system

Abstract

Provide a system. 【Solution means】Means for obtaining the number of visitors, Means for obtaining the temperature inside the building, Means for obtaining the outside air temperature, Means for obtaining the weather, Means for obtaining the solar radiation amount, Means for predicting the indoor environment information based on the obtained data, Means for recommending optimal equipment operation based on the predicted indoor environment information, Means for calculating the expected power saving amount based on the recommendation, Means for generating a request for power-saving behavior to the building users when additional power-saving measures are required, A 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 steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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 modern office buildings and commercial facilities, it is becoming increasingly important to balance effective energy management and user comfort. Conventional energy management systems are based on fixed settings and single parameters, and it is difficult to respond immediately to real - time situation changes. Also, there are insufficient specific measures to encourage efficient power - saving actions, which has led to an increase in energy consumption. It is necessary to solve such problems, maximize energy efficiency, and improve user comfort.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing the following means. Specifically, it includes means for acquiring the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. It also includes means for predicting indoor environmental information based on this acquired data. Furthermore, it provides means for recommending optimal equipment operation based on the predicted indoor environmental information and for calculating the estimated amount of energy saved based on that recommendation. In addition, if additional energy saving measures are required, it includes means for generating specific energy-saving action requests to building users. The present invention enables optimal energy management based on real-time data, achieving both user comfort and energy efficiency.

[0006] "Visitor count" is an indicator that refers to the number of people who are inside a building.

[0007] "Building temperature" refers to the temperature measurements taken at various points inside a building.

[0008] "Outside temperature" refers to meteorological data that indicates the ambient temperature outside the building.

[0009] "Weather" refers to the current weather conditions around the building, including conditions such as sunny, cloudy, rainy, and snowy.

[0010] "Solar radiation" is an indicator that shows the amount of energy that reaches the Earth's surface from the sun, and represents the intensity of radiant energy at a specific location.

[0011] "Means of acquisition" refers to functions and devices that acquire necessary data using various sensors and external APIs.

[0012] "Predictive means" refers to algorithms and software that calculate future environmental information within the building based on collected data.

[0013] "Methods for recommendation" refer to functions and procedures for proposing optimal equipment operation settings based on the obtained predictive data.

[0014] "Means for calculating estimated energy savings" refers to functions or algorithms that calculate the amount of energy reduction expected as a result of setting changes or action requests.

[0015] "Means for generating requests for energy-saving actions from building users" refers to a function that creates and sends messages and notifications to encourage specific energy-saving actions from building users as needed. [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] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This 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 combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the 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, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

[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 a system for optimizing environmental control and energy efficiency within a building. This system collects real-time data, performs predictive analysis, and generates recommendations for optimal equipment operation, thereby achieving both comfort and energy savings.

[0038] System Overview

[0039] This system primarily consists of sensor devices, a server, and terminals. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data and uses a predictive model to forecast the future indoor environment. Furthermore, the server recommends optimal equipment operation settings based on the predicted data and notifies facility managers and building users of the results.

[0040] Program processing

[0041] Server: Collects the following data from each sensor device and external API.

[0042] Number of visitors

[0043] Indoor temperature

[0044] outside temperature

[0045] weather

[0046] solar radiation

[0047] The collected data is stored in a database, and machine learning algorithms are used to predict the future environment inside the building. For example, it predicts the number of visitors, indoor temperature, and energy consumption for the next few hours. Based on the predicted data, specific recommendations are made to maximize comfort and energy efficiency, such as the following:

[0048] Changing the set temperature

[0049] Lights ON / OFF

[0050] Based on these recommendations, the estimated amount of energy saved is calculated and generated as a report. Furthermore, depending on the predicted results, messages are prepared requesting additional energy-saving actions from building users as needed, such as turning off unnecessary lights on specific floors or adjusting the temperature settings.

[0051] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement appropriate equipment operation and building users to take concrete energy-saving actions.

[0052] Specific example

[0053] For example, suppose a sensor device in an office building collects the following data.

[0054] The number of visitors at 10:00 AM was 500.

[0055] The temperature inside the building is 25℃

[0056] The outside temperature is 30℃

[0057] The weather is sunny.

[0058] Solar radiation is 800 W / m²

[0059] Server: Based on the above data, it generates forecast data for 12:00 AM. Based on this forecast, it makes the following facility operation recommendations.

[0060] The number of visitors will increase to 600.

[0061] The temperature inside the building is predicted to rise to 27°C.

[0062] As a result, the server recommends the following configuration changes.

[0063] Lower the set temperature to 24°C.

[0064] Turn off the lights in unused meeting rooms.

[0065] Furthermore, the report will include calculations of estimated energy savings based on these recommendations, showing that energy consumption reductions of 10% and 5%, respectively, can be expected.

[0066] Terminal: Displays recommended temperature settings and lighting-off instructions to facility managers and building users. For example, the following message may be displayed:

[0067] (Recommendation)

[0068] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[0069] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0070] (Request for energy conservation actions)

[0071] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0072] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[0073] The following describes the processing flow.

[0074] Step 1:

[0075] Server: Collects real-time data from various sensor devices and external APIs. The number of visitors is measured using counter sensors installed at each entrance of the building, and the indoor temperature is obtained from temperature sensors on each floor. Outdoor temperature is obtained from outdoor temperature sensors, and weather information is obtained via a weather API. Solar radiation is obtained from solar radiation sensors. All collected data is stored in a database.

[0076] Step 2:

[0077] Server: Uses machine learning models based on collected data to predict future data. Specifically, it uses models trained on historical data to predict fluctuations in visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation. For example, it uses linear regression or deep learning algorithms to generate predicted visitor numbers and indoor temperature for the next few hours.

[0078] Step 3:

[0079] Server: Based on predictive data, it generates optimal equipment operating settings to maximize comfort and energy efficiency within the building. For example, if the building temperature is predicted to rise to 27°C, it will generate a recommendation to change the set temperature to 24°C. It also includes recommendations to turn off unnecessary lights.

[0080] Step 4:

[0081] Server: Calculates estimated energy savings based on recommendations. It calculates specific energy-saving effects, such as a 10% reduction in energy consumption when the set temperature is lowered by 1°C, or a 5% reduction when the lights are turned off, and compiles the results into a report.

[0082] Step 5:

[0083] Server: If additional energy-saving measures are needed based on the prediction results, prepare specific energy-saving action requests for building users. For example, generate messages requesting that unnecessary lights be turned off on specific floors or for specific groups of people.

[0084] Step 6:

[0085] Terminal: Displays messages to facility managers and building users that include recommendations, estimated energy savings, and requests for energy-saving actions received from the server. This enables facility managers to operate equipment appropriately and building users to take concrete energy-saving actions. For example, the following messages may be displayed via the display or notification system.

[0086] (Recommendation)

[0087] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[0088] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0089] (Request for energy conservation actions)

[0090] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0091] (Example 1)

[0092] 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."

[0093] In modern building management, achieving both a comfortable indoor environment and optimized energy efficiency simultaneously is crucial. However, few systems manage multiple factors such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and use this data to make predictions and recommendations. Furthermore, there are insufficient means to encourage building users to take action to conserve energy. As a result, there is a problem where excessive energy consumption can occur, compromising comfort levels.

[0094] 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.

[0095] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for storing the acquired data in a time-series database, means for predicting indoor environmental information using a machine learning algorithm based on the stored data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to building users when additional energy-saving measures are needed, means for notifying building users of changes in equipment operation, and means for monitoring user behavior and generating a report on the effects. This enables real-time data collection and analysis, and the recommendation of optimal equipment operation based on predictions, thereby achieving both energy efficiency and comfort.

[0096] "Means for obtaining the number of visitors" refers to devices and technologies for detecting and measuring the number of people entering a building in real time and collecting that data.

[0097] "Means for obtaining building temperature" refers to devices and technologies for detecting and measuring the temperature inside a building in real time and collecting that data.

[0098] "Means for obtaining outside air temperature" refers to devices and technologies for detecting and measuring the temperature outside a building in real time and collecting that data.

[0099] "Means of acquiring weather information" refers to devices and technologies for acquiring current weather conditions in real time and collecting that data.

[0100] "Means for acquiring solar radiation" refers to devices and technologies for measuring the amount of sunlight irradiating in real time and collecting that data.

[0101] "Means of storing data in a time-series database" refers to the technology of a database and the method of storing data in a chronological order.

[0102] "Methods for predicting in-building environmental information using machine learning algorithms" refers to methods and technologies that use stored data and machine learning techniques to predict future in-building environmental conditions.

[0103] "A means of recommending optimal equipment operation" is a technology that proposes the optimal equipment operation method to maximize energy efficiency and comfort based on predicted data.

[0104] A "means for calculating estimated energy savings" is a technology that calculates how much energy consumption reduction can be expected based on recommended equipment operation settings.

[0105] "Means for generating requests for energy-saving actions from building users" refers to technology that generates request messages to encourage specific actions from building users when additional energy-saving actions are needed.

[0106] "Means of notifying building users of changes in equipment operation" refers to technology that informs building users of recommended changes in equipment operation through displays or notification systems.

[0107] "A means of monitoring user behavior and generating results as a report" refers to technology that monitors user actions, analyzes the results, and provides them in report format.

[0108] This invention relates to a system for optimizing environmental control and energy efficiency within a building. This system primarily consists of sensor devices, servers, and terminals. Specific embodiments are described below.

[0109] Server Processing

[0110] 1. Data Collection

[0111] The server collects data in real time from various sensor devices and external APIs. Specifically, the sensor devices measure the current number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, and transmit this data to the server. The hardware and software used include temperature sensors, an access control system, and various APIs. The server stores this data in a time-series database (e.g., InfluxDB).

[0112] 2. Data Analysis and Prediction

[0113] The server uses machine learning algorithms (e.g., TENSORFLOW®) based on stored data to predict information about the building's environment. This prediction includes accurately forecasting future visitor numbers, building temperature, energy consumption, and more by combining historical and real-time data.

[0114] 3. Recommendation generation

[0115] The server recommends optimal equipment operating settings based on predictive data. This includes changing the set temperature and turning lights on or off. Furthermore, it calculates the estimated amount of energy saved based on these recommendations. For example, if the predictive data indicates that the number of visitors or the temperature will fluctuate in the next few hours, it will generate recommendations such as changing the set temperature to 24°C and turning off the lights in unused meeting rooms.

[0116] 4. Generating requests for energy-saving actions

[0117] If additional energy-saving measures are required, the server generates energy-saving requests for building users. Specifically, it notifies them via message to turn off unnecessary lights on certain floors or adjust the temperature settings.

[0118] Terminal processing

[0119] 1. Display of recommendations and notifications

[0120] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. This allows facility managers to operate the facilities appropriately and building users to take concrete energy-saving actions. Notification methods include email, SMS, and notifications via a dedicated app.

[0121] User behavior

[0122] 1. Operation by the facility administrator

[0123] The facility manager checks the terminal notifications and makes changes to the temperature settings or turns lights on / off according to the server's recommendations. For example, they might change the HVAC system's temperature setting to 24°C and manually turn off the lights in unused conference rooms.

[0124] 2. Cooperation from building users

[0125] Building users will also check the notification and take specific energy-saving actions. For example, they may manually turn off unnecessary lights, or automated systems may turn off the lights.

[0126] Specific example

[0127] For example, suppose a sensor device in an office building collects the following data.

[0128] The number of visitors at 10:00 AM was 500.

[0129] The temperature inside the building is 25℃

[0130] The outside temperature is 30℃

[0131] The weather is sunny.

[0132] Solar radiation is 800 W / m²

[0133] Based on the above data, the server generates forecast data for 12:00 AM. Based on this forecast, the server makes the following facility operation recommendations.

[0134] The number of visitors will increase to 600.

[0135] The temperature inside the building is predicted to rise to 27°C.

[0136] This will lead to the following recommended setting changes.

[0137] Lower the set temperature to 24°C.

[0138] Turn off the lights in unused meeting rooms.

[0139] Furthermore, the report calculates the estimated energy savings based on these recommendations and includes a figure indicating that energy consumption can be reduced by 10% and 5%, respectively. For example, the following message will be displayed on the device.

[0140] (Recommendation)

[0141] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[0142] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0143] (Request for energy conservation actions)

[0144] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0145] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[0146] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0147] Step 1:

[0148] Sensor data collection

[0149] The server collects data in real time from each sensor device and external API. Inputs include the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, all transmitted from the sensor devices. The server acquires this data and processes it accordingly. Specifically, the temperature sensor transmits current temperature data every 30 seconds, and the outdoor temperature sensor transmits data similarly. The number of visitors is also acquired in real time in conjunction with the visitor management system.

[0150] Input: Number of visitors from sensor devices, indoor temperature, outdoor temperature, weather, solar radiation.

[0151] Output: Collected real-time data

[0152] Step 2:

[0153] Data storage

[0154] The server stores the collected data in a time-series database (e.g., InfluxDB). The input is the data collected in step 1. During storage, the server checks data quality and flags any outliers or missing values. Specifically, as soon as data arrives, it is inserted into the database and marked for later anomaly analysis.

[0155] Input: Collected real-time data

[0156] Output: Data stored in a time-series database

[0157] Step 3:

[0158] Generation of Predictive Models

[0159] The server generates a predictive model using a machine learning algorithm (e.g., TensorFlow) based on data stored in a time-series database. The input is the stored time-series data. This data is fed into the machine learning model to predict future conditions within the building (number of visitors, indoor temperature, energy consumption, etc.). For example, the ML model is updated every night at midnight using the day's data. Real-time predictions are recalculated every 10 minutes to update future conditions.

[0160] Input: Data stored in a time-series database

[0161] Output: Predicted in-building environment data

[0162] Step 4:

[0163] Creating recommendations

[0164] The server recommends optimal equipment operation settings based on predictive data. The input is predicted in-building environment data. To maximize energy efficiency and comfort, it suggests changes to the set temperature and turning lights on / off. Specifically, based on the predictive data, the server recommends lowering the set temperature to 24°C and generates recommendations to turn off the lights in unused conference rooms.

[0165] Input: Predicted in-building environment data

[0166] Output: Recommended equipment operation schedule

[0167] Step 5:

[0168] Calculation of estimated energy savings

[0169] The server calculates the estimated amount of energy savings based on recommendations. The input is the recommended equipment operating settings. For example, it calculates that lowering the set temperature to 24°C can reduce energy consumption by 10%. In specific operations, it analyzes the predicted data and actual consumption data to estimate the energy saving effect.

[0170] Input: Recommended equipment operation settings

[0171] Output: Estimated amount of energy saved

[0172] Step 6:

[0173] Generating requests for energy-saving actions

[0174] The server generates energy-saving requests for building users when additional energy-saving measures are needed. The inputs are estimated energy savings and forecast data. For example, it generates messages notifying users to turn off unnecessary lights on specific floors or adjust temperature settings.

[0175] Input: Estimated amount of electricity saved, forecast data

[0176] Output: Message requesting energy-saving actions

[0177] Step 7:

[0178] Sending recommendations and notifications

[0179] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. Input consists of recommendations and energy-saving requests sent from the server. Notifications can be sent via pop-up notifications, email, or SMS, for example.

[0180] Input: Recommendation and energy-saving action request messages sent from the server

[0181] Output: Information displayed via the display or notification system.

[0182] Step 8:

[0183] User behavior

[0184] Users check notifications on their devices and perform actions such as changing the temperature setting or turning lights on or off as instructed. Specifically, the facility manager changes the HVAC system's temperature setting to 24°C, and users manually turn off unnecessary lights. In some cases, an automated system may also turn off the lights.

[0185] Input: Device notifications

[0186] Output: Changes to the set temperature and lighting ON / OFF have been performed.

[0187] Step 9:

[0188] Report generation

[0189] The server monitors user behavior and energy consumption, and generates reports based on the collected data. Inputs include user behavior data and energy consumption data. This allows for the creation of reports that include comparisons between predictions and actual data, energy saving effectiveness, and comfort level evaluations. Monthly reports can be generated as PDFs and sent via email.

[0190] Input: User behavior data, energy consumption data

[0191] Output: Report (PDF format, etc.)

[0192] The above outlines the specific processing steps of this system.

[0193] (Application Example 1)

[0194] 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."

[0195] In modern buildings and factories, maintaining a comfortable environment while maximizing energy efficiency is a crucial challenge. However, current systems often lack sufficient real-time data collection and predictive analysis, and energy consumption optimization and efficient operation schedules are frequently managed manually, leading to significant energy waste. Furthermore, ineffective robot scheduling and energy management within factories result in high operating costs.

[0196] 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.

[0197] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to facility users when additional energy-saving measures are needed, means for predicting the robot's operation schedule and energy consumption based on data collected from sensor devices throughout the factory, and means for instructing the robot to perform optimal operation schedules and energy management based on the predictions. This enables environmental control and optimization of energy efficiency within buildings and factories.

[0198] "Means for obtaining visitor numbers" refers to devices or mechanisms that measure the number of visitors to a building or facility in real time and acquire that information as data.

[0199] "Means for obtaining indoor temperature" refers to devices or mechanisms that measure the temperature inside a building or facility and acquire that temperature data.

[0200] "Means for obtaining outside air temperature" refers to devices or mechanisms that measure the temperature outside a building or facility and acquire that data.

[0201] "Means of acquiring weather information" refers to devices or mechanisms that measure current weather conditions and acquire that information as data.

[0202] "Means for acquiring solar radiation" refers to devices or mechanisms that measure the amount of radiant energy from the sun and acquire that data.

[0203] "Means for predicting in-building environmental information" refers to devices or systems that predict the environmental conditions inside a building at a future point in time based on acquired data.

[0204] "Means for recommending optimal equipment operation" refers to devices or systems that generate optimal recommendations for equipment operation methods and settings based on predicted in-building environmental information.

[0205] "Means for calculating estimated energy savings" refers to devices or software that calculate the expected amount of energy savings based on recommendations.

[0206] A "means for generating requests for energy-saving actions" refers to a device or system that generates a message requesting facility users to take additional energy-saving measures when necessary.

[0207] "Factory-wide sensor devices" refer to a group of sensors installed to measure various environmental conditions and operational status within a factory.

[0208] "Means for predicting robot operation schedules and energy consumption" refers to devices or systems that predict robot operation schedules and energy consumption based on data collected from sensor devices throughout the factory.

[0209] "Means for instructing robots on operating schedules and energy management" refers to devices or systems that, based on predictions, transmit optimal operating schedules and energy management instructions to robots.

[0210] Overall system configuration

[0211] This invention relates to a system for optimizing environmental control and energy efficiency within buildings or factories. The system primarily consists of sensor devices, a server, and terminals. Each sensor device acquires data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time and transmits this data to the server. The server analyzes the received data and uses a predictive model to forecast future indoor environments, robot operation schedules, and energy consumption within factories. This allows for recommendations for optimal equipment operation and energy management.

[0212] Hardware and software to be used

[0213] hardware

[0214] Sensor devices: Indoor thermometer, outdoor thermometer, weather sensor, solar radiation sensor, motion sensor

[0215] Server: Collects, analyzes, and builds predictive models for data.

[0216] Robots: Devices that operate within a factory.

[0217] Terminal: A device for managing facilities, including a display and notification system.

[0218] software

[0219] Python: Run programs for data collection, analysis, prediction, and recommendation generation.

[0220] Requests module: Handles communication with external APIs.

[0221] Scikit-learn: Building and analyzing predictive models

[0222] Smtplib: Sending email notifications

[0223] Data flow and processing

[0224] 1. Data Collection

[0225] The sensor device acquires data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and sends this data to the server. For example, the Python Requests module can be used to retrieve data from the sensor API.

[0226] 2. Predictive Analytics

[0227] The server uses the collected data to predict future building environments, robot operating schedules within factories, and energy consumption. For example, it uses Scikit-learn to build a linear regression model to predict environmental changes and energy consumption over the next few hours.

[0228] 3. Recommendation generation

[0229] The server recommends optimal equipment operation and energy management based on predictive data. For example, if a rise in indoor temperature is predicted, it recommends changing the temperature setting or turning lights on or off. It also optimizes robot operation schedules and generates instructions to reduce energy consumption.

[0230] 4. Notifications and Display

[0231] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server. This allows facility managers to implement appropriate equipment operation and enables building and factory users to take concrete energy-saving actions. Information is also sent to facility managers via email notifications.

[0232] Specific example

[0233] For example, in one office building, the following sensor data was acquired at 10:00 AM:

[0234] The number of visitors was 500.

[0235] The temperature inside the building is 25℃

[0236] The outside temperature is 30℃

[0237] The weather is sunny.

[0238] Solar radiation is 800 W / m²

[0239] Based on this data, the server generated a forecast for 12:00 AM, predicting that the number of visitors would increase to 600 and the indoor temperature would rise to 27°C. The server recommended lowering the thermostat to 24°C and turning off the lights in unused conference rooms, and calculated the estimated amount of energy consumption reduction.

[0240] Example of a prompt

[0241] Based on the following sensor data, predict the future factory environment and create optimal equipment operation settings.

[0242] Sensor data:

[0243] Temperature: 28℃

[0244] Humidity: 50%

[0245] Number of visitors: 100

[0246] Please provide future forecast data, showing how temperature, humidity, and visitor numbers will change, and recommend specific setting changes.

[0247] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0248] Step 1:

[0249] Sensor devices measure data within buildings and factories in real time and transmit that data to a server. Specifically, data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation are collected. Each sensor device sends data to the server via an API, and the server stores this data collectively in a database.

[0250] Input: Real-time data from a sensor device.

[0251] Output: Measurement data stored in the database.

[0252] Step 2:

[0253] The system analyzes data collected by the server to predict future conditions within the building and factory. Here, Python is used to process the data, and Scikit-learn is used to build predictive models. For example, a linear regression model is used to predict temperature, humidity, visitor numbers, and energy consumption over the next few hours.

[0254] Input: Measurement data stored in the database.

[0255] Output: Predictive data on future indoor environments and factory conditions.

[0256] Step 3:

[0257] The server generates recommendations for optimal equipment operation based on predictive data. Specifically, it determines the optimal temperature settings, lighting ON / OFF states, etc., for predicted environmental conditions. This process generates recommendations by making conditional judgments based on the output of the predictive model.

[0258] Input: Prediction data.

[0259] Output: Recommendations for optimal equipment operation.

[0260] Step 4:

[0261] Based on recommendations generated by the server, the expected amount of energy savings is calculated. For example, it calculates how much energy can be saved by changing the temperature setting, or how much cost reduction can be expected by turning off unnecessary lights.

[0262] Input: Recommendation.

[0263] Output: Calculation result of estimated energy savings.

[0264] Step 5:

[0265] The server generates additional energy-saving requests for facility users as needed. For example, in addition to requests to change the temperature or turn lights on or off, it generates messages requesting specific energy-saving actions from users.

[0266] Input: Calculation result of estimated energy savings.

[0267] Output: Message requesting energy-saving actions.

[0268] Step 6:

[0269] The terminal displays recommendations and energy-saving action requests received from the server. This allows facility managers to take concrete action and maximize energy efficiency. The information is displayed via a display or notification system.

[0270] Input: Messages requesting energy-saving actions or recommendations.

[0271] Output: The message displayed on the terminal.

[0272] Step 7:

[0273] The server sends an email notification to the facility administrator as needed. Smtplib is used to send the generated message to the facility administrator via email, allowing them to respond immediately.

[0274] Input: Message requesting energy-saving actions.

[0275] Output: Email notification to the facility administrator.

[0276] 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.

[0277] The present invention combines an engine for recognizing users' emotions with a system for optimizing environmental control and energy efficiency within a building, enhancing the comfort of users while maximizing energy efficiency. This system performs real-time data collection, predictive analysis, and sentiment analysis, and then generates recommendations for optimal facility operation and requests energy-saving actions from building users, thereby achieving both further energy efficiency and comfort.

[0278] System Overview

[0279] This system consists of a sensor device, a server, a terminal, and an emotion engine. The sensor device acquires the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time. The server collects and analyzes this data and predicts the indoor environmental information. Furthermore, the emotion engine obtains the emotional data of users and adjusts the facility operation recommendations. Finally, the server generates optimal settings based on this information and notifies the facility manager and building users.

[0280] Program Processing

[0281] Server: Collects the following data in real time from various sensor devices and external APIs.

[0282] Number of visitors

[0283] Indoor temperature

[0284] Outdoor temperature

[0285] Weather

[0286] Solar radiation

[0287] The collected data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Then, an emotion engine collects user emotion data, which is then analyzed. User emotion data is obtained, for example, through cameras and wearable devices installed within the building.

[0288] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[0289] Server: Also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it prepares additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[0290] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[0291] (Recommendation)

[0292] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0293] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0294] (Request for energy conservation actions)

[0295] Dear users on Floor B, please cooperate. Please turn off unnecessary lighting. Number of people needed for cooperation: 20

[0296] Specific example

[0297] For example, suppose the following data was collected in an office building

[0298] The number of people entering the building at 10:00 am is 500

[0299] The temperature inside the building is 25°C

[0300] The outside air temperature is 30°C

[0301] The weather is sunny

[0302] The solar radiation is 800 W / m²

[0303] Furthermore, when it is recognized by the emotion engine that many users feel "uncomfortable", the following predictions and recommendations are made

[0304] The number of people entering the building increases to 600

[0305] It is predicted that the temperature inside the building will rise to 27°C

[0306] Many users feel uncomfortable

[0307] Server: Based on these data, recommend lowering the set temperature to 24°C and turning off the lighting in unused conference rooms. Also, considering the emotion data, estimate the energy consumption reduction effect and include an approximately 10% energy consumption reduction effect in the report

[0308] Terminal: Notify the facility manager and building users of the above recommendations and requests for energy-saving actions. By combining real-time data and emotion data in this way, a more comfortable and efficient building management system can be realized

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] Server: Collects real-time data from each sensor device and external API. Specifically, the number of visitors is obtained from a counter sensor installed at the entrance, the indoor temperature from temperature sensors installed on each floor, and the outdoor temperature from outdoor temperature sensors. Weather information is obtained via a weather API, and solar radiation is obtained from a solar radiation sensor. The collected data is centrally managed and stored in a database.

[0312] Step 2:

[0313] Server: Uses machine learning algorithms to predict future data based on collected data. Specifically, it generates predictions for the next few hours using data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. In this process, it trains a model using historical datasets to achieve highly accurate predictions.

[0314] Step 3:

[0315] Server: Uses an emotion engine to collect user emotion data. This is done by analyzing users' facial expressions and behavior through cameras and wearable devices installed within the building. The emotion data is then analyzed to determine which emotion it corresponds to, such as pleasant or unpleasant.

[0316] Step 4:

[0317] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the predicted indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature setting to 24°C. Furthermore, it also generates recommendations to adjust lighting brightness and on / off settings based on sentiment data.

[0318] Step 5:

[0319] Server: Calculates estimated energy savings based on recommendations. For example, it makes specific predictions for cases where lowering the temperature by 1°C reduces energy consumption by 10%, or where turning off the lights reduces energy consumption by 5%. The calculation results are compiled into a report, clearly indicating the estimated energy savings.

[0320] Step 6:

[0321] Server: If additional energy-saving measures are needed, it generates specific energy-saving action requests for building users. For example, if many users are feeling uncomfortable on a particular floor, it generates a message requesting users on that floor to turn off unnecessary lights.

[0322] Step 7:

[0323] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement realistic operational settings and building users to take concrete energy-saving actions. For example, the following messages may be displayed:

[0324] (Recommendation)

[0325] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0326] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0327] (Request for energy conservation actions)

[0328] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0329] In this way, the system of the present invention realizes a system that can maximize the comfort level and energy efficiency of the building environment by combining real-time data and emotional data.

[0330] (Example 2)

[0331] 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".

[0332] In recent years, building environment management has demanded a balance between improved energy efficiency and user comfort. However, conventional systems can only control systems based on limited information obtained from simple collection and analysis of environmental data, making it difficult to set optimal equipment operation settings that take into account user emotions and specific experiences. Furthermore, messages encouraging energy-saving behavior tend to be monotonous, making it difficult to gain user cooperation. Therefore, more advanced data analysis and equipment operation that takes user experience into consideration are needed.

[0333] 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.

[0334] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating energy-saving action requests to building users when additional energy-saving measures are needed, means for collecting and analyzing user emotion data, and means for adjusting equipment operation settings based on emotion data. By combining user emotion data with conventional environmental data, more accurate and optimal equipment operation settings become possible, achieving both improved energy efficiency and user comfort. Furthermore, by generating specific energy-saving action request messages tailored to the user's situation, it becomes easier to obtain cooperation from users.

[0335] "Means for obtaining the number of visitors" refers to devices or methods for measuring and recording the number of people who enter a building within a certain period of time, using sensors or access control systems installed within the building.

[0336] "Means for obtaining indoor temperature" refers to devices or methods for measuring and recording the real-time temperature of a location using temperature sensors placed on each floor or in each room within a building.

[0337] "Means for obtaining outside air temperature" refers to devices or methods for measuring and recording the temperature of the external environment using sensors installed on the outside of a building.

[0338] "Means for acquiring weather information" refers to devices and methods for acquiring and recording weather information using weather sensors installed near a building or external weather data provision services.

[0339] "Means for acquiring solar radiation" refers to devices or methods for measuring and recording the intensity and illuminance of direct sunlight using solar radiation sensors installed on the exterior or rooftop of a building.

[0340] "Methods for predicting in-building environmental information based on acquired data" refer to algorithms and methods for analyzing collected data such as temperature, number of visitors, weather, and solar radiation to estimate and predict the future in-building environment.

[0341] "Means for recommending optimal equipment operation based on predicted in-building environmental information" refers to devices or methods that use prediction results to propose and recommend the optimal operating methods for equipment within a building (such as air conditioners and lighting).

[0342] "Means for calculating estimated energy savings based on recommendations" refers to devices or methods for calculating the energy consumption reduction effect predicted by the proposed equipment operation method.

[0343] "Means for generating requests for energy-saving actions from building users when additional energy-saving measures are needed" refers to devices or methods for creating and notifying building users of specific energy-saving actions when further energy conservation is required.

[0344] "Means for collecting and analyzing user emotional data" refers to devices and methods that use cameras and wearable devices installed within a building to analyze users' facial expressions and behavior, and to recognize and record their emotional state.

[0345] "Means for adjusting equipment operation settings based on emotional data" refers to devices or methods for appropriately adjusting equipment operation methods to improve user comfort based on collected emotional data.

[0346] This invention is a system for optimizing environmental control and energy efficiency within a building. By integrating user emotion data, it aims to maximize energy efficiency while enhancing user comfort. This system performs multi-stage processing, including real-time data collection, predictive analysis, and emotion analysis, to generate recommendations for optimal equipment operation and request energy-saving behavior from building users, thereby achieving both energy efficiency and comfort.

[0347] System Configuration

[0348] This system consists of the following elements:

[0349] Sensor devices

[0350] server

[0351] terminal

[0352] Emotional Engine

[0353] Sensor devices: These are installed inside and outside buildings to acquire data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time. Specifically, they include temperature sensors, access control systems, weather sensors, and solar radiation sensors.

[0354] Server: Integrates and stores data collected from sensor devices and uses machine learning algorithms to predict future data. It also collects and analyzes user emotion data through an emotion engine. Based on this data, it also has the function of generating optimal equipment operation settings and calculating estimated energy savings.

[0355] Terminals: These devices display recommendations and energy-saving requests received from the server to facility managers and building users. Specifically, this includes smartphones, tablets, and PC displays.

[0356] Emotion Engine: Collects the user's facial expressions and heart rate through cameras and wearable devices, and analyzes their emotional state. It determines whether the user is comfortable or uncomfortable and sends that data to a server.

[0357] Program processing

[0358] Server: Collects data on visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation in real time from various sensor devices and external APIs, and stores it in a database. The stored data is used with machine learning algorithms to predict future data and generate predicted values ​​for visitor numbers, indoor temperature, and energy consumption. Furthermore, it collects and analyzes user sentiment data through an emotion engine and generates optimal equipment operation settings based on the obtained sentiment data. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the set temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[0359] Server: Calculates estimated energy savings based on recommendations, determines the expected reduction in energy consumption by adjusting temperature settings or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it creates a message encouraging specific energy-saving actions on that floor.

[0360] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[0361] (Recommendation)

[0362] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0363] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0364] (Request for energy conservation actions)

[0365] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0366] Specific example

[0367] For example, suppose the following data was collected in a certain office building.

[0368] The number of visitors at 10:00 AM was 500.

[0369] The temperature inside the building is 25℃

[0370] The outside temperature is 30℃

[0371] The weather is sunny.

[0372] Solar radiation is 800 W / m²

[0373] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[0374] The number of visitors will increase to 600.

[0375] The temperature inside the building is expected to rise to 27°C.

[0376] Many users find it unpleasant.

[0377] Server: Based on this data, it generates recommendations to lower the set temperature to 24°C and turn off the lights in unused meeting rooms. It also takes sentiment data into account to estimate the energy consumption reduction effect and includes an estimated 10% energy consumption reduction in the report.

[0378] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[0379] Examples of prompt statements

[0380] The following are examples of prompts used by a generative AI model to generate appropriate recommendation messages.

[0381] Please generate recommendations for building environmental control based on the following data.

[0382] Number of visitors: 500

[0383] Indoor temperature: 25℃

[0384] Outside temperature: 30℃

[0385] Weather: Sunny

[0386] Solar radiation: 800 W / m²

[0387] User sentiment data: Many users feel uncomfortable.

[0388] Please output appropriate action recommendations and predicted energy-saving effects.

[0389] By inputting this prompt into the generating AI model, it becomes possible to obtain recommendations that balance efficient energy management with user comfort.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] Data collection

[0393] The server collects data in real time from various sensor devices installed within the building (such as access control systems, temperature sensors, weather sensors, and solar radiation sensors). Specifically, it acquires the following information every minute:

[0394] input:

[0395] Number of visitors

[0396] Indoor temperature

[0397] outside temperature

[0398] weather

[0399] solar radiation

[0400] output:

[0401] The collected data set (raw data)

[0402] By regularly saving data to a database, we create a foundation for accumulating historical data and using it for future predictions.

[0403] Step 2:

[0404] Data storage and management

[0405] The server stores the collected data in a database. A timestamp is added to each data entry during storage, and the data is managed centrally.

[0406] input:

[0407] Raw data collected in Step 1

[0408] output:

[0409] Data stored in a database with timestamps

[0410] This enables time-series analysis of the data and provides a data infrastructure for use in subsequent processing.

[0411] Step 3:

[0412] Data Prediction

[0413] The server uses machine learning algorithms to predict future data based on stored data. This includes past visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation data.

[0414] input:

[0415] Historical data in the database

[0416] output:

[0417] Predicted values ​​for future visitor numbers, indoor temperature, and energy consumption.

[0418] Specifically, it learns trends and patterns in collected data to predict, for example, the number of visitors or the temperature inside the building in the next hour.

[0419] Step 4:

[0420] Emotional data collection

[0421] The server collects users' facial expressions and biometric information through cameras and wearable devices installed within the building, and analyzes it using an emotion engine.

[0422] input:

[0423] Biometric information from cameras and wearable devices (facial expressions, heart rate, etc.)

[0424] output:

[0425] User emotional state data (comfortable, uncomfortable, etc.)

[0426] Emotional data is organized in formats such as JSON and stored in a database in real time.

[0427] Step 5:

[0428] Data integration analysis

[0429] The server integrates environmental and sentiment data and performs a comprehensive analysis. During this process, it evaluates the correlation and impact of each data point.

[0430] input:

[0431] Environmental data (temperature inside the building, number of visitors, etc.)

[0432] Emotional data

[0433] output:

[0434] Analysis results (correlation between emotional state and environment, etc.)

[0435] Specifically, visualization in the form of graphs and statistical information should also be considered.

[0436] Step 6:

[0437] Generating equipment operation recommendations

[0438] Based on these analysis results, the server generates specific equipment operation recommendations. For example, it creates specific temperature settings for adjusting the building temperature and instructions for turning lights on and off.

[0439] input:

[0440] Analysis results

[0441] output:

[0442] Equipment operation recommendations (temperature settings, lighting management, etc.)

[0443] For example, it can generate specific instructions such as, "The temperature inside the building has risen to 27°C, so lower the set temperature to 24°C."

[0444] Step 7:

[0445] Calculation of estimated energy savings

[0446] The server calculates the expected reduction in energy consumption based on the generated equipment operation recommendations.

[0447] input:

[0448] Equipment operation recommendations

[0449] output:

[0450] Calculation results of estimated energy savings (reduction rate and specific energy amount)

[0451] For example, it can output specific figures such as "lowering the air conditioner's temperature setting by 2°C will reduce energy consumption by 10%."

[0452] Step 8:

[0453] Generating a message requesting energy-saving actions

[0454] The server generates messages to building users as needed, prompting them to take specific energy-saving actions. These messages may include specific instructions such as "turn off the lights" on certain floors.

[0455] input:

[0456] Equipment operation recommendations

[0457] Calculation results of estimated power savings

[0458] output:

[0459] Message requesting energy conservation actions

[0460] Specifically, it generates messages such as, "We ask users of Floor B to turn off any unnecessary lights."

[0461] Step 9:

[0462] Notifications and displays

[0463] The terminal notifies and displays recommendations, estimated power savings, and power-saving action request messages sent from the server to facility managers and building users.

[0464] input:

[0465] Notification data from the server (recommendations, estimated volume, request messages)

[0466] output:

[0467] Display and notification as a display or alert.

[0468] For example, a notification might appear on your smartphone or tablet saying, "The temperature inside the building will rise to 27°C, so please adjust the temperature setting to 24°C."

[0469] This allows the server, terminal, and user to each perform their specific actions, ensuring a smooth overall system processing flow.

[0470] (Application Example 2)

[0471] 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".

[0472] Conventional environmental control systems in buildings and physical stores primarily relied on physical data such as temperature and lighting for their settings. This often resulted in insufficient management that considered user comfort, potentially leading to decreased user satisfaction. Furthermore, optimal equipment operation was often not achieved, hindering energy efficiency improvements. Therefore, this invention aims to achieve both user comfort and energy efficiency by acquiring user emotional data, optimizing environmental control within buildings and physical stores based on this data, and further enhancing energy efficiency.

[0473] 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.

[0474] In this invention, the server includes means for acquiring emotional data, means for analyzing the user's level of comfort based on the acquired emotional data, and means for adjusting equipment operation recommendations according to the analyzed level of comfort. This enables environmental control based on user comfort. Furthermore, it makes it possible to optimize the energy efficiency of the facility and reduce energy consumption.

[0475] "Means for obtaining the number of visitors" refers to devices or systems that detect the number of people entering and leaving a facility and collect that data.

[0476] "Means for obtaining indoor temperature" refers to devices or systems for measuring the temperature inside a facility and collecting that data.

[0477] "Means for obtaining outside air temperature" refers to devices or systems for measuring the temperature outside a facility and collecting that data.

[0478] "Means of acquiring weather information" refers to devices and systems that detect current weather conditions (such as sunny, rainy, or snowy) and collect that data.

[0479] "Means for acquiring solar radiation" refers to devices or systems for measuring the amount of sunlight irradiating the area and collecting that data.

[0480] "Means for predicting in-building environmental information" refers to devices and systems that predict future environmental conditions within a building based on various acquired data.

[0481] "Means for recommending optimal equipment operation" refers to devices or systems that propose the optimal operating method for equipment based on predicted in-building environmental information.

[0482] A "means for calculating estimated energy savings" refers to a device or system used to calculate how much energy can be saved by operating equipment according to recommended specifications.

[0483] "Means for generating requests for energy-saving actions" refers to devices or systems that generate messages encouraging users to take specific energy-saving actions.

[0484] "Means for acquiring emotional data" refers to devices or systems that detect a user's emotional state and collect that data.

[0485] "Means for analyzing user comfort levels" refer to devices and systems that analyze how comfortable users feel based on acquired emotional data.

[0486] "Means for adjusting equipment operation recommendations" refer to devices or systems that propose adjustments to the operation methods of equipment within a facility based on the analyzed comfort level.

[0487] This invention combines a system that optimizes environmental control and energy efficiency within buildings and retail stores with an engine that recognizes user emotions, thereby maximizing energy efficiency while improving user comfort. This system generates recommendations for optimal equipment operation based on real-time data collection, predictive analysis, and sentiment analysis, and requests energy-saving actions from building users and store managers, thereby achieving a further balance of energy efficiency and comfort.

[0488] System Overview

[0489] The server will use the following hardware and software.

[0490] hardware

[0491] Various sensors

[0492] Visitor count sensor

[0493] Building temperature sensor

[0494] Outdoor temperature sensor

[0495] Weather sensor

[0496] Solar radiation sensor

[0497] software

[0498] Data Acquisition Module

[0499] Predictive Analytics Module

[0500] Emotional Engine

[0501] Recommendation generation module

[0502] Energy saving estimate calculation module

[0503] Notification generation module

[0504] The server collects the following data in real time from various sensor devices and external APIs:

[0505] Number of visitors

[0506] Indoor temperature

[0507] outside temperature

[0508] weather

[0509] solar radiation

[0510] This data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Furthermore, a sentiment engine collects and analyzes user sentiment data. User sentiment data is acquired, for example, through cameras and wearable devices installed within the building or stores.

[0511] The server combines predictive and sentiment data to generate optimal facility operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[0512] The system also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[0513] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[0514] (Recommendation)

[0515] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0516] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0517] (Request for energy conservation actions)

[0518] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0519] Specific example

[0520] For example, suppose the following data was collected at a physical store.

[0521] The number of visitors at 10:00 AM was 100.

[0522] The temperature inside the building is 25℃

[0523] The outside temperature is 30℃

[0524] The weather is sunny.

[0525] Solar radiation is 800 W / m²

[0526] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[0527] The number of visitors will increase to 120.

[0528] The temperature inside the building is expected to rise to 27°C.

[0529] Many users find it unpleasant.

[0530] Based on this data, the server recommends lowering the set temperature to 24°C and turning off the lights in unused meeting rooms. It also considers sentiment data to estimate the energy consumption reduction effect and includes a report showing an energy consumption reduction of approximately 10%. The terminal notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. In this way, combining real-time data with sentiment data enables the creation of a more comfortable and efficient environmental management system.

[0531] Example of a prompt

[0532] The following are specific examples of prompt statements for a generative AI model:

[0533] "Design a smartphone app version of the environmental management system. The app will collect environmental data and customer sentiment data from physical stores in real time and suggest optimal environmental settings. It should also suggest setting changes, calculate the resulting energy-saving effects, and notify the administrator."

[0534] This can improve customer satisfaction and energy efficiency in physical stores.

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

[0536] Step 1:

[0537] The server collects necessary data in real time from various sensor devices and external APIs. Specifically, it acquires current data using visitor count sensors, indoor temperature sensors, outdoor temperature sensors, weather sensors, and solar radiation sensors. The input is the data from each sensor, and the output is an integrated environmental dataset containing that data.

[0538] Step 2:

[0539] The server stores collected environmental data in a database and uses machine learning algorithms to predict future data. The input is an integrated environmental dataset, and the output includes predicted visitor numbers, indoor temperature, energy consumption, and other data. Time series analysis and regression analysis are used for prediction.

[0540] Step 3:

[0541] The server uses an emotion engine to acquire and analyze user emotion data. Specifically, it extracts emotion data from cameras and wearable devices installed within buildings and stores. The input is emotion data, and the output is analyzed user comfort level information.

[0542] Step 4:

[0543] The server generates optimal equipment operation settings based on predictive data and sentiment data. Inputs are predictive data and comfort level information, while outputs are recommendation information such as temperature settings and lighting adjustments. This process utilizes a condition-dependent optimization algorithm.

[0544] Step 5:

[0545] The server calculates the energy-saving effect of configuration changes based on the generated recommendation information. The input is the recommendation information, and the output is the estimated amount of energy saved. An energy model is used to calculate the effect of reducing energy consumption.

[0546] Step 6:

[0547] The server compiles estimated energy savings and recommendation information into a report and generates energy-saving action request messages as needed. The input is estimated energy savings and recommendation information, and the output is the report and energy-saving action request messages.

[0548] Step 7:

[0549] The terminal displays recommendation information, estimated energy savings, and energy-saving action request messages received from the server. This allows facility managers and building users to take concrete actions. The inputs are recommendation information, estimated energy savings, and energy-saving action request messages, and the output is a display screen showing this information.

[0550] Step 8:

[0551] Users take action based on recommendations and energy-saving requests displayed on their devices. For example, they might adjust the temperature setting or turn off unnecessary lights. The input is the information displayed on the screen, and the output is the specific energy-saving action performed by the user.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] [Second Embodiment]

[0556] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0557] 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.

[0558] 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).

[0559] 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.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] 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".

[0568] This invention is a system for optimizing environmental control and energy efficiency within a building. This system collects real-time data, performs predictive analysis, and generates recommendations for optimal equipment operation, thereby achieving both comfort and energy savings.

[0569] System Overview

[0570] This system primarily consists of sensor devices, a server, and terminals. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data and uses a predictive model to forecast the future indoor environment. Furthermore, the server recommends optimal equipment operation settings based on the predicted data and notifies facility managers and building users of the results.

[0571] Program processing

[0572] Server: Collects the following data from each sensor device and external API.

[0573] Number of visitors

[0574] Indoor temperature

[0575] outside temperature

[0576] weather

[0577] solar radiation

[0578] The collected data is stored in a database, and machine learning algorithms are used to predict the future environment inside the building. For example, it predicts the number of visitors, indoor temperature, and energy consumption for the next few hours. Based on the predicted data, specific recommendations are made to maximize comfort and energy efficiency, such as the following:

[0579] Changing the set temperature

[0580] Lights ON / OFF

[0581] Based on these recommendations, the estimated amount of energy saved is calculated and generated as a report. Furthermore, depending on the predicted results, messages are prepared requesting additional energy-saving actions from building users as needed, such as turning off unnecessary lights on specific floors or adjusting the temperature settings.

[0582] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement appropriate equipment operation and building users to take concrete energy-saving actions.

[0583] Specific example

[0584] For example, suppose a sensor device in an office building collects the following data.

[0585] The number of visitors at 10:00 AM was 500.

[0586] The temperature inside the building is 25℃

[0587] The outside temperature is 30℃

[0588] The weather is sunny.

[0589] Solar radiation is 800 W / m²

[0590] Server: Based on the above data, it generates forecast data for 12:00 AM. Based on this forecast, it makes the following facility operation recommendations.

[0591] The number of visitors will increase to 600.

[0592] The temperature inside the building is predicted to rise to 27°C.

[0593] As a result, the server recommends the following configuration changes.

[0594] Lower the set temperature to 24°C.

[0595] Turn off the lights in unused meeting rooms.

[0596] Furthermore, the report will include calculations of estimated energy savings based on these recommendations, showing that energy consumption reductions of 10% and 5%, respectively, can be expected.

[0597] Terminal: Displays recommended temperature settings and lighting-off instructions to facility managers and building users. For example, the following message may be displayed:

[0598] (Recommendation)

[0599] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[0600] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0601] (Request for energy conservation actions)

[0602] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0603] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] Server: Collects real-time data from various sensor devices and external APIs. The number of visitors is measured using counter sensors installed at each entrance of the building, and the indoor temperature is obtained from temperature sensors on each floor. Outdoor temperature is obtained from outdoor temperature sensors, and weather information is obtained via a weather API. Solar radiation is obtained from solar radiation sensors. All collected data is stored in a database.

[0607] Step 2:

[0608] Server: Uses machine learning models based on collected data to predict future data. Specifically, it uses models trained on historical data to predict fluctuations in visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation. For example, it uses linear regression or deep learning algorithms to generate predicted visitor numbers and indoor temperature for the next few hours.

[0609] Step 3:

[0610] Server: Based on predictive data, it generates optimal equipment operating settings to maximize comfort and energy efficiency within the building. For example, if the building temperature is predicted to rise to 27°C, it will generate a recommendation to change the set temperature to 24°C. It also includes recommendations to turn off unnecessary lights.

[0611] Step 4:

[0612] Server: Calculates estimated energy savings based on recommendations. It calculates specific energy-saving effects, such as a 10% reduction in energy consumption when the set temperature is lowered by 1°C, or a 5% reduction when the lights are turned off, and compiles the results into a report.

[0613] Step 5:

[0614] Server: If additional energy-saving measures are needed based on the prediction results, prepare specific energy-saving action requests for building users. For example, generate messages requesting that unnecessary lights be turned off on specific floors or for specific groups of people.

[0615] Step 6:

[0616] Terminal: Displays messages to facility managers and building users that include recommendations, estimated energy savings, and requests for energy-saving actions received from the server. This enables facility managers to operate equipment appropriately and building users to take concrete energy-saving actions. For example, the following messages may be displayed via the display or notification system.

[0617] (Recommendation)

[0618] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[0619] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0620] (Request for energy conservation actions)

[0621] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0622] (Example 1)

[0623] 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."

[0624] In modern building management, achieving both a comfortable indoor environment and optimized energy efficiency simultaneously is crucial. However, few systems manage multiple factors such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and use this data to make predictions and recommendations. Furthermore, there are insufficient means to encourage building users to take action to conserve energy. As a result, there is a problem where excessive energy consumption can occur, compromising comfort levels.

[0625] 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.

[0626] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for storing the acquired data in a time-series database, means for predicting indoor environmental information using a machine learning algorithm based on the stored data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to building users when additional energy-saving measures are needed, means for notifying building users of changes in equipment operation, and means for monitoring user behavior and generating a report on the effects. This enables real-time data collection and analysis, and the recommendation of optimal equipment operation based on predictions, thereby achieving both energy efficiency and comfort.

[0627] "Means for obtaining the number of visitors" refers to devices and technologies for detecting and measuring the number of people entering a building in real time and collecting that data.

[0628] "Means for obtaining building temperature" refers to devices and technologies for detecting and measuring the temperature inside a building in real time and collecting that data.

[0629] "Means for obtaining outside air temperature" refers to devices and technologies for detecting and measuring the temperature outside a building in real time and collecting that data.

[0630] "Means of acquiring weather information" refers to devices and technologies for acquiring current weather conditions in real time and collecting that data.

[0631] "Means for acquiring solar radiation" refers to devices and technologies for measuring the amount of sunlight irradiating in real time and collecting that data.

[0632] "Means of storing data in a time-series database" refers to the technology of a database and the method of storing data in a chronological order.

[0633] "Methods for predicting in-building environmental information using machine learning algorithms" refers to methods and technologies that use stored data and machine learning techniques to predict future in-building environmental conditions.

[0634] "A means of recommending optimal equipment operation" is a technology that proposes the optimal equipment operation method to maximize energy efficiency and comfort based on predicted data.

[0635] A "means for calculating estimated energy savings" is a technology that calculates how much energy consumption reduction can be expected based on recommended equipment operation settings.

[0636] "Means for generating requests for energy-saving actions from building users" refers to technology that generates request messages to encourage specific actions from building users when additional energy-saving actions are needed.

[0637] "Means of notifying building users of changes in equipment operation" refers to technology that informs building users of recommended changes in equipment operation through displays or notification systems.

[0638] "A means of monitoring user behavior and generating results as a report" refers to technology that monitors user actions, analyzes the results, and provides them in report format.

[0639] This invention relates to a system for optimizing environmental control and energy efficiency within a building. This system primarily consists of sensor devices, servers, and terminals. Specific embodiments are described below.

[0640] Server Processing

[0641] 1. Data Collection

[0642] The server collects data in real time from various sensor devices and external APIs. Specifically, the sensor devices measure the current number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, and transmit this data to the server. The hardware and software used include temperature sensors, an access control system, and various APIs. The server stores this data in a time-series database (e.g., InfluxDB).

[0643] 2. Data Analysis and Prediction

[0644] The server uses machine learning algorithms (e.g., TensorFlow) based on stored data to predict information about the building's environment. This prediction includes accurately forecasting future visitor numbers, building temperature, energy consumption, and more by combining historical and real-time data.

[0645] 3. Recommendation generation

[0646] The server recommends optimal equipment operating settings based on predictive data. This includes changing the set temperature and turning lights on or off. Furthermore, it calculates the estimated amount of energy saved based on these recommendations. For example, if the predictive data indicates that the number of visitors or the temperature will fluctuate in the next few hours, it will generate recommendations such as changing the set temperature to 24°C and turning off the lights in unused meeting rooms.

[0647] 4. Generating requests for energy-saving actions

[0648] If additional energy-saving measures are required, the server generates energy-saving requests for building users. Specifically, it notifies them via message to turn off unnecessary lights on certain floors or adjust the temperature settings.

[0649] Terminal processing

[0650] 1. Display of recommendations and notifications

[0651] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. This allows facility managers to operate the facilities appropriately and building users to take concrete energy-saving actions. Notification methods include email, SMS, and notifications via a dedicated app.

[0652] User behavior

[0653] 1. Operation by the facility administrator

[0654] The facility manager checks the terminal notifications and makes changes to the temperature settings or turns lights on / off according to the server's recommendations. For example, they might change the HVAC system's temperature setting to 24°C and manually turn off the lights in unused conference rooms.

[0655] 2. Cooperation from building users

[0656] Building users will also check the notification and take specific energy-saving actions. For example, they may manually turn off unnecessary lights, or automated systems may turn off the lights.

[0657] Specific example

[0658] For example, suppose a sensor device in an office building collects the following data.

[0659] The number of visitors at 10:00 AM was 500.

[0660] The temperature inside the building is 25℃

[0661] The outside temperature is 30℃

[0662] The weather is sunny.

[0663] Solar radiation is 800 W / m²

[0664] Based on the above data, the server generates forecast data for 12:00 AM. Based on this forecast, the server makes the following facility operation recommendations.

[0665] The number of visitors will increase to 600.

[0666] The temperature inside the building is predicted to rise to 27°C.

[0667] This will lead to the following recommended setting changes.

[0668] Lower the set temperature to 24°C.

[0669] Turn off the lights in unused meeting rooms.

[0670] Furthermore, the report calculates the estimated energy savings based on these recommendations and includes a figure indicating that energy consumption can be reduced by 10% and 5%, respectively. For example, the following message will be displayed on the device.

[0671] (Recommendation)

[0672] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[0673] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0674] (Request for energy conservation actions)

[0675] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0676] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[0677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0678] Step 1:

[0679] Sensor data collection

[0680] The server collects data in real time from each sensor device and external API. Inputs include the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, all transmitted from the sensor devices. The server acquires this data and processes it accordingly. Specifically, the temperature sensor transmits current temperature data every 30 seconds, and the outdoor temperature sensor transmits data similarly. The number of visitors is also acquired in real time in conjunction with the visitor management system.

[0681] Input: Number of visitors from sensor devices, indoor temperature, outdoor temperature, weather, solar radiation.

[0682] Output: Collected real-time data

[0683] Step 2:

[0684] Data storage

[0685] The server stores the collected data in a time-series database (e.g., InfluxDB). The input is the data collected in step 1. During storage, the server checks data quality and flags any outliers or missing values. Specifically, as soon as data arrives, it is inserted into the database and marked for later anomaly analysis.

[0686] Input: Collected real-time data

[0687] Output: Data stored in a time-series database

[0688] Step 3:

[0689] Generation of Predictive Models

[0690] The server generates a predictive model using a machine learning algorithm (e.g., TensorFlow) based on data stored in a time-series database. The input is the stored time-series data. This data is fed into the machine learning model to predict future conditions within the building (number of visitors, indoor temperature, energy consumption, etc.). For example, the ML model is updated every night at midnight using the day's data. Real-time predictions are recalculated every 10 minutes to update future conditions.

[0691] Input: Data stored in a time-series database

[0692] Output: Predicted in-building environment data

[0693] Step 4:

[0694] Creating recommendations

[0695] The server recommends optimal equipment operation settings based on predictive data. The input is predicted in-building environment data. To maximize energy efficiency and comfort, it suggests changes to the set temperature and turning lights on / off. Specifically, based on the predictive data, the server recommends lowering the set temperature to 24°C and generates recommendations to turn off the lights in unused conference rooms.

[0696] Input: Predicted in-building environment data

[0697] Output: Recommended equipment operation schedule

[0698] Step 5:

[0699] Calculation of estimated energy savings

[0700] The server calculates the estimated amount of energy savings based on recommendations. The input is the recommended equipment operating settings. For example, it calculates that lowering the set temperature to 24°C can reduce energy consumption by 10%. In specific operations, it analyzes the predicted data and actual consumption data to estimate the energy saving effect.

[0701] Input: Recommended equipment operation settings

[0702] Output: Estimated amount of energy saved

[0703] Step 6:

[0704] Generating requests for energy-saving actions

[0705] The server generates energy-saving requests for building users when additional energy-saving measures are needed. The inputs are estimated energy savings and forecast data. For example, it generates messages notifying users to turn off unnecessary lights on specific floors or adjust temperature settings.

[0706] Input: Estimated amount of electricity saved, forecast data

[0707] Output: Message requesting energy-saving actions

[0708] Step 7:

[0709] Sending recommendations and notifications

[0710] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. Input consists of recommendations and energy-saving requests sent from the server. Notifications can be sent via pop-up notifications, email, or SMS, for example.

[0711] Input: Recommendation and energy-saving action request messages sent from the server

[0712] Output: Information displayed via the display or notification system.

[0713] Step 8:

[0714] User behavior

[0715] Users check notifications on their devices and perform actions such as changing the temperature setting or turning lights on or off as instructed. Specifically, the facility manager changes the HVAC system's temperature setting to 24°C, and users manually turn off unnecessary lights. In some cases, an automated system may also turn off the lights.

[0716] Input: Device notifications

[0717] Output: Changes to the set temperature and lighting ON / OFF have been performed.

[0718] Step 9:

[0719] Report generation

[0720] The server monitors user behavior and energy consumption, and generates reports based on the collected data. Inputs include user behavior data and energy consumption data. This allows for the creation of reports that include comparisons between predictions and actual data, energy saving effectiveness, and comfort level evaluations. Monthly reports can be generated as PDFs and sent via email.

[0721] Input: User behavior data, energy consumption data

[0722] Output: Report (PDF format, etc.)

[0723] The above outlines the specific processing steps of this system.

[0724] (Application Example 1)

[0725] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0726] In modern buildings and factories, maintaining a comfortable environment while maximizing energy efficiency is a crucial challenge. However, current systems often lack sufficient real-time data collection and predictive analysis, and energy consumption optimization and efficient operation schedules are frequently managed manually, leading to significant energy waste. Furthermore, ineffective robot scheduling and energy management within factories result in high operating costs.

[0727] 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.

[0728] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to facility users when additional energy-saving measures are needed, means for predicting the robot's operation schedule and energy consumption based on data collected from sensor devices throughout the factory, and means for instructing the robot to perform optimal operation schedules and energy management based on the predictions. This enables environmental control and optimization of energy efficiency within buildings and factories.

[0729] "Means for obtaining visitor numbers" refers to devices or mechanisms that measure the number of visitors to a building or facility in real time and acquire that information as data.

[0730] "Means for obtaining indoor temperature" refers to devices or mechanisms that measure the temperature inside a building or facility and acquire that temperature data.

[0731] "Means for obtaining outside air temperature" refers to devices or mechanisms that measure the temperature outside a building or facility and acquire that data.

[0732] "Means of acquiring weather information" refers to devices or mechanisms that measure current weather conditions and acquire that information as data.

[0733] "Means for acquiring solar radiation" refers to devices or mechanisms that measure the amount of radiant energy from the sun and acquire that data.

[0734] "Means for predicting in-building environmental information" refers to devices or systems that predict the environmental conditions inside a building at a future point in time based on acquired data.

[0735] "Means for recommending optimal equipment operation" refers to devices or systems that generate optimal recommendations for equipment operation methods and settings based on predicted in-building environmental information.

[0736] "Means for calculating estimated energy savings" refers to devices or software that calculate the expected amount of energy savings based on recommendations.

[0737] A "means for generating requests for energy-saving actions" refers to a device or system that generates a message requesting facility users to take additional energy-saving measures when necessary.

[0738] "Factory-wide sensor devices" refer to a group of sensors installed to measure various environmental conditions and operational status within a factory.

[0739] "Means for predicting robot operation schedules and energy consumption" refers to devices or systems that predict robot operation schedules and energy consumption based on data collected from sensor devices throughout the factory.

[0740] "Means for instructing robots on operating schedules and energy management" refers to devices or systems that, based on predictions, transmit optimal operating schedules and energy management instructions to robots.

[0741] Overall system configuration

[0742] This invention relates to a system for optimizing environmental control and energy efficiency within buildings or factories. The system primarily consists of sensor devices, a server, and terminals. Each sensor device acquires data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time and transmits this data to the server. The server analyzes the received data and uses a predictive model to forecast future indoor environments, robot operation schedules, and energy consumption within factories. This allows for recommendations for optimal equipment operation and energy management.

[0743] Hardware and software to be used

[0744] hardware

[0745] Sensor devices: Indoor thermometer, outdoor thermometer, weather sensor, solar radiation sensor, motion sensor

[0746] Server: Collects, analyzes, and builds predictive models for data.

[0747] Robots: Devices that operate within a factory.

[0748] Terminal: A device for managing facilities, including a display and notification system.

[0749] software

[0750] Python: Run programs for data collection, analysis, prediction, and recommendation generation.

[0751] Requests module: Handles communication with external APIs.

[0752] Scikit-learn: Building and analyzing predictive models

[0753] Smtplib: Sending email notifications

[0754] Data flow and processing

[0755] 1. Data Collection

[0756] The sensor device acquires data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and sends this data to the server. For example, the Python Requests module can be used to retrieve data from the sensor API.

[0757] 2. Predictive Analytics

[0758] The server uses the collected data to predict future building environments, robot operating schedules within factories, and energy consumption. For example, it uses Scikit-learn to build a linear regression model to predict environmental changes and energy consumption over the next few hours.

[0759] 3. Recommendation generation

[0760] The server recommends optimal equipment operation and energy management based on predictive data. For example, if a rise in indoor temperature is predicted, it recommends changing the temperature setting or turning lights on or off. It also optimizes robot operation schedules and generates instructions to reduce energy consumption.

[0761] 4. Notifications and Display

[0762] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server. This allows facility managers to implement appropriate equipment operation and enables building and factory users to take concrete energy-saving actions. Information is also sent to facility managers via email notifications.

[0763] Specific example

[0764] For example, in one office building, the following sensor data was acquired at 10:00 AM:

[0765] The number of visitors was 500.

[0766] The temperature inside the building is 25℃

[0767] The outside temperature is 30℃

[0768] The weather is sunny.

[0769] Solar radiation is 800 W / m²

[0770] Based on this data, the server generated a forecast for 12:00 AM, predicting that the number of visitors would increase to 600 and the indoor temperature would rise to 27°C. The server recommended lowering the thermostat to 24°C and turning off the lights in unused conference rooms, and calculated the estimated amount of energy consumption reduction.

[0771] Example of a prompt

[0772] Based on the following sensor data, predict the future factory environment and create optimal equipment operation settings.

[0773] Sensor data:

[0774] Temperature: 28℃

[0775] Humidity: 50%

[0776] Number of visitors: 100

[0777] Please provide future forecast data, showing how temperature, humidity, and visitor numbers will change, and recommend specific setting changes.

[0778] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0779] Step 1:

[0780] Sensor devices measure data within buildings and factories in real time and transmit that data to a server. Specifically, data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation are collected. Each sensor device sends data to the server via an API, and the server stores this data collectively in a database.

[0781] Input: Real-time data from a sensor device.

[0782] Output: Measurement data stored in the database.

[0783] Step 2:

[0784] The system analyzes data collected by the server to predict future conditions within the building and factory. Here, Python is used to process the data, and Scikit-learn is used to build predictive models. For example, a linear regression model is used to predict temperature, humidity, visitor numbers, and energy consumption over the next few hours.

[0785] Input: Measurement data stored in the database.

[0786] Output: Predictive data on future indoor environments and factory conditions.

[0787] Step 3:

[0788] The server generates recommendations for optimal equipment operation based on predictive data. Specifically, it determines the optimal temperature settings, lighting ON / OFF states, etc., for predicted environmental conditions. This process generates recommendations by making conditional judgments based on the output of the predictive model.

[0789] Input: Prediction data.

[0790] Output: Recommendations for optimal equipment operation.

[0791] Step 4:

[0792] Based on recommendations generated by the server, the expected amount of energy savings is calculated. For example, it calculates how much energy can be saved by changing the temperature setting, or how much cost reduction can be expected by turning off unnecessary lights.

[0793] Input: Recommendation.

[0794] Output: Calculation result of estimated energy savings.

[0795] Step 5:

[0796] The server generates additional energy-saving requests for facility users as needed. For example, in addition to requests to change the temperature or turn lights on or off, it generates messages requesting specific energy-saving actions from users.

[0797] Input: Calculation result of estimated energy savings.

[0798] Output: Message requesting energy-saving actions.

[0799] Step 6:

[0800] The terminal displays recommendations and energy-saving action requests received from the server. This allows facility managers to take concrete action and maximize energy efficiency. The information is displayed via a display or notification system.

[0801] Input: Messages requesting energy-saving actions or recommendations.

[0802] Output: The message displayed on the terminal.

[0803] Step 7:

[0804] The server sends an email notification to the facility administrator as needed. Smtplib is used to send the generated message to the facility administrator via email, allowing them to respond immediately.

[0805] Input: Message requesting energy-saving actions.

[0806] Output: Email notification to the facility administrator.

[0807] 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.

[0808] This invention combines a system for optimizing environmental control and energy efficiency within a building with an engine that recognizes user emotions, thereby maximizing energy efficiency while enhancing user comfort. This system generates recommendations for optimal equipment operation based on real-time data collection, predictive analysis, and emotion analysis, and requests energy-saving actions from building users, thereby achieving a further balance of energy efficiency and comfort.

[0809] System Overview

[0810] This system consists of sensor devices, a server, terminals, and an emotion engine. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data to predict the building's environmental conditions. Furthermore, the emotion engine acquires user emotion data and adjusts facility operation recommendations accordingly. Finally, the server generates optimal settings based on this information and notifies facility managers and building users.

[0811] Program processing

[0812] Server: Collects the following data in real time from various sensor devices and external APIs.

[0813] Number of visitors

[0814] Indoor temperature

[0815] outside temperature

[0816] weather

[0817] solar radiation

[0818] The collected data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Then, an emotion engine collects user emotion data, which is then analyzed. User emotion data is obtained, for example, through cameras and wearable devices installed within the building.

[0819] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[0820] Server: Also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it prepares additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[0821] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[0822] (Recommendation)

[0823] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0824] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0825] (Request for energy conservation actions)

[0826] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0827] Specific example

[0828] For example, suppose the following data was collected in a certain office building.

[0829] The number of visitors at 10:00 AM was 500.

[0830] The temperature inside the building is 25℃

[0831] The outside temperature is 30℃

[0832] The weather is sunny.

[0833] Solar radiation is 800 W / m²

[0834] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[0835] The number of visitors will increase to 600.

[0836] The temperature inside the building is expected to rise to 27°C.

[0837] Many users find it unpleasant.

[0838] Server: Based on this data, recommend lowering the temperature setting to 24°C and turning off the lights in unused meeting rooms. Also, consider sentiment data to estimate the energy consumption reduction effect and include an estimated 10% energy consumption reduction in the report.

[0839] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[0840] The following describes the processing flow.

[0841] Step 1:

[0842] Server: Collects real-time data from each sensor device and external API. Specifically, the number of visitors is obtained from a counter sensor installed at the entrance, the indoor temperature from temperature sensors installed on each floor, and the outdoor temperature from outdoor temperature sensors. Weather information is obtained via a weather API, and solar radiation is obtained from a solar radiation sensor. The collected data is centrally managed and stored in a database.

[0843] Step 2:

[0844] Server: Uses machine learning algorithms to predict future data based on collected data. Specifically, it generates predictions for the next few hours using data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. In this process, it trains a model using historical datasets to achieve highly accurate predictions.

[0845] Step 3:

[0846] Server: Uses an emotion engine to collect user emotion data. This is done by analyzing users' facial expressions and behavior through cameras and wearable devices installed within the building. The emotion data is then analyzed to determine which emotion it corresponds to, such as pleasant or unpleasant.

[0847] Step 4:

[0848] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the predicted indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature setting to 24°C. Furthermore, it also generates recommendations to adjust lighting brightness and on / off settings based on sentiment data.

[0849] Step 5:

[0850] Server: Calculates estimated energy savings based on recommendations. For example, it makes specific predictions for cases where lowering the temperature by 1°C reduces energy consumption by 10%, or where turning off the lights reduces energy consumption by 5%. The calculation results are compiled into a report, clearly indicating the estimated energy savings.

[0851] Step 6:

[0852] Server: If additional energy-saving measures are needed, it generates specific energy-saving action requests for building users. For example, if many users are feeling uncomfortable on a particular floor, it generates a message requesting users on that floor to turn off unnecessary lights.

[0853] Step 7:

[0854] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement realistic operational settings and building users to take concrete energy-saving actions. For example, the following messages may be displayed:

[0855] (Recommendation)

[0856] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0857] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0858] (Request for energy conservation actions)

[0859] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0860] In this way, the system of the present invention realizes a system that can maximize the comfort level and energy efficiency of the building environment by combining real-time data and emotional data.

[0861] (Example 2)

[0862] 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".

[0863] In recent years, building environment management has demanded a balance between improved energy efficiency and user comfort. However, conventional systems can only control systems based on limited information obtained from simple collection and analysis of environmental data, making it difficult to set optimal equipment operation settings that take into account user emotions and specific experiences. Furthermore, messages encouraging energy-saving behavior tend to be monotonous, making it difficult to gain user cooperation. Therefore, more advanced data analysis and equipment operation that takes user experience into consideration are needed.

[0864] 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.

[0865] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating energy-saving action requests to building users when additional energy-saving measures are needed, means for collecting and analyzing user emotion data, and means for adjusting equipment operation settings based on emotion data. By combining user emotion data with conventional environmental data, more accurate and optimal equipment operation settings become possible, achieving both improved energy efficiency and user comfort. Furthermore, by generating specific energy-saving action request messages tailored to the user's situation, it becomes easier to obtain cooperation from users.

[0866] "Means for obtaining the number of visitors" refers to devices or methods for measuring and recording the number of people who enter a building within a certain period of time, using sensors or access control systems installed within the building.

[0867] "Means for obtaining indoor temperature" refers to devices or methods for measuring and recording the real-time temperature of a location using temperature sensors placed on each floor or in each room within a building.

[0868] "Means for obtaining outside air temperature" refers to devices or methods for measuring and recording the temperature of the external environment using sensors installed on the outside of a building.

[0869] "Means for acquiring weather information" refers to devices and methods for acquiring and recording weather information using weather sensors installed near a building or external weather data provision services.

[0870] "Means for acquiring solar radiation" refers to devices or methods for measuring and recording the intensity and illuminance of direct sunlight using solar radiation sensors installed on the exterior or rooftop of a building.

[0871] "Methods for predicting in-building environmental information based on acquired data" refer to algorithms and methods for analyzing collected data such as temperature, number of visitors, weather, and solar radiation to estimate and predict the future in-building environment.

[0872] "Means for recommending optimal equipment operation based on predicted in-building environmental information" refers to devices or methods that use prediction results to propose and recommend the optimal operating methods for equipment within a building (such as air conditioners and lighting).

[0873] "Means for calculating estimated energy savings based on recommendations" refers to devices or methods for calculating the energy consumption reduction effect predicted by the proposed equipment operation method.

[0874] "Means for generating requests for energy-saving actions from building users when additional energy-saving measures are needed" refers to devices or methods for creating and notifying building users of specific energy-saving actions when further energy conservation is required.

[0875] "Means for collecting and analyzing user emotional data" refers to devices and methods that use cameras and wearable devices installed within a building to analyze users' facial expressions and behavior, and to recognize and record their emotional state.

[0876] "Means for adjusting equipment operation settings based on emotional data" refers to devices or methods for appropriately adjusting equipment operation methods to improve user comfort based on collected emotional data.

[0877] This invention is a system for optimizing environmental control and energy efficiency within a building. By integrating user emotion data, it aims to maximize energy efficiency while enhancing user comfort. This system performs multi-stage processing, including real-time data collection, predictive analysis, and emotion analysis, to generate recommendations for optimal equipment operation and request energy-saving behavior from building users, thereby achieving both energy efficiency and comfort.

[0878] System Configuration

[0879] This system consists of the following elements:

[0880] Sensor devices

[0881] server

[0882] terminal

[0883] Emotional Engine

[0884] Sensor devices: These are installed inside and outside buildings to acquire data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time. Specifically, they include temperature sensors, access control systems, weather sensors, and solar radiation sensors.

[0885] Server: Integrates and stores data collected from sensor devices and uses machine learning algorithms to predict future data. It also collects and analyzes user emotion data through an emotion engine. Based on this data, it also has the function of generating optimal equipment operation settings and calculating estimated energy savings.

[0886] Terminals: These devices display recommendations and energy-saving requests received from the server to facility managers and building users. Specifically, this includes smartphones, tablets, and PC displays.

[0887] Emotion Engine: Collects the user's facial expressions and heart rate through cameras and wearable devices, and analyzes their emotional state. It determines whether the user is comfortable or uncomfortable and sends that data to a server.

[0888] Program processing

[0889] Server: Collects data on visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation in real time from various sensor devices and external APIs, and stores it in a database. The stored data is used with machine learning algorithms to predict future data and generate predicted values ​​for visitor numbers, indoor temperature, and energy consumption. Furthermore, it collects and analyzes user sentiment data through an emotion engine and generates optimal equipment operation settings based on the obtained sentiment data. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the set temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[0890] Server: Calculates estimated energy savings based on recommendations, determines the expected reduction in energy consumption by adjusting temperature settings or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it creates a message encouraging specific energy-saving actions on that floor.

[0891] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[0892] (Recommendation)

[0893] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[0894] Please turn off the lights in the conference room. Estimated energy savings: 5%

[0895] (Request for energy conservation actions)

[0896] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[0897] Specific example

[0898] For example, suppose the following data was collected in a certain office building.

[0899] The number of visitors at 10:00 AM was 500.

[0900] The temperature inside the building is 25℃

[0901] The outside temperature is 30℃

[0902] The weather is sunny.

[0903] Solar radiation is 800 W / m²

[0904] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[0905] The number of visitors will increase to 600.

[0906] The temperature inside the building is expected to rise to 27°C.

[0907] Many users find it unpleasant.

[0908] Server: Based on this data, it generates recommendations to lower the set temperature to 24°C and turn off the lights in unused meeting rooms. It also takes sentiment data into account to estimate the energy consumption reduction effect and includes an estimated 10% energy consumption reduction in the report.

[0909] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[0910] Examples of prompt statements

[0911] The following are examples of prompts used by a generative AI model to generate appropriate recommendation messages.

[0912] Please generate recommendations for building environmental control based on the following data.

[0913] Number of visitors: 500

[0914] Indoor temperature: 25℃

[0915] Outside temperature: 30℃

[0916] Weather: Sunny

[0917] Solar radiation: 800 W / m²

[0918] User sentiment data: Many users feel uncomfortable.

[0919] Please output appropriate action recommendations and predicted energy-saving effects.

[0920] By inputting this prompt into the generating AI model, it becomes possible to obtain recommendations that balance efficient energy management with user comfort.

[0921] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0922] Step 1:

[0923] Data collection

[0924] The server collects data in real time from various sensor devices installed within the building (such as access control systems, temperature sensors, weather sensors, and solar radiation sensors). Specifically, it acquires the following information every minute:

[0925] input:

[0926] Number of visitors

[0927] Indoor temperature

[0928] outside temperature

[0929] weather

[0930] solar radiation

[0931] output:

[0932] The collected data set (raw data)

[0933] By regularly saving data to a database, we create a foundation for accumulating historical data and using it for future predictions.

[0934] Step 2:

[0935] Data storage and management

[0936] The server stores the collected data in a database. A timestamp is added to each data entry during storage, and the data is managed centrally.

[0937] input:

[0938] Raw data collected in Step 1

[0939] output:

[0940] Data stored in a database with timestamps

[0941] This enables time-series analysis of the data and provides a data infrastructure for use in subsequent processing.

[0942] Step 3:

[0943] Data Prediction

[0944] The server uses machine learning algorithms to predict future data based on stored data. This includes past visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation data.

[0945] input:

[0946] Historical data in the database

[0947] output:

[0948] Predicted values ​​for future visitor numbers, indoor temperature, and energy consumption.

[0949] Specifically, it learns trends and patterns in collected data to predict, for example, the number of visitors or the temperature inside the building in the next hour.

[0950] Step 4:

[0951] Emotional data collection

[0952] The server collects users' facial expressions and biometric information through cameras and wearable devices installed within the building, and analyzes it using an emotion engine.

[0953] input:

[0954] Biometric information from cameras and wearable devices (facial expressions, heart rate, etc.)

[0955] output:

[0956] User emotional state data (comfortable, uncomfortable, etc.)

[0957] Emotional data is organized in formats such as JSON and stored in a database in real time.

[0958] Step 5:

[0959] Data integration analysis

[0960] The server integrates environmental and sentiment data and performs a comprehensive analysis. During this process, it evaluates the correlation and impact of each data point.

[0961] input:

[0962] Environmental data (temperature inside the building, number of visitors, etc.)

[0963] Emotional data

[0964] output:

[0965] Analysis results (correlation between emotional state and environment, etc.)

[0966] Specifically, visualization in the form of graphs and statistical information should also be considered.

[0967] Step 6:

[0968] Generating equipment operation recommendations

[0969] Based on these analysis results, the server generates specific equipment operation recommendations. For example, it creates specific temperature settings for adjusting the building temperature and instructions for turning lights on and off.

[0970] input:

[0971] Analysis results

[0972] output:

[0973] Equipment operation recommendations (temperature settings, lighting management, etc.)

[0974] For example, it can generate specific instructions such as, "The temperature inside the building has risen to 27°C, so lower the set temperature to 24°C."

[0975] Step 7:

[0976] Calculation of estimated energy savings

[0977] The server calculates the expected reduction in energy consumption based on the generated equipment operation recommendations.

[0978] input:

[0979] Equipment operation recommendations

[0980] output:

[0981] Calculation results of estimated energy savings (reduction rate and specific energy amount)

[0982] For example, it can output specific figures such as "lowering the air conditioner's temperature setting by 2°C will reduce energy consumption by 10%."

[0983] Step 8:

[0984] Generating a message requesting energy-saving actions

[0985] The server generates messages to building users as needed, prompting them to take specific energy-saving actions. These messages may include specific instructions such as "turn off the lights" on certain floors.

[0986] input:

[0987] Equipment operation recommendations

[0988] Calculation results of estimated power savings

[0989] output:

[0990] Message requesting energy conservation actions

[0991] Specifically, it generates messages such as, "We ask users of Floor B to turn off any unnecessary lights."

[0992] Step 9:

[0993] Notifications and displays

[0994] The terminal notifies and displays recommendations, estimated power savings, and power-saving action request messages sent from the server to facility managers and building users.

[0995] input:

[0996] Notification data from the server (recommendations, estimated volume, request messages)

[0997] output:

[0998] Display and notification as a display or alert.

[0999] For example, a notification might appear on your smartphone or tablet saying, "The temperature inside the building will rise to 27°C, so please adjust the temperature setting to 24°C."

[1000] This allows the server, terminal, and user to each perform their specific actions, ensuring a smooth overall system processing flow.

[1001] (Application Example 2)

[1002] 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."

[1003] Conventional environmental control systems in buildings and physical stores primarily relied on physical data such as temperature and lighting for their settings. This often resulted in insufficient management that considered user comfort, potentially leading to decreased user satisfaction. Furthermore, optimal equipment operation was often not achieved, hindering energy efficiency improvements. Therefore, this invention aims to achieve both user comfort and energy efficiency by acquiring user emotional data, optimizing environmental control within buildings and physical stores based on this data, and further enhancing energy efficiency.

[1004] 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.

[1005] In this invention, the server includes means for acquiring emotional data, means for analyzing the user's level of comfort based on the acquired emotional data, and means for adjusting equipment operation recommendations according to the analyzed level of comfort. This enables environmental control based on user comfort. Furthermore, it makes it possible to optimize the energy efficiency of the facility and reduce energy consumption.

[1006] "Means for obtaining the number of visitors" refers to devices or systems that detect the number of people entering and leaving a facility and collect that data.

[1007] "Means for obtaining indoor temperature" refers to devices or systems for measuring the temperature inside a facility and collecting that data.

[1008] "Means for obtaining outside air temperature" refers to devices or systems for measuring the temperature outside a facility and collecting that data.

[1009] "Means of acquiring weather information" refers to devices and systems that detect current weather conditions (such as sunny, rainy, or snowy) and collect that data.

[1010] "Means for acquiring solar radiation" refers to devices or systems for measuring the amount of sunlight irradiating the area and collecting that data.

[1011] "Means for predicting in-building environmental information" refers to devices and systems that predict future environmental conditions within a building based on various acquired data.

[1012] "Means for recommending optimal equipment operation" refers to devices or systems that propose the optimal operating method for equipment based on predicted in-building environmental information.

[1013] A "means for calculating estimated energy savings" refers to a device or system used to calculate how much energy can be saved by operating equipment according to recommended specifications.

[1014] "Means for generating requests for energy-saving actions" refers to devices or systems that generate messages encouraging users to take specific energy-saving actions.

[1015] "Means for acquiring emotional data" refers to devices or systems that detect a user's emotional state and collect that data.

[1016] "Means for analyzing user comfort levels" refer to devices and systems that analyze how comfortable users feel based on acquired emotional data.

[1017] "Means for adjusting equipment operation recommendations" refer to devices or systems that propose adjustments to the operation methods of equipment within a facility based on the analyzed comfort level.

[1018] This invention combines a system that optimizes environmental control and energy efficiency within buildings and retail stores with an engine that recognizes user emotions, thereby maximizing energy efficiency while improving user comfort. This system generates recommendations for optimal equipment operation based on real-time data collection, predictive analysis, and sentiment analysis, and requests energy-saving actions from building users and store managers, thereby achieving a further balance of energy efficiency and comfort.

[1019] System Overview

[1020] The server will use the following hardware and software.

[1021] hardware

[1022] Various sensors

[1023] Visitor count sensor

[1024] Building temperature sensor

[1025] Outdoor temperature sensor

[1026] Weather sensor

[1027] Solar radiation sensor

[1028] software

[1029] Data Acquisition Module

[1030] Predictive Analytics Module

[1031] Emotional Engine

[1032] Recommendation generation module

[1033] Energy saving estimate calculation module

[1034] Notification generation module

[1035] The server collects the following data in real time from various sensor devices and external APIs:

[1036] Number of visitors

[1037] Indoor temperature

[1038] outside temperature

[1039] weather

[1040] solar radiation

[1041] This data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Furthermore, a sentiment engine collects and analyzes user sentiment data. User sentiment data is acquired, for example, through cameras and wearable devices installed within the building or stores.

[1042] The server combines predictive and sentiment data to generate optimal facility operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[1043] The system also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[1044] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[1045] (Recommendation)

[1046] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1047] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1048] (Request for energy conservation actions)

[1049] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1050] Specific example

[1051] For example, suppose the following data was collected at a physical store.

[1052] The number of visitors at 10:00 AM was 100.

[1053] The temperature inside the building is 25℃

[1054] The outside temperature is 30℃

[1055] The weather is sunny.

[1056] Solar radiation is 800 W / m²

[1057] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[1058] The number of visitors will increase to 120.

[1059] The temperature inside the building is expected to rise to 27°C.

[1060] Many users find it unpleasant.

[1061] Based on this data, the server recommends lowering the set temperature to 24°C and turning off the lights in unused meeting rooms. It also considers sentiment data to estimate the energy consumption reduction effect and includes a report showing an energy consumption reduction of approximately 10%. The terminal notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. In this way, combining real-time data with sentiment data enables the creation of a more comfortable and efficient environmental management system.

[1062] Example of a prompt

[1063] The following are specific examples of prompt statements for a generative AI model:

[1064] "Design a smartphone app version of the environmental management system. The app will collect environmental data and customer sentiment data from physical stores in real time and suggest optimal environmental settings. It should also suggest setting changes, calculate the resulting energy-saving effects, and notify the administrator."

[1065] This can improve customer satisfaction and energy efficiency in physical stores.

[1066] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1067] Step 1:

[1068] The server collects necessary data in real time from various sensor devices and external APIs. Specifically, it acquires current data using visitor count sensors, indoor temperature sensors, outdoor temperature sensors, weather sensors, and solar radiation sensors. The input is the data from each sensor, and the output is an integrated environmental dataset containing that data.

[1069] Step 2:

[1070] The server stores collected environmental data in a database and uses machine learning algorithms to predict future data. The input is an integrated environmental dataset, and the output includes predicted visitor numbers, indoor temperature, energy consumption, and other data. Time series analysis and regression analysis are used for prediction.

[1071] Step 3:

[1072] The server uses an emotion engine to acquire and analyze user emotion data. Specifically, it extracts emotion data from cameras and wearable devices installed within buildings and stores. The input is emotion data, and the output is analyzed user comfort level information.

[1073] Step 4:

[1074] The server generates optimal equipment operation settings based on predictive data and sentiment data. Inputs are predictive data and comfort level information, while outputs are recommendation information such as temperature settings and lighting adjustments. This process utilizes a condition-dependent optimization algorithm.

[1075] Step 5:

[1076] The server calculates the energy-saving effect of configuration changes based on the generated recommendation information. The input is the recommendation information, and the output is the estimated amount of energy saved. An energy model is used to calculate the effect of reducing energy consumption.

[1077] Step 6:

[1078] The server compiles estimated energy savings and recommendation information into a report and generates energy-saving action request messages as needed. The input is estimated energy savings and recommendation information, and the output is the report and energy-saving action request messages.

[1079] Step 7:

[1080] The terminal displays recommendation information, estimated energy savings, and energy-saving action request messages received from the server. This allows facility managers and building users to take concrete actions. The inputs are recommendation information, estimated energy savings, and energy-saving action request messages, and the output is a display screen showing this information.

[1081] Step 8:

[1082] Users take action based on recommendations and energy-saving requests displayed on their devices. For example, they might adjust the temperature setting or turn off unnecessary lights. The input is the information displayed on the screen, and the output is the specific energy-saving action performed by the user.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] [Third Embodiment]

[1087] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1088] 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.

[1089] 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).

[1090] 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.

[1091] 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.

[1092] 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).

[1093] 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.

[1094] 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.

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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".

[1099] This invention is a system for optimizing environmental control and energy efficiency within a building. This system collects real-time data, performs predictive analysis, and generates recommendations for optimal equipment operation, thereby achieving both comfort and energy savings.

[1100] System Overview

[1101] This system primarily consists of sensor devices, a server, and terminals. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data and uses a predictive model to forecast the future indoor environment. Furthermore, the server recommends optimal equipment operation settings based on the predicted data and notifies facility managers and building users of the results.

[1102] Program processing

[1103] Server: Collects the following data from each sensor device and external API.

[1104] Number of visitors

[1105] Indoor temperature

[1106] outside temperature

[1107] weather

[1108] solar radiation

[1109] The collected data is stored in a database, and machine learning algorithms are used to predict the future environment inside the building. For example, it predicts the number of visitors, indoor temperature, and energy consumption for the next few hours. Based on the predicted data, specific recommendations are made to maximize comfort and energy efficiency, such as the following:

[1110] Changing the set temperature

[1111] Lights ON / OFF

[1112] Based on these recommendations, the estimated amount of energy saved is calculated and generated as a report. Furthermore, depending on the predicted results, messages are prepared requesting additional energy-saving actions from building users as needed, such as turning off unnecessary lights on specific floors or adjusting the temperature settings.

[1113] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement appropriate equipment operation and building users to take concrete energy-saving actions.

[1114] Specific example

[1115] For example, suppose a sensor device in an office building collects the following data.

[1116] The number of visitors at 10:00 AM was 500.

[1117] The temperature inside the building is 25℃

[1118] The outside temperature is 30℃

[1119] The weather is sunny.

[1120] Solar radiation is 800 W / m²

[1121] Server: Based on the above data, it generates forecast data for 12:00 AM. Based on this forecast, it makes the following facility operation recommendations.

[1122] The number of visitors will increase to 600.

[1123] The temperature inside the building is predicted to rise to 27°C.

[1124] As a result, the server recommends the following configuration changes.

[1125] Lower the set temperature to 24°C.

[1126] Turn off the lights in unused meeting rooms.

[1127] Furthermore, the report will include calculations of estimated energy savings based on these recommendations, showing that energy consumption reductions of 10% and 5%, respectively, can be expected.

[1128] Terminal: Displays recommended temperature settings and lighting-off instructions to facility managers and building users. For example, the following message may be displayed:

[1129] (Recommendation)

[1130] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[1131] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1132] (Request for energy conservation actions)

[1133] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1134] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[1135] The following describes the processing flow.

[1136] Step 1:

[1137] Server: Collects real-time data from various sensor devices and external APIs. The number of visitors is measured using counter sensors installed at each entrance of the building, and the indoor temperature is obtained from temperature sensors on each floor. Outdoor temperature is obtained from outdoor temperature sensors, and weather information is obtained via a weather API. Solar radiation is obtained from solar radiation sensors. All collected data is stored in a database.

[1138] Step 2:

[1139] Server: Uses machine learning models based on collected data to predict future data. Specifically, it uses models trained on historical data to predict fluctuations in visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation. For example, it uses linear regression or deep learning algorithms to generate predicted visitor numbers and indoor temperature for the next few hours.

[1140] Step 3:

[1141] Server: Based on predictive data, it generates optimal equipment operating settings to maximize comfort and energy efficiency within the building. For example, if the building temperature is predicted to rise to 27°C, it will generate a recommendation to change the set temperature to 24°C. It also includes recommendations to turn off unnecessary lights.

[1142] Step 4:

[1143] Server: Calculates estimated energy savings based on recommendations. It calculates specific energy-saving effects, such as a 10% reduction in energy consumption when the set temperature is lowered by 1°C, or a 5% reduction when the lights are turned off, and compiles the results into a report.

[1144] Step 5:

[1145] Server: If additional energy-saving measures are needed based on the prediction results, prepare specific energy-saving action requests for building users. For example, generate messages requesting that unnecessary lights be turned off on specific floors or for specific groups of people.

[1146] Step 6:

[1147] Terminal: Displays messages to facility managers and building users that include recommendations, estimated energy savings, and requests for energy-saving actions received from the server. This enables facility managers to operate equipment appropriately and building users to take concrete energy-saving actions. For example, the following messages may be displayed via the display or notification system.

[1148] (Recommendation)

[1149] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[1150] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1151] (Request for energy conservation actions)

[1152] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1153] (Example 1)

[1154] 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."

[1155] In modern building management, achieving both a comfortable indoor environment and optimized energy efficiency simultaneously is crucial. However, few systems manage multiple factors such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and use this data to make predictions and recommendations. Furthermore, there are insufficient means to encourage building users to take action to conserve energy. As a result, there is a problem where excessive energy consumption can occur, compromising comfort levels.

[1156] 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.

[1157] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for storing the acquired data in a time-series database, means for predicting indoor environmental information using a machine learning algorithm based on the stored data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to building users when additional energy-saving measures are needed, means for notifying building users of changes in equipment operation, and means for monitoring user behavior and generating a report on the effects. This enables real-time data collection and analysis, and the recommendation of optimal equipment operation based on predictions, thereby achieving both energy efficiency and comfort.

[1158] "Means for obtaining the number of visitors" refers to devices and technologies for detecting and measuring the number of people entering a building in real time and collecting that data.

[1159] "Means for obtaining building temperature" refers to devices and technologies for detecting and measuring the temperature inside a building in real time and collecting that data.

[1160] "Means for obtaining outside air temperature" refers to devices and technologies for detecting and measuring the temperature outside a building in real time and collecting that data.

[1161] "Means of acquiring weather information" refers to devices and technologies for acquiring current weather conditions in real time and collecting that data.

[1162] "Means for acquiring solar radiation" refers to devices and technologies for measuring the amount of sunlight irradiating in real time and collecting that data.

[1163] "Means of storing data in a time-series database" refers to the technology of a database and the method of storing data in a chronological order.

[1164] "Methods for predicting in-building environmental information using machine learning algorithms" refers to methods and technologies that use stored data and machine learning techniques to predict future in-building environmental conditions.

[1165] "A means of recommending optimal equipment operation" is a technology that proposes the optimal equipment operation method to maximize energy efficiency and comfort based on predicted data.

[1166] A "means for calculating estimated energy savings" is a technology that calculates how much energy consumption reduction can be expected based on recommended equipment operation settings.

[1167] "Means for generating requests for energy-saving actions from building users" refers to technology that generates request messages to encourage specific actions from building users when additional energy-saving actions are needed.

[1168] "Means of notifying building users of changes in equipment operation" refers to technology that informs building users of recommended changes in equipment operation through displays or notification systems.

[1169] "A means of monitoring user behavior and generating results as a report" refers to technology that monitors user actions, analyzes the results, and provides them in report format.

[1170] This invention relates to a system for optimizing environmental control and energy efficiency within a building. This system primarily consists of sensor devices, servers, and terminals. Specific embodiments are described below.

[1171] Server Processing

[1172] 1. Data Collection

[1173] The server collects data in real time from various sensor devices and external APIs. Specifically, the sensor devices measure the current number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, and transmit this data to the server. The hardware and software used include temperature sensors, an access control system, and various APIs. The server stores this data in a time-series database (e.g., InfluxDB).

[1174] 2. Data Analysis and Prediction

[1175] The server uses machine learning algorithms (e.g., TensorFlow) based on stored data to predict information about the building's environment. This prediction includes accurately forecasting future visitor numbers, building temperature, energy consumption, and more by combining historical and real-time data.

[1176] 3. Recommendation generation

[1177] The server recommends optimal equipment operating settings based on predictive data. This includes changing the set temperature and turning lights on or off. Furthermore, it calculates the estimated amount of energy saved based on these recommendations. For example, if the predictive data indicates that the number of visitors or the temperature will fluctuate in the next few hours, it will generate recommendations such as changing the set temperature to 24°C and turning off the lights in unused meeting rooms.

[1178] 4. Generating requests for energy-saving actions

[1179] If additional energy-saving measures are required, the server generates energy-saving requests for building users. Specifically, it notifies them via message to turn off unnecessary lights on certain floors or adjust the temperature settings.

[1180] Terminal processing

[1181] 1. Display of recommendations and notifications

[1182] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. This allows facility managers to operate the facilities appropriately and building users to take concrete energy-saving actions. Notification methods include email, SMS, and notifications via a dedicated app.

[1183] User behavior

[1184] 1. Operation by the facility administrator

[1185] The facility manager checks the terminal notifications and makes changes to the temperature settings or turns lights on / off according to the server's recommendations. For example, they might change the HVAC system's temperature setting to 24°C and manually turn off the lights in unused conference rooms.

[1186] 2. Cooperation from building users

[1187] Building users will also check the notification and take specific energy-saving actions. For example, they may manually turn off unnecessary lights, or automated systems may turn off the lights.

[1188] Specific example

[1189] For example, suppose a sensor device in an office building collects the following data.

[1190] The number of visitors at 10:00 AM was 500.

[1191] The temperature inside the building is 25℃

[1192] The outside temperature is 30℃

[1193] The weather is sunny.

[1194] Solar radiation is 800 W / m²

[1195] Based on the above data, the server generates forecast data for 12:00 AM. Based on this forecast, the server makes the following facility operation recommendations.

[1196] The number of visitors will increase to 600.

[1197] The temperature inside the building is predicted to rise to 27°C.

[1198] This will lead to the following recommended setting changes.

[1199] Lower the set temperature to 24°C.

[1200] Turn off the lights in unused meeting rooms.

[1201] Furthermore, the report calculates the estimated energy savings based on these recommendations and includes a figure indicating that energy consumption can be reduced by 10% and 5%, respectively. For example, the following message will be displayed on the device.

[1202] (Recommendation)

[1203] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[1204] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1205] (Request for energy conservation actions)

[1206] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1207] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[1208] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1209] Step 1:

[1210] Sensor data collection

[1211] The server collects data in real time from each sensor device and external API. Inputs include the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, all transmitted from the sensor devices. The server acquires this data and processes it accordingly. Specifically, the temperature sensor transmits current temperature data every 30 seconds, and the outdoor temperature sensor transmits data similarly. The number of visitors is also acquired in real time in conjunction with the visitor management system.

[1212] Input: Number of visitors from sensor devices, indoor temperature, outdoor temperature, weather, solar radiation.

[1213] Output: Collected real-time data

[1214] Step 2:

[1215] Data storage

[1216] The server stores the collected data in a time-series database (e.g., InfluxDB). The input is the data collected in step 1. During storage, the server checks data quality and flags any outliers or missing values. Specifically, as soon as data arrives, it is inserted into the database and marked for later anomaly analysis.

[1217] Input: Collected real-time data

[1218] Output: Data stored in a time-series database

[1219] Step 3:

[1220] Generation of Predictive Models

[1221] The server generates a predictive model using a machine learning algorithm (e.g., TensorFlow) based on data stored in a time-series database. The input is the stored time-series data. This data is fed into the machine learning model to predict future conditions within the building (number of visitors, indoor temperature, energy consumption, etc.). For example, the ML model is updated every night at midnight using the day's data. Real-time predictions are recalculated every 10 minutes to update future conditions.

[1222] Input: Data stored in a time-series database

[1223] Output: Predicted in-building environment data

[1224] Step 4:

[1225] Creating recommendations

[1226] The server recommends optimal equipment operation settings based on predictive data. The input is predicted in-building environment data. To maximize energy efficiency and comfort, it suggests changes to the set temperature and turning lights on / off. Specifically, based on the predictive data, the server recommends lowering the set temperature to 24°C and generates recommendations to turn off the lights in unused conference rooms.

[1227] Input: Predicted in-building environment data

[1228] Output: Recommended equipment operation schedule

[1229] Step 5:

[1230] Calculation of estimated energy savings

[1231] The server calculates the estimated amount of energy savings based on recommendations. The input is the recommended equipment operating settings. For example, it calculates that lowering the set temperature to 24°C can reduce energy consumption by 10%. In specific operations, it analyzes the predicted data and actual consumption data to estimate the energy saving effect.

[1232] Input: Recommended equipment operation settings

[1233] Output: Estimated amount of energy saved

[1234] Step 6:

[1235] Generating requests for energy-saving actions

[1236] The server generates energy-saving requests for building users when additional energy-saving measures are needed. The inputs are estimated energy savings and forecast data. For example, it generates messages notifying users to turn off unnecessary lights on specific floors or adjust temperature settings.

[1237] Input: Estimated amount of electricity saved, forecast data

[1238] Output: Message requesting energy-saving actions

[1239] Step 7:

[1240] Sending recommendations and notifications

[1241] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. Input consists of recommendations and energy-saving requests sent from the server. Notifications can be sent via pop-up notifications, email, or SMS, for example.

[1242] Input: Recommendation and energy-saving action request messages sent from the server

[1243] Output: Information displayed via the display or notification system.

[1244] Step 8:

[1245] User behavior

[1246] Users check notifications on their devices and perform actions such as changing the temperature setting or turning lights on or off as instructed. Specifically, the facility manager changes the HVAC system's temperature setting to 24°C, and users manually turn off unnecessary lights. In some cases, an automated system may also turn off the lights.

[1247] Input: Device notifications

[1248] Output: Changes to the set temperature and lighting ON / OFF have been performed.

[1249] Step 9:

[1250] Report generation

[1251] The server monitors user behavior and energy consumption, and generates reports based on the collected data. Inputs include user behavior data and energy consumption data. This allows for the creation of reports that include comparisons between predictions and actual data, energy saving effectiveness, and comfort level evaluations. Monthly reports can be generated as PDFs and sent via email.

[1252] Input: User behavior data, energy consumption data

[1253] Output: Report (PDF format, etc.)

[1254] The above outlines the specific processing steps of this system.

[1255] (Application Example 1)

[1256] 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."

[1257] In modern buildings and factories, maintaining a comfortable environment while maximizing energy efficiency is a crucial challenge. However, current systems often lack sufficient real-time data collection and predictive analysis, and energy consumption optimization and efficient operation schedules are frequently managed manually, leading to significant energy waste. Furthermore, ineffective robot scheduling and energy management within factories result in high operating costs.

[1258] 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.

[1259] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to facility users when additional energy-saving measures are needed, means for predicting the robot's operation schedule and energy consumption based on data collected from sensor devices throughout the factory, and means for instructing the robot to perform optimal operation schedules and energy management based on the predictions. This enables environmental control and optimization of energy efficiency within buildings and factories.

[1260] "Means for obtaining visitor numbers" refers to devices or mechanisms that measure the number of visitors to a building or facility in real time and acquire that information as data.

[1261] "Means for obtaining indoor temperature" refers to devices or mechanisms that measure the temperature inside a building or facility and acquire that temperature data.

[1262] "Means for obtaining outside air temperature" refers to devices or mechanisms that measure the temperature outside a building or facility and acquire that data.

[1263] "Means of acquiring weather information" refers to devices or mechanisms that measure current weather conditions and acquire that information as data.

[1264] "Means for acquiring solar radiation" refers to devices or mechanisms that measure the amount of radiant energy from the sun and acquire that data.

[1265] "Means for predicting in-building environmental information" refers to devices or systems that predict the environmental conditions inside a building at a future point in time based on acquired data.

[1266] "Means for recommending optimal equipment operation" refers to devices or systems that generate optimal recommendations for equipment operation methods and settings based on predicted in-building environmental information.

[1267] "Means for calculating estimated energy savings" refers to devices or software that calculate the expected amount of energy savings based on recommendations.

[1268] A "means for generating requests for energy-saving actions" refers to a device or system that generates a message requesting facility users to take additional energy-saving measures when necessary.

[1269] "Factory-wide sensor devices" refer to a group of sensors installed to measure various environmental conditions and operational status within a factory.

[1270] "Means for predicting robot operation schedules and energy consumption" refers to devices or systems that predict robot operation schedules and energy consumption based on data collected from sensor devices throughout the factory.

[1271] "Means for instructing robots on operating schedules and energy management" refers to devices or systems that, based on predictions, transmit optimal operating schedules and energy management instructions to robots.

[1272] Overall system configuration

[1273] This invention relates to a system for optimizing environmental control and energy efficiency within buildings or factories. The system primarily consists of sensor devices, a server, and terminals. Each sensor device acquires data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time and transmits this data to the server. The server analyzes the received data and uses a predictive model to forecast future indoor environments, robot operation schedules, and energy consumption within factories. This allows for recommendations for optimal equipment operation and energy management.

[1274] Hardware and software to be used

[1275] hardware

[1276] Sensor devices: Indoor thermometer, outdoor thermometer, weather sensor, solar radiation sensor, motion sensor

[1277] Server: Collects, analyzes, and builds predictive models for data.

[1278] Robots: Devices that operate within a factory.

[1279] Terminal: A device for managing facilities, including a display and notification system.

[1280] software

[1281] Python: Run programs for data collection, analysis, prediction, and recommendation generation.

[1282] Requests module: Handles communication with external APIs.

[1283] Scikit-learn: Building and analyzing predictive models

[1284] Smtplib: Sending email notifications

[1285] Data flow and processing

[1286] 1. Data Collection

[1287] The sensor device acquires data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and sends this data to the server. For example, the Python Requests module can be used to retrieve data from the sensor API.

[1288] 2. Predictive Analytics

[1289] The server uses the collected data to predict future building environments, robot operating schedules within factories, and energy consumption. For example, it uses Scikit-learn to build a linear regression model to predict environmental changes and energy consumption over the next few hours.

[1290] 3. Recommendation generation

[1291] The server recommends optimal equipment operation and energy management based on predictive data. For example, if a rise in indoor temperature is predicted, it recommends changing the temperature setting or turning lights on or off. It also optimizes robot operation schedules and generates instructions to reduce energy consumption.

[1292] 4. Notifications and Display

[1293] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server. This allows facility managers to implement appropriate equipment operation and enables building and factory users to take concrete energy-saving actions. Information is also sent to facility managers via email notifications.

[1294] Specific example

[1295] For example, in one office building, the following sensor data was acquired at 10:00 AM:

[1296] The number of visitors was 500.

[1297] The temperature inside the building is 25℃

[1298] The outside temperature is 30℃

[1299] The weather is sunny.

[1300] Solar radiation is 800 W / m²

[1301] Based on this data, the server generated a forecast for 12:00 AM, predicting that the number of visitors would increase to 600 and the indoor temperature would rise to 27°C. The server recommended lowering the thermostat to 24°C and turning off the lights in unused conference rooms, and calculated the estimated amount of energy consumption reduction.

[1302] Example of a prompt

[1303] Based on the following sensor data, predict the future factory environment and create optimal equipment operation settings.

[1304] Sensor data:

[1305] Temperature: 28℃

[1306] Humidity: 50%

[1307] Number of visitors: 100

[1308] Please provide future forecast data, showing how temperature, humidity, and visitor numbers will change, and recommend specific setting changes.

[1309] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1310] Step 1:

[1311] Sensor devices measure data within buildings and factories in real time and transmit that data to a server. Specifically, data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation are collected. Each sensor device sends data to the server via an API, and the server stores this data collectively in a database.

[1312] Input: Real-time data from a sensor device.

[1313] Output: Measurement data stored in the database.

[1314] Step 2:

[1315] The system analyzes data collected by the server to predict future conditions within the building and factory. Here, Python is used to process the data, and Scikit-learn is used to build predictive models. For example, a linear regression model is used to predict temperature, humidity, visitor numbers, and energy consumption over the next few hours.

[1316] Input: Measurement data stored in the database.

[1317] Output: Predictive data on future indoor environments and factory conditions.

[1318] Step 3:

[1319] The server generates recommendations for optimal equipment operation based on predictive data. Specifically, it determines the optimal temperature settings, lighting ON / OFF states, etc., for predicted environmental conditions. This process generates recommendations by making conditional judgments based on the output of the predictive model.

[1320] Input: Prediction data.

[1321] Output: Recommendations for optimal equipment operation.

[1322] Step 4:

[1323] Based on recommendations generated by the server, the expected amount of energy savings is calculated. For example, it calculates how much energy can be saved by changing the temperature setting, or how much cost reduction can be expected by turning off unnecessary lights.

[1324] Input: Recommendation.

[1325] Output: Calculation result of estimated energy savings.

[1326] Step 5:

[1327] The server generates additional energy-saving requests for facility users as needed. For example, in addition to requests to change the temperature or turn lights on or off, it generates messages requesting specific energy-saving actions from users.

[1328] Input: Calculation result of estimated energy savings.

[1329] Output: Message requesting energy-saving actions.

[1330] Step 6:

[1331] The terminal displays recommendations and energy-saving action requests received from the server. This allows facility managers to take concrete action and maximize energy efficiency. The information is displayed via a display or notification system.

[1332] Input: Messages requesting energy-saving actions or recommendations.

[1333] Output: The message displayed on the terminal.

[1334] Step 7:

[1335] The server sends an email notification to the facility administrator as needed. Smtplib is used to send the generated message to the facility administrator via email, allowing them to respond immediately.

[1336] Input: Message requesting energy-saving actions.

[1337] Output: Email notification to the facility administrator.

[1338] 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.

[1339] This invention combines a system for optimizing environmental control and energy efficiency within a building with an engine that recognizes user emotions, thereby maximizing energy efficiency while enhancing user comfort. This system generates recommendations for optimal equipment operation based on real-time data collection, predictive analysis, and emotion analysis, and requests energy-saving actions from building users, thereby achieving a further balance of energy efficiency and comfort.

[1340] System Overview

[1341] This system consists of sensor devices, a server, terminals, and an emotion engine. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data to predict the building's environmental conditions. Furthermore, the emotion engine acquires user emotion data and adjusts facility operation recommendations accordingly. Finally, the server generates optimal settings based on this information and notifies facility managers and building users.

[1342] Program processing

[1343] Server: Collects the following data in real time from various sensor devices and external APIs.

[1344] Number of visitors

[1345] Indoor temperature

[1346] outside temperature

[1347] weather

[1348] solar radiation

[1349] The collected data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Then, an emotion engine collects user emotion data, which is then analyzed. User emotion data is obtained, for example, through cameras and wearable devices installed within the building.

[1350] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[1351] Server: Also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it prepares additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[1352] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[1353] (Recommendation)

[1354] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1355] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1356] (Request for energy conservation actions)

[1357] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1358] Specific example

[1359] For example, suppose the following data was collected in a certain office building.

[1360] The number of visitors at 10:00 AM was 500.

[1361] The temperature inside the building is 25℃

[1362] The outside temperature is 30℃

[1363] The weather is sunny.

[1364] Solar radiation is 800 W / m²

[1365] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[1366] The number of visitors will increase to 600.

[1367] The temperature inside the building is expected to rise to 27°C.

[1368] Many users find it unpleasant.

[1369] Server: Based on this data, recommend lowering the temperature setting to 24°C and turning off the lights in unused meeting rooms. Also, consider sentiment data to estimate the energy consumption reduction effect and include an estimated 10% energy consumption reduction in the report.

[1370] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[1371] The following describes the processing flow.

[1372] Step 1:

[1373] Server: Collects real-time data from each sensor device and external API. Specifically, the number of visitors is obtained from a counter sensor installed at the entrance, the indoor temperature from temperature sensors installed on each floor, and the outdoor temperature from outdoor temperature sensors. Weather information is obtained via a weather API, and solar radiation is obtained from a solar radiation sensor. The collected data is centrally managed and stored in a database.

[1374] Step 2:

[1375] Server: Uses machine learning algorithms to predict future data based on collected data. Specifically, it generates predictions for the next few hours using data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. In this process, it trains a model using historical datasets to achieve highly accurate predictions.

[1376] Step 3:

[1377] Server: Uses an emotion engine to collect user emotion data. This is done by analyzing users' facial expressions and behavior through cameras and wearable devices installed within the building. The emotion data is then analyzed to determine which emotion it corresponds to, such as pleasant or unpleasant.

[1378] Step 4:

[1379] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the predicted indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature setting to 24°C. Furthermore, it also generates recommendations to adjust lighting brightness and on / off settings based on sentiment data.

[1380] Step 5:

[1381] Server: Calculates estimated energy savings based on recommendations. For example, it makes specific predictions for cases where lowering the temperature by 1°C reduces energy consumption by 10%, or where turning off the lights reduces energy consumption by 5%. The calculation results are compiled into a report, clearly indicating the estimated energy savings.

[1382] Step 6:

[1383] Server: If additional energy-saving measures are needed, it generates specific energy-saving action requests for building users. For example, if many users are feeling uncomfortable on a particular floor, it generates a message requesting users on that floor to turn off unnecessary lights.

[1384] Step 7:

[1385] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement realistic operational settings and building users to take concrete energy-saving actions. For example, the following messages may be displayed:

[1386] (Recommendation)

[1387] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1388] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1389] (Request for energy conservation actions)

[1390] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1391] In this way, the system of the present invention realizes a system that can maximize the comfort level and energy efficiency of the building environment by combining real-time data and emotional data.

[1392] (Example 2)

[1393] 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."

[1394] In recent years, building environment management has demanded a balance between improved energy efficiency and user comfort. However, conventional systems can only control systems based on limited information obtained from simple collection and analysis of environmental data, making it difficult to set optimal equipment operation settings that take into account user emotions and specific experiences. Furthermore, messages encouraging energy-saving behavior tend to be monotonous, making it difficult to gain user cooperation. Therefore, more advanced data analysis and equipment operation that takes user experience into consideration are needed.

[1395] 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.

[1396] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating energy-saving action requests to building users when additional energy-saving measures are needed, means for collecting and analyzing user emotion data, and means for adjusting equipment operation settings based on emotion data. By combining user emotion data with conventional environmental data, more accurate and optimal equipment operation settings become possible, achieving both improved energy efficiency and user comfort. Furthermore, by generating specific energy-saving action request messages tailored to the user's situation, it becomes easier to obtain cooperation from users.

[1397] "Means for obtaining the number of visitors" refers to devices or methods for measuring and recording the number of people who enter a building within a certain period of time, using sensors or access control systems installed within the building.

[1398] "Means for obtaining indoor temperature" refers to devices or methods for measuring and recording the real-time temperature of a location using temperature sensors placed on each floor or in each room within a building.

[1399] "Means for obtaining outside air temperature" refers to devices or methods for measuring and recording the temperature of the external environment using sensors installed on the outside of a building.

[1400] "Means for acquiring weather information" refers to devices and methods for acquiring and recording weather information using weather sensors installed near a building or external weather data provision services.

[1401] "Means for acquiring solar radiation" refers to devices or methods for measuring and recording the intensity and illuminance of direct sunlight using solar radiation sensors installed on the exterior or rooftop of a building.

[1402] "Methods for predicting in-building environmental information based on acquired data" refer to algorithms and methods for analyzing collected data such as temperature, number of visitors, weather, and solar radiation to estimate and predict the future in-building environment.

[1403] "Means for recommending optimal equipment operation based on predicted in-building environmental information" refers to devices or methods that use prediction results to propose and recommend the optimal operating methods for equipment within a building (such as air conditioners and lighting).

[1404] "Means for calculating estimated energy savings based on recommendations" refers to devices or methods for calculating the energy consumption reduction effect predicted by the proposed equipment operation method.

[1405] "Means for generating requests for energy-saving actions from building users when additional energy-saving measures are needed" refers to devices or methods for creating and notifying building users of specific energy-saving actions when further energy conservation is required.

[1406] "Means for collecting and analyzing user emotional data" refers to devices and methods that use cameras and wearable devices installed within a building to analyze users' facial expressions and behavior, and to recognize and record their emotional state.

[1407] "Means for adjusting equipment operation settings based on emotional data" refers to devices or methods for appropriately adjusting equipment operation methods to improve user comfort based on collected emotional data.

[1408] This invention is a system for optimizing environmental control and energy efficiency within a building. By integrating user emotion data, it aims to maximize energy efficiency while enhancing user comfort. This system performs multi-stage processing, including real-time data collection, predictive analysis, and emotion analysis, to generate recommendations for optimal equipment operation and request energy-saving behavior from building users, thereby achieving both energy efficiency and comfort.

[1409] System Configuration

[1410] This system consists of the following elements:

[1411] Sensor devices

[1412] server

[1413] terminal

[1414] Emotional Engine

[1415] Sensor devices: These are installed inside and outside buildings to acquire data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time. Specifically, they include temperature sensors, access control systems, weather sensors, and solar radiation sensors.

[1416] Server: Integrates and stores data collected from sensor devices and uses machine learning algorithms to predict future data. It also collects and analyzes user emotion data through an emotion engine. Based on this data, it also has the function of generating optimal equipment operation settings and calculating estimated energy savings.

[1417] Terminals: These devices display recommendations and energy-saving requests received from the server to facility managers and building users. Specifically, this includes smartphones, tablets, and PC displays.

[1418] Emotion Engine: Collects the user's facial expressions and heart rate through cameras and wearable devices, and analyzes their emotional state. It determines whether the user is comfortable or uncomfortable and sends that data to a server.

[1419] Program processing

[1420] Server: Collects data on visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation in real time from various sensor devices and external APIs, and stores it in a database. The stored data is used with machine learning algorithms to predict future data and generate predicted values ​​for visitor numbers, indoor temperature, and energy consumption. Furthermore, it collects and analyzes user sentiment data through an emotion engine and generates optimal equipment operation settings based on the obtained sentiment data. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the set temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[1421] Server: Calculates estimated energy savings based on recommendations, determines the expected reduction in energy consumption by adjusting temperature settings or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it creates a message encouraging specific energy-saving actions on that floor.

[1422] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[1423] (Recommendation)

[1424] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1425] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1426] (Request for energy conservation actions)

[1427] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1428] Specific example

[1429] For example, suppose the following data was collected in a certain office building.

[1430] The number of visitors at 10:00 AM was 500.

[1431] The temperature inside the building is 25℃

[1432] The outside temperature is 30℃

[1433] The weather is sunny.

[1434] Solar radiation is 800 W / m²

[1435] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[1436] The number of visitors will increase to 600.

[1437] The temperature inside the building is expected to rise to 27°C.

[1438] Many users find it unpleasant.

[1439] Server: Based on this data, it generates recommendations to lower the set temperature to 24°C and turn off the lights in unused meeting rooms. It also takes sentiment data into account to estimate the energy consumption reduction effect and includes an estimated 10% energy consumption reduction in the report.

[1440] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[1441] Examples of prompt statements

[1442] The following are examples of prompts used by a generative AI model to generate appropriate recommendation messages.

[1443] Please generate recommendations for building environmental control based on the following data.

[1444] Number of visitors: 500

[1445] Indoor temperature: 25℃

[1446] Outside temperature: 30℃

[1447] Weather: Sunny

[1448] Solar radiation: 800 W / m²

[1449] User sentiment data: Many users feel uncomfortable.

[1450] Please output appropriate action recommendations and predicted energy-saving effects.

[1451] By inputting this prompt into the generating AI model, it becomes possible to obtain recommendations that balance efficient energy management with user comfort.

[1452] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1453] Step 1:

[1454] Data collection

[1455] The server collects data in real time from various sensor devices installed within the building (such as access control systems, temperature sensors, weather sensors, and solar radiation sensors). Specifically, it acquires the following information every minute:

[1456] input:

[1457] Number of visitors

[1458] Indoor temperature

[1459] outside temperature

[1460] weather

[1461] solar radiation

[1462] output:

[1463] The collected data set (raw data)

[1464] By regularly saving data to a database, we create a foundation for accumulating historical data and using it for future predictions.

[1465] Step 2:

[1466] Data storage and management

[1467] The server stores the collected data in a database. A timestamp is added to each data entry during storage, and the data is managed centrally.

[1468] input:

[1469] Raw data collected in Step 1

[1470] output:

[1471] Data stored in a database with timestamps

[1472] This enables time-series analysis of the data and provides a data infrastructure for use in subsequent processing.

[1473] Step 3:

[1474] Data Prediction

[1475] The server uses machine learning algorithms to predict future data based on stored data. This includes past visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation data.

[1476] input:

[1477] Historical data in the database

[1478] output:

[1479] Predicted values ​​for future visitor numbers, indoor temperature, and energy consumption.

[1480] Specifically, it learns trends and patterns in collected data to predict, for example, the number of visitors or the temperature inside the building in the next hour.

[1481] Step 4:

[1482] Emotional data collection

[1483] The server collects users' facial expressions and biometric information through cameras and wearable devices installed within the building, and analyzes it using an emotion engine.

[1484] input:

[1485] Biometric information from cameras and wearable devices (facial expressions, heart rate, etc.)

[1486] output:

[1487] User emotional state data (comfortable, uncomfortable, etc.)

[1488] Emotional data is organized in formats such as JSON and stored in a database in real time.

[1489] Step 5:

[1490] Data integration analysis

[1491] The server integrates environmental and sentiment data and performs a comprehensive analysis. During this process, it evaluates the correlation and impact of each data point.

[1492] input:

[1493] Environmental data (temperature inside the building, number of visitors, etc.)

[1494] Emotional data

[1495] output:

[1496] Analysis results (correlation between emotional state and environment, etc.)

[1497] Specifically, visualization in the form of graphs and statistical information should also be considered.

[1498] Step 6:

[1499] Generating equipment operation recommendations

[1500] Based on these analysis results, the server generates specific equipment operation recommendations. For example, it creates specific temperature settings for adjusting the building temperature and instructions for turning lights on and off.

[1501] input:

[1502] Analysis results

[1503] output:

[1504] Equipment operation recommendations (temperature settings, lighting management, etc.)

[1505] For example, it can generate specific instructions such as, "The temperature inside the building has risen to 27°C, so lower the set temperature to 24°C."

[1506] Step 7:

[1507] Calculation of estimated energy savings

[1508] The server calculates the expected reduction in energy consumption based on the generated equipment operation recommendations.

[1509] input:

[1510] Equipment operation recommendations

[1511] output:

[1512] Calculation results of estimated energy savings (reduction rate and specific energy amount)

[1513] For example, it can output specific figures such as "lowering the air conditioner's temperature setting by 2°C will reduce energy consumption by 10%."

[1514] Step 8:

[1515] Generating a message requesting energy-saving actions

[1516] The server generates messages to building users as needed, prompting them to take specific energy-saving actions. These messages may include specific instructions such as "turn off the lights" on certain floors.

[1517] input:

[1518] Equipment operation recommendations

[1519] Calculation results of estimated power savings

[1520] output:

[1521] Message requesting energy conservation actions

[1522] Specifically, it generates messages such as, "We ask users of Floor B to turn off any unnecessary lights."

[1523] Step 9:

[1524] Notifications and displays

[1525] The terminal notifies and displays recommendations, estimated power savings, and power-saving action request messages sent from the server to facility managers and building users.

[1526] input:

[1527] Notification data from the server (recommendations, estimated volume, request messages)

[1528] output:

[1529] Display and notification as a display or alert.

[1530] For example, a notification might appear on your smartphone or tablet saying, "The temperature inside the building will rise to 27°C, so please adjust the temperature setting to 24°C."

[1531] This allows the server, terminal, and user to each perform their specific actions, ensuring a smooth overall system processing flow.

[1532] (Application Example 2)

[1533] 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."

[1534] Conventional environmental control systems in buildings and physical stores primarily relied on physical data such as temperature and lighting for their settings. This often resulted in insufficient management that considered user comfort, potentially leading to decreased user satisfaction. Furthermore, optimal equipment operation was often not achieved, hindering energy efficiency improvements. Therefore, this invention aims to achieve both user comfort and energy efficiency by acquiring user emotional data, optimizing environmental control within buildings and physical stores based on this data, and further enhancing energy efficiency.

[1535] 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.

[1536] In this invention, the server includes means for acquiring emotional data, means for analyzing the user's level of comfort based on the acquired emotional data, and means for adjusting equipment operation recommendations according to the analyzed level of comfort. This enables environmental control based on user comfort. Furthermore, it makes it possible to optimize the energy efficiency of the facility and reduce energy consumption.

[1537] "Means for obtaining the number of visitors" refers to devices or systems that detect the number of people entering and leaving a facility and collect that data.

[1538] "Means for obtaining indoor temperature" refers to devices or systems for measuring the temperature inside a facility and collecting that data.

[1539] "Means for obtaining outside air temperature" refers to devices or systems for measuring the temperature outside a facility and collecting that data.

[1540] "Means of acquiring weather information" refers to devices and systems that detect current weather conditions (such as sunny, rainy, or snowy) and collect that data.

[1541] "Means for acquiring solar radiation" refers to devices or systems for measuring the amount of sunlight irradiating the area and collecting that data.

[1542] "Means for predicting in-building environmental information" refers to devices and systems that predict future environmental conditions within a building based on various acquired data.

[1543] "Means for recommending optimal equipment operation" refers to devices or systems that propose the optimal operating method for equipment based on predicted in-building environmental information.

[1544] A "means for calculating estimated energy savings" refers to a device or system used to calculate how much energy can be saved by operating equipment according to recommended specifications.

[1545] "Means for generating requests for energy-saving actions" refers to devices or systems that generate messages encouraging users to take specific energy-saving actions.

[1546] "Means for acquiring emotional data" refers to devices or systems that detect a user's emotional state and collect that data.

[1547] "Means for analyzing user comfort levels" refer to devices and systems that analyze how comfortable users feel based on acquired emotional data.

[1548] "Means for adjusting equipment operation recommendations" refer to devices or systems that propose adjustments to the operation methods of equipment within a facility based on the analyzed comfort level.

[1549] This invention combines a system that optimizes environmental control and energy efficiency within buildings and retail stores with an engine that recognizes user emotions, thereby maximizing energy efficiency while improving user comfort. This system generates recommendations for optimal equipment operation based on real-time data collection, predictive analysis, and sentiment analysis, and requests energy-saving actions from building users and store managers, thereby achieving a further balance of energy efficiency and comfort.

[1550] System Overview

[1551] The server will use the following hardware and software.

[1552] hardware

[1553] Various sensors

[1554] Visitor count sensor

[1555] Building temperature sensor

[1556] Outdoor temperature sensor

[1557] Weather sensor

[1558] Solar radiation sensor

[1559] software

[1560] Data Acquisition Module

[1561] Predictive Analytics Module

[1562] Emotional Engine

[1563] Recommendation generation module

[1564] Energy saving estimate calculation module

[1565] Notification generation module

[1566] The server collects the following data in real time from various sensor devices and external APIs:

[1567] Number of visitors

[1568] Indoor temperature

[1569] outside temperature

[1570] weather

[1571] solar radiation

[1572] This data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Furthermore, a sentiment engine collects and analyzes user sentiment data. User sentiment data is acquired, for example, through cameras and wearable devices installed within the building or stores.

[1573] The server combines predictive and sentiment data to generate optimal facility operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[1574] The system also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[1575] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[1576] (Recommendation)

[1577] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1578] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1579] (Request for energy conservation actions)

[1580] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1581] Specific example

[1582] For example, suppose the following data was collected at a physical store.

[1583] The number of visitors at 10:00 AM was 100.

[1584] The temperature inside the building is 25℃

[1585] The outside temperature is 30℃

[1586] The weather is sunny.

[1587] Solar radiation is 800 W / m²

[1588] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[1589] The number of visitors will increase to 120.

[1590] The temperature inside the building is expected to rise to 27°C.

[1591] Many users find it unpleasant.

[1592] Based on this data, the server recommends lowering the set temperature to 24°C and turning off the lights in unused meeting rooms. It also considers sentiment data to estimate the energy consumption reduction effect and includes a report showing an energy consumption reduction of approximately 10%. The terminal notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. In this way, combining real-time data with sentiment data enables the creation of a more comfortable and efficient environmental management system.

[1593] Example of a prompt

[1594] The following are specific examples of prompt statements for a generative AI model:

[1595] "Design a smartphone app version of the environmental management system. The app will collect environmental data and customer sentiment data from physical stores in real time and suggest optimal environmental settings. It should also suggest setting changes, calculate the resulting energy-saving effects, and notify the administrator."

[1596] This can improve customer satisfaction and energy efficiency in physical stores.

[1597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1598] Step 1:

[1599] The server collects necessary data in real time from various sensor devices and external APIs. Specifically, it acquires current data using visitor count sensors, indoor temperature sensors, outdoor temperature sensors, weather sensors, and solar radiation sensors. The input is the data from each sensor, and the output is an integrated environmental dataset containing that data.

[1600] Step 2:

[1601] The server stores collected environmental data in a database and uses machine learning algorithms to predict future data. The input is an integrated environmental dataset, and the output includes predicted visitor numbers, indoor temperature, energy consumption, and other data. Time series analysis and regression analysis are used for prediction.

[1602] Step 3:

[1603] The server uses an emotion engine to acquire and analyze user emotion data. Specifically, it extracts emotion data from cameras and wearable devices installed within buildings and stores. The input is emotion data, and the output is analyzed user comfort level information.

[1604] Step 4:

[1605] The server generates optimal equipment operation settings based on predictive data and sentiment data. Inputs are predictive data and comfort level information, while outputs are recommendation information such as temperature settings and lighting adjustments. This process utilizes a condition-dependent optimization algorithm.

[1606] Step 5:

[1607] The server calculates the energy-saving effect of configuration changes based on the generated recommendation information. The input is the recommendation information, and the output is the estimated amount of energy saved. An energy model is used to calculate the effect of reducing energy consumption.

[1608] Step 6:

[1609] The server compiles estimated energy savings and recommendation information into a report and generates energy-saving action request messages as needed. The input is estimated energy savings and recommendation information, and the output is the report and energy-saving action request messages.

[1610] Step 7:

[1611] The terminal displays recommendation information, estimated energy savings, and energy-saving action request messages received from the server. This allows facility managers and building users to take concrete actions. The inputs are recommendation information, estimated energy savings, and energy-saving action request messages, and the output is a display screen showing this information.

[1612] Step 8:

[1613] Users take action based on recommendations and energy-saving requests displayed on their devices. For example, they might adjust the temperature setting or turn off unnecessary lights. The input is the information displayed on the screen, and the output is the specific energy-saving action performed by the user.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] [Fourth Embodiment]

[1618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1619] 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.

[1620] 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).

[1621] 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.

[1622] 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.

[1623] 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).

[1624] 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.

[1625] 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.

[1626] 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.

[1627] 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.

[1628] 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.

[1629] 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.

[1630] 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".

[1631] This invention is a system for optimizing environmental control and energy efficiency within a building. This system collects real-time data, performs predictive analysis, and generates recommendations for optimal equipment operation, thereby achieving both comfort and energy savings.

[1632] System Overview

[1633] This system primarily consists of sensor devices, a server, and terminals. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data and uses a predictive model to forecast the future indoor environment. Furthermore, the server recommends optimal equipment operation settings based on the predicted data and notifies facility managers and building users of the results.

[1634] Program processing

[1635] Server: Collects the following data from each sensor device and external API.

[1636] Number of visitors

[1637] Indoor temperature

[1638] outside temperature

[1639] weather

[1640] solar radiation

[1641] The collected data is stored in a database, and machine learning algorithms are used to predict the future environment inside the building. For example, it predicts the number of visitors, indoor temperature, and energy consumption for the next few hours. Based on the predicted data, specific recommendations are made to maximize comfort and energy efficiency, such as the following:

[1642] Changing the set temperature

[1643] Lights ON / OFF

[1644] Based on these recommendations, the estimated amount of energy saved is calculated and generated as a report. Furthermore, depending on the predicted results, messages are prepared requesting additional energy-saving actions from building users as needed, such as turning off unnecessary lights on specific floors or adjusting the temperature settings.

[1645] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement appropriate equipment operation and building users to take concrete energy-saving actions.

[1646] Specific example

[1647] For example, suppose a sensor device in an office building collects the following data.

[1648] The number of visitors at 10:00 AM was 500.

[1649] The temperature inside the building is 25℃

[1650] The outside temperature is 30℃

[1651] The weather is sunny.

[1652] Solar radiation is 800 W / m²

[1653] Server: Based on the above data, it generates forecast data for 12:00 AM. Based on this forecast, it makes the following facility operation recommendations.

[1654] The number of visitors will increase to 600.

[1655] The temperature inside the building is predicted to rise to 27°C.

[1656] As a result, the server recommends the following configuration changes.

[1657] Lower the set temperature to 24°C.

[1658] Turn off the lights in unused meeting rooms.

[1659] Furthermore, the report will include calculations of estimated energy savings based on these recommendations, showing that energy consumption reductions of 10% and 5%, respectively, can be expected.

[1660] Terminal: Displays recommended temperature settings and lighting-off instructions to facility managers and building users. For example, the following message may be displayed:

[1661] (Recommendation)

[1662] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[1663] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1664] (Request for energy conservation actions)

[1665] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1666] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[1667] The following describes the processing flow.

[1668] Step 1:

[1669] Server: Collects real-time data from various sensor devices and external APIs. The number of visitors is measured using counter sensors installed at each entrance of the building, and the indoor temperature is obtained from temperature sensors on each floor. Outdoor temperature is obtained from outdoor temperature sensors, and weather information is obtained via a weather API. Solar radiation is obtained from solar radiation sensors. All collected data is stored in a database.

[1670] Step 2:

[1671] Server: Uses machine learning models based on collected data to predict future data. Specifically, it uses models trained on historical data to predict fluctuations in visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation. For example, it uses linear regression or deep learning algorithms to generate predicted visitor numbers and indoor temperature for the next few hours.

[1672] Step 3:

[1673] Server: Based on predictive data, it generates optimal equipment operating settings to maximize comfort and energy efficiency within the building. For example, if the building temperature is predicted to rise to 27°C, it will generate a recommendation to change the set temperature to 24°C. It also includes recommendations to turn off unnecessary lights.

[1674] Step 4:

[1675] Server: Calculates estimated energy savings based on recommendations. It calculates specific energy-saving effects, such as a 10% reduction in energy consumption when the set temperature is lowered by 1°C, or a 5% reduction when the lights are turned off, and compiles the results into a report.

[1676] Step 5:

[1677] Server: If additional energy-saving measures are needed based on the prediction results, prepare specific energy-saving action requests for building users. For example, generate messages requesting that unnecessary lights be turned off on specific floors or for specific groups of people.

[1678] Step 6:

[1679] Terminal: Displays messages to facility managers and building users that include recommendations, estimated energy savings, and requests for energy-saving actions received from the server. This enables facility managers to operate equipment appropriately and building users to take concrete energy-saving actions. For example, the following messages may be displayed via the display or notification system.

[1680] (Recommendation)

[1681] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[1682] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1683] (Request for energy conservation actions)

[1684] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1685] (Example 1)

[1686] 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".

[1687] In modern building management, achieving both a comfortable indoor environment and optimized energy efficiency simultaneously is crucial. However, few systems manage multiple factors such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and use this data to make predictions and recommendations. Furthermore, there are insufficient means to encourage building users to take action to conserve energy. As a result, there is a problem where excessive energy consumption can occur, compromising comfort levels.

[1688] 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.

[1689] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for storing the acquired data in a time-series database, means for predicting indoor environmental information using a machine learning algorithm based on the stored data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to building users when additional energy-saving measures are needed, means for notifying building users of changes in equipment operation, and means for monitoring user behavior and generating a report on the effects. This enables real-time data collection and analysis, and the recommendation of optimal equipment operation based on predictions, thereby achieving both energy efficiency and comfort.

[1690] "Means for obtaining the number of visitors" refers to devices and technologies for detecting and measuring the number of people entering a building in real time and collecting that data.

[1691] "Means for obtaining building temperature" refers to devices and technologies for detecting and measuring the temperature inside a building in real time and collecting that data.

[1692] "Means for obtaining outside air temperature" refers to devices and technologies for detecting and measuring the temperature outside a building in real time and collecting that data.

[1693] "Means of acquiring weather information" refers to devices and technologies for acquiring current weather conditions in real time and collecting that data.

[1694] "Means for acquiring solar radiation" refers to devices and technologies for measuring the amount of sunlight irradiating in real time and collecting that data.

[1695] "Means of storing data in a time-series database" refers to the technology of a database and the method of storing data in a chronological order.

[1696] "Methods for predicting in-building environmental information using machine learning algorithms" refers to methods and technologies that use stored data and machine learning techniques to predict future in-building environmental conditions.

[1697] "A means of recommending optimal equipment operation" is a technology that proposes the optimal equipment operation method to maximize energy efficiency and comfort based on predicted data.

[1698] A "means for calculating estimated energy savings" is a technology that calculates how much energy consumption reduction can be expected based on recommended equipment operation settings.

[1699] "Means for generating requests for energy-saving actions from building users" refers to technology that generates request messages to encourage specific actions from building users when additional energy-saving actions are needed.

[1700] "Means of notifying building users of changes in equipment operation" refers to technology that informs building users of recommended changes in equipment operation through displays or notification systems.

[1701] "A means of monitoring user behavior and generating results as a report" refers to technology that monitors user actions, analyzes the results, and provides them in report format.

[1702] This invention relates to a system for optimizing environmental control and energy efficiency within a building. This system primarily consists of sensor devices, servers, and terminals. Specific embodiments are described below.

[1703] Server Processing

[1704] 1. Data Collection

[1705] The server collects data in real time from various sensor devices and external APIs. Specifically, the sensor devices measure the current number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, and transmit this data to the server. The hardware and software used include temperature sensors, an access control system, and various APIs. The server stores this data in a time-series database (e.g., InfluxDB).

[1706] 2. Data Analysis and Prediction

[1707] The server uses machine learning algorithms (e.g., TensorFlow) based on stored data to predict information about the building's environment. This prediction includes accurately forecasting future visitor numbers, building temperature, energy consumption, and more by combining historical and real-time data.

[1708] 3. Recommendation generation

[1709] The server recommends optimal equipment operating settings based on predictive data. This includes changing the set temperature and turning lights on or off. Furthermore, it calculates the estimated amount of energy saved based on these recommendations. For example, if the predictive data indicates that the number of visitors or the temperature will fluctuate in the next few hours, it will generate recommendations such as changing the set temperature to 24°C and turning off the lights in unused meeting rooms.

[1710] 4. Generating requests for energy-saving actions

[1711] If additional energy-saving measures are required, the server generates energy-saving requests for building users. Specifically, it notifies them via message to turn off unnecessary lights on certain floors or adjust the temperature settings.

[1712] Terminal processing

[1713] 1. Display of recommendations and notifications

[1714] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. This allows facility managers to operate the facilities appropriately and building users to take concrete energy-saving actions. Notification methods include email, SMS, and notifications via a dedicated app.

[1715] User behavior

[1716] 1. Operation by the facility administrator

[1717] The facility manager checks the terminal notifications and makes changes to the temperature settings or turns lights on / off according to the server's recommendations. For example, they might change the HVAC system's temperature setting to 24°C and manually turn off the lights in unused conference rooms.

[1718] 2. Cooperation from building users

[1719] Building users will also check the notification and take specific energy-saving actions. For example, they may manually turn off unnecessary lights, or automated systems may turn off the lights.

[1720] Specific example

[1721] For example, suppose a sensor device in an office building collects the following data.

[1722] The number of visitors at 10:00 AM was 500.

[1723] The temperature inside the building is 25℃

[1724] The outside temperature is 30℃

[1725] The weather is sunny.

[1726] Solar radiation is 800 W / m²

[1727] Based on the above data, the server generates forecast data for 12:00 AM. Based on this forecast, the server makes the following facility operation recommendations.

[1728] The number of visitors will increase to 600.

[1729] The temperature inside the building is predicted to rise to 27°C.

[1730] This will lead to the following recommended setting changes.

[1731] Lower the set temperature to 24°C.

[1732] Turn off the lights in unused meeting rooms.

[1733] Furthermore, the report calculates the estimated energy savings based on these recommendations and includes a figure indicating that energy consumption can be reduced by 10% and 5%, respectively. For example, the following message will be displayed on the device.

[1734] (Recommendation)

[1735] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Estimated energy savings: 10%

[1736] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1737] (Request for energy conservation actions)

[1738] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1739] In this way, the system of the present invention achieves optimal equipment operation based on real-time data collection and predictive analysis, thereby maximizing energy efficiency and ensuring user comfort.

[1740] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1741] Step 1:

[1742] Sensor data collection

[1743] The server collects data in real time from each sensor device and external API. Inputs include the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation, all transmitted from the sensor devices. The server acquires this data and processes it accordingly. Specifically, the temperature sensor transmits current temperature data every 30 seconds, and the outdoor temperature sensor transmits data similarly. The number of visitors is also acquired in real time in conjunction with the visitor management system.

[1744] Input: Number of visitors from sensor devices, indoor temperature, outdoor temperature, weather, solar radiation.

[1745] Output: Collected real-time data

[1746] Step 2:

[1747] Data storage

[1748] The server stores the collected data in a time-series database (e.g., InfluxDB). The input is the data collected in step 1. During storage, the server checks data quality and flags any outliers or missing values. Specifically, as soon as data arrives, it is inserted into the database and marked for later anomaly analysis.

[1749] Input: Collected real-time data

[1750] Output: Data stored in a time-series database

[1751] Step 3:

[1752] Generation of Predictive Models

[1753] The server generates a predictive model using a machine learning algorithm (e.g., TensorFlow) based on data stored in a time-series database. The input is the stored time-series data. This data is fed into the machine learning model to predict future conditions within the building (number of visitors, indoor temperature, energy consumption, etc.). For example, the ML model is updated every night at midnight using the day's data. Real-time predictions are recalculated every 10 minutes to update future conditions.

[1754] Input: Data stored in a time-series database

[1755] Output: Predicted in-building environment data

[1756] Step 4:

[1757] Creating recommendations

[1758] The server recommends optimal equipment operation settings based on predictive data. The input is predicted in-building environment data. To maximize energy efficiency and comfort, it suggests changes to the set temperature and turning lights on / off. Specifically, based on the predictive data, the server recommends lowering the set temperature to 24°C and generates recommendations to turn off the lights in unused conference rooms.

[1759] Input: Predicted in-building environment data

[1760] Output: Recommended equipment operation schedule

[1761] Step 5:

[1762] Calculation of estimated energy savings

[1763] The server calculates the estimated amount of energy savings based on recommendations. The input is the recommended equipment operating settings. For example, it calculates that lowering the set temperature to 24°C can reduce energy consumption by 10%. In specific operations, it analyzes the predicted data and actual consumption data to estimate the energy saving effect.

[1764] Input: Recommended equipment operation settings

[1765] Output: Estimated amount of energy saved

[1766] Step 6:

[1767] Generating requests for energy-saving actions

[1768] The server generates energy-saving requests for building users when additional energy-saving measures are needed. The inputs are estimated energy savings and forecast data. For example, it generates messages notifying users to turn off unnecessary lights on specific floors or adjust temperature settings.

[1769] Input: Estimated amount of electricity saved, forecast data

[1770] Output: Message requesting energy-saving actions

[1771] Step 7:

[1772] Sending recommendations and notifications

[1773] The terminal displays recommendations and energy-saving requests received from the server to facility managers and building users via its display and notification system. Input consists of recommendations and energy-saving requests sent from the server. Notifications can be sent via pop-up notifications, email, or SMS, for example.

[1774] Input: Recommendation and energy-saving action request messages sent from the server

[1775] Output: Information displayed via the display or notification system.

[1776] Step 8:

[1777] User behavior

[1778] Users check notifications on their devices and perform actions such as changing the temperature setting or turning lights on or off as instructed. Specifically, the facility manager changes the HVAC system's temperature setting to 24°C, and users manually turn off unnecessary lights. In some cases, an automated system may also turn off the lights.

[1779] Input: Device notifications

[1780] Output: Changes to the set temperature and lighting ON / OFF have been performed.

[1781] Step 9:

[1782] Report generation

[1783] The server monitors user behavior and energy consumption, and generates reports based on the collected data. Inputs include user behavior data and energy consumption data. This allows for the creation of reports that include comparisons between predictions and actual data, energy saving effectiveness, and comfort level evaluations. Monthly reports can be generated as PDFs and sent via email.

[1784] Input: User behavior data, energy consumption data

[1785] Output: Report (PDF format, etc.)

[1786] The above outlines the specific processing steps of this system.

[1787] (Application Example 1)

[1788] 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".

[1789] In modern buildings and factories, maintaining a comfortable environment while maximizing energy efficiency is a crucial challenge. However, current systems often lack sufficient real-time data collection and predictive analysis, and energy consumption optimization and efficient operation schedules are frequently managed manually, leading to significant energy waste. Furthermore, ineffective robot scheduling and energy management within factories result in high operating costs.

[1790] 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.

[1791] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating requests for energy-saving actions to facility users when additional energy-saving measures are needed, means for predicting the robot's operation schedule and energy consumption based on data collected from sensor devices throughout the factory, and means for instructing the robot to perform optimal operation schedules and energy management based on the predictions. This enables environmental control and optimization of energy efficiency within buildings and factories.

[1792] "Means for obtaining visitor numbers" refers to devices or mechanisms that measure the number of visitors to a building or facility in real time and acquire that information as data.

[1793] "Means for obtaining indoor temperature" refers to devices or mechanisms that measure the temperature inside a building or facility and acquire that temperature data.

[1794] "Means for obtaining outside air temperature" refers to devices or mechanisms that measure the temperature outside a building or facility and acquire that data.

[1795] "Means of acquiring weather information" refers to devices or mechanisms that measure current weather conditions and acquire that information as data.

[1796] "Means for acquiring solar radiation" refers to devices or mechanisms that measure the amount of radiant energy from the sun and acquire that data.

[1797] "Means for predicting in-building environmental information" refers to devices or systems that predict the environmental conditions inside a building at a future point in time based on acquired data.

[1798] "Means for recommending optimal equipment operation" refers to devices or systems that generate optimal recommendations for equipment operation methods and settings based on predicted in-building environmental information.

[1799] "Means for calculating estimated energy savings" refers to devices or software that calculate the expected amount of energy savings based on recommendations.

[1800] A "means for generating requests for energy-saving actions" refers to a device or system that generates a message requesting facility users to take additional energy-saving measures when necessary.

[1801] "Factory-wide sensor devices" refer to a group of sensors installed to measure various environmental conditions and operational status within a factory.

[1802] "Means for predicting robot operation schedules and energy consumption" refers to devices or systems that predict robot operation schedules and energy consumption based on data collected from sensor devices throughout the factory.

[1803] "Means for instructing robots on operating schedules and energy management" refers to devices or systems that, based on predictions, transmit optimal operating schedules and energy management instructions to robots.

[1804] Overall system configuration

[1805] This invention relates to a system for optimizing environmental control and energy efficiency within buildings or factories. The system primarily consists of sensor devices, a server, and terminals. Each sensor device acquires data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time and transmits this data to the server. The server analyzes the received data and uses a predictive model to forecast future indoor environments, robot operation schedules, and energy consumption within factories. This allows for recommendations for optimal equipment operation and energy management.

[1806] Hardware and software to be used

[1807] hardware

[1808] Sensor devices: Indoor thermometer, outdoor thermometer, weather sensor, solar radiation sensor, motion sensor

[1809] Server: Collects, analyzes, and builds predictive models for data.

[1810] Robots: Devices that operate within a factory.

[1811] Terminal: A device for managing facilities, including a display and notification system.

[1812] software

[1813] Python: Run programs for data collection, analysis, prediction, and recommendation generation.

[1814] Requests module: Handles communication with external APIs.

[1815] Scikit-learn: Building and analyzing predictive models

[1816] Smtplib: Sending email notifications

[1817] Data flow and processing

[1818] 1. Data Collection

[1819] The sensor device acquires data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time, and sends this data to the server. For example, the Python Requests module can be used to retrieve data from the sensor API.

[1820] 2. Predictive Analytics

[1821] The server uses the collected data to predict future building environments, robot operating schedules within factories, and energy consumption. For example, it uses Scikit-learn to build a linear regression model to predict environmental changes and energy consumption over the next few hours.

[1822] 3. Recommendation generation

[1823] The server recommends optimal equipment operation and energy management based on predictive data. For example, if a rise in indoor temperature is predicted, it recommends changing the temperature setting or turning lights on or off. It also optimizes robot operation schedules and generates instructions to reduce energy consumption.

[1824] 4. Notifications and Display

[1825] The terminal displays recommendations, estimated energy savings, and energy-saving action requests received from the server. This allows facility managers to implement appropriate equipment operation and enables building and factory users to take concrete energy-saving actions. Information is also sent to facility managers via email notifications.

[1826] Specific example

[1827] For example, in one office building, the following sensor data was acquired at 10:00 AM:

[1828] The number of visitors was 500.

[1829] The temperature inside the building is 25℃

[1830] The outside temperature is 30℃

[1831] The weather is sunny.

[1832] Solar radiation is 800 W / m²

[1833] Based on this data, the server generated a forecast for 12:00 AM, predicting that the number of visitors would increase to 600 and the indoor temperature would rise to 27°C. The server recommended lowering the thermostat to 24°C and turning off the lights in unused conference rooms, and calculated the estimated amount of energy consumption reduction.

[1834] Example of a prompt

[1835] Based on the following sensor data, predict the future factory environment and create optimal equipment operation settings.

[1836] Sensor data:

[1837] Temperature: 28℃

[1838] Humidity: 50%

[1839] Number of visitors: 100

[1840] Please provide future forecast data, showing how temperature, humidity, and visitor numbers will change, and recommend specific setting changes.

[1841] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1842] Step 1:

[1843] Sensor devices measure data within buildings and factories in real time and transmit that data to a server. Specifically, data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation are collected. Each sensor device sends data to the server via an API, and the server stores this data collectively in a database.

[1844] Input: Real-time data from a sensor device.

[1845] Output: Measurement data stored in the database.

[1846] Step 2:

[1847] The system analyzes data collected by the server to predict future conditions within the building and factory. Here, Python is used to process the data, and Scikit-learn is used to build predictive models. For example, a linear regression model is used to predict temperature, humidity, visitor numbers, and energy consumption over the next few hours.

[1848] Input: Measurement data stored in the database.

[1849] Output: Predictive data on future indoor environments and factory conditions.

[1850] Step 3:

[1851] The server generates recommendations for optimal equipment operation based on predictive data. Specifically, it determines the optimal temperature settings, lighting ON / OFF states, etc., for predicted environmental conditions. This process generates recommendations by making conditional judgments based on the output of the predictive model.

[1852] Input: Prediction data.

[1853] Output: Recommendations for optimal equipment operation.

[1854] Step 4:

[1855] Based on recommendations generated by the server, the expected amount of energy savings is calculated. For example, it calculates how much energy can be saved by changing the temperature setting, or how much cost reduction can be expected by turning off unnecessary lights.

[1856] Input: Recommendation.

[1857] Output: Calculation result of estimated energy savings.

[1858] Step 5:

[1859] The server generates additional energy-saving requests for facility users as needed. For example, in addition to requests to change the temperature or turn lights on or off, it generates messages requesting specific energy-saving actions from users.

[1860] Input: Calculation result of estimated energy savings.

[1861] Output: Message requesting energy-saving actions.

[1862] Step 6:

[1863] The terminal displays recommendations and energy-saving action requests received from the server. This allows facility managers to take concrete action and maximize energy efficiency. The information is displayed via a display or notification system.

[1864] Input: Messages requesting energy-saving actions or recommendations.

[1865] Output: The message displayed on the terminal.

[1866] Step 7:

[1867] The server sends an email notification to the facility administrator as needed. Smtplib is used to send the generated message to the facility administrator via email, allowing them to respond immediately.

[1868] Input: Message requesting energy-saving actions.

[1869] Output: Email notification to the facility administrator.

[1870] 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.

[1871] This invention combines a system for optimizing environmental control and energy efficiency within a building with an engine that recognizes user emotions, thereby maximizing energy efficiency while enhancing user comfort. This system generates recommendations for optimal equipment operation based on real-time data collection, predictive analysis, and emotion analysis, and requests energy-saving actions from building users, thereby achieving a further balance of energy efficiency and comfort.

[1872] System Overview

[1873] This system consists of sensor devices, a server, terminals, and an emotion engine. The sensor devices acquire real-time data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. The server collects and analyzes this data to predict the building's environmental conditions. Furthermore, the emotion engine acquires user emotion data and adjusts facility operation recommendations accordingly. Finally, the server generates optimal settings based on this information and notifies facility managers and building users.

[1874] Program processing

[1875] Server: Collects the following data in real time from various sensor devices and external APIs.

[1876] Number of visitors

[1877] Indoor temperature

[1878] outside temperature

[1879] weather

[1880] solar radiation

[1881] The collected data is stored in a database, and machine learning algorithms are used to predict future data. At this stage, predictions are generated for the number of visitors, indoor temperature, and energy consumption. Then, an emotion engine collects user emotion data, which is then analyzed. User emotion data is obtained, for example, through cameras and wearable devices installed within the building.

[1882] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[1883] Server: Also calculates estimated energy savings based on recommendations. It calculates the expected reduction in energy consumption by adjusting the temperature setting or turning off lights, and compiles the results into a report. Furthermore, it prepares additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it generates a message encouraging specific energy-saving actions on that floor.

[1884] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[1885] (Recommendation)

[1886] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1887] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1888] (Request for energy conservation actions)

[1889] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1890] Specific example

[1891] For example, suppose the following data was collected in a certain office building.

[1892] The number of visitors at 10:00 AM was 500.

[1893] The temperature inside the building is 25℃

[1894] The outside temperature is 30℃

[1895] The weather is sunny.

[1896] Solar radiation is 800 W / m²

[1897] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[1898] The number of visitors will increase to 600.

[1899] The temperature inside the building is expected to rise to 27°C.

[1900] Many users find it unpleasant.

[1901] Server: Based on this data, recommend lowering the temperature setting to 24°C and turning off the lights in unused meeting rooms. Also, consider sentiment data to estimate the energy consumption reduction effect and include an estimated 10% energy consumption reduction in the report.

[1902] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[1903] The following describes the processing flow.

[1904] Step 1:

[1905] Server: Collects real-time data from each sensor device and external API. Specifically, the number of visitors is obtained from a counter sensor installed at the entrance, the indoor temperature from temperature sensors installed on each floor, and the outdoor temperature from outdoor temperature sensors. Weather information is obtained via a weather API, and solar radiation is obtained from a solar radiation sensor. The collected data is centrally managed and stored in a database.

[1906] Step 2:

[1907] Server: Uses machine learning algorithms to predict future data based on collected data. Specifically, it generates predictions for the next few hours using data on the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation. In this process, it trains a model using historical datasets to achieve highly accurate predictions.

[1908] Step 3:

[1909] Server: Uses an emotion engine to collect user emotion data. This is done by analyzing users' facial expressions and behavior through cameras and wearable devices installed within the building. The emotion data is then analyzed to determine which emotion it corresponds to, such as pleasant or unpleasant.

[1910] Step 4:

[1911] Server: Combines predictive data and sentiment data to generate optimal equipment operation settings. For example, if the predicted indoor temperature rises to 27°C and many users feel uncomfortable, it recommends lowering the temperature setting to 24°C. Furthermore, it also generates recommendations to adjust lighting brightness and on / off settings based on sentiment data.

[1912] Step 5:

[1913] Server: Calculates estimated energy savings based on recommendations. For example, it makes specific predictions for cases where lowering the temperature by 1°C reduces energy consumption by 10%, or where turning off the lights reduces energy consumption by 5%. The calculation results are compiled into a report, clearly indicating the estimated energy savings.

[1914] Step 6:

[1915] Server: If additional energy-saving measures are needed, it generates specific energy-saving action requests for building users. For example, if many users are feeling uncomfortable on a particular floor, it generates a message requesting users on that floor to turn off unnecessary lights.

[1916] Step 7:

[1917] Terminal: Recommendations, estimated energy savings, and energy-saving action requests received from the server are displayed to facility managers and building users via displays and notification systems. This allows facility managers to implement realistic operational settings and building users to take concrete energy-saving actions. For example, the following messages may be displayed:

[1918] (Recommendation)

[1919] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1920] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1921] (Request for energy conservation actions)

[1922] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1923] In this way, the system of the present invention realizes a system that can maximize the comfort level and energy efficiency of the building environment by combining real-time data and emotional data.

[1924] (Example 2)

[1925] 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".

[1926] In recent years, building environment management has demanded a balance between improved energy efficiency and user comfort. However, conventional systems can only control systems based on limited information obtained from simple collection and analysis of environmental data, making it difficult to set optimal equipment operation settings that take into account user emotions and specific experiences. Furthermore, messages encouraging energy-saving behavior tend to be monotonous, making it difficult to gain user cooperation. Therefore, more advanced data analysis and equipment operation that takes user experience into consideration are needed.

[1927] 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.

[1928] In this invention, the server includes means for acquiring the number of visitors, means for acquiring the indoor temperature, means for acquiring the outdoor temperature, means for acquiring the weather, means for acquiring solar radiation, means for predicting indoor environmental information based on the acquired data, means for recommending optimal equipment operation based on the predicted indoor environmental information, means for calculating the estimated amount of energy saved based on the recommendation, means for generating energy-saving action requests to building users when additional energy-saving measures are needed, means for collecting and analyzing user emotion data, and means for adjusting equipment operation settings based on emotion data. By combining user emotion data with conventional environmental data, more accurate and optimal equipment operation settings become possible, achieving both improved energy efficiency and user comfort. Furthermore, by generating specific energy-saving action request messages tailored to the user's situation, it becomes easier to obtain cooperation from users.

[1929] "Means for obtaining the number of visitors" refers to devices or methods for measuring and recording the number of people who enter a building within a certain period of time, using sensors or access control systems installed within the building.

[1930] "Means for obtaining indoor temperature" refers to devices or methods for measuring and recording the real-time temperature of a location using temperature sensors placed on each floor or in each room within a building.

[1931] "Means for obtaining outside air temperature" refers to devices or methods for measuring and recording the temperature of the external environment using sensors installed on the outside of a building.

[1932] "Means for acquiring weather information" refers to devices and methods for acquiring and recording weather information using weather sensors installed near a building or external weather data provision services.

[1933] "Means for acquiring solar radiation" refers to devices or methods for measuring and recording the intensity and illuminance of direct sunlight using solar radiation sensors installed on the exterior or rooftop of a building.

[1934] "Methods for predicting in-building environmental information based on acquired data" refer to algorithms and methods for analyzing collected data such as temperature, number of visitors, weather, and solar radiation to estimate and predict the future in-building environment.

[1935] "Means for recommending optimal equipment operation based on predicted in-building environmental information" refers to devices or methods that use prediction results to propose and recommend the optimal operating methods for equipment within a building (such as air conditioners and lighting).

[1936] "Means for calculating estimated energy savings based on recommendations" refers to devices or methods for calculating the energy consumption reduction effect predicted by the proposed equipment operation method.

[1937] "Means for generating requests for energy-saving actions from building users when additional energy-saving measures are needed" refers to devices or methods for creating and notifying building users of specific energy-saving actions when further energy conservation is required.

[1938] "Means for collecting and analyzing user emotional data" refers to devices and methods that use cameras and wearable devices installed within a building to analyze users' facial expressions and behavior, and to recognize and record their emotional state.

[1939] "Means for adjusting equipment operation settings based on emotional data" refers to devices or methods for appropriately adjusting equipment operation methods to improve user comfort based on collected emotional data.

[1940] This invention is a system for optimizing environmental control and energy efficiency within a building. By integrating user emotion data, it aims to maximize energy efficiency while enhancing user comfort. This system performs multi-stage processing, including real-time data collection, predictive analysis, and emotion analysis, to generate recommendations for optimal equipment operation and request energy-saving behavior from building users, thereby achieving both energy efficiency and comfort.

[1941] System Configuration

[1942] This system consists of the following elements:

[1943] Sensor devices

[1944] server

[1945] terminal

[1946] Emotional Engine

[1947] Sensor devices: These are installed inside and outside buildings to acquire data such as the number of visitors, indoor temperature, outdoor temperature, weather, and solar radiation in real time. Specifically, they include temperature sensors, access control systems, weather sensors, and solar radiation sensors.

[1948] Server: Integrates and stores data collected from sensor devices and uses machine learning algorithms to predict future data. It also collects and analyzes user emotion data through an emotion engine. Based on this data, it also has the function of generating optimal equipment operation settings and calculating estimated energy savings.

[1949] Terminals: These devices display recommendations and energy-saving requests received from the server to facility managers and building users. Specifically, this includes smartphones, tablets, and PC displays.

[1950] Emotion Engine: Collects the user's facial expressions and heart rate through cameras and wearable devices, and analyzes their emotional state. It determines whether the user is comfortable or uncomfortable and sends that data to a server.

[1951] Program processing

[1952] Server: Collects data on visitor numbers, indoor temperature, outdoor temperature, weather, and solar radiation in real time from various sensor devices and external APIs, and stores it in a database. The stored data is used with machine learning algorithms to predict future data and generate predicted values ​​for visitor numbers, indoor temperature, and energy consumption. Furthermore, it collects and analyzes user sentiment data through an emotion engine and generates optimal equipment operation settings based on the obtained sentiment data. For example, if the indoor temperature rises to 27°C and many users feel uncomfortable, it will recommend lowering the set temperature to 24°C. It can also adjust the brightness and on / off status of lighting based on sentiment data.

[1953] Server: Calculates estimated energy savings based on recommendations, determines the expected reduction in energy consumption by adjusting temperature settings or turning off lights, and compiles the results into a report. Furthermore, it generates additional energy-saving action request messages as needed. For example, if many users feel uncomfortable on a particular floor, it creates a message encouraging specific energy-saving actions on that floor.

[1954] Terminal: Displays recommendations, estimated energy savings, and energy-saving action requests received from the server to facility managers and building users. For example, the following message may be displayed:

[1955] (Recommendation)

[1956] The predicted indoor temperature is 27°C, and a recommended setting temperature of 24°C. Many users are finding this uncomfortable. Estimated energy savings: 10%

[1957] Please turn off the lights in the conference room. Estimated energy savings: 5%

[1958] (Request for energy conservation actions)

[1959] To all users of Floor B, we ask for your cooperation. Please turn off any unnecessary lights. Number of participants: 20

[1960] Specific example

[1961] For example, suppose the following data was collected in a certain office building.

[1962] The number of visitors at 10:00 AM was 500.

[1963] The temperature inside the building is 25℃

[1964] The outside temperature is 30℃

[1965] The weather is sunny.

[1966] Solar radiation is 800 W / m²

[1967] Furthermore, if the emotion engine recognizes that many users feel "uncomfortable," the following predictions and recommendations will be made.

[1968] The number of visitors will increase to 600.

[1969] The temperature inside the building is expected to rise to 27°C.

[1970] Many users find it unpleasant.

[1971] Server: Based on this data, it generates recommendations to lower the set temperature to 24°C and turn off the lights in unused meeting rooms. It also takes sentiment data into account to estimate the energy consumption reduction effect and includes an estimated 10% energy consumption reduction in the report.

[1972] Terminal: Notifies facility managers and building users of the aforementioned recommendations and requests for energy-saving actions. By combining real-time data and sentiment data in this way, a more comfortable and efficient building management system can be realized.

[1973] Examples of prompt statements

[1974] The following are examples of prompts used by a generative AI model to generate appropriate recommendation messages.

[1975] Please generate recommendations for building environmental control based on the following data.

[1976] Number of visitors: 500

[1977] Indoor temperature: 25℃

[1978] Outside temperature: 30℃

[1979] Weather: Sunny

[1980] Solar radiation: 800 W / m²

[1981] User sentiment data: Many users feel uncomfortable.

[1982] Please output appropriate action recommendations and predicted energy-saving effects.

[1983] By inputting this prompt into the generating AI model, it becomes possible to obtain recommendations that balance efficient energy management with user comfort.

[1984] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1985] Step 1:

[1986] Data collection

[1987] The se...

Claims

1. Methods for obtaining the number of visitors, A means of obtaining the temperature inside the building, A means of obtaining the outside air temperature, Means of obtaining weather information, Means for obtaining solar radiation, A means of predicting in-building environmental information based on acquired data, A means of recommending optimal equipment operation based on predicted in-house environmental information, A means for calculating the estimated amount of electricity saved based on recommendations, A means of generating requests for energy-saving actions from building users when additional energy-saving measures are needed, A system that includes this.

2. The system according to claim 1, further comprising means for displaying equipment operation recommendations on a display.

3. The system according to claim 1, further comprising means for notifying building users of a request for energy-saving actions.

Images