1474] a means for remotely operating power or breakers;

[1475] A means of monitoring the power consumption of work equipment in the factory and collecting data in real time;

[1476] A means for storing the data collected in real time on a server;

[1477] A means for analyzing the stored data by an AI analysis module;

[1478] A means of generating and proposing optimal energy-saving measures based on user input using generative AI;

[1479] A means for enabling remote power control of specific areas or devices;

[1480] A system including:

[1481] (Claim 2)

[1482] 10. The system of claim 1, wherein the power consumption data is collected in real time for each measurement location.

[1483] (Claim 3)

[1484] The system of claim 1, wherein the generative algorithm provides recommendations to the user based on the analysis results.

[1485] "Example 2: Combining Emotion Engines"

[1486] (Claim 1)

[1487] means for collecting electricity consumption data;

[1488] means for storing the collected power consumption data;

[1489] means for analyzing the stored power consumption data;

[1490] means for interacting with a user and including a generative algorithm for suggesting power saving measures;

[1491] means including an emotion engine for analyzing the emotion of a user;

[1492] a means for remotely operating power or breakers;

[1493] A system including:

[1494] (Claim 2)

[1495] 10. The system of claim 1, wherein the power consumption data is collected in real time for each measurement location.

[1496] (Claim 3)

[1497] The system of claim 1, wherein the generative algorithm provides recommendations to the user based on the analysis results and the user's emotions.

[1498] "Application example 2 when combining emotion engines"

[1499] (Claim 1)

[1500] means for collecting electricity consumption data;

[1501] means for analyzing the collected power consumption data;

[1502] means for interacting with a user and including a generative algorithm for suggesting power saving measures;

[1503] A means for analyzing emotion data and making suggestions according to the emotion of the user;

[1504] a means for collecting real-time power consumption data of an industrial facility;

[1505] A means of remotely controlling power or breakers for specific work areas or equipment;

[1506] A system including:

[1507] (Claim 2)

[1508] 10. The system of claim 1, wherein the power consumption data and emotion data are collected in real time for each measurement location.

[1509] (Claim 3)

[1510] 2. The system of claim 1, wherein the generative algorithm provides recommendations to the user based on the analysis results and the emotional data. [Explanation of symbols]

[1511] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting electricity consumption data; means for analyzing the collected power consumption data; means for interacting with a user and including a generative algorithm for suggesting power saving measures; a means for remotely operating power or breakers; A system including:

2. 10. The system of claim 1, wherein the power consumption data is collected in real time for each measurement point.

3. The system according to claim 1 , wherein the generative algorithm provides recommendations to the user based on the analysis results.

Images