system

Abstract

Provide a system. 【Solution means】 Means for obtaining environmental data from sensors in real time, Means for initially processing the received data and detecting abnormal values, Means for generating an energy usage plan based on a generative artificial intelligence model, Means for referring to regulatory information and modifying the energy usage plan based on regulations, Means for automatically executing the plan and performing equipment control, Means for monitoring energy performance and adjusting it in real time, Means for recording data and using it for the next plan generation, A real-time energy management system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to the increase in energy costs and strict environmental regulations, optimizing the energy use of the entire building has become increasingly important. However, in conventional systems, real-time energy management is difficult, and there are also concerns about data privacy and security. In addition, energy management for achieving ZEB is complicated, and a quick response to environmental regulations is required. To solve these problems, a new system for realizing effective and sustainable energy management is required.

Means for Solving the Problems

[0005] This invention provides a means for acquiring environmental data from sensors in real time and detecting anomalies through initial processing. This is followed by a means for generating an energy use plan using a generative artificial intelligence model. Furthermore, it includes a function to compare this plan with regulatory information and modify it as necessary. The plan is automatically executed and uses equipment control to optimize energy performance. In addition, data is processed on-site using edge computing technology to enhance privacy and security. The system also provides an interface that allows users to review and manually modify the energy use plan, enabling flexible energy management.

[0006] "Environmental data" refers to information about the surrounding environment, such as temperature, humidity, light intensity, and occupancy status, and is acquired by sensors.

[0007] A "sensor" is a device that measures various environmental conditions and acquires them as digital signals.

[0008] "Initial processing" refers to the pre-processing of data performed to detect and correct outliers and missing values.

[0009] An "outlier" refers to a data value that exceeds the normal acceptable range and is subject to being ignored or corrected under certain conditions.

[0010] A "generative artificial intelligence model" refers to an algorithm that automatically generates plans for prediction and decision-making based on vast amounts of data.

[0011] An "energy use plan" refers to a feasible plan designed to optimize energy consumption and is used to improve the energy efficiency of a facility.

[0012] "Regulatory information" refers to information about standards and conditions set by governments and standardization organizations, and provides criteria for determining whether a particular activity or situation is legally compliant.

[0013] "Equipment control" refers to the process of managing the operation of equipment and systems within a building and making setting changes.

[0014] "Edge computing technology" refers to technology that performs data processing on a device close to where the data is generated, improving real-time capabilities and enhancing privacy.

[0015] A "user interface" refers to the screens and operating systems that allow a user to interact with a system, inputting and outputting information, and changing settings. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is implemented as a system for optimizing energy use within a building in real time. This system includes IoT sensors, servers, generative artificial intelligence models, edge computing technology, and a user interface.

[0038] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental data such as temperature, humidity, light intensity, and occupancy status. This data is acquired at regular intervals and transmitted to a server.

[0039] The server performs initial processing on the received raw data. Here, outliers and missing values ​​are detected, and filtering is performed to ensure data accuracy. The clean data is then input into a generative artificial intelligence model. This AI model analyzes the large amount of collected environmental data and generates a specific energy use plan to optimize energy consumption.

[0040] The generated energy usage plan is verified to comply with the latest environmental regulations by referencing regulatory information. A regulatory compliance AI module is used for this verification. The plan is automatically adjusted as needed.

[0041] On the other hand, communication with users (facility operators) is also important. The server notifies users of the generated energy usage plan through a user interface. Users can use this interface to review the plan and make manual modifications as needed.

[0042] Once the energy usage plan is finalized, the server sends commands to the building management system (BMS) to control equipment such as heating, cooling, and lighting. This optimizes energy performance in real time.

[0043] Furthermore, the servers utilize edge computing technology to perform data processing on-site. This improves response speed while ensuring data privacy and security. All processing results and operation logs are recorded and used as reference for future plan generation.

[0044] As a concrete example, on a hot summer day, a sensor detects high temperatures, and an AI model optimizes the air conditioning temperature setting. The plan is adjusted to ensure that energy consumption does not exceed the permissible limit based on regulatory information. This allows facility operators to manage energy consumption comfortably and efficiently while complying with regulations.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The terminals (IoT sensors) measure and collect environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the building. This data is transmitted to a server at regular intervals.

[0048] Step 2:

[0049] The server performs initial processing on the raw data it receives. This processing includes detecting outliers and imputing missing values, as well as performing the necessary filtering to ensure data accuracy.

[0050] Step 3:

[0051] The server inputs clean environmental data into a generative artificial intelligence model, which performs data analysis and generates energy usage plans. The AI ​​then suggests appropriate temperature settings for heating and cooling, as well as planned lighting usage.

[0052] Step 4:

[0053] The server uses a regulatory compliance AI module to verify that the generated energy use plan complies with current environmental regulations. By comparing it with regulatory information, the plan is automatically modified if necessary.

[0054] Step 5:

[0055] Users (facility operators) receive energy usage plans from the server and can review them through a provided user interface. Users can also manually modify the plans using this interface.

[0056] Step 6:

[0057] After the server verifies the user, it sends commands to the building management system (BMS) to execute the energy usage plan, such as changing settings for heating, cooling, and lighting.

[0058] Step 7:

[0059] The server monitors energy performance in real time and adjusts energy usage plans as needed. Data processing is performed on-site using edge computing technology, enabling rapid response.

[0060] Step 8:

[0061] The server records all operation logs and performance data, saving them as feedback data to be used in generating future energy usage plans.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] Conventional energy management systems face challenges in achieving efficient real-time control because each step, such as collecting environmental information, detecting anomalies, and creating energy consumption plans, is performed individually. Furthermore, limitations in user flexibility for manual adjustments and the ability to respond immediately to environmental regulations are problematic. Additionally, centralized data processing presents challenges in response speed and ensuring privacy.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for continuously acquiring environmental information from a measuring device, means for processing the received information in an initial stage and detecting outliers and missing values, and means for creating an energy consumption plan based on a predictive model. This makes it possible to optimize energy efficiency in real time.

[0067] "Environmental information" refers to data on the physical or chemical conditions inside a building, such as temperature, humidity, light levels, and occupancy status.

[0068] A "measuring device" refers to a group of sensors installed to acquire environmental information, and each sensor plays a role in detecting changes in its respective element.

[0069] "Reception" refers to the process by which a server acquires data transmitted from a measuring device and incorporates it in a processable format.

[0070] "Initial processing" refers to pre-processing that detects outliers and imputes missing values ​​to ensure the accuracy of the acquired data.

[0071] An "outlier" refers to an extreme value that falls outside the normal range and may indicate a sensor malfunction or an abnormal situation.

[0072] "Missing values" refer to a state in a dataset where data that should be present is missing.

[0073] A "predictive model" refers to a machine learning algorithm that generates future energy consumption forecasts and optimized usage plans based on collected environmental information.

[0074] An "energy consumption plan" outlines specific guidelines for allocating and using energy resources in an efficient and regulated manner.

[0075] "Facilities management" refers to activities that include the automatic control of air conditioning, lighting, and other building facilities, and operations aimed at maximizing energy efficiency.

[0076] "Response speed" refers to the time it takes for a system to take action after receiving input information, and it is desirable for it to be fast.

[0077] "Privacy" refers to a state in which the data of individuals and businesses is protected from being leaked to external parties or used without their consent.

[0078] This invention relates to an energy management system for optimizing energy use within a building in real time. The system includes IoT sensors as measuring devices, a server for data processing and management, and a user interface that provides an interface with the user.

[0079] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. This information is acquired at regular intervals and sent to the server as data packets.

[0080] The server processes the received information in an initial stage, detecting outliers and missing values. To this end, data cleaning techniques are used to identify outliers and impute missing values, improving data accuracy. Next, the clean data is input into a generating AI model to develop a specific energy use plan that optimizes energy consumption. This AI model learns from past data and generates an optimization plan suitable for future environmental conditions. An example of a prompt used in this process is: "Based on the current room temperature, humidity, light intensity, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption."

[0081] The generated energy use plan is evaluated by a regulatory compliance module to ensure it is consistent with environmental laws and energy regulations. This module automatically generates a regulatory-compliant use plan and makes any necessary adjustments.

[0082] Subsequently, the energy usage plan is notified to the user (facility operator). The user can use this interface to review the plan and make manual adjustments as needed. Once the final plan is confirmed, the server sends commands to the building's management system to control equipment such as heating, cooling, and lighting. This optimizes energy performance while maintaining comfort in each room.

[0083] Furthermore, the server utilizes edge computing technology to perform local data processing, improving response speed while ensuring data privacy and security. All process results and operation logs are recorded and used as reference for future planning.

[0084] For example, on a hot summer day, a sensor detects high temperatures, and an AI model suggests the optimal temperature setting for the air conditioner. At this time, the user could also slightly increase the light intensity for a specific event. In this way, it is possible to achieve comfortable and efficient energy management while complying with regulations.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The terminals (IoT sensors) are placed in each room of the building and continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. The input is raw data acquired from various sensors. The sensors collect data at regular intervals, convert the data into a digital format, and send it to the server. The output is data packets containing environmental information.

[0088] Step 2:

[0089] The server receives raw data transmitted from the measurement terminal. The input is data packets containing environmental information. The server performs initial processing on this data, such as anomaly detection and missing value imputation. Specifically, it identifies anomalies using statistical methods and imputes missing parts based on the mean or past data. The output is clean and highly accurate environmental information.

[0090] Step 3:

[0091] The server generates clean data and inputs it into the AI ​​model. The input is pre-processed environmental information data. This AI model uses machine learning algorithms to create an energy usage plan to optimize energy consumption from a large amount of data. Specifically, the AI ​​model analyzes environmental conditions and user usage patterns and performs predictions and optimizations using the prompt message "Based on the current room temperature, humidity, light level, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption." The output is the energy usage plan.

[0092] Step 4:

[0093] The server verifies the compliance of the generated energy use plan against environmental laws and energy regulations. The input is the energy use plan generated by the AI ​​model. The server utilizes a regulatory compliance module to verify that the plan meets all legal standards. If necessary, it automatically adjusts the plan. Specifically, it checks energy consumption limits and fine-tunes the plan. The output is the energy use plan that has been verified as compliant.

[0094] Step 5:

[0095] The user (facility operator) reviews the energy usage plan presented via the server through the user interface. The input is the energy usage plan that has been verified for suitability. The user can review the plan using the interface and manually adjust it as needed. Specifically, the user adjusts heating and cooling settings and lighting according to specific usage conditions. The output is the final energy usage plan approved or modified by the user.

[0096] Step 6:

[0097] The server sends instructions to the building management system (BMS) based on the final energy use plan, controlling the equipment. The input is the final energy use plan confirmed by the user. The server sends control signals to heating and cooling systems and lighting equipment, adjusting the set temperature and light intensity. Specifically, it optimizes energy use in each room through automatic control. The output is the optimized energy performance.

[0098] Step 7:

[0099] The server utilizes edge computing technology to perform data processing on-site. The input is real-time data collected during the execution of the plan. The server processes this data to improve response speed while protecting data privacy and security. The output is efficient data processing while ensuring privacy and security. All process results and operation logs are also recorded for reference in future planning.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Energy consumption within factories is crucial for improving production efficiency and reducing costs. However, many current systems lack sufficient real-time control to adapt to environmental changes, making efficient energy management difficult. Furthermore, limited means for users to modify plans in real time can lead to delays in situations requiring rapid response.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes means for acquiring environmental data from a detection device in real time, means for initial processing the received information and detecting abnormal values, means for generating a power utilization plan based on a generative artificial intelligence model, and means for presenting the power utilization plan through a personal electronic device that allows for on-site plan modification. This enables rapid and efficient energy management and real-time plan modification by the user.

[0105] "Environmental data" refers to information such as temperature, humidity, light intensity, and occupancy status that is acquired in real time using detection devices within buildings and facilities.

[0106] A "detection device" is a hardware device that uses various sensor technologies to acquire environmental data.

[0107] "Initial processing" refers to the process of detecting anomalies and cleaning data in acquired environmental data before input.

[0108] A "generative artificial intelligence model" is an artificial intelligence algorithm used to analyze large amounts of collected data and generate specific plans to optimize energy consumption.

[0109] A "power utilization plan" is an operational plan aimed at efficient energy consumption, built based on a generative artificial intelligence model.

[0110] "Regulatory information" refers to information that outlines various laws, regulations, and guidelines that restrict energy use.

[0111] "Personal electronic devices" refer to electronic devices that people carry and use on a daily basis, such as smartphones and visual display devices.

[0112] "Plan modification" refers to the act of manually changing the generated power utilization plan as needed.

[0113] Edge computing is a technology that performs data processing and analysis near the actual location, improving response speed while ensuring data privacy and security.

[0114] This system is designed to optimize energy efficiency within the factory. The system's design and operation are described in detail below.

[0115] First, multiple detection devices positioned as terminals continuously acquire environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the factory. This data is immediately transmitted to a server. The server first performs initial processing on the received information and then performs data cleaning to remove outliers in order to maintain data integrity.

[0116] Next, Python and TENSORFLOW® will be used as the software to build the generative artificial intelligence model. The AI ​​model will analyze cleansed data and generate an efficient power utilization plan. This model has the flexibility to evaluate environmental changes in real time and adjust the plan as needed.

[0117] The generated power usage plan is presented to the user via their personal electronic device. The user can directly review the plan using a smartphone or visual display device and manually modify it as needed. This allows for more efficient and faster energy management.

[0118] By using edge computing techniques, data processing is performed closer to the site, resulting in improved response speed and enhanced data privacy. Furthermore, by integrating with the factory's building management system, power control based on the generated plan can be automated.

[0119] For example, on a hot summer day, the outside temperature rises, and sensors inside the factory detect this change. At this point, the AI ​​model adjusts the air conditioning temperature setting, achieving both efficient energy consumption and a comfortable working environment.

[0120] An example of a prompt message is, "The current temperature is over 30°C. Please suggest the optimal air conditioning settings to maintain a comfortable working environment while minimizing energy consumption." This prompt helps the AI ​​model achieve optimal energy use by providing specific instructions.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The terminal acquires environmental data such as temperature, humidity, light intensity, and occupancy status in real time from detection devices placed throughout the factory. This information is transmitted to a server via a communication network. The input is raw data from the detection devices, and the output is well-formed data sent to the server.

[0124] Step 2:

[0125] The server performs initial processing on the received data, including detecting outliers and cleaning the data. Specifically, it filters outliers and missing values ​​to ensure data integrity. In this step, raw data is used as input, and cleansed data is generated as output.

[0126] Step 3:

[0127] The server inputs cleansed data into a generative artificial intelligence model. The AI ​​model is built using Python and TensorFlow. The model analyzes large amounts of data and generates an efficient power utilization plan. The input is cleansed data, and the output is an optimized power utilization plan.

[0128] Step 4:

[0129] The server presents the generated power usage plan to the user via their personal electronic device. The user can review this plan using a smartphone or visual display device. The input for this step is an optimized plan, and the output is user-readable plan information.

[0130] Step 5:

[0131] The user can manually modify the plan as needed. User input is the instruction for manual adjustment, and output is the adjusted power utilization plan.

[0132] Step 6:

[0133] The server uses edge computing techniques to process data near the site. This improves response speed and maintains data privacy. The input for this step is energy adjustment information, and the output is control commands updated in real time.

[0134] Step 7:

[0135] The server integrates with the factory's building management system to automatically control power based on the generated plan. This ensures efficient energy consumption. The input is the adjusted plan, and the output is the automatic power control instruction.

[0136] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0137] This invention relates to a real-time energy management system that optimizes energy use within a building, incorporating an emotion engine. The system includes IoT sensors, a server, a generative artificial intelligence model, an emotion engine, edge computing technology, and a user interface.

[0138] First, terminals (IoT sensors) collect environmental data in real time at various locations within the building. This includes temperature, humidity, light levels, and occupancy status. The data from the sensors is periodically transmitted to a server.

[0139] The server performs initial processing on the received data, filtering out outliers and missing values. Next, it uses a generative artificial intelligence model to analyze the data and create an optimal energy usage plan. This plan includes user comfort and cost-effectiveness as factors to consider.

[0140] The server further utilizes a regulatory compliance AI module to verify that the energy use plan complies with current legal regulations. If necessary, it automatically modifies the plan.

[0141] The emotion engine recognizes the user's current emotional state and reflects this in the energy usage plan. It collects emotional data, such as the user's facial expressions and voice, from various input sources, and the server analyzes this data. For example, if the system determines that the user is relaxed, it adjusts the lighting to create a calmer atmosphere.

[0142] Users (facility operators) can view the energy usage plan presented by the server through a user interface. This interface allows users to manually modify the plan. For example, they can individually change specific lighting settings.

[0143] Once the final energy usage plan is determined, the server executes the plan and controls equipment via the building management system (BMS). This adjusts heating, cooling, and lighting, resulting in energy efficiency.

[0144] Furthermore, the servers utilize edge computing to process data on-site, ensuring rapid response times and high security. All processing logs and sentiment data are recorded and used to optimize future energy usage plans.

[0145] For example, if a resident is experiencing stress, the emotion engine detects this and adjusts the energy usage plan to play music and dim the lighting. In this way, personalized responses tailored to the user's emotions become possible.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The terminal (IoT sensor) measures environmental data such as temperature, humidity, light level, and occupancy status inside the building in real time and transmits the data to the server.

[0149] Step 2:

[0150] The server performs initial processing on the raw data it receives, detecting and correcting outliers and missing values. This maintains data consistency and accuracy.

[0151] Step 3:

[0152] The server inputs clean data into a generative artificial intelligence model for analysis and generates an energy usage plan. This plan includes optimal settings for heating, cooling, and lighting.

[0153] Step 4:

[0154] The server uses a regulatory compliance AI module to verify whether the energy use plan complies with current environmental regulations. If there are any non-compliances, the plan is automatically revised.

[0155] Step 5:

[0156] The terminal (emotion engine) recognizes the user's emotional state, sends that data to the server, and incorporates it into the energy usage plan. This recognition uses the user's facial expressions and voice data.

[0157] Step 6:

[0158] Users (facility operators) receive notifications of energy usage plans from the server and can review the plans through the user interface. They can manually modify the plans through the user interface as needed.

[0159] Step 7:

[0160] The server executes the final energy usage plan and sends instructions to the building management system (BMS) to control equipment such as heating, cooling, and lighting.

[0161] Step 8:

[0162] The server continuously monitors energy performance and sentiment data, and adjusts the plan in real time as needed. This result is stored in a database for future energy usage planning.

[0163] Step 9:

[0164] The server utilizes edge computing technology to perform data processing on-site, ensuring rapid system response and data security.

[0165] As a concrete example, when a user becomes relaxed, the emotion engine detects this, and the server adjusts the room lighting to a warmer tone and optimizes the heating and cooling settings to suit the user's comfort.

[0166] (Example 2)

[0167] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0168] Conventional energy management systems have the drawback of not being able to flexibly respond to environmental fluctuations or the emotional state of users. In particular, their lack of real-time capabilities made it difficult to comply with regulations, efficiently control equipment, and ensure user comfort, thus hindering the optimization of energy use.

[0169] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0170] In this invention, the server includes means for acquiring environmental information from a detector in real time, means for generating a usage plan based on a generative information processing model, and means for recognizing the user's emotional state and reflecting it in the usage plan. This enables rapid and adaptive energy management that is in line with environmental changes and the user's emotions.

[0171] "Environmental information" refers to physical variables such as temperature, humidity, light intensity, and occupancy status, and is data necessary for energy management within a building.

[0172] A "detector" is a device installed to measure and collect environmental information in real time, and IoT sensors are included in this category.

[0173] A "generative information processing model" is an information technology model used to perform complex data analysis and formulate energy use plans, and is characterized by machine learning algorithms.

[0174] A "utilization plan" is an optimal energy use strategy created based on collected environmental information and the results of analysis using generative information processing models.

[0175] "Laws and regulations" refer to the regulations and standards that must be followed in energy management, and include local rules and laws.

[0176] "Emotional state" refers to the user's current psychological state and is derived from data obtained through facial expression and voice analysis.

[0177] "Equipment control" refers to the operation of adjusting and managing energy equipment within a building based on usage plans.

[0178] "Distributed information processing technology" refers to a technology that processes a portion of the data at a location closer to the actual site, with the aim of improving response speed and strengthening security.

[0179] The real-time energy management system of the present invention is configured by combining multiple hardware and software components to achieve efficient energy use.

[0180] First, terminals (IoT sensors) are installed throughout the building to collect environmental information such as temperature, humidity, light intensity, and occupancy status in real time. This information is transmitted to a server via wireless communication. Specific sensors used include digital temperature sensors, humidity sensors, light sensors, and motion sensors.

[0181] The server performs initial processing of the received environmental information, detecting and removing outliers and missing values. Data cleaning software is used for this process. Subsequently, a generative AI model is used to generate an optimal usage plan based on the received data. The generated usage plan takes into account energy efficiency and user comfort. An example of a prompt message is, "Please suggest the optimal temperature setting based on the current environmental data."

[0182] Furthermore, the server checks whether the plan complies with the law by referencing regulatory information. If it does not comply with the law, the plan is automatically corrected. This enables energy management that meets legal standards. A software module for regulatory compliance supports this process.

[0183] Next, the emotion engine analyzes the user's emotional state from input devices such as cameras and microphones, and incorporates this into the usage plan. This analysis allows, for example, if the system determines that the user is relaxed, it can adjust the lighting to a softer color. This, in turn, improves the user's comfort.

[0184] Finally, users (facility operators) can review the energy usage plan generated by the server through the provided user interface. This interface works on PCs and tablets, and users can also manually modify the plan. Adjustments can be made to meet individual needs, such as pre-setting lighting for specific time periods.

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The terminals (IoT sensors) are installed throughout the building to acquire environmental information in real time. Input data includes temperature, humidity, light intensity, and occupancy status. This data is measured by the sensors and transmitted wirelessly to a server. Environmental information is collected continuously, requiring high-precision data collection.

[0188] Step 2:

[0189] The server performs initial processing of the received environmental information. It detects outliers and missing values ​​from the sensor data received as input and removes them through filtering. Data cleaning software is used here to remove and impute outliers. The output is a clean dataset suitable for analysis. This step improves the reliability of the analyzed data.

[0190] Step 3:

[0191] The server performs data analysis using a generative AI model based on clean data. It uses the cleaned dataset from the previous step as input and generates an optimal energy use plan based on that data. In this analysis, the prompt "Please suggest the optimal temperature setting based on the current environmental data" is sent to the generative AI model, and a specific usage plan is obtained as output. This plan prioritizes user comfort and energy efficiency.

[0192] Step 4:

[0193] The server uses a function to reference laws and regulations to verify that the generated usage plan complies with legal standards. The input is the generated energy usage plan, and the output is the final plan that complies with the law. Any parts that violate regulations are automatically corrected. Through this process, operation without legal risk is guaranteed.

[0194] Step 5:

[0195] The server analyzes the user's emotional state, which is captured by the emotion engine. Input data includes the user's facial expressions and voice information collected from cameras and microphones. This emotional data is analyzed, and the results are reflected in the energy usage plan. For example, if the server determines the user is relaxed, adjustments such as changing the lighting to a calmer tone are made. The output is an energy usage plan synchronized with the user's emotions.

[0196] Step 6:

[0197] The user (facility operator) reviews the energy usage plan created by the server through the user interface. The input here is the adjusted final usage plan, which the user can view on a monitor. Manual configuration changes are also possible as needed, allowing individual requests to be reflected in the configured plan. The output is the finalized energy usage plan.

[0198] Step 7:

[0199] Once the plan is finalized, the server controls the actual equipment through the building management system. The final usage plan to be implemented is used as input. The system controls equipment such as heating, cooling, and lighting, and outputs that optimize energy efficiency. This execution realizes real-world energy management.

[0200] (Application Example 2)

[0201] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0202] In autonomous vehicles, it is necessary to optimize the internal environment based on the emotional state of passengers to provide a comfortable travel experience. However, conventional vehicle management systems have difficulty adjusting the environment in real time to reflect the passenger's state, and improvements in comfort have not been fully achieved. Thus, a method is needed that enables efficient energy management while making appropriate environmental adjustments in response to passenger emotions.

[0203] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0204] In this invention, the server includes means for acquiring environmental information from detectors in real time, means for generating an energy usage plan based on a generative artificial intelligence model, and means for optimizing environmental conditions based on the emotional state of passengers. This makes it possible to create a comfortable in-vehicle environment that is tailored to the emotions of passengers while achieving efficient energy use.

[0205] "Environmental information" refers to information that includes multiple elements such as temperature, humidity, and light intensity, acquired in real time through detectors.

[0206] A "detector" is a device used to acquire environmental information, and this includes various types of sensors.

[0207] A "generative artificial intelligence model" is a programmatic method for analyzing acquired data and generating energy usage plans.

[0208] An "energy use plan" refers to pre-established guidelines and strategies for achieving efficient energy management.

[0209] "Passenger emotional state" refers to the psychological and emotional condition of the vehicle's users, and is usually determined from facial expressions and voice data.

[0210] "Environmental conditions" refers to the surrounding environment that passengers directly experience, including temperature, humidity, lighting, and music inside the vehicle.

[0211] A "management system" is a comprehensive system consisting of a series of devices and programs that automatically execute energy usage plans and adjust environmental conditions.

[0212] The system of this invention is realized by collecting environmental information from sensors in real time within buildings and vehicles. This environmental information includes elements such as temperature, humidity, and light intensity, and is acquired by sensors. The terminal transmits this data to a server, which then analyzes it using a generative artificial intelligence model. In this case, an AI model using TensorFlow analyzes the data and generates an optimal energy usage plan.

[0213] The server also uses cameras and microphones to collect facial expressions and voice data to determine the emotional state of passengers. This allows the system to adjust environmental conditions in real time to reflect the passengers' psychological state and improve their comfort. Specifically, it adjusts the lighting inside the vehicle and plays music based on the generated data.

[0214] Leveraging edge computing technology, this data processing is performed in real time at the site. This technology is highly effective in ensuring rapid response and high security. Furthermore, users can monitor energy usage plans provided by the server and manually modify the plans as needed. This operation is performed through a user interface, which is implemented using React Native.

[0215] As a concrete example, if the system detects a passenger's facial expression indicating stress, it will dim the interior lighting and use a generative AI model to select and play relaxing music. This allows passengers to have a more comfortable travel experience. A specific action scenario is set using a prompt such as, "If the passenger's emotion is classified as 'relaxed,' how should the in-car environment be changed?"

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The terminal collects environmental information in real time from sensors installed inside buildings and vehicles. The input consists of data from the sensors, including temperature, humidity, and light intensity. This input data is then transmitted directly to the server.

[0219] Step 2:

[0220] The server performs initial processing of the received environmental information. The input is raw data from sensors, and the output is filtered data. It improves data quality by detecting and filtering out abnormal or missing values.

[0221] Step 3:

[0222] The server analyzes filtered environmental data using a generative artificial intelligence model. The input is filtered environmental data, and the output is an energy usage plan. TensorFlow is used for data analysis and model-based predictions.

[0223] Step 4:

[0224] The server detects passengers' emotional states in real time via cameras and microphones. Inputs include facial expressions and voice data, and the output is the recognized emotional state. This processing is performed by an emotion recognition algorithm.

[0225] Step 5:

[0226] The server adjusts the in-car environmental conditions, taking into account the generated energy usage plan and the passengers' emotional states. The inputs are the energy usage plan and emotional state data, and the output is an optimized in-car environment setting. Specifically, this involves actions such as adjusting the brightness of the lighting and selecting and playing music.

[0227] Step 6:

[0228] The user reviews the energy usage plan provided by the server through a user interface and makes manual corrections as needed. The input is the generated energy usage plan, and the output is the corrected plan. This operation is performed through a React Native interface.

[0229] Step 7:

[0230] The server utilizes edge computing technology to perform all processing rapidly and securely on-site. The input is the entirety of the processing up to the previous step, and the output is the result of the data processing, executed quickly and securely. User and environment data are securely protected.

[0231] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0232] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0233] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0234] [Second Embodiment]

[0235] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0236] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0237] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0238] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0239] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0240] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0241] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0242] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0243] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0244] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0245] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0246] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0247] This invention is implemented as a system for optimizing energy use within a building in real time. This system includes IoT sensors, servers, generative artificial intelligence models, edge computing technology, and a user interface.

[0248] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental data such as temperature, humidity, light intensity, and occupancy status. This data is acquired at regular intervals and transmitted to a server.

[0249] The server performs initial processing on the received raw data. Here, outliers and missing values ​​are detected, and filtering is performed to ensure data accuracy. The clean data is then input into a generative artificial intelligence model. This AI model analyzes the large amount of collected environmental data and generates a specific energy use plan to optimize energy consumption.

[0250] The generated energy usage plan is verified to comply with the latest environmental regulations by referencing regulatory information. A regulatory compliance AI module is used for this verification. The plan is automatically adjusted as needed.

[0251] On the other hand, communication with users (facility operators) is also important. The server notifies users of the generated energy usage plan through a user interface. Users can use this interface to review the plan and make manual modifications as needed.

[0252] Once the energy usage plan is finalized, the server sends commands to the building management system (BMS) to control equipment such as heating, cooling, and lighting. This optimizes energy performance in real time.

[0253] Furthermore, the servers utilize edge computing technology to perform data processing on-site. This improves response speed while ensuring data privacy and security. All processing results and operation logs are recorded and used as reference for future plan generation.

[0254] As a concrete example, on a hot summer day, a sensor detects high temperatures, and an AI model optimizes the air conditioning temperature setting. The plan is adjusted to ensure that energy consumption does not exceed the permissible limit based on regulatory information. This allows facility operators to manage energy consumption comfortably and efficiently while complying with regulations.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The terminals (IoT sensors) measure and collect environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the building. This data is transmitted to a server at regular intervals.

[0258] Step 2:

[0259] The server performs initial processing on the raw data it receives. This processing includes detecting outliers and imputing missing values, as well as performing the necessary filtering to ensure data accuracy.

[0260] Step 3:

[0261] The server inputs clean environmental data into a generative artificial intelligence model, which performs data analysis and generates energy usage plans. The AI ​​then suggests appropriate temperature settings for heating and cooling, as well as planned lighting usage.

[0262] Step 4:

[0263] The server uses a regulatory compliance AI module to verify that the generated energy use plan complies with current environmental regulations. By comparing it with regulatory information, the plan is automatically modified if necessary.

[0264] Step 5:

[0265] Users (facility operators) receive energy usage plans from the server and can review them through a provided user interface. Users can also manually modify the plans using this interface.

[0266] Step 6:

[0267] After the server verifies the user, it sends commands to the building management system (BMS) to execute the energy usage plan, such as changing settings for heating, cooling, and lighting.

[0268] Step 7:

[0269] The server monitors energy performance in real time and adjusts energy usage plans as needed. Data processing is performed on-site using edge computing technology, enabling rapid response.

[0270] Step 8:

[0271] The server records all operation logs and performance data, saving them as feedback data to be used in generating future energy usage plans.

[0272] (Example 1)

[0273] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] Conventional energy management systems face challenges in achieving efficient real-time control because each step, such as collecting environmental information, detecting anomalies, and creating energy consumption plans, is performed individually. Furthermore, limitations in user flexibility for manual adjustments and the ability to respond immediately to environmental regulations are problematic. Additionally, centralized data processing presents challenges in response speed and ensuring privacy.

[0275] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0276] In this invention, the server includes means for continuously acquiring environmental information from a measuring device, means for processing the received information in an initial stage and detecting outliers and missing values, and means for creating an energy consumption plan based on a predictive model. This makes it possible to optimize energy efficiency in real time.

[0277] "Environmental information" refers to data related to the physical or chemical state such as temperature, humidity, light intensity, occupancy status, etc. within a building.

[0278] "Measurement device" refers to a group of sensors installed to acquire environmental information and is responsible for detecting changes in each element.

[0279] "Receiving" is a process in which the server acquires the data transmitted from the measurement device and takes it in a processable form.

[0280] "Processing at the initial stage" refers to the preprocessing of detecting abnormal values and complementing missing values to ensure the accuracy of the acquired data.

[0281] "Abnormal value" refers to an extreme value outside the normal range and indicates data that may indicate malfunction or abnormal situation of the sensor.

[0282] "Missing value" is a term that refers to the state where the data that should originally exist in the dataset is missing.

[0283] "Prediction model" refers to a machine learning algorithm for generating future energy consumption and optimized usage plans based on the collected environmental information.

[0284] "Energy consumption plan" indicates a specific policy for allocating and using energy resources in an efficient and regulatory-compliant manner.

[0285] "Facility management" is an activity that includes operations for automatically controlling air conditioning, lighting, and other building facilities to maximize energy efficiency.

[0286] "Response speed" refers to the time from when the system receives input information until it moves to action, and it is desirable to be fast.

[0287] "Privacy" indicates the state in which the data of individuals or enterprises is protected so that it does not leak outside or be used without permission.

[0288] This invention relates to an energy management system for optimizing energy use within a building in real time. The system includes IoT sensors as measuring devices, a server for data processing and management, and a user interface that provides an interface with the user.

[0289] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. This information is acquired at regular intervals and sent to the server as data packets.

[0290] The server processes the received information in an initial stage, detecting outliers and missing values. To this end, data cleaning techniques are used to identify outliers and impute missing values, improving data accuracy. Next, the clean data is input into a generating AI model to develop a specific energy use plan that optimizes energy consumption. This AI model learns from past data and generates an optimization plan suitable for future environmental conditions. An example of a prompt used in this process is: "Based on the current room temperature, humidity, light intensity, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption."

[0291] The generated energy use plan is evaluated by a regulatory compliance module to ensure it is consistent with environmental laws and energy regulations. This module automatically generates a regulatory-compliant use plan and makes any necessary adjustments.

[0292] Subsequently, the energy usage plan is notified to the user (facility operator). The user can use this interface to review the plan and make manual adjustments as needed. Once the final plan is confirmed, the server sends commands to the building's management system to control equipment such as heating, cooling, and lighting. This optimizes energy performance while maintaining comfort in each room.

[0293] Furthermore, the server utilizes edge computing technology to perform local data processing, improving response speed while ensuring data privacy and security. All process results and operation logs are recorded and used as reference for future planning.

[0294] For example, on a hot summer day, a sensor detects high temperatures, and an AI model suggests the optimal temperature setting for the air conditioner. At this time, the user could also slightly increase the light intensity for a specific event. In this way, it is possible to achieve comfortable and efficient energy management while complying with regulations.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The terminals (IoT sensors) are placed in each room of the building and continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. The input is raw data acquired from various sensors. The sensors collect data at regular intervals, convert the data into a digital format, and send it to the server. The output is data packets containing environmental information.

[0298] Step 2:

[0299] The server receives raw data transmitted from the measurement terminal. The input is data packets containing environmental information. The server performs initial processing on this data, such as anomaly detection and missing value imputation. Specifically, it identifies anomalies using statistical methods and imputes missing parts based on the mean or past data. The output is clean and highly accurate environmental information.

[0300] Step 3:

[0301] The server generates clean data and inputs it into the AI ​​model. The input is pre-processed environmental information data. This AI model uses machine learning algorithms to create an energy usage plan to optimize energy consumption from a large amount of data. Specifically, the AI ​​model analyzes environmental conditions and user usage patterns and performs predictions and optimizations using the prompt message "Based on the current room temperature, humidity, light level, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption." The output is the energy usage plan.

[0302] Step 4:

[0303] The server verifies the compliance of the generated energy use plan against environmental laws and energy regulations. The input is the energy use plan generated by the AI ​​model. The server utilizes a regulatory compliance module to verify that the plan meets all legal standards. If necessary, it automatically adjusts the plan. Specifically, it checks energy consumption limits and fine-tunes the plan. The output is the energy use plan that has been verified as compliant.

[0304] Step 5:

[0305] The user (facility operator) reviews the energy usage plan presented via the server through the user interface. The input is the energy usage plan that has been verified for suitability. The user can review the plan using the interface and manually adjust it as needed. Specifically, the user adjusts heating and cooling settings and lighting according to specific usage conditions. The output is the final energy usage plan approved or modified by the user.

[0306] Step 6:

[0307] The server sends instructions to the building management system (BMS) of the building based on the final energy usage plan and controls the facilities. The input is the final energy usage plan confirmed by the user. The server sends control signals to the heating, ventilation, and air conditioning (HVAC) equipment and lighting facilities to adjust the set temperature and light intensity. As a specific operation, it optimizes the energy usage of each room through automatic control. The output is the optimized energy performance.

[0308] Step 7:

[0309] The server utilizes edge computing technology to perform data processing locally. The input is the real-time data collected during the execution of the plan. The server processes this data to improve the response speed and protect the privacy and security of the data. The output is efficient data processing with ensured privacy and security. Also, all process results and operation logs are recorded for reference during the next planning.

[0310] (Application Example 1)

[0311] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] Energy consumption in a factory is very important for improving production efficiency and reducing costs. However, in many current systems, there is a problem that real-time control for adapting to environmental changes is not sufficiently performed, making efficient energy management difficult. Also, since the means for the user to modify the plan in real time are limited, delays may occur in scenarios where quick response is required.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0314] In this invention, the server includes means for acquiring environmental data from a detection device in real time, means for initial processing the received information and detecting abnormal values, means for generating a power utilization plan based on a generative artificial intelligence model, and means for presenting the power utilization plan through a personal electronic device that allows for on-site plan modification. This enables rapid and efficient energy management and real-time plan modification by the user.

[0315] "Environmental data" refers to information such as temperature, humidity, light intensity, and occupancy status that is acquired in real time using detection devices within buildings and facilities.

[0316] A "detection device" is a hardware device that uses various sensor technologies to acquire environmental data.

[0317] "Initial processing" refers to the process of detecting anomalies and cleaning data in acquired environmental data before input.

[0318] A "generative artificial intelligence model" is an artificial intelligence algorithm used to analyze large amounts of collected data and generate specific plans to optimize energy consumption.

[0319] A "power utilization plan" is an operational plan aimed at efficient energy consumption, built based on a generative artificial intelligence model.

[0320] "Regulatory information" refers to information that outlines various laws, regulations, and guidelines that restrict energy use.

[0321] "Personal electronic devices" refer to electronic devices that people carry and use on a daily basis, such as smartphones and visual display devices.

[0322] "Plan modification" refers to the act of manually changing the generated power utilization plan as needed.

[0323] Edge computing is a technology that performs data processing and analysis near the actual location, improving response speed while ensuring data privacy and security.

[0324] This system is designed to optimize energy efficiency within the factory. The system's design and operation are described in detail below.

[0325] First, multiple detection devices positioned as terminals continuously acquire environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the factory. This data is immediately transmitted to a server. The server first performs initial processing on the received information and then performs data cleaning to remove outliers in order to maintain data integrity.

[0326] Next, Python and TensorFlow will be used as the software for building the generative artificial intelligence model. The AI ​​model will analyze cleansed data and generate an efficient power utilization plan. This model has the flexibility to evaluate environmental changes in real time and adjust the plan as needed.

[0327] The generated power usage plan is presented to the user via their personal electronic device. The user can directly review the plan using a smartphone or visual display device and manually modify it as needed. This allows for more efficient and faster energy management.

[0328] By using edge computing techniques, data processing is performed closer to the site, resulting in improved response speed and enhanced data privacy. Furthermore, by integrating with the factory's building management system, power control based on the generated plan can be automated.

[0329] For example, on a hot summer day, the outside temperature rises, and sensors inside the factory detect this change. At this point, the AI ​​model adjusts the air conditioning temperature setting, achieving both efficient energy consumption and a comfortable working environment.

[0330] An example of a prompt message is, "The current temperature is over 30°C. Please suggest the optimal air conditioning settings to maintain a comfortable working environment while minimizing energy consumption." This prompt helps the AI ​​model achieve optimal energy use by providing specific instructions.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The terminal acquires environmental data such as temperature, humidity, light intensity, and occupancy status in real time from detection devices placed throughout the factory. This information is transmitted to a server via a communication network. The input is raw data from the detection devices, and the output is well-formed data sent to the server.

[0334] Step 2:

[0335] The server performs initial processing on the received data, including detecting outliers and cleaning the data. Specifically, it filters outliers and missing values ​​to ensure data integrity. In this step, raw data is used as input, and cleansed data is generated as output.

[0336] Step 3:

[0337] The server inputs cleansed data into a generative artificial intelligence model. The AI ​​model is built using Python and TensorFlow. The model analyzes large amounts of data and generates an efficient power utilization plan. The input is cleansed data, and the output is an optimized power utilization plan.

[0338] Step 4:

[0339] The server presents the generated power usage plan to the user via their personal electronic device. The user can review this plan using a smartphone or visual display device. The input for this step is an optimized plan, and the output is user-readable plan information.

[0340] Step 5:

[0341] The user can manually modify the plan as needed. User input is the instruction for manual adjustment, and output is the adjusted power utilization plan.

[0342] Step 6:

[0343] The server uses edge computing techniques to process data near the site. This improves response speed and maintains data privacy. The input for this step is energy adjustment information, and the output is control commands updated in real time.

[0344] Step 7:

[0345] The server integrates with the factory's building management system to automatically control power based on the generated plan. This ensures efficient energy consumption. The input is the adjusted plan, and the output is the automatic power control instruction.

[0346] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0347] This invention relates to a real-time energy management system that optimizes energy use within a building, incorporating an emotion engine. The system includes IoT sensors, a server, a generative artificial intelligence model, an emotion engine, edge computing technology, and a user interface.

[0348] First, terminals (IoT sensors) collect environmental data in real time at various locations within the building. This includes temperature, humidity, light levels, and occupancy status. The data from the sensors is periodically transmitted to a server.

[0349] The server performs initial processing on the received data, filtering out outliers and missing values. Next, it uses a generative artificial intelligence model to analyze the data and create an optimal energy usage plan. This plan includes user comfort and cost-effectiveness as factors to consider.

[0350] The server further utilizes a regulatory compliance AI module to verify that the energy use plan complies with current legal regulations. If necessary, it automatically modifies the plan.

[0351] The emotion engine recognizes the user's current emotional state and reflects this in the energy usage plan. It collects emotional data, such as the user's facial expressions and voice, from various input sources, and the server analyzes this data. For example, if the system determines that the user is relaxed, it adjusts the lighting to create a calmer atmosphere.

[0352] Users (facility operators) can view the energy usage plan presented by the server through a user interface. This interface allows users to manually modify the plan. For example, they can individually change specific lighting settings.

[0353] Once the final energy usage plan is determined, the server executes the plan and controls equipment via the building management system (BMS). This adjusts heating, cooling, and lighting, resulting in energy efficiency.

[0354] Furthermore, the servers utilize edge computing to process data on-site, ensuring rapid response times and high security. All processing logs and sentiment data are recorded and used to optimize future energy usage plans.

[0355] For example, if a resident is experiencing stress, the emotion engine detects this and adjusts the energy usage plan to play music and dim the lighting. In this way, personalized responses tailored to the user's emotions become possible.

[0356] The following describes the processing flow.

[0357] Step 1:

[0358] The terminal (IoT sensor) measures environmental data such as temperature, humidity, light level, and occupancy status inside the building in real time and transmits the data to the server.

[0359] Step 2:

[0360] The server performs initial processing on the raw data it receives, detecting and correcting outliers and missing values. This maintains data consistency and accuracy.

[0361] Step 3:

[0362] The server inputs clean data into a generative artificial intelligence model for analysis and generates an energy usage plan. This plan includes optimal settings for heating, cooling, and lighting.

[0363] Step 4:

[0364] The server uses a regulatory compliance AI module to verify whether the energy use plan complies with current environmental regulations. If there are any non-compliances, the plan is automatically revised.

[0365] Step 5:

[0366] The terminal (emotion engine) recognizes the user's emotional state, sends that data to the server, and incorporates it into the energy usage plan. This recognition uses the user's facial expressions and voice data.

[0367] Step 6:

[0368] Users (facility operators) receive notifications of energy usage plans from the server and can review the plans through the user interface. They can manually modify the plans through the user interface as needed.

[0369] Step 7:

[0370] The server executes the final energy usage plan and sends instructions to the building management system (BMS) to control equipment such as heating, cooling, and lighting.

[0371] Step 8:

[0372] The server continuously monitors energy performance and sentiment data, and adjusts the plan in real time as needed. This result is stored in a database for future energy usage planning.

[0373] Step 9:

[0374] The server utilizes edge computing technology to perform data processing on-site, ensuring rapid system response and data security.

[0375] As a concrete example, when a user becomes relaxed, the emotion engine detects this, and the server adjusts the room lighting to a warmer tone and optimizes the heating and cooling settings to suit the user's comfort.

[0376] (Example 2)

[0377] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0378] Conventional energy management systems have the drawback of not being able to flexibly respond to environmental fluctuations or the emotional state of users. In particular, their lack of real-time capabilities made it difficult to comply with regulations, efficiently control equipment, and ensure user comfort, thus hindering the optimization of energy use.

[0379] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0380] In this invention, the server includes means for acquiring environmental information from a detector in real time, means for generating a usage plan based on a generative information processing model, and means for recognizing the user's emotional state and reflecting it in the usage plan. This enables rapid and adaptive energy management that is in line with environmental changes and the user's emotions.

[0381] "Environmental information" refers to physical variables such as temperature, humidity, light intensity, and occupancy status, and is data necessary for energy management within a building.

[0382] A "detector" is a device installed to measure and collect environmental information in real time, and IoT sensors are included in this category.

[0383] A "generative information processing model" is an information technology model used to perform complex data analysis and formulate energy use plans, and is characterized by machine learning algorithms.

[0384] A "utilization plan" is an optimal energy use strategy created based on collected environmental information and the results of analysis using generative information processing models.

[0385] "Laws and regulations" refer to the regulations and standards that must be followed in energy management, and include local rules and laws.

[0386] "Emotional state" refers to the user's current psychological state and is derived from data obtained through facial expression and voice analysis.

[0387] "Equipment control" refers to the operation of adjusting and managing energy equipment within a building based on usage plans.

[0388] "Distributed information processing technology" refers to a technology that processes a portion of the data at a location closer to the actual site, with the aim of improving response speed and strengthening security.

[0389] The real-time energy management system of the present invention is configured by combining multiple hardware and software components to achieve efficient energy use.

[0390] First, terminals (IoT sensors) are installed throughout the building to collect environmental information such as temperature, humidity, light intensity, and occupancy status in real time. This information is transmitted to a server via wireless communication. Specific sensors used include digital temperature sensors, humidity sensors, light sensors, and motion sensors.

[0391] The server performs initial processing of the received environmental information, detecting and removing outliers and missing values. Data cleaning software is used for this process. Subsequently, a generative AI model is used to generate an optimal usage plan based on the received data. The generated usage plan takes into account energy efficiency and user comfort. An example of a prompt message is, "Please suggest the optimal temperature setting based on the current environmental data."

[0392] Furthermore, the server checks whether the plan complies with the law by referencing regulatory information. If it does not comply with the law, the plan is automatically corrected. This enables energy management that meets legal standards. A software module for regulatory compliance supports this process.

[0393] Next, the emotion engine analyzes the user's emotional state from input devices such as cameras and microphones, and incorporates this into the usage plan. This analysis allows, for example, if the system determines that the user is relaxed, it can adjust the lighting to a softer color. This, in turn, improves the user's comfort.

[0394] Finally, users (facility operators) can review the energy usage plan generated by the server through the provided user interface. This interface works on PCs and tablets, and users can also manually modify the plan. Adjustments can be made to meet individual needs, such as pre-setting lighting for specific time periods.

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] The terminals (IoT sensors) are installed throughout the building to acquire environmental information in real time. Input data includes temperature, humidity, light intensity, and occupancy status. This data is measured by the sensors and transmitted wirelessly to a server. Environmental information is collected continuously, requiring high-precision data collection.

[0398] Step 2:

[0399] The server performs initial processing of the received environmental information. It detects outliers and missing values ​​from the sensor data received as input and removes them through filtering. Data cleaning software is used here to remove and impute outliers. The output is a clean dataset suitable for analysis. This step improves the reliability of the analyzed data.

[0400] Step 3:

[0401] The server performs data analysis using a generative AI model based on clean data. It uses the cleaned dataset from the previous step as input and generates an optimal energy use plan based on that data. In this analysis, the prompt "Please suggest the optimal temperature setting based on the current environmental data" is sent to the generative AI model, and a specific usage plan is obtained as output. This plan prioritizes user comfort and energy efficiency.

[0402] Step 4:

[0403] The server uses a function to reference laws and regulations to verify that the generated usage plan complies with legal standards. The input is the generated energy usage plan, and the output is the final plan that complies with the law. Any parts that violate regulations are automatically corrected. Through this process, operation without legal risk is guaranteed.

[0404] Step 5:

[0405] The server analyzes the user's emotional state, which is captured by the emotion engine. Input data includes the user's facial expressions and voice information collected from cameras and microphones. This emotional data is analyzed, and the results are reflected in the energy usage plan. For example, if the server determines the user is relaxed, adjustments such as changing the lighting to a calmer tone are made. The output is an energy usage plan synchronized with the user's emotions.

[0406] Step 6:

[0407] The user (facility operator) reviews the energy usage plan created by the server through the user interface. The input here is the adjusted final usage plan, which the user can view on a monitor. Manual configuration changes are also possible as needed, allowing individual requests to be reflected in the configured plan. The output is the finalized energy usage plan.

[0408] Step 7:

[0409] Once the plan is finalized, the server controls the actual equipment through the building management system. The final usage plan to be implemented is used as input. The system controls equipment such as heating, cooling, and lighting, and outputs that optimize energy efficiency. This execution realizes real-world energy management.

[0410] (Application Example 2)

[0411] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0412] In autonomous vehicles, it is necessary to optimize the internal environment based on the emotional state of passengers to provide a comfortable travel experience. However, conventional vehicle management systems have difficulty adjusting the environment in real time to reflect the passenger's state, and improvements in comfort have not been fully achieved. Thus, a method is needed that enables efficient energy management while making appropriate environmental adjustments in response to passenger emotions.

[0413] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0414] In this invention, the server includes means for acquiring environmental information from detectors in real time, means for generating an energy usage plan based on a generative artificial intelligence model, and means for optimizing environmental conditions based on the emotional state of passengers. This makes it possible to create a comfortable in-vehicle environment that is tailored to the emotions of passengers while achieving efficient energy use.

[0415] "Environmental information" refers to information that includes multiple elements such as temperature, humidity, and light intensity, acquired in real time through detectors.

[0416] A "detector" is a device used to acquire environmental information, and this includes various types of sensors.

[0417] A "generative artificial intelligence model" is a programmatic method for analyzing acquired data and generating energy usage plans.

[0418] An "energy use plan" refers to pre-established guidelines and strategies for achieving efficient energy management.

[0419] "Passenger emotional state" refers to the psychological and emotional condition of the vehicle's users, and is usually determined from facial expressions and voice data.

[0420] "Environmental conditions" refers to the surrounding environment that passengers directly experience, including temperature, humidity, lighting, and music inside the vehicle.

[0421] A "management system" is a comprehensive system consisting of a series of devices and programs that automatically execute energy usage plans and adjust environmental conditions.

[0422] The system of this invention is realized by collecting environmental information from sensors in real time within buildings and vehicles. This environmental information includes elements such as temperature, humidity, and light intensity, and is acquired by sensors. The terminal transmits this data to a server, which then analyzes it using a generative artificial intelligence model. In this case, an AI model using TensorFlow analyzes the data and generates an optimal energy usage plan.

[0423] The server also uses cameras and microphones to collect facial expressions and voice data to determine the emotional state of passengers. This allows the system to adjust environmental conditions in real time to reflect the passengers' psychological state and improve their comfort. Specifically, it adjusts the lighting inside the vehicle and plays music based on the generated data.

[0424] Leveraging edge computing technology, this data processing is performed in real time at the site. This technology is highly effective in ensuring rapid response and high security. Furthermore, users can monitor energy usage plans provided by the server and manually modify the plans as needed. This operation is performed through a user interface, which is implemented using React Native.

[0425] As a concrete example, if the system detects a passenger's facial expression indicating stress, it will dim the interior lighting and use a generative AI model to select and play relaxing music. This allows passengers to have a more comfortable travel experience. A specific action scenario is set using a prompt such as, "If the passenger's emotion is classified as 'relaxed,' how should the in-car environment be changed?"

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The terminal collects environmental information in real time from sensors installed inside buildings and vehicles. The input consists of data from the sensors, including temperature, humidity, and light intensity. This input data is then transmitted directly to the server.

[0429] Step 2:

[0430] The server performs initial processing of the received environmental information. The input is raw data from sensors, and the output is filtered data. It improves data quality by detecting and filtering out abnormal or missing values.

[0431] Step 3:

[0432] The server analyzes filtered environmental data using a generative artificial intelligence model. The input is filtered environmental data, and the output is an energy usage plan. TensorFlow is used for data analysis and model-based predictions.

[0433] Step 4:

[0434] The server detects passengers' emotional states in real time via cameras and microphones. Inputs include facial expressions and voice data, and the output is the recognized emotional state. This processing is performed by an emotion recognition algorithm.

[0435] Step 5:

[0436] The server adjusts the in-car environmental conditions, taking into account the generated energy usage plan and the passengers' emotional states. The inputs are the energy usage plan and emotional state data, and the output is an optimized in-car environment setting. Specifically, this involves actions such as adjusting the brightness of the lighting and selecting and playing music.

[0437] Step 6:

[0438] The user reviews the energy usage plan provided by the server through a user interface and makes manual corrections as needed. The input is the generated energy usage plan, and the output is the corrected plan. This operation is performed through a React Native interface.

[0439] Step 7:

[0440] The server utilizes edge computing technology to perform all processing rapidly and securely on-site. The input is the entirety of the processing up to the previous step, and the output is the result of the data processing, executed quickly and securely. User and environment data are securely protected.

[0441] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0442] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0447] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0449] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0451] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0452] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0453] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0454] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0456] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0457] This invention is implemented as a system for optimizing energy use within a building in real time. This system includes IoT sensors, servers, generative artificial intelligence models, edge computing technology, and a user interface.

[0458] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental data such as temperature, humidity, light intensity, and occupancy status. This data is acquired at regular intervals and transmitted to a server.

[0459] The server performs initial processing on the received raw data. Here, outliers and missing values ​​are detected, and filtering is performed to ensure data accuracy. The clean data is then input into a generative artificial intelligence model. This AI model analyzes the large amount of collected environmental data and generates a specific energy use plan to optimize energy consumption.

[0460] The generated energy usage plan is verified to comply with the latest environmental regulations by referencing regulatory information. A regulatory compliance AI module is used for this verification. The plan is automatically adjusted as needed.

[0461] On the other hand, communication with users (facility operators) is also important. The server notifies users of the generated energy usage plan through a user interface. Users can use this interface to review the plan and make manual modifications as needed.

[0462] Once the energy usage plan is finalized, the server sends commands to the building management system (BMS) to control equipment such as heating, cooling, and lighting. This optimizes energy performance in real time.

[0463] Furthermore, the servers utilize edge computing technology to perform data processing on-site. This improves response speed while ensuring data privacy and security. All processing results and operation logs are recorded and used as reference for future plan generation.

[0464] As a concrete example, on a hot summer day, a sensor detects high temperatures, and an AI model optimizes the air conditioning temperature setting. The plan is adjusted to ensure that energy consumption does not exceed the permissible limit based on regulatory information. This allows facility operators to manage energy consumption comfortably and efficiently while complying with regulations.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The terminals (IoT sensors) measure and collect environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the building. This data is transmitted to a server at regular intervals.

[0468] Step 2:

[0469] The server performs initial processing on the raw data it receives. This processing includes detecting outliers and imputing missing values, as well as performing the necessary filtering to ensure data accuracy.

[0470] Step 3:

[0471] The server inputs clean environmental data into a generative artificial intelligence model, which performs data analysis and generates energy usage plans. The AI ​​then suggests appropriate temperature settings for heating and cooling, as well as planned lighting usage.

[0472] Step 4:

[0473] The server uses a regulatory compliance AI module to verify that the generated energy use plan complies with current environmental regulations. By comparing it with regulatory information, the plan is automatically modified if necessary.

[0474] Step 5:

[0475] Users (facility operators) receive energy usage plans from the server and can review them through a provided user interface. Users can also manually modify the plans using this interface.

[0476] Step 6:

[0477] After the server verifies the user, it sends commands to the building management system (BMS) to execute the energy usage plan, such as changing settings for heating, cooling, and lighting.

[0478] Step 7:

[0479] The server monitors energy performance in real time and adjusts energy usage plans as needed. Data processing is performed on-site using edge computing technology, enabling rapid response.

[0480] Step 8:

[0481] The server records all operation logs and performance data, saving them as feedback data to be used in generating future energy usage plans.

[0482] (Example 1)

[0483] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0484] Conventional energy management systems face challenges in achieving efficient real-time control because each step, such as collecting environmental information, detecting anomalies, and creating energy consumption plans, is performed individually. Furthermore, limitations in user flexibility for manual adjustments and the ability to respond immediately to environmental regulations are problematic. Additionally, centralized data processing presents challenges in response speed and ensuring privacy.

[0485] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0486] In this invention, the server includes means for continuously acquiring environmental information from a measuring device, means for processing the received information in an initial stage and detecting outliers and missing values, and means for creating an energy consumption plan based on a predictive model. This makes it possible to optimize energy efficiency in real time.

[0487] "Environmental information" refers to data on the physical or chemical conditions inside a building, such as temperature, humidity, light levels, and occupancy status.

[0488] A "measuring device" refers to a group of sensors installed to acquire environmental information, and each sensor plays a role in detecting changes in its respective element.

[0489] "Reception" refers to the process by which a server acquires data transmitted from a measuring device and incorporates it in a processable format.

[0490] "Initial processing" refers to pre-processing that detects outliers and imputes missing values ​​to ensure the accuracy of the acquired data.

[0491] An "outlier" refers to an extreme value that falls outside the normal range and may indicate a sensor malfunction or an abnormal situation.

[0492] "Missing values" refer to a state in a dataset where data that should be present is missing.

[0493] A "predictive model" refers to a machine learning algorithm that generates future energy consumption forecasts and optimized usage plans based on collected environmental information.

[0494] An "energy consumption plan" outlines specific guidelines for allocating and using energy resources in an efficient and regulated manner.

[0495] "Facilities management" refers to activities that include the automatic control of air conditioning, lighting, and other building facilities, and operations aimed at maximizing energy efficiency.

[0496] "Response speed" refers to the time it takes for a system to take action after receiving input information, and it is desirable for it to be fast.

[0497] "Privacy" refers to a state in which the data of individuals and businesses is protected from being leaked to external parties or used without their consent.

[0498] This invention relates to an energy management system for optimizing energy use within a building in real time. The system includes IoT sensors as measuring devices, a server for data processing and management, and a user interface that provides an interface with the user.

[0499] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. This information is acquired at regular intervals and sent to the server as data packets.

[0500] The server processes the received information in an initial stage, detecting outliers and missing values. To this end, data cleaning techniques are used to identify outliers and impute missing values, improving data accuracy. Next, the clean data is input into a generating AI model to develop a specific energy use plan that optimizes energy consumption. This AI model learns from past data and generates an optimization plan suitable for future environmental conditions. An example of a prompt used in this process is: "Based on the current room temperature, humidity, light intensity, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption."

[0501] The generated energy use plan is evaluated by a regulatory compliance module to ensure it is consistent with environmental laws and energy regulations. This module automatically generates a regulatory-compliant use plan and makes any necessary adjustments.

[0502] Subsequently, the energy usage plan is notified to the user (facility operator). The user can use this interface to review the plan and make manual adjustments as needed. Once the final plan is confirmed, the server sends commands to the building's management system to control equipment such as heating, cooling, and lighting. This optimizes energy performance while maintaining comfort in each room.

[0503] Furthermore, the server utilizes edge computing technology to perform local data processing, improving response speed while ensuring data privacy and security. All process results and operation logs are recorded and used as reference for future planning.

[0504] For example, on a hot summer day, a sensor detects high temperatures, and an AI model suggests the optimal temperature setting for the air conditioner. At this time, the user could also slightly increase the light intensity for a specific event. In this way, it is possible to achieve comfortable and efficient energy management while complying with regulations.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The terminals (IoT sensors) are placed in each room of the building and continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. The input is raw data acquired from various sensors. The sensors collect data at regular intervals, convert the data into a digital format, and send it to the server. The output is data packets containing environmental information.

[0508] Step 2:

[0509] The server receives raw data transmitted from the measurement terminal. The input is data packets containing environmental information. The server performs initial processing on this data, such as anomaly detection and missing value imputation. Specifically, it identifies anomalies using statistical methods and imputes missing parts based on the mean or past data. The output is clean and highly accurate environmental information.

[0510] Step 3:

[0511] The server generates clean data and inputs it into the AI ​​model. The input is pre-processed environmental information data. This AI model uses machine learning algorithms to create an energy usage plan to optimize energy consumption from a large amount of data. Specifically, the AI ​​model analyzes environmental conditions and user usage patterns and performs predictions and optimizations using the prompt message "Based on the current room temperature, humidity, light level, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption." The output is the energy usage plan.

[0512] Step 4:

[0513] The server verifies the compliance of the generated energy use plan against environmental laws and energy regulations. The input is the energy use plan generated by the AI ​​model. The server utilizes a regulatory compliance module to verify that the plan meets all legal standards. If necessary, it automatically adjusts the plan. Specifically, it checks energy consumption limits and fine-tunes the plan. The output is the energy use plan that has been verified as compliant.

[0514] Step 5:

[0515] The user (facility operator) reviews the energy usage plan presented via the server through the user interface. The input is the energy usage plan that has been verified for suitability. The user can review the plan using the interface and manually adjust it as needed. Specifically, the user adjusts heating and cooling settings and lighting according to specific usage conditions. The output is the final energy usage plan approved or modified by the user.

[0516] Step 6:

[0517] The server sends instructions to the building management system (BMS) based on the final energy use plan, controlling the equipment. The input is the final energy use plan confirmed by the user. The server sends control signals to heating and cooling systems and lighting equipment, adjusting the set temperature and light intensity. Specifically, it optimizes energy use in each room through automatic control. The output is the optimized energy performance.

[0518] Step 7:

[0519] The server utilizes edge computing technology to perform data processing on-site. The input is real-time data collected during the execution of the plan. The server processes this data to improve response speed while protecting data privacy and security. The output is efficient data processing while ensuring privacy and security. All process results and operation logs are also recorded for reference in future planning.

[0520] (Application Example 1)

[0521] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0522] Energy consumption within factories is crucial for improving production efficiency and reducing costs. However, many current systems lack sufficient real-time control to adapt to environmental changes, making efficient energy management difficult. Furthermore, limited means for users to modify plans in real time can lead to delays in situations requiring rapid response.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0524] In this invention, the server includes means for acquiring environmental data from a detection device in real time, means for initial processing the received information and detecting abnormal values, means for generating a power utilization plan based on a generative artificial intelligence model, and means for presenting the power utilization plan through a personal electronic device that allows for on-site plan modification. This enables rapid and efficient energy management and real-time plan modification by the user.

[0525] "Environmental data" refers to information such as temperature, humidity, light intensity, and occupancy status that is acquired in real time using detection devices within buildings and facilities.

[0526] A "detection device" is a hardware device that uses various sensor technologies to acquire environmental data.

[0527] "Initial processing" refers to the process of detecting anomalies and cleaning data in acquired environmental data before input.

[0528] A "generative artificial intelligence model" is an artificial intelligence algorithm used to analyze large amounts of collected data and generate specific plans to optimize energy consumption.

[0529] A "power utilization plan" is an operational plan aimed at efficient energy consumption, built based on a generative artificial intelligence model.

[0530] "Regulatory information" refers to information that outlines various laws, regulations, and guidelines that restrict energy use.

[0531] "Personal electronic devices" refer to electronic devices that people carry and use on a daily basis, such as smartphones and visual display devices.

[0532] "Plan modification" refers to the act of manually changing the generated power utilization plan as needed.

[0533] Edge computing is a technology that performs data processing and analysis near the actual location, improving response speed while ensuring data privacy and security.

[0534] This system is designed to optimize energy efficiency within the factory. The system's design and operation are described in detail below.

[0535] First, multiple detection devices positioned as terminals continuously acquire environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the factory. This data is immediately transmitted to a server. The server first performs initial processing on the received information and then performs data cleaning to remove outliers in order to maintain data integrity.

[0536] Next, Python and TensorFlow will be used as the software for building the generative artificial intelligence model. The AI ​​model will analyze cleansed data and generate an efficient power utilization plan. This model has the flexibility to evaluate environmental changes in real time and adjust the plan as needed.

[0537] The generated power usage plan is presented to the user via their personal electronic device. The user can directly review the plan using a smartphone or visual display device and manually modify it as needed. This allows for more efficient and faster energy management.

[0538] By using edge computing techniques, data processing is performed closer to the site, resulting in improved response speed and enhanced data privacy. Furthermore, by integrating with the factory's building management system, power control based on the generated plan can be automated.

[0539] For example, on a hot summer day, the outside temperature rises, and sensors inside the factory detect this change. At this point, the AI ​​model adjusts the air conditioning temperature setting, achieving both efficient energy consumption and a comfortable working environment.

[0540] An example of a prompt message is, "The current temperature is over 30°C. Please suggest the optimal air conditioning settings to maintain a comfortable working environment while minimizing energy consumption." This prompt helps the AI ​​model achieve optimal energy use by providing specific instructions.

[0541] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0542] Step 1:

[0543] The terminal acquires environmental data such as temperature, humidity, light intensity, and occupancy status in real time from detection devices placed throughout the factory. This information is transmitted to a server via a communication network. The input is raw data from the detection devices, and the output is well-formed data sent to the server.

[0544] Step 2:

[0545] The server performs initial processing on the received data, including detecting outliers and cleaning the data. Specifically, it filters outliers and missing values ​​to ensure data integrity. In this step, raw data is used as input, and cleansed data is generated as output.

[0546] Step 3:

[0547] The server inputs cleansed data into a generative artificial intelligence model. The AI ​​model is built using Python and TensorFlow. The model analyzes large amounts of data and generates an efficient power utilization plan. The input is cleansed data, and the output is an optimized power utilization plan.

[0548] Step 4:

[0549] The server presents the generated power usage plan to the user via their personal electronic device. The user can review this plan using a smartphone or visual display device. The input for this step is an optimized plan, and the output is user-readable plan information.

[0550] Step 5:

[0551] The user can manually modify the plan as needed. User input is the instruction for manual adjustment, and output is the adjusted power utilization plan.

[0552] Step 6:

[0553] The server uses edge computing techniques to process data near the site. This improves response speed and maintains data privacy. The input for this step is energy adjustment information, and the output is control commands updated in real time.

[0554] Step 7:

[0555] The server integrates with the factory's building management system to automatically control power based on the generated plan. This ensures efficient energy consumption. The input is the adjusted plan, and the output is the automatic power control instruction.

[0556] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0557] This invention relates to a real-time energy management system that optimizes energy use within a building, incorporating an emotion engine. The system includes IoT sensors, a server, a generative artificial intelligence model, an emotion engine, edge computing technology, and a user interface.

[0558] First, terminals (IoT sensors) collect environmental data in real time at various locations within the building. This includes temperature, humidity, light levels, and occupancy status. The data from the sensors is periodically transmitted to a server.

[0559] The server performs initial processing on the received data, filtering out outliers and missing values. Next, it uses a generative artificial intelligence model to analyze the data and create an optimal energy usage plan. This plan includes user comfort and cost-effectiveness as factors to consider.

[0560] The server further utilizes a regulatory compliance AI module to verify that the energy use plan complies with current legal regulations. If necessary, it automatically modifies the plan.

[0561] The emotion engine recognizes the user's current emotional state and reflects this in the energy usage plan. It collects emotional data, such as the user's facial expressions and voice, from various input sources, and the server analyzes this data. For example, if the system determines that the user is relaxed, it adjusts the lighting to create a calmer atmosphere.

[0562] Users (facility operators) can view the energy usage plan presented by the server through a user interface. This interface allows users to manually modify the plan. For example, they can individually change specific lighting settings.

[0563] Once the final energy usage plan is determined, the server executes the plan and controls equipment via the building management system (BMS). This adjusts heating, cooling, and lighting, resulting in energy efficiency.

[0564] Furthermore, the servers utilize edge computing to process data on-site, ensuring rapid response times and high security. All processing logs and sentiment data are recorded and used to optimize future energy usage plans.

[0565] For example, if a resident is experiencing stress, the emotion engine detects this and adjusts the energy usage plan to play music and dim the lighting. In this way, personalized responses tailored to the user's emotions become possible.

[0566] The following describes the processing flow.

[0567] Step 1:

[0568] The terminal (IoT sensor) measures environmental data such as temperature, humidity, light level, and occupancy status inside the building in real time and transmits the data to the server.

[0569] Step 2:

[0570] The server performs initial processing on the raw data it receives, detecting and correcting outliers and missing values. This maintains data consistency and accuracy.

[0571] Step 3:

[0572] The server inputs clean data into a generative artificial intelligence model for analysis and generates an energy usage plan. This plan includes optimal settings for heating, cooling, and lighting.

[0573] Step 4:

[0574] The server uses a regulatory compliance AI module to verify whether the energy use plan complies with current environmental regulations. If there are any non-compliances, the plan is automatically revised.

[0575] Step 5:

[0576] The terminal (emotion engine) recognizes the user's emotional state, sends that data to the server, and incorporates it into the energy usage plan. This recognition uses the user's facial expressions and voice data.

[0577] Step 6:

[0578] Users (facility operators) receive notifications of energy usage plans from the server and can review the plans through the user interface. They can manually modify the plans through the user interface as needed.

[0579] Step 7:

[0580] The server executes the final energy usage plan and sends instructions to the building management system (BMS) to control equipment such as heating, cooling, and lighting.

[0581] Step 8:

[0582] The server continuously monitors energy performance and sentiment data, and adjusts the plan in real time as needed. This result is stored in a database for future energy usage planning.

[0583] Step 9:

[0584] The server utilizes edge computing technology to perform data processing on-site, ensuring rapid system response and data security.

[0585] As a concrete example, when a user becomes relaxed, the emotion engine detects this, and the server adjusts the room lighting to a warmer tone and optimizes the heating and cooling settings to suit the user's comfort.

[0586] (Example 2)

[0587] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0588] Conventional energy management systems have the drawback of not being able to flexibly respond to environmental fluctuations or the emotional state of users. In particular, their lack of real-time capabilities made it difficult to comply with regulations, efficiently control equipment, and ensure user comfort, thus hindering the optimization of energy use.

[0589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0590] In this invention, the server includes means for acquiring environmental information from a detector in real time, means for generating a usage plan based on a generative information processing model, and means for recognizing the user's emotional state and reflecting it in the usage plan. This enables rapid and adaptive energy management that is in line with environmental changes and the user's emotions.

[0591] "Environmental information" refers to physical variables such as temperature, humidity, light intensity, and occupancy status, and is data necessary for energy management within a building.

[0592] A "detector" is a device installed to measure and collect environmental information in real time, and IoT sensors are included in this category.

[0593] A "generative information processing model" is an information technology model used to perform complex data analysis and formulate energy use plans, and is characterized by machine learning algorithms.

[0594] A "utilization plan" is an optimal energy use strategy created based on collected environmental information and the results of analysis using generative information processing models.

[0595] "Laws and regulations" refer to the regulations and standards that must be followed in energy management, and include local rules and laws.

[0596] "Emotional state" refers to the user's current psychological state and is derived from data obtained through facial expression and voice analysis.

[0597] "Equipment control" refers to the operation of adjusting and managing energy equipment within a building based on usage plans.

[0598] "Distributed information processing technology" refers to a technology that processes a portion of the data at a location closer to the actual site, with the aim of improving response speed and strengthening security.

[0599] The real-time energy management system of the present invention is configured by combining multiple hardware and software components to achieve efficient energy use.

[0600] First, terminals (IoT sensors) are installed throughout the building to collect environmental information such as temperature, humidity, light intensity, and occupancy status in real time. This information is transmitted to a server via wireless communication. Specific sensors used include digital temperature sensors, humidity sensors, light sensors, and motion sensors.

[0601] The server performs initial processing of the received environmental information, detecting and removing outliers and missing values. Data cleaning software is used for this process. Subsequently, a generative AI model is used to generate an optimal usage plan based on the received data. The generated usage plan takes into account energy efficiency and user comfort. An example of a prompt message is, "Please suggest the optimal temperature setting based on the current environmental data."

[0602] Furthermore, the server checks whether the plan complies with the law by referencing regulatory information. If it does not comply with the law, the plan is automatically corrected. This enables energy management that meets legal standards. A software module for regulatory compliance supports this process.

[0603] Next, the emotion engine analyzes the user's emotional state from input devices such as cameras and microphones, and incorporates this into the usage plan. This analysis allows, for example, if the system determines that the user is relaxed, it can adjust the lighting to a softer color. This, in turn, improves the user's comfort.

[0604] Finally, users (facility operators) can review the energy usage plan generated by the server through the provided user interface. This interface works on PCs and tablets, and users can also manually modify the plan. Adjustments can be made to meet individual needs, such as pre-setting lighting for specific time periods.

[0605] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0606] Step 1:

[0607] The terminals (IoT sensors) are installed throughout the building to acquire environmental information in real time. Input data includes temperature, humidity, light intensity, and occupancy status. This data is measured by the sensors and transmitted wirelessly to a server. Environmental information is collected continuously, requiring high-precision data collection.

[0608] Step 2:

[0609] The server performs initial processing of the received environmental information. It detects outliers and missing values ​​from the sensor data received as input and removes them through filtering. Data cleaning software is used here to remove and impute outliers. The output is a clean dataset suitable for analysis. This step improves the reliability of the analyzed data.

[0610] Step 3:

[0611] The server performs data analysis using a generative AI model based on clean data. It uses the cleaned dataset from the previous step as input and generates an optimal energy use plan based on that data. In this analysis, the prompt "Please suggest the optimal temperature setting based on the current environmental data" is sent to the generative AI model, and a specific usage plan is obtained as output. This plan prioritizes user comfort and energy efficiency.

[0612] Step 4:

[0613] The server uses a function to reference laws and regulations to verify that the generated usage plan complies with legal standards. The input is the generated energy usage plan, and the output is the final plan that complies with the law. Any parts that violate regulations are automatically corrected. Through this process, operation without legal risk is guaranteed.

[0614] Step 5:

[0615] The server analyzes the user's emotional state, which is captured by the emotion engine. Input data includes the user's facial expressions and voice information collected from cameras and microphones. This emotional data is analyzed, and the results are reflected in the energy usage plan. For example, if the server determines the user is relaxed, adjustments such as changing the lighting to a calmer tone are made. The output is an energy usage plan synchronized with the user's emotions.

[0616] Step 6:

[0617] The user (facility operator) reviews the energy usage plan created by the server through the user interface. The input here is the adjusted final usage plan, which the user can view on a monitor. Manual configuration changes are also possible as needed, allowing individual requests to be reflected in the configured plan. The output is the finalized energy usage plan.

[0618] Step 7:

[0619] Once the plan is finalized, the server controls the actual equipment through the building management system. The final usage plan to be implemented is used as input. The system controls equipment such as heating, cooling, and lighting, and outputs that optimize energy efficiency. This execution realizes real-world energy management.

[0620] (Application Example 2)

[0621] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0622] In autonomous vehicles, it is necessary to optimize the internal environment based on the emotional state of passengers to provide a comfortable travel experience. However, conventional vehicle management systems have difficulty adjusting the environment in real time to reflect the passenger's state, and improvements in comfort have not been fully achieved. Thus, a method is needed that enables efficient energy management while making appropriate environmental adjustments in response to passenger emotions.

[0623] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0624] In this invention, the server includes means for acquiring environmental information from detectors in real time, means for generating an energy usage plan based on a generative artificial intelligence model, and means for optimizing environmental conditions based on the emotional state of passengers. This makes it possible to create a comfortable in-vehicle environment that is tailored to the emotions of passengers while achieving efficient energy use.

[0625] "Environmental information" refers to information that includes multiple elements such as temperature, humidity, and light intensity, acquired in real time through detectors.

[0626] A "detector" is a device used to acquire environmental information, and this includes various types of sensors.

[0627] A "generative artificial intelligence model" is a programmatic method for analyzing acquired data and generating energy usage plans.

[0628] An "energy use plan" refers to pre-established guidelines and strategies for achieving efficient energy management.

[0629] "Passenger emotional state" refers to the psychological and emotional condition of the vehicle's users, and is usually determined from facial expressions and voice data.

[0630] "Environmental conditions" refers to the surrounding environment that passengers directly experience, including temperature, humidity, lighting, and music inside the vehicle.

[0631] A "management system" is a comprehensive system consisting of a series of devices and programs that automatically execute energy usage plans and adjust environmental conditions.

[0632] The system of this invention is realized by collecting environmental information from sensors in real time within buildings and vehicles. This environmental information includes elements such as temperature, humidity, and light intensity, and is acquired by sensors. The terminal transmits this data to a server, which then analyzes it using a generative artificial intelligence model. In this case, an AI model using TensorFlow analyzes the data and generates an optimal energy usage plan.

[0633] The server also uses cameras and microphones to collect facial expressions and voice data to determine the emotional state of passengers. This allows the system to adjust environmental conditions in real time to reflect the passengers' psychological state and improve their comfort. Specifically, it adjusts the lighting inside the vehicle and plays music based on the generated data.

[0634] Leveraging edge computing technology, this data processing is performed in real time at the site. This technology is highly effective in ensuring rapid response and high security. Furthermore, users can monitor energy usage plans provided by the server and manually modify the plans as needed. This operation is performed through a user interface, which is implemented using React Native.

[0635] As a concrete example, if the system detects a passenger's facial expression indicating stress, it will dim the interior lighting and use a generative AI model to select and play relaxing music. This allows passengers to have a more comfortable travel experience. A specific action scenario is set using a prompt such as, "If the passenger's emotion is classified as 'relaxed,' how should the in-car environment be changed?"

[0636] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0637] Step 1:

[0638] The terminal collects environmental information in real time from sensors installed inside buildings and vehicles. The input consists of data from the sensors, including temperature, humidity, and light intensity. This input data is then transmitted directly to the server.

[0639] Step 2:

[0640] The server performs initial processing of the received environmental information. The input is raw data from sensors, and the output is filtered data. It improves data quality by detecting and filtering out abnormal or missing values.

[0641] Step 3:

[0642] The server analyzes filtered environmental data using a generative artificial intelligence model. The input is filtered environmental data, and the output is an energy usage plan. TensorFlow is used for data analysis and model-based predictions.

[0643] Step 4:

[0644] The server detects passengers' emotional states in real time via cameras and microphones. Inputs include facial expressions and voice data, and the output is the recognized emotional state. This processing is performed by an emotion recognition algorithm.

[0645] Step 5:

[0646] The server adjusts the in-car environmental conditions, taking into account the generated energy usage plan and the passengers' emotional states. The inputs are the energy usage plan and emotional state data, and the output is an optimized in-car environment setting. Specifically, this involves actions such as adjusting the brightness of the lighting and selecting and playing music.

[0647] Step 6:

[0648] The user reviews the energy usage plan provided by the server through a user interface and makes manual corrections as needed. The input is the generated energy usage plan, and the output is the corrected plan. This operation is performed through a React Native interface.

[0649] Step 7:

[0650] The server utilizes edge computing technology to perform all processing rapidly and securely on-site. The input is the entirety of the processing up to the previous step, and the output is the result of the data processing, executed quickly and securely. User and environment data are securely protected.

[0651] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0652] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0653] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0654] [Fourth Embodiment]

[0655] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0656] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0657] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0658] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0659] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0660] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0661] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0662] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0663] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0664] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0665] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0666] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0667] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] This invention is implemented as a system for optimizing energy use within a building in real time. This system includes IoT sensors, servers, generative artificial intelligence models, edge computing technology, and a user interface.

[0669] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental data such as temperature, humidity, light intensity, and occupancy status. This data is acquired at regular intervals and transmitted to a server.

[0670] The server performs initial processing on the received raw data. Here, outliers and missing values ​​are detected, and filtering is performed to ensure data accuracy. The clean data is then input into a generative artificial intelligence model. This AI model analyzes the large amount of collected environmental data and generates a specific energy use plan to optimize energy consumption.

[0671] The generated energy usage plan is verified to comply with the latest environmental regulations by referencing regulatory information. A regulatory compliance AI module is used for this verification. The plan is automatically adjusted as needed.

[0672] On the other hand, communication with users (facility operators) is also important. The server notifies users of the generated energy usage plan through a user interface. Users can use this interface to review the plan and make manual modifications as needed.

[0673] Once the energy usage plan is finalized, the server sends commands to the building management system (BMS) to control equipment such as heating, cooling, and lighting. This optimizes energy performance in real time.

[0674] Furthermore, the servers utilize edge computing technology to perform data processing on-site. This improves response speed while ensuring data privacy and security. All processing results and operation logs are recorded and used as reference for future plan generation.

[0675] As a concrete example, on a hot summer day, a sensor detects high temperatures, and an AI model optimizes the air conditioning temperature setting. The plan is adjusted to ensure that energy consumption does not exceed the permissible limit based on regulatory information. This allows facility operators to manage energy consumption comfortably and efficiently while complying with regulations.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The terminals (IoT sensors) measure and collect environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the building. This data is transmitted to a server at regular intervals.

[0679] Step 2:

[0680] The server performs initial processing on the raw data it receives. This processing includes detecting outliers and imputing missing values, as well as performing the necessary filtering to ensure data accuracy.

[0681] Step 3:

[0682] The server inputs clean environmental data into a generative artificial intelligence model, which performs data analysis and generates energy usage plans. The AI ​​then suggests appropriate temperature settings for heating and cooling, as well as planned lighting usage.

[0683] Step 4:

[0684] The server uses a regulatory compliance AI module to verify that the generated energy use plan complies with current environmental regulations. By comparing it with regulatory information, the plan is automatically modified if necessary.

[0685] Step 5:

[0686] Users (facility operators) receive energy usage plans from the server and can review them through a provided user interface. Users can also manually modify the plans using this interface.

[0687] Step 6:

[0688] After the server verifies the user, it sends commands to the building management system (BMS) to execute the energy usage plan, such as changing settings for heating, cooling, and lighting.

[0689] Step 7:

[0690] The server monitors energy performance in real time and adjusts energy usage plans as needed. Data processing is performed on-site using edge computing technology, enabling rapid response.

[0691] Step 8:

[0692] The server records all operation logs and performance data, saving them as feedback data to be used in generating future energy usage plans.

[0693] (Example 1)

[0694] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0695] Conventional energy management systems face challenges in achieving efficient real-time control because each step, such as collecting environmental information, detecting anomalies, and creating energy consumption plans, is performed individually. Furthermore, limitations in user flexibility for manual adjustments and the ability to respond immediately to environmental regulations are problematic. Additionally, centralized data processing presents challenges in response speed and ensuring privacy.

[0696] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0697] In this invention, the server includes means for continuously acquiring environmental information from a measuring device, means for processing the received information in an initial stage and detecting outliers and missing values, and means for creating an energy consumption plan based on a predictive model. This makes it possible to optimize energy efficiency in real time.

[0698] "Environmental information" refers to data on the physical or chemical conditions inside a building, such as temperature, humidity, light levels, and occupancy status.

[0699] A "measuring device" refers to a group of sensors installed to acquire environmental information, and each sensor plays a role in detecting changes in its respective element.

[0700] "Reception" refers to the process by which a server acquires data transmitted from a measuring device and incorporates it in a processable format.

[0701] "Initial processing" refers to pre-processing that detects outliers and imputes missing values ​​to ensure the accuracy of the acquired data.

[0702] An "outlier" refers to an extreme value that falls outside the normal range and may indicate a sensor malfunction or an abnormal situation.

[0703] "Missing values" refer to a state in a dataset where data that should be present is missing.

[0704] A "predictive model" refers to a machine learning algorithm that generates future energy consumption forecasts and optimized usage plans based on collected environmental information.

[0705] An "energy consumption plan" outlines specific guidelines for allocating and using energy resources in an efficient and regulated manner.

[0706] "Facilities management" refers to activities that include the automatic control of air conditioning, lighting, and other building facilities, and operations aimed at maximizing energy efficiency.

[0707] "Response speed" refers to the time it takes for a system to take action after receiving input information, and it is desirable for it to be fast.

[0708] "Privacy" refers to a state in which the data of individuals and businesses is protected from being leaked to external parties or used without their consent.

[0709] This invention relates to an energy management system for optimizing energy use within a building in real time. The system includes IoT sensors as measuring devices, a server for data processing and management, and a user interface that provides an interface with the user.

[0710] First, terminals (IoT sensors) are placed in each room of the building to continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. This information is acquired at regular intervals and sent to the server as data packets.

[0711] The server processes the received information in an initial stage, detecting outliers and missing values. To this end, data cleaning techniques are used to identify outliers and impute missing values, improving data accuracy. Next, the clean data is input into a generating AI model to develop a specific energy use plan that optimizes energy consumption. This AI model learns from past data and generates an optimization plan suitable for future environmental conditions. An example of a prompt used in this process is: "Based on the current room temperature, humidity, light intensity, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption."

[0712] The generated energy use plan is evaluated by a regulatory compliance module to ensure it is consistent with environmental laws and energy regulations. This module automatically generates a regulatory-compliant use plan and makes any necessary adjustments.

[0713] Subsequently, the energy usage plan is notified to the user (facility operator). The user can use this interface to review the plan and make manual adjustments as needed. Once the final plan is confirmed, the server sends commands to the building's management system to control equipment such as heating, cooling, and lighting. This optimizes energy performance while maintaining comfort in each room.

[0714] Furthermore, the server utilizes edge computing technology to perform local data processing, improving response speed while ensuring data privacy and security. All process results and operation logs are recorded and used as reference for future planning.

[0715] For example, on a hot summer day, a sensor detects high temperatures, and an AI model suggests the optimal temperature setting for the air conditioner. At this time, the user could also slightly increase the light intensity for a specific event. In this way, it is possible to achieve comfortable and efficient energy management while complying with regulations.

[0716] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0717] Step 1:

[0718] The terminals (IoT sensors) are placed in each room of the building and continuously measure environmental information such as temperature, humidity, light intensity, and occupancy status. The input is raw data acquired from various sensors. The sensors collect data at regular intervals, convert the data into a digital format, and send it to the server. The output is data packets containing environmental information.

[0719] Step 2:

[0720] The server receives raw data transmitted from the measurement terminal. The input is data packets containing environmental information. The server performs initial processing on this data, such as anomaly detection and missing value imputation. Specifically, it identifies anomalies using statistical methods and imputes missing parts based on the mean or past data. The output is clean and highly accurate environmental information.

[0721] Step 3:

[0722] The server generates clean data and inputs it into the AI ​​model. The input is pre-processed environmental information data. This AI model uses machine learning algorithms to create an energy usage plan to optimize energy consumption from a large amount of data. Specifically, the AI ​​model analyzes environmental conditions and user usage patterns and performs predictions and optimizations using the prompt message "Based on the current room temperature, humidity, light level, and occupancy data, please provide heating, cooling, and lighting settings to optimize energy consumption." The output is the energy usage plan.

[0723] Step 4:

[0724] The server verifies the compliance of the generated energy use plan against environmental laws and energy regulations. The input is the energy use plan generated by the AI ​​model. The server utilizes a regulatory compliance module to verify that the plan meets all legal standards. If necessary, it automatically adjusts the plan. Specifically, it checks energy consumption limits and fine-tunes the plan. The output is the energy use plan that has been verified as compliant.

[0725] Step 5:

[0726] The user (facility operator) reviews the energy usage plan presented via the server through the user interface. The input is the energy usage plan that has been verified for suitability. The user can review the plan using the interface and manually adjust it as needed. Specifically, the user adjusts heating and cooling settings and lighting according to specific usage conditions. The output is the final energy usage plan approved or modified by the user.

[0727] Step 6:

[0728] The server sends instructions to the building management system (BMS) based on the final energy use plan, controlling the equipment. The input is the final energy use plan confirmed by the user. The server sends control signals to heating and cooling systems and lighting equipment, adjusting the set temperature and light intensity. Specifically, it optimizes energy use in each room through automatic control. The output is the optimized energy performance.

[0729] Step 7:

[0730] The server utilizes edge computing technology to perform data processing on-site. The input is real-time data collected during the execution of the plan. The server processes this data to improve response speed while protecting data privacy and security. The output is efficient data processing while ensuring privacy and security. All process results and operation logs are also recorded for reference in future planning.

[0731] (Application Example 1)

[0732] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0733] Energy consumption within factories is crucial for improving production efficiency and reducing costs. However, many current systems lack sufficient real-time control to adapt to environmental changes, making efficient energy management difficult. Furthermore, limited means for users to modify plans in real time can lead to delays in situations requiring rapid response.

[0734] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0735] In this invention, the server includes means for acquiring environmental data from a detection device in real time, means for initial processing the received information and detecting abnormal values, means for generating a power utilization plan based on a generative artificial intelligence model, and means for presenting the power utilization plan through a personal electronic device that allows for on-site plan modification. This enables rapid and efficient energy management and real-time plan modification by the user.

[0736] "Environmental data" refers to information such as temperature, humidity, light intensity, and occupancy status that is acquired in real time using detection devices within buildings and facilities.

[0737] A "detection device" is a hardware device that uses various sensor technologies to acquire environmental data.

[0738] "Initial processing" refers to the process of detecting anomalies and cleaning data in acquired environmental data before input.

[0739] A "generative artificial intelligence model" is an artificial intelligence algorithm used to analyze large amounts of collected data and generate specific plans to optimize energy consumption.

[0740] A "power utilization plan" is an operational plan aimed at efficient energy consumption, built based on a generative artificial intelligence model.

[0741] "Regulatory information" refers to information that outlines various laws, regulations, and guidelines that restrict energy use.

[0742] "Personal electronic devices" refer to electronic devices that people carry and use on a daily basis, such as smartphones and visual display devices.

[0743] "Plan modification" refers to the act of manually changing the generated power utilization plan as needed.

[0744] Edge computing is a technology that performs data processing and analysis near the actual location, improving response speed while ensuring data privacy and security.

[0745] This system is designed to optimize energy efficiency within the factory. The system's design and operation are described in detail below.

[0746] First, multiple detection devices positioned as terminals continuously acquire environmental data such as temperature, humidity, light intensity, and occupancy status at various locations within the factory. This data is immediately transmitted to a server. The server first performs initial processing on the received information and then performs data cleaning to remove outliers in order to maintain data integrity.

[0747] Next, Python and TensorFlow will be used as the software for building the generative artificial intelligence model. The AI ​​model will analyze cleansed data and generate an efficient power utilization plan. This model has the flexibility to evaluate environmental changes in real time and adjust the plan as needed.

[0748] The generated power usage plan is presented to the user via their personal electronic device. The user can directly review the plan using a smartphone or visual display device and manually modify it as needed. This allows for more efficient and faster energy management.

[0749] By using edge computing techniques, data processing is performed closer to the site, resulting in improved response speed and enhanced data privacy. Furthermore, by integrating with the factory's building management system, power control based on the generated plan can be automated.

[0750] For example, on a hot summer day, the outside temperature rises, and sensors inside the factory detect this change. At this point, the AI ​​model adjusts the air conditioning temperature setting, achieving both efficient energy consumption and a comfortable working environment.

[0751] An example of a prompt message is, "The current temperature is over 30°C. Please suggest the optimal air conditioning settings to maintain a comfortable working environment while minimizing energy consumption." This prompt helps the AI ​​model achieve optimal energy use by providing specific instructions.

[0752] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0753] Step 1:

[0754] The terminal acquires environmental data such as temperature, humidity, light intensity, and occupancy status in real time from detection devices placed throughout the factory. This information is transmitted to a server via a communication network. The input is raw data from the detection devices, and the output is well-formed data sent to the server.

[0755] Step 2:

[0756] The server performs initial processing on the received data, including detecting outliers and cleaning the data. Specifically, it filters outliers and missing values ​​to ensure data integrity. In this step, raw data is used as input, and cleansed data is generated as output.

[0757] Step 3:

[0758] The server inputs cleansed data into a generative artificial intelligence model. The AI ​​model is built using Python and TensorFlow. The model analyzes large amounts of data and generates an efficient power utilization plan. The input is cleansed data, and the output is an optimized power utilization plan.

[0759] Step 4:

[0760] The server presents the generated power usage plan to the user via their personal electronic device. The user can review this plan using a smartphone or visual display device. The input for this step is an optimized plan, and the output is user-readable plan information.

[0761] Step 5:

[0762] The user can manually modify the plan as needed. User input is the instruction for manual adjustment, and output is the adjusted power utilization plan.

[0763] Step 6:

[0764] The server uses edge computing techniques to process data near the site. This improves response speed and maintains data privacy. The input for this step is energy adjustment information, and the output is control commands updated in real time.

[0765] Step 7:

[0766] The server integrates with the factory's building management system to automatically control power based on the generated plan. This ensures efficient energy consumption. The input is the adjusted plan, and the output is the automatic power control instruction.

[0767] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0768] This invention relates to a real-time energy management system that optimizes energy use within a building, incorporating an emotion engine. The system includes IoT sensors, a server, a generative artificial intelligence model, an emotion engine, edge computing technology, and a user interface.

[0769] First, terminals (IoT sensors) collect environmental data in real time at various locations within the building. This includes temperature, humidity, light levels, and occupancy status. The data from the sensors is periodically transmitted to a server.

[0770] The server performs initial processing on the received data, filtering out outliers and missing values. Next, it uses a generative artificial intelligence model to analyze the data and create an optimal energy usage plan. This plan includes user comfort and cost-effectiveness as factors to consider.

[0771] The server further utilizes a regulatory compliance AI module to verify that the energy use plan complies with current legal regulations. If necessary, it automatically modifies the plan.

[0772] The emotion engine recognizes the user's current emotional state and reflects this in the energy usage plan. It collects emotional data, such as the user's facial expressions and voice, from various input sources, and the server analyzes this data. For example, if the system determines that the user is relaxed, it adjusts the lighting to create a calmer atmosphere.

[0773] Users (facility operators) can view the energy usage plan presented by the server through a user interface. This interface allows users to manually modify the plan. For example, they can individually change specific lighting settings.

[0774] Once the final energy usage plan is determined, the server executes the plan and controls equipment via the building management system (BMS). This adjusts heating, cooling, and lighting, resulting in energy efficiency.

[0775] Furthermore, the servers utilize edge computing to process data on-site, ensuring rapid response times and high security. All processing logs and sentiment data are recorded and used to optimize future energy usage plans.

[0776] For example, if a resident is experiencing stress, the emotion engine detects this and adjusts the energy usage plan to play music and dim the lighting. In this way, personalized responses tailored to the user's emotions become possible.

[0777] The following describes the processing flow.

[0778] Step 1:

[0779] The terminal (IoT sensor) measures environmental data such as temperature, humidity, light level, and occupancy status inside the building in real time and transmits the data to the server.

[0780] Step 2:

[0781] The server performs initial processing on the raw data it receives, detecting and correcting outliers and missing values. This maintains data consistency and accuracy.

[0782] Step 3:

[0783] The server inputs clean data into a generative artificial intelligence model for analysis and generates an energy usage plan. This plan includes optimal settings for heating, cooling, and lighting.

[0784] Step 4:

[0785] The server uses a regulatory compliance AI module to verify whether the energy use plan complies with current environmental regulations. If there are any non-compliances, the plan is automatically revised.

[0786] Step 5:

[0787] The terminal (emotion engine) recognizes the user's emotional state, sends that data to the server, and incorporates it into the energy usage plan. This recognition uses the user's facial expressions and voice data.

[0788] Step 6:

[0789] Users (facility operators) receive notifications of energy usage plans from the server and can review the plans through the user interface. They can manually modify the plans through the user interface as needed.

[0790] Step 7:

[0791] The server executes the final energy usage plan and sends instructions to the building management system (BMS) to control equipment such as heating, cooling, and lighting.

[0792] Step 8:

[0793] The server continuously monitors energy performance and sentiment data, and adjusts the plan in real time as needed. This result is stored in a database for future energy usage planning.

[0794] Step 9:

[0795] The server utilizes edge computing technology to perform data processing on-site, ensuring rapid system response and data security.

[0796] As a concrete example, when a user becomes relaxed, the emotion engine detects this, and the server adjusts the room lighting to a warmer tone and optimizes the heating and cooling settings to suit the user's comfort.

[0797] (Example 2)

[0798] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0799] Conventional energy management systems have the drawback of not being able to flexibly respond to environmental fluctuations or the emotional state of users. In particular, their lack of real-time capabilities made it difficult to comply with regulations, efficiently control equipment, and ensure user comfort, thus hindering the optimization of energy use.

[0800] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0801] In this invention, the server includes means for acquiring environmental information from a detector in real time, means for generating a usage plan based on a generative information processing model, and means for recognizing the user's emotional state and reflecting it in the usage plan. This enables rapid and adaptive energy management that is in line with environmental changes and the user's emotions.

[0802] "Environmental information" refers to physical variables such as temperature, humidity, light intensity, and occupancy status, and is data necessary for energy management within a building.

[0803] A "detector" is a device installed to measure and collect environmental information in real time, and IoT sensors are included in this category.

[0804] A "generative information processing model" is an information technology model used to perform complex data analysis and formulate energy use plans, and is characterized by machine learning algorithms.

[0805] A "utilization plan" is an optimal energy use strategy created based on collected environmental information and the results of analysis using generative information processing models.

[0806] "Laws and regulations" refer to the regulations and standards that must be followed in energy management, and include local rules and laws.

[0807] "Emotional state" refers to the user's current psychological state and is derived from data obtained through facial expression and voice analysis.

[0808] "Equipment control" refers to the operation of adjusting and managing energy equipment within a building based on usage plans.

[0809] "Distributed information processing technology" refers to a technology that processes a portion of the data at a location closer to the actual site, with the aim of improving response speed and strengthening security.

[0810] The real-time energy management system of the present invention is configured by combining multiple hardware and software components to achieve efficient energy use.

[0811] First, terminals (IoT sensors) are installed throughout the building to collect environmental information such as temperature, humidity, light intensity, and occupancy status in real time. This information is transmitted to a server via wireless communication. Specific sensors used include digital temperature sensors, humidity sensors, light sensors, and motion sensors.

[0812] The server performs initial processing of the received environmental information, detecting and removing outliers and missing values. Data cleaning software is used for this process. Subsequently, a generative AI model is used to generate an optimal usage plan based on the received data. The generated usage plan takes into account energy efficiency and user comfort. An example of a prompt message is, "Please suggest the optimal temperature setting based on the current environmental data."

[0813] Furthermore, the server checks whether the plan complies with the law by referencing regulatory information. If it does not comply with the law, the plan is automatically corrected. This enables energy management that meets legal standards. A software module for regulatory compliance supports this process.

[0814] Next, the emotion engine analyzes the user's emotional state from input devices such as cameras and microphones, and incorporates this into the usage plan. This analysis allows, for example, if the system determines that the user is relaxed, it can adjust the lighting to a softer color. This, in turn, improves the user's comfort.

[0815] Finally, users (facility operators) can review the energy usage plan generated by the server through the provided user interface. This interface works on PCs and tablets, and users can also manually modify the plan. Adjustments can be made to meet individual needs, such as pre-setting lighting for specific time periods.

[0816] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0817] Step 1:

[0818] The terminals (IoT sensors) are installed throughout the building to acquire environmental information in real time. Input data includes temperature, humidity, light intensity, and occupancy status. This data is measured by the sensors and transmitted wirelessly to a server. Environmental information is collected continuously, requiring high-precision data collection.

[0819] Step 2:

[0820] The server performs initial processing of the received environmental information. It detects outliers and missing values ​​from the sensor data received as input and removes them through filtering. Data cleaning software is used here to remove and impute outliers. The output is a clean dataset suitable for analysis. This step improves the reliability of the analyzed data.

[0821] Step 3:

[0822] The server performs data analysis using a generative AI model based on clean data. It uses the cleaned dataset from the previous step as input and generates an optimal energy use plan based on that data. In this analysis, the prompt "Please suggest the optimal temperature setting based on the current environmental data" is sent to the generative AI model, and a specific usage plan is obtained as output. This plan prioritizes user comfort and energy efficiency.

[0823] Step 4:

[0824] The server uses a function to reference laws and regulations to verify that the generated usage plan complies with legal standards. The input is the generated energy usage plan, and the output is the final plan that complies with the law. Any parts that violate regulations are automatically corrected. Through this process, operation without legal risk is guaranteed.

[0825] Step 5:

[0826] The server analyzes the user's emotional state, which is captured by the emotion engine. Input data includes the user's facial expressions and voice information collected from cameras and microphones. This emotional data is analyzed, and the results are reflected in the energy usage plan. For example, if the server determines the user is relaxed, adjustments such as changing the lighting to a calmer tone are made. The output is an energy usage plan synchronized with the user's emotions.

[0827] Step 6:

[0828] The user (facility operator) reviews the energy usage plan created by the server through the user interface. The input here is the adjusted final usage plan, which the user can view on a monitor. Manual configuration changes are also possible as needed, allowing individual requests to be reflected in the configured plan. The output is the finalized energy usage plan.

[0829] Step 7:

[0830] Once the plan is finalized, the server controls the actual equipment through the building management system. The final usage plan to be implemented is used as input. The system controls equipment such as heating, cooling, and lighting, and outputs that optimize energy efficiency. This execution realizes real-world energy management.

[0831] (Application Example 2)

[0832] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0833] In autonomous vehicles, it is necessary to optimize the internal environment based on the emotional state of passengers to provide a comfortable travel experience. However, conventional vehicle management systems have difficulty adjusting the environment in real time to reflect the passenger's state, and improvements in comfort have not been fully achieved. Thus, a method is needed that enables efficient energy management while making appropriate environmental adjustments in response to passenger emotions.

[0834] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0835] In this invention, the server includes means for acquiring environmental information from detectors in real time, means for generating an energy usage plan based on a generative artificial intelligence model, and means for optimizing environmental conditions based on the emotional state of passengers. This makes it possible to create a comfortable in-vehicle environment that is tailored to the emotions of passengers while achieving efficient energy use.

[0836] "Environmental information" refers to information that includes multiple elements such as temperature, humidity, and light intensity, acquired in real time through detectors.

[0837] A "detector" is a device used to acquire environmental information, and this includes various types of sensors.

[0838] A "generative artificial intelligence model" is a programmatic method for analyzing acquired data and generating energy usage plans.

[0839] An "energy use plan" refers to pre-established guidelines and strategies for achieving efficient energy management.

[0840] "Passenger emotional state" refers to the psychological and emotional condition of the vehicle's users, and is usually determined from facial expressions and voice data.

[0841] "Environmental conditions" refers to the surrounding environment that passengers directly experience, including temperature, humidity, lighting, and music inside the vehicle.

[0842] A "management system" is a comprehensive system consisting of a series of devices and programs that automatically execute energy usage plans and adjust environmental conditions.

[0843] The system of this invention is realized by collecting environmental information from sensors in real time within buildings and vehicles. This environmental information includes elements such as temperature, humidity, and light intensity, and is acquired by sensors. The terminal transmits this data to a server, which then analyzes it using a generative artificial intelligence model. In this case, an AI model using TensorFlow analyzes the data and generates an optimal energy usage plan.

[0844] The server also uses cameras and microphones to collect facial expressions and voice data to determine the emotional state of passengers. This allows the system to adjust environmental conditions in real time to reflect the passengers' psychological state and improve their comfort. Specifically, it adjusts the lighting inside the vehicle and plays music based on the generated data.

[0845] Leveraging edge computing technology, this data processing is performed in real time at the site. This technology is highly effective in ensuring rapid response and high security. Furthermore, users can monitor energy usage plans provided by the server and manually modify the plans as needed. This operation is performed through a user interface, which is implemented using React Native.

[0846] As a concrete example, if the system detects a passenger's facial expression indicating stress, it will dim the interior lighting and use a generative AI model to select and play relaxing music. This allows passengers to have a more comfortable travel experience. A specific action scenario is set using a prompt such as, "If the passenger's emotion is classified as 'relaxed,' how should the in-car environment be changed?"

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The terminal collects environmental information in real time from sensors installed inside buildings and vehicles. The input consists of data from the sensors, including temperature, humidity, and light intensity. This input data is then transmitted directly to the server.

[0850] Step 2:

[0851] The server performs initial processing of the received environmental information. The input is raw data from sensors, and the output is filtered data. It improves data quality by detecting and filtering out abnormal or missing values.

[0852] Step 3:

[0853] The server analyzes filtered environmental data using a generative artificial intelligence model. The input is filtered environmental data, and the output is an energy usage plan. TensorFlow is used for data analysis and model-based predictions.

[0854] Step 4:

[0855] The server detects passengers' emotional states in real time via cameras and microphones. Inputs include facial expressions and voice data, and the output is the recognized emotional state. This processing is performed by an emotion recognition algorithm.

[0856] Step 5:

[0857] The server adjusts the in-car environmental conditions, taking into account the generated energy usage plan and the passengers' emotional states. The inputs are the energy usage plan and emotional state data, and the output is an optimized in-car environment setting. Specifically, this involves actions such as adjusting the brightness of the lighting and selecting and playing music.

[0858] Step 6:

[0859] The user reviews the energy usage plan provided by the server through a user interface and makes manual corrections as needed. The input is the generated energy usage plan, and the output is the corrected plan. This operation is performed through a React Native interface.

[0860] Step 7:

[0861] The server utilizes edge computing technology to perform all processing rapidly and securely on-site. The input is the entirety of the processing up to the previous step, and the output is the result of the data processing, executed quickly and securely. User and environment data are securely protected.

[0862] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0863] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0864] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0865] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0866] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0867] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0868] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0869] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0870] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0871] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0872] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0873] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0874] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0875] 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.

[0876] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0877] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0878] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0879] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0880] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0881] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0882] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0883] The following is further disclosed regarding the embodiments described above.

[0884] (Claim 1)

[0885] A means of acquiring environmental data from sensors in real time,

[0886] A means for initial processing the received data and detecting abnormal values,

[0887] A means for generating an energy use plan based on a generative artificial intelligence model,

[0888] Means of referring to regulatory information and modifying energy use plans in accordance with legal regulations,

[0889] A means for automatically executing plans and controlling equipment,

[0890] A means to monitor and adjust energy performance in real time,

[0891] A means of recording data and using it for future plan generation,

[0892] A real-time energy management system including this.

[0893] (Claim 2)

[0894] The system according to claim 1, which performs the above data processing on-site using edge computing technology.

[0895] (Claim 3)

[0896] The system according to claim 1, which provides an interface that presents an energy usage plan to the user and allows manual modification of the plan.

[0897] "Example 1"

[0898] (Claim 1)

[0899] A means for continuously acquiring environmental information from a measuring device,

[0900] A means for processing the received information in an initial stage and detecting outliers and missing values,

[0901] A means of creating an energy consumption plan based on a predictive model,

[0902] Means of referring to legal information and adjusting consumption plans in accordance with legal standards,

[0903] A means to automatically execute plans and manage equipment,

[0904] A means to monitor and optimize energy efficiency in real time,

[0905] A means of recording information and using it for future planning,

[0906] A means of providing users with an energy consumption plan and a recording device to enable manual adjustment,

[0907] A means to improve response speed by performing data processing on-site,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, which performs the above information processing using a local execution method.

[0911] (Claim 3)

[0912] The system according to claim 1, which presents an energy consumption plan to the user and provides an operation screen that allows manual modification of the content.

[0913] "Application Example 1"

[0914] (Claim 1)

[0915] A means of acquiring environmental data in real time from a detection device,

[0916] A means for initial processing of received information and detecting abnormal values,

[0917] A means for generating a power utilization plan based on a generative artificial intelligence model,

[0918] Means of referring to regulatory information and modifying power utilization plans in accordance with legal regulations,

[0919] A means for automatically executing plans and controlling equipment,

[0920] A means of monitoring and adjusting energy performance in real time,

[0921] A means of recording information and using it to generate the next plan,

[0922] A means of presenting a power utilization plan through personal electronic devices that allow for on-site plan modifications,

[0923] A management system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, which performs the above information processing on-site using edge computing techniques.

[0926] (Claim 3)

[0927] The system according to claim 1, which uses a portable information terminal or visual display device to evaluate environmental changes in real time to improve energy efficiency and to suggest optimal control parameters.

[0928] "Example 2 of combining an emotion engine"

[0929] (Claim 1)

[0930] A means of acquiring environmental information from a detector in real time,

[0931] A means for initial processing of received information and detecting abnormal values ​​and missing values,

[0932] A means for generating a usage plan based on a generative information processing model,

[0933] Means to refer to regulatory information and revise the usage plan in accordance with the law,

[0934] A means of recognizing the user's emotional state and reflecting it in the usage plan,

[0935] A means to present a usage plan to the user and allow for manual plan modifications,

[0936] A means of automatically executing a plan and controlling equipment,

[0937] A means to monitor performance and make adjustments in real time,

[0938] A means of recording information and using it to generate the next plan,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, which performs the above information processing on-site using distributed information processing technology.

[0942] (Claim 3)

[0943] The system according to claim 1, which acquires the user's emotional state using an emotion detection function and reflects it in the usage plan.

[0944] "Application example 2 when combining with an emotional engine"

[0945] (Claim 1)

[0946] A means of acquiring environmental information from a detector in real time,

[0947] A means for initial processing the received information and detecting abnormal values,

[0948] A means for generating an energy use plan based on a generative artificial intelligence model,

[0949] Means of referring to regulatory information and modifying energy use plans in accordance with legal regulations,

[0950] A means for automatically executing plans and controlling equipment,

[0951] A means of monitoring and adjusting energy performance in real time,

[0952] A means of recording data and using it for future plan generation,

[0953] A means of optimizing environmental conditions based on the emotional state of passengers,

[0954] A management system that includes this.

[0955] (Claim 2)

[0956] The system according to claim 1, which performs the above information processing on-site using edge computing technology.

[0957] (Claim 3)

[0958] The system according to claim 1, which provides a display interface that presents an energy usage plan to the user and allows manual modification of the plan. [Explanation of symbols]

[0959] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring environmental data from sensors in real time, A means for initial processing the received data and detecting abnormal values, A means for generating an energy use plan based on a generative artificial intelligence model, Means of referring to regulatory information and modifying energy use plans in accordance with legal regulations, A means for automatically executing plans and controlling equipment, A means to monitor and adjust energy performance in real time, A means of recording data and using it for future plan generation, A real-time energy management system including this.

2. The system according to claim 1, which uses edge computing technology to perform the above data processing on-site.

3. The system according to claim 1, which provides an interface that presents an energy usage plan to the user and allows for manual modification of the plan.

Images