System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting infrastructure use information, a means for analyzing the collected infrastructure use information and predicting a use pattern and a cost, a means for transmitting an alert to a user on the basis of a prediction result, a means for optimizing a contract plan of the infrastructure service, and a means for transmitting an instruction for applying an energy saving mode to a terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The increase in infrastructure usage costs is due to seasonal and lifecycle fluctuations, making it difficult to take appropriate measures in advance. Furthermore, it is complicated for users to select the optimal contract plan and maximize energy-saving effects, which requires specialized knowledge and real-time information collection and analysis. This invention aims to solve these problems and improve the efficiency and optimization of users' infrastructure usage. [Means for solving the problem]

[0005] This invention provides a means for collecting infrastructure usage information, which obtains daily usage data for electricity, water, gas, and communications. It then uses a means for analyzing the collected data and forecasting usage patterns and seasonal costs. It also includes a means for sending alerts to users about potential cost increases at specific times or under specific conditions based on the analysis results. It also includes a means for proposing optimal contract plans based on the analysis results and automatically changing the contract plans as necessary. Finally, it provides a means for sending instructions to apply energy-saving modes to terminals based on the usage data and analysis results, automatically changing the settings on the terminals. This allows users to manage their infrastructure usage efficiently and cost-effectively.

[0006] "Infrastructure Usage Information" refers to consumption data and usage patterns related to infrastructure services such as electricity, water, gas, and communications.

[0007] "Means for collecting infrastructure usage information" refers to devices and systems that acquire data from smart meters, water meters, gas meters, communication devices, etc.

[0008] "Means of analysis" refers to algorithms and software used to generate usage patterns and predict costs based on collected data.

[0009] "Means for sending alerts" refers to devices and systems for notifying users of important information, such as increases in costs at specific times or under specific conditions.

[0010] "Means for optimizing contract plans" refers to a system that proposes the optimal infrastructure service contract plan to a user based on usage data and analysis results, and automatically changes the plan as necessary.

[0011] The term "means for sending an instruction to apply an energy saving mode to a terminal" refers to a device and a system thereof that sends a control signal to a user's terminal to apply an energy saving setting.

[0012] "Terminal" refers to power equipment, communication equipment, home appliances, etc. used by users, and includes devices that can change their operation in response to instructions from a server. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[0035] System Overview

[0036] The following elements play a key role in this system:

[0037] 1. Collection of infrastructure usage information

[0038] The server collects real-time usage information from smart electricity bills, water meters, gas meters, communication devices, etc. This allows for a detailed understanding of users' consumption patterns.

[0039] 2. Data Analysis

[0040] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[0041] 3. Alert delivery

[0042] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[0043] 4. Optimizing your contract plan

[0044] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[0045] 5. Applying energy saving mode

[0046] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[0047] Specific examples

[0048] Example 1: Increased electricity consumption in summer

[0049] 1. Data Collection

[0050] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[0051] 2. Data Analysis

[0052] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[0053] 3. Alert delivery

[0054] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[0055] 4. Optimizing your contract plan

[0056] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[0057] 5. Applying energy saving mode

[0058] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[0059] Example 2: Increased gas consumption in winter

[0060] 1. Data Collection

[0061] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February.

[0062] 2. Data Analysis

[0063] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year.

[0064] 3. Alert delivery

[0065] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak and urging them to take measures.

[0066] 4. Optimizing your contract plan

[0067] The server checks the user's gas company plan and suggests changing to a special discount plan for the winter season.

[0068] 5. Applying energy saving mode

[0069] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode in response to instructions from the server.

[0070] In this way, the system of the present invention provides a set of processes for monitoring and optimizing users' infrastructure usage in real time, thereby enabling users to achieve efficient and cost-effective infrastructure usage.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[0074] Step 2:

[0075] The server analyzes the collected infrastructure usage information. This involves applying algorithms that use historical data to identify seasonal and event usage patterns and then predict future usage and costs. For example, it analyzes patterns that indicate increased gas consumption for heating in the winter (December to February).

[0076] Step 3:

[0077] Based on the analysis results, the server identifies when usage costs are expected to increase at a specific time, creates an alert for the identified event, and prepares to send the alert to the user.

[0078] Step 4:

[0079] The server sends an alert to the user via email or the notification function of a smartphone app. For example, it could send an alert stating, "Power consumption is expected to increase due to air conditioning use next week."

[0080] Step 5:

[0081] The server checks the user's current contract plan and considers whether an optimal plan is available. It compares the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction. For example, it investigates whether a plan that offers reduced charges during specific peak hours is applicable.

[0082] Step 6:

[0083] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[0084] Step 7:

[0085] The server sends instructions to the terminal to apply an energy-saving mode based on the forecast data and the cost reduction policy, for example, to automatically adjust the temperature setting of the air conditioner.

[0086] Step 8:

[0087] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[0088] Step 9:

[0089] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] In today's world, where energy consumption is increasing in homes and businesses, it is difficult to understand consumption patterns and specific costs. Furthermore, it is often difficult to take appropriate measures to prevent energy waste and increased costs. Furthermore, optimizing contract plans and switching to energy-saving modes is done manually, making effective energy management difficult.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server includes a means for collecting infrastructure usage information, a means for analyzing the collected infrastructure usage information using a big data analysis tool to predict usage patterns and costs, a means for sending alerts to user devices based on the prediction results, a means for using an energy company's API to optimize infrastructure service contract plans, and a means for sending instructions to apply energy-saving modes to home appliances, thereby enabling visualization and optimization of energy consumption and automatic energy-saving measures.

[0095] "Infrastructure usage information" refers to usage data related to infrastructure services such as electricity, water, gas, and communications.

[0096] "Means of collection" refers to technologies including sensors and APIs for obtaining information from smart meters, communication devices, etc.

[0097] "Big data analysis tools" are software and frameworks for processing and analyzing huge data sets, including Spark and Hadoop.

[0098] "Usage patterns" are data that indicate trends in the use of energy, etc. at specific times or under specific conditions.

[0099] "Cost forecasting" refers to estimating future charges based on future energy and other usage.

[0100] An "alert" is a message that notifies the user based on a specific condition or prediction result.

[0101] "User devices" refer to terminals and applications used by users, including smartphones and PCs.

[0102] An "energy company API" is an interface for accessing data and services offered by energy providers.

[0103] "Contract plan optimization" is the process of proposing or changing the most cost-effective energy plan based on the user's consumption patterns.

[0104] "Energy saving mode" is a setting that switches home appliances to a specific operating state to reduce energy consumption.

[0105] "Home appliances" are electronic devices used in the home, such as heating and cooling equipment and lighting.

[0106] "Means for sending instructions to home appliances" refers to the communication technology and protocols used to transmit instructions from the server to home appliances. Examples include Wi-Fi and Bluetooth.

[0107] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[0108] 1. Program Generation

[0109] The server generates a program that contains the following main modules:

[0110] 1. Infrastructure usage information collection module

[0111] 2. Data Analysis Module

[0112] 3. Alert Delivery Module

[0113] 4. Contract plan optimization module

[0114] 5. Energy-saving mode application module

[0115] 2. Explain the program's processing in natural language

[0116] Collection of infrastructure usage information

[0117] The server collects data in real time from meters such as smart electricity bills, water meters, and gas meters. This data collection is done using the API of the meter. For example, the server obtains electricity usage data every minute and stores it in a relational database such as MySQL (registered trademark) or PostgreSQL.

[0118] Data analysis

[0119] The server analyzes the collected data using big data analytics tools (e.g., Spark, Hadoop) to identify seasonal usage patterns and peak periods. The analysis results are used to predict the next peak period and potential cost increases. For example, the server uses data from the past year to predict peak usage times in a particular month with an accuracy of over 80%.

[0120] Alert delivery

[0121] The server then sends alerts to the user based on the analysis results. Twilio's SMS API or Firebase Cloud Messaging are often used for alert delivery. For example, the server might send a notification to the user's smartphone saying, "Power usage will soon reach its peak. Please take measures to reduce energy consumption."

[0122] Optimizing contract plans

[0123] The server compares the analysis results with the user's current contract plan and suggests changing to the optimal plan. It also uses the energy company's API to obtain the user's usage history and the optimal plan. For example, the server might send the user a message saying, "We have a new plan that offers lower rates during peak hours. We recommend you change to it."

[0124] Applying energy saving mode

[0125] The device automatically adjusts its settings upon receiving instructions from the server. For example, if an air conditioner receives an instruction to "change the set temperature from 24 degrees to 26 degrees," it will automatically change the setting and reduce power consumption. This is achieved using smart device integration software such as Home Assistant and GOOGLE HOME (registered trademark) for IoT control.

[0126] Specific examples

[0127] Below are some concrete examples and examples of prompts for the generative AI model:

[0128] Example 1: Increased electricity consumption in summer

[0129] 1. Data Collection:

[0130] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[0131] 2. Data Analysis:

[0132] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[0133] 3. Alert Delivery:

[0134] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[0135] 4. Plan optimization:

[0136] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[0137] 5. Apply energy saving mode:

[0138] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[0139] Example prompts for generative AI models

[0140] Describe the system's program in natural language. Include the following elements:

[0141] Use the server, terminal, and user as subjects

[0142] Specific hardware and software names for each process

[0143] Data collection, data analysis, alert distribution, contract plan optimization, energy saving mode application

[0144] Specific examples of events

[0145] What the program does

[0146] 1. Data collection: The server collects usage information from smart electricity bills and gas meters.

[0147] 2. Data analysis: The server analyzes the data using Hadoop or Spark.

[0148] 3. Alert delivery: The server sends an alert via Twilio or Firebase

[0149] 4. Optimizing contract plans: The server uses the energy company's API to propose the optimal plan.

[0150] 5. Applying power saving mode: The device switches to power saving mode using Home Assistant

[0151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0152] Divide the program processing flow into processing steps

[0153] Step 1:

[0154] Step 2:

[0155] Step 3:

[0156] Step 4:

[0157] Step 5:

[0158] Detailed explanation of each processing step

[0159] Step 1:

[0160] The server collects infrastructure usage information, including electricity, water, and gas usage. As input, it uses real-time data from smart electricity bills, water meters, and gas meters. As output, this data is stored in a relational database, such as MySQL or PostgreSQL. Specifically, the server calls a remote API every minute to retrieve data from each meter.

[0161] Step 2:

[0162] The server analyzes the collected data using big data analysis tools. The data collected in step 1 is used as input. The output generates forecast data that identifies seasonal usage patterns and peak periods. Specifically, the server runs batch processing overnight and performs time series analysis using past data sets.

[0163] Step 3:

[0164] The server sends an alert to the user device based on the prediction results. The analysis results from step 2 are used as input. The output is a notification sent to the user's smartphone or computer. Specifically, the server generates a notification using Twilio's SMS API or Firebase Cloud Messaging and sends it to the user device.

[0165] Step 4:

[0166] The server compares the analysis results with the current contract plan and proposes a change to the optimal plan. The input uses the user's current contract plan information and the analysis results from step 2. The output is a proposal for the optimal energy plan for the user. Specifically, the server accesses the energy company's API, obtains the optimal rate plan information, and notifies the user.

[0167] Step 5:

[0168] The device receives instructions from the server and applies energy-saving mode. The instruction information from the server is used as input. The setting of the home appliance is changed as output. Specifically, the device (e.g., air conditioner) automatically changes the set temperature and switches to energy-saving mode. This process uses smart device integration software such as Home Assistant or Google (registered trademark) Home.

[0169] This allows for efficient energy management and automated energy saving measures.

[0170] (Application example 1)

[0171] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0172] In recent years, energy consumption by factory equipment and robots has increased, resulting in increased operating costs. There is a need to efficiently manage this energy consumption and reduce costs. However, current management systems are unable to collect and analyze energy usage information in real time, making it difficult to predict peak energy consumption. Furthermore, automation for optimizing infrastructure service contract plans and applying energy-saving modes has not been fully achieved. As a result, efficient energy management in factories has yet to be achieved.

[0173] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0174] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected energy consumption data and predicting peak energy consumption of specific equipment or robots, and means for optimizing energy consumption by applying an energy-saving mode during peak times. This makes it possible to monitor energy consumption in a factory in real time, propose a change to an optimal contract plan, and automatically apply an energy-saving mode.

[0175] "Infrastructure usage information" refers to data on the energy consumption of each device and robot within a factory, such as data obtained from electricity meters and gas meters.

[0176] "Means of collection" is a general term for hardware and software used to collect data in real time from electricity meters, water meters, gas meters, communication devices, etc.

[0177] The "analytical means" refers to algorithms and computer systems that analyze energy consumption patterns and predict future consumption peaks based on collected infrastructure usage information.

[0178] The "prediction method" refers to a calculation method and platform that uses past data to analyze consumption patterns and estimate peak energy consumption during specific times and situations.

[0179] "Means for sending alerts" are communications means and software for sending notifications to users based on the results of the analysis and predictions.

[0180] The "means for optimizing contract plans" is a system that analyzes the contents of the current infrastructure service contract and proposes or automatically applies the most suitable rate plan or service plan to the user.

[0181] The "means for sending instructions to terminals to apply energy-saving mode" refers to a control system that sends energy-saving mode instructions generated on the server side to various terminals (e.g., robots and devices) to automatically perform operations to reduce energy consumption.

[0182] The "energy saving mode" is an operating mode in which a particular device or robot minimizes energy consumption, and includes, for example, settings such as reducing the operating speed or turning off the power when not in operation.

[0183] This invention is a system for efficiently managing energy consumption in factories and reducing operational costs. The system consists of a server, terminals, and users. The server collects and analyzes infrastructure usage information in real time, and automatically proposes optimal contract plans and applies energy-saving modes.

[0184] System Overview

[0185] 1. Collection of infrastructure usage information

[0186] The server collects energy consumption data from various measuring devices in the factory (e.g., electricity meters, gas meters, temperature sensors, etc.), allowing the system to grasp in real time how much energy each piece of equipment and robot is consuming.

[0187] 2. Data Analysis

[0188] The server uses data processing libraries such as pandas and numpy to analyze the collected data. Algorithms for predicting energy consumption patterns and detecting outliers are used for the analysis. Specifically, machine learning models such as random forests are used to predict consumption peaks.

[0189] 3. Alert delivery

[0190] Based on the analysis results, the server will send an alert to the user if energy consumption is expected to exceed a certain threshold, which can be achieved using a notification system such as Pushbullet.

[0191] 4. Optimizing your contract plan

[0192] The server analyzes the current infrastructure service contract based on the energy consumption data and proposes changes to the optimal contract plan, which may result in cost savings for the user.

[0193] 5. Applying energy saving mode

[0194] The server sends instructions to specific equipment or robots to enter energy-saving mode, and the devices that receive these instructions automatically apply energy-saving settings, such as reducing their operating speed or turning off the power during non-operating hours.

[0195] Program processing explanation

[0196] The server first collects information from various measurement devices, then analyzes the collected data and predicts peak energy consumption using machine learning models such as random forests. For example, libraries such as pandas and numpy are used to preprocess and analyze the data.

[0197] If the system predicts that energy consumption will exceed the threshold, Pushbullet will be used to send an alert to the user, allowing the user to take appropriate measures. The server will also suggest optimizing the contract plan and send instructions to enter energy-saving mode. Devices that receive this instruction will automatically change their settings and begin taking actions to reduce energy consumption.

[0198] Examples and prompts

[0199] As a concrete example, consider a factory where peak energy consumption is predicted to occur between 10:00 AM and 2:00 PM on Mondays. To apply energy saving mode during this time, the server generates the following prompt:

[0200] Example prompt sentence:

[0201] "Please set your system to apply energy saving mode from 10:00 AM to 2:00 PM tomorrow."

[0202] As described above, by introducing this system, it will be possible to efficiently manage energy consumption and reduce costs in factories.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The server collects energy consumption data in real time from various measuring devices installed in the factory (e.g., electricity meters, gas meters, temperature sensors). This data includes the instantaneous electricity and gas consumption of each piece of equipment and robot. The server accumulates this data by hour and creates a data set for analysis.

[0206] Input: Real-time energy consumption data

[0207] Output: Hourly accumulated energy consumption dataset

[0208] Step 2:

[0209] The server analyzes the collected energy consumption data using data processing libraries such as pandas and numpy, and applies machine learning algorithms (e.g., random forests) to analyze consumption patterns, thereby forecasting hourly energy consumption and identifying peak consumption periods.

[0210] Input: Energy consumption dataset accumulated by hour

[0211] Output: A forecasting model to identify consumption peaks

[0212] Step 3:

[0213] The server then sends an alert to the user when energy consumption is expected to exceed a threshold based on the predicted peak consumption data. This alert is sent to the user in real time using a notification system such as Pushbullet.

[0214] Input: A forecast model to identify consumption peaks

[0215] Output: Energy consumption peak alert

[0216] Step 4:

[0217] The server analyzes the current infrastructure service contract plans and proposes the optimal contract plan based on the energy consumption data, and sends the proposal to the user as a notification.

[0218] Input: Energy consumption data, current contract plan information

[0219] Output: Proposal of the best contract plan

[0220] Step 5:

[0221] The server sends instructions to specific equipment or robots to enter energy-saving mode. The terminals (e.g., robots) that receive these instructions automatically change their operating settings to energy-saving settings, such as slowing down the operating speed or turning off the power during non-operating hours.

[0222] Input: Energy saving mode instruction

[0223] Output: Change the device's operating settings to apply power saving mode

[0224] The specific operation is as follows:

[0225] Example: The server predicts that the peak energy consumption period is from 10:00 AM to 2:00 PM on Mondays. Based on this prediction, it generates energy-saving mode instructions and sends them to the associated robots. The robots receive these instructions, reduce their operating speed, and automatically turn off their power during non-operating hours if necessary. This process optimizes power usage during peak energy consumption periods.

[0226] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0227] This invention combines a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes with an emotion engine that recognizes user emotions. This system consists of a server, terminals, users, and an emotion engine.

[0228] System Overview

[0229] The following elements play a key role in this system:

[0230] 1. Collection of infrastructure usage information

[0231] The server collects real-time infrastructure usage information from smart electricity bills, water meters, gas meters, and communication devices, allowing for detailed understanding of users' consumption patterns.

[0232] 2. Data Analysis

[0233] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[0234] 3. Alert delivery

[0235] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[0236] 4. Optimizing your contract plan

[0237] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[0238] 5. Applying energy saving mode

[0239] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[0240] 6. Introducing the Emotion Engine

[0241] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information, enabling optimal responses according to the user's emotional state.

[0242] Specific examples

[0243] Example 1: Increased electricity consumption in summer and utilization of emotion engine

[0244] 1. Data Collection

[0245] The server collects electricity consumption data that indicates high air conditioner usage from June to August, while the emotion engine collects user emotion data from smart devices.

[0246] 2. Data Analysis

[0247] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[0248] 3. Alert delivery

[0249] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[0250] 4. Optimizing your contract plan

[0251] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[0252] 5. Applying energy saving mode

[0253] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server. The emotion engine gives instructions on temperature settings that take comfort into consideration.

[0254] Example 2: Increased gas consumption in winter and the use of emotion engines

[0255] 1. Data Collection

[0256] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February, and the emotion engine collects information from smart devices that indicate a user's sensitivity to cold.

[0257] 2. Data Analysis

[0258] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year. The emotion engine evaluates the user's emotional state and identifies discomfort due to the cold.

[0259] 3. Alert delivery

[0260] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak, urging them to take appropriate measures. The emotion engine will adjust the content of the alert to take into account the user's emotions.

[0261] 4. Optimizing your contract plan

[0262] The server checks the user's gas company plan and suggests switching to a special winter discount plan. The emotion engine adjusts the suggestion to reassure the user.

[0263] 5. Applying energy saving mode

[0264] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode according to instructions from the server. The emotion engine gives instructions on temperature settings that prioritize the user's comfort.

[0265] In this way, the system of the present invention provides a series of processes for monitoring and optimizing users' infrastructure usage in real time. Furthermore, by combining it with an emotion engine, it is possible to optimize responses according to the user's emotional state, further improving the user experience.

[0266] The processing flow will be explained below.

[0267] Step 1:

[0268] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[0269] Step 2:

[0270] The emotion engine collects emotion data from users' smart devices (e.g., smartphones and wearable devices), including physiological and behavioral data such as heart rate, facial expression recognition, and voice tone.

[0271] Step 3:

[0272] The server analyzes collected infrastructure usage information to identify seasonal usage patterns and lifecycle fluctuations, thereby predicting upcoming peak periods and identifying potential cost increases.

[0273] Step 4:

[0274] The emotion engine analyzes the collected emotion data to determine the user's emotional state, for example, whether the user is stressed by high temperatures or uncomfortable by cold temperatures.

[0275] Step 5:

[0276] Based on the analysis, the server identifies periods when usage costs are expected to be high, for example, when air conditioning use increases in the summer and electricity consumption peaks.

[0277] Step 6:

[0278] The server creates alerts for identified events and prepares to send them to the user. The content of the alerts is adjusted based on the analysis results of the emotion engine. For example, if the user is feeling stressed, the alert wording will be changed to a gentler tone.

[0279] Step 7:

[0280] The server sends alerts to users via email or smartphone app notifications, such as "Power consumption is expected to increase due to air conditioning use next week. Please check your settings to keep cool and save energy."

[0281] Step 8:

[0282] The server checks the user's current contract plan and considers whether there is an optimal plan available. It compares this with the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction.

[0283] Step 9:

[0284] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[0285] Step 10:

[0286] Based on the predicted data and the user's emotional state, the server sends an instruction to the terminal to apply an energy-saving mode, for example, adjusting the temperature setting of the air conditioner to be comfortable and energy-efficient.

[0287] Step 11:

[0288] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[0289] Step 12:

[0290] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[0291] Step 13:

[0292] The emotion engine monitors the user's reactions to notifications and acceptance of suggestions, assessing changes in their emotional state and providing feedback to improve the quality of future alerts and energy-saving mode instructions.

[0293] Example 2

[0294] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] Conventional systems that collect and analyze infrastructure usage information and issue alerts have the problem of being unable to respond optimally while taking into account the user's emotional state. For example, if a user receives a harsh alert when they are feeling stressed, it may actually increase their discomfort. Furthermore, changes to contract plans or the application of energy-saving modes do not take into account the user's emotional state, which can make them less likely to agree or reduce their comfort. This presents a challenge in making infrastructure use more efficient.

[0296] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to the user based on the prediction results, means for optimizing a contract plan for infrastructure services, means for sending an instruction to apply an energy-saving mode to the terminal, means for collecting and analyzing user emotion data and associating the emotion data with the infrastructure usage information, and means for generating an appropriate alert and a proposal to change the contract plan according to the user's emotional state using a generative AI model. This makes it possible to optimize infrastructure usage while taking the user's emotional state into consideration, thereby achieving both user comfort and efficient resource management.

[0297] "Infrastructure usage information" is data on the usage of infrastructure services such as electricity, water, gas, and communications.

[0298] The "collection means" refers to a means for acquiring infrastructure usage information in real time using a data measurement device or a communication device.

[0299] "Analysis tools" refers to data analysis tools and algorithms used to generate usage patterns and cost forecasts based on collected infrastructure usage information.

[0300] The "alert sending means" is a means for sending a notification to the user by email, SMS, or other means based on the prediction results.

[0301] The "contract plan optimization means" is a means for checking the user's contract plan and proposing and applying a change to the most suitable plan.

[0302] The "energy saving mode instruction means" is a means for instructing application of the energy saving mode based on the infrastructure usage information.

[0303] "Terminals" refers to home appliances such as air conditioners and heaters, as well as other IoT devices.

[0304] "Emotion data" is data that indicates the user's emotional state, and is information collected from audio, video, text, and the like.

[0305] "Means for collecting and analyzing emotional data" refers to tools and algorithms for collecting and analyzing emotional data from audio, video, etc.

[0306] A "generative AI model" is an artificial intelligence model used to generate appropriate alerts and suggestions based on the user's emotional state.

[0307] A "prompt sentence" is text data that is input into a generative AI model to specify the content and tone of the sentence to be generated.

[0308] This invention combines a system that collects and analyzes infrastructure usage information to send alerts to users at appropriate times, optimizes contract plans, and applies energy-saving modes, with a mechanism that takes into account user emotion data. This system is composed of a server, terminals, users, and an emotion engine.

[0309] How the system is implemented

[0310] 1. Collection of infrastructure usage information

[0311] The server collects infrastructure usage information in real time from smart electricity bills, water meters, gas meters, and communication devices. This data collection is performed using data measurement devices and communication devices.

[0312] The server streams the collected data using Amazon Web Services (AWS (registered trademark)) Kinesis Data Streams, temporarily stores it, and then stores it in a database such as Amazon RDS or Google Cloud SQL.

[0313] 2. Data Analysis

[0314] The server uses Python's pandas library to preprocess the data and perform seasonal decomposition to identify seasonality and trends.

[0315] Additionally, we use scikit-learn predictive models (e.g., linear regression and random forest) to predict the next peak period and evaluate fluctuations in consumption patterns.

[0316] 3. Alert delivery

[0317] The server then uses the predictions to identify when usage costs will be high and sends alerts to users via email or SMS using SMTP or the Twilio API.

[0318] The emotion engine analyzes the emotion data and tailors the wording of the alert to the user's emotional state.

[0319] 4. Optimizing your contract plan

[0320] The server checks the user's contract plan information and searches the database for the most suitable plan.

[0321] Users are sent emails and push notifications with proposals for changes to their contract plans, which are empathetically worded using a generative AI model to make them more likely to be accepted.

[0322] 5. Applying energy saving mode

[0323] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[0324] The device (e.g., an air conditioner or heater) automatically adjusts the set temperature and switches to energy-saving mode according to the received instructions.

[0325] The emotion engine analyzes the user's emotion data and instructs them to change settings within a range that does not impair comfort.

[0326] 6. Introducing the Emotion Engine

[0327] The server uses an emotion engine to collect emotion data from smartphones and smart speakers, specifically analyzing emotions from audio and video data.

[0328] The emotion engine uses TENSORFLOW® and PyTorch emotion analysis models to assess users' real-time emotional state. Emotion data is associated with infrastructure usage information and stored in a database.

[0329] Specific examples

[0330] Increased electricity consumption in summer and utilization of emotion engine

[0331] The server collects data showing that air conditioner usage is high from June to August, and the emotion engine collects emotional data showing stress levels caused by high temperatures.

[0332] The server predicts that power consumption will peak in mid-July, and when sending an alert based on that prediction, the emotion engine adjusts the wording.

[0333] When optimizing contract plans, the server proposes the optimal plan, and the emotion engine generates empathetic proposals.

[0334] When energy-saving mode is applied, the device follows the server's instructions to raise the set temperature by 2 degrees, and the emotion engine also takes comfort into consideration.

[0335] Increased gas consumption in winter and the use of emotion engines

[0336] The server collects data showing that heating appliances are used more frequently from December to February. The emotion engine collects emotion data showing discomfort due to cold weather.

[0337] The server predicts that gas consumption will peak at the end of January, and when it sends an alert in mid-December, the emotion engine adjusts the content.

[0338] When optimizing contract plans, a special discount plan for the winter season is proposed, and the emotion engine generates a reassuring proposal.

[0339] When applying the energy-saving mode, the terminal adjusts the set temperature to an appropriate level according to the server's instructions, and the emotion engine takes into account the user's comfort.

[0340] Prompt Sentence Examples

[0341] Summer energy consumption alert: "Electricity consumption is expected to peak in mid-July. We recommend taking precautions in advance, such as adjusting your air conditioner temperature setting."

[0342] Winter gas consumption alert: "Gas consumption is expected to peak at the end of January. Please check your heating settings in advance and consider using energy-saving modes."

[0343] As described above, the present invention can be implemented using the following method. First, infrastructure usage information is collected in real time using a data measurement device or a communication device. Next, the collected data is processed by an analysis device to predict usage patterns and costs. Then, based on the prediction results, an alert is sent, and instructions are given to optimize the contract plan or apply an energy-saving mode. Furthermore, by combining an emotion engine that collects and analyzes user emotion data and using a generative AI model to generate appropriate alerts and suggestions according to the user's emotional state, it becomes possible to achieve both user comfort and efficient resource management.

[0344] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0345] Step 1: Collecting infrastructure usage information

[0346] The server connects to smart electricity meters, water meters, gas meters, and communication devices to collect data in real time.

[0347] Input: Real-time data from data measurement equipment.

[0348] Output: Streamed infrastructure usage information.

[0349] How it works: The server streams this data using AWS Kinesis Data Streams and stores it temporarily. The streaming data is periodically aggregated and stored in a database such as Amazon RDS or Google Cloud SQL.

[0350] Step 2: Data analysis

[0351] The server preprocesses the collected data and converts it into a format that is easy to analyze, for example by imputing missing values ​​and checking for outliers.

[0352] Input: Infrastructure usage information from streaming data.

[0353] Output: A dataset that can be analyzed.

[0354] How it works: The server preprocesses the data using Python's pandas library, then performs seasonal decomposition to identify seasonality and trends, and uses scikit-learn predictive models (e.g., linear regression and random forest) to forecast fluctuations in consumption patterns.

[0355] Step 3: Alert Delivery

[0356] Based on the prediction results, the server identifies when usage costs will be high and sends an alert to the user.

[0357] Input: Analysis results from the predictive model.

[0358] Output: The alert message to send to the user.

[0359] Specific operation: The server uses SMTP or Twilio API to send predictive alerts to users via email or SMS, and adjusts the wording of the alert text based on the user's emotional data analyzed by the emotion engine.

[0360] Step 4: Optimize your plan

[0361] The server checks the user's contract plan and proposes changing to the most suitable plan.

[0362] Input: User contract plan information and infrastructure usage information.

[0363] Output: Optimal plan suggestion message.

[0364] Specific operation: The server uses the contract plan API to compare plans and select the most cost-effective plan. The generative AI model uses an emotion engine to generate empathetic recommendations and send them to the user.

[0365] Step 5: Apply Energy Saving Mode

[0366] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[0367] Input: Predicted results and consumption pattern data.

[0368] Output: Energy saving mode instruction message.

[0369] Specific operation: The device (e.g., air conditioner or heater) receives instructions from the server and automatically adjusts the set temperature. It also uses the emotion engine to instruct the device to change the settings within a range that does not impair the user's comfort.

[0370] Step 6: Implementing the Emotion Engine

[0371] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information.

[0372] Input: Audio and video data, text data.

[0373] Output: Analyzed data about the user's emotional state.

[0374] Specific operation: The server collects audio and video data from smartphones and smart speakers, and evaluates user emotions in real time using emotion analysis models in TensorFlow and PyTorch. The emotion data is associated with infrastructure usage information and stored in a database, and the results are used as feedback for subsequent processing (sending alerts, optimizing contract plans, instructing energy-saving modes).

[0375] (Application example 2)

[0376] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0377] In modern factories and facilities, optimizing energy use and managing costs are important issues. Furthermore, it is known that workers' emotional states have a significant impact on productivity and work efficiency, but systems that comprehensively manage these factors have yet to be fully developed. Conventional systems focus on monitoring and optimizing energy consumption and do not take into account workers' emotional states, making it difficult to improve overall efficiency. Furthermore, selecting an efficient energy contract plan and applying energy-saving modes are often performed manually, making it difficult to respond in a timely manner. The purpose of this invention is to provide a system that comprehensively manages energy consumption and workers' emotional states, providing an efficient and comfortable work environment.

[0378] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0379] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to a user based on the prediction results, means for optimizing an infrastructure service contract plan, means for sending an instruction to apply an energy-saving mode to a terminal, means for collecting and analyzing user emotion data, and means for adjusting the wording of the alert and the energy-saving mode settings based on the emotion data. This enables the optimization of energy usage and the emotional state of workers to be managed in an integrated manner, thereby providing an efficient and comfortable work environment.

[0380] "Infrastructure usage information" refers to data on energy consumption such as electricity, water, and gas at factories and facilities.

[0381] "Means of collection" refers to the equipment and methods for collecting information on infrastructure usage through measuring devices such as sensors and meters.

[0382] "Means for analyzing and generating usage patterns and cost projections" refers to algorithms and software used to analyze collected data and predict trends in energy usage and future consumption costs.

[0383] "Means for sending alerts to users based on prediction results" refers to a mechanism for sending warnings or notifications to users based on analysis results.

[0384] "Means for optimizing contract plans" refers to a system or method that selects the optimal energy contract plan based on analyzed data and automatically changes it as necessary.

[0385] "Means for sending instructions to terminals to apply energy-saving mode" refers to a mechanism for sending settings to reduce energy consumption as commands to each terminal and changing the operating mode accordingly.

[0386] "User emotion data" refers to data that indicates the stress level and emotional state of a worker or user.

[0387] "Means for collecting and analyzing emotional data" refers to technologies and methods for collecting and analyzing the emotional state of workers and users using sensors and emotion recognition software.

[0388] "Means for adjusting alert wording and energy-saving mode settings based on emotional data" refers to a mechanism that appropriately adjusts notification content and energy settings for users based on collected emotional data.

[0389] "System" refers to a collection of devices and software that includes all of the above means and operates in conjunction with one another.

[0390] overview

[0391] The system that realizes this invention consists of a server, a terminal, a user, and an emotion engine. The server collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. The emotion engine also collects user emotion data and takes appropriate action accordingly.

[0392] Hardware and software used

[0393] Hardware: Factory robots, servers, smart sensors (electricity, water, gas, etc.), smart glasses (for workers)

[0394] Software: Data analysis software (e.g., Amazon SageMaker), emotion engine (e.g., Google Cloud Emotion AI), alert distribution system (e.g., Twilio)

[0395] Data collection and analysis

[0396] The server collects real-time consumption data on electricity, water, gas, etc. from smart sensors in the factory. In addition, worker emotion data is collected through smart glasses. This data is analyzed using data analysis software (e.g., Amazon SageMaker) on the server to predict energy consumption patterns and future consumption costs.

[0397] Alert generation and notification

[0398] The server generates timely alerts based on the prediction results. This uses an alert distribution system (e.g., Twilio) to notify users and workers of important events, allowing them to take proactive measures. In addition, an emotion engine (e.g., Google Cloud Emotion AI) adjusts the content of the alerts according to the user's emotional state.

[0399] Optimizing contract plans

[0400] The server then proposes the optimal energy contract plan based on the analyzed data and automatically changes it, allowing users to reduce unnecessary costs.

[0401] Applying energy saving mode

[0402] Factory robots and other devices switch to energy-saving mode in response to instructions from the server. For example, during times of high energy consumption, they automatically change their operating settings to reduce consumption. The emotion engine adjusts the energy-saving mode while taking into account the user's emotional state and ensuring comfort.

[0403] Specific examples

[0404] Example 1: Increase in summer electricity consumption and utilization of emotion engine

[0405] 1. Data Collection

[0406] The server collects electricity consumption data that indicates high air conditioner usage from June to August, and the emotion engine collects user emotion data from smart glasses.

[0407] 2. Data Analysis

[0408] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[0409] 3. Alert delivery

[0410] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[0411] 4. Optimizing your contract plan

[0412] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[0413] 5. Applying energy saving mode

[0414] Terminals such as factory robots automatically raise the set temperature by 2 degrees and switch to energy-saving mode in response to instructions from the server. The emotion engine also takes comfort into consideration when instructing the temperature setting.

[0415] Prompt Sentence Examples

[0416] "Analyze the power consumption data in the factory and predict peak periods this week."

[0417] "Analyze the emotional data of Worker A and identify his stress level and its contributing factors."

[0418] "Based on your consumption patterns, suggest and automatically apply the most suitable energy contract plan."

[0419] In this way, the present invention provides a system that manages infrastructure usage information and emotion data in an integrated manner, and aims to use energy efficiently and optimize the working environment.

[0420] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0421] Step 1:

[0422] The server collects real-time infrastructure usage information from smart sensors (electricity, water, gas, etc.) within the factory.

[0423] Input: Data from smart sensors (electricity, water, gas consumption information)

[0424] Processing: Various consumption data is collected on the server and stored in a database.

[0425] Output: Infrastructure usage data set

[0426] Step 2:

[0427] The server collects the user's (worker's) emotional data through smart glasses.

[0428] Input: Emotion data from smart glasses (worker's facial expressions and voice)

[0429] Processing: Emotion data is analyzed by an emotion engine (e.g., Google Cloud Emotion AI) to assess the worker's stress and emotional state.

[0430] Output: Emotion analysis results

[0431] Step 3:

[0432] The server analyzes the collected infrastructure usage information using data analysis software (e.g., Amazon SageMaker) to predict energy consumption patterns and future consumption costs.

[0433] Input: Infrastructure usage data set

[0434] Processing: Run data analysis algorithms to predict trends and peak periods in energy consumption.

[0435] Output: Energy consumption prediction results

[0436] Step 4:

[0437] The server generates an alert for the user based on the emotion analysis results and the energy consumption prediction results, and sends it using an alert delivery system (e.g., Twilio).

[0438] Input: Sentiment analysis results, energy consumption prediction results

[0439] Processing: The alert generation algorithm determines what to notify the user, adjusting the wording of the alert based on sentiment data.

[0440] Output: Alert message (e.g. "Power consumption is expected to reach a peak. Please take measures.")

[0441] Step 5:

[0442] Based on the analysis results, the server optimizes the user's energy contract plan.

[0443] Input: Energy consumption forecast results

[0444] Processing: Select the optimal plan and automatically change the contract plan if necessary.

[0445] Output: Optimized energy contract plan information

[0446] Step 6:

[0447] The server sends instructions to various terminals (factory robots and equipment) to apply energy-saving mode.

[0448] Input: Energy consumption prediction results, emotion analysis results

[0449] Processing: Determines energy-saving mode settings and issues instructions to various devices. Adjusts settings based on emotional data, taking comfort into account.

[0450] Output: Energy saving mode instruction message (e.g. "Raise the set temperature by 2 degrees to switch to energy saving mode.")

[0451] Step 7:

[0452] The terminal (factory robot) receives instructions from the server and switches to energy-saving mode.

[0453] Input: Power saving mode instruction message from the server

[0454] Action: Automatically change operating settings and apply energy saving mode

[0455] Output: Energy saving operation state

[0456] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0457] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0458] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0462] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0463] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0464] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0465] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0466] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0467] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0468] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0469] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0470] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0471] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0472] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[0473] System Overview

[0474] The following elements play a key role in this system:

[0475] 1. Collection of infrastructure usage information

[0476] The server collects real-time usage information from smart electricity bills, water meters, gas meters, communication devices, etc. This allows for a detailed understanding of users' consumption patterns.

[0477] 2. Data Analysis

[0478] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[0479] 3. Alert delivery

[0480] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[0481] 4. Optimizing your contract plan

[0482] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[0483] 5. Applying energy saving mode

[0484] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[0485] Specific examples

[0486] Example 1: Increased electricity consumption in summer

[0487] 1. Data Collection

[0488] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[0489] 2. Data Analysis

[0490] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[0491] 3. Alert delivery

[0492] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[0493] 4. Optimizing your contract plan

[0494] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[0495] 5. Applying energy saving mode

[0496] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[0497] Example 2: Increased gas consumption in winter

[0498] 1. Data Collection

[0499] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February.

[0500] 2. Data Analysis

[0501] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year.

[0502] 3. Alert delivery

[0503] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak and urging them to take measures.

[0504] 4. Optimizing your contract plan

[0505] The server checks the user's gas company plan and suggests changing to a special discount plan for the winter season.

[0506] 5. Applying energy saving mode

[0507] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode in response to instructions from the server.

[0508] In this way, the system of the present invention provides a set of processes for monitoring and optimizing users' infrastructure usage in real time, thereby enabling users to achieve efficient and cost-effective infrastructure usage.

[0509] The processing flow will be explained below.

[0510] Step 1:

[0511] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[0512] Step 2:

[0513] The server analyzes the collected infrastructure usage information. This involves applying algorithms that use historical data to identify seasonal and event usage patterns and then predict future usage and costs. For example, it analyzes patterns that indicate increased gas consumption for heating in the winter (December to February).

[0514] Step 3:

[0515] Based on the analysis results, the server identifies when usage costs are expected to increase at a specific time, creates an alert for the identified event, and prepares to send the alert to the user.

[0516] Step 4:

[0517] The server sends an alert to the user via email or the notification function of a smartphone app. For example, it could send an alert stating, "Power consumption is expected to increase due to air conditioning use next week."

[0518] Step 5:

[0519] The server checks the user's current contract plan and considers whether an optimal plan is available. It compares the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction. For example, it investigates whether a plan that offers reduced charges during specific peak hours is applicable.

[0520] Step 6:

[0521] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[0522] Step 7:

[0523] The server sends instructions to the terminal to apply an energy-saving mode based on the forecast data and the cost reduction policy, for example, to automatically adjust the temperature setting of the air conditioner.

[0524] Step 8:

[0525] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[0526] Step 9:

[0527] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[0528] Example 1

[0529] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0530] In today's world, where energy consumption is increasing in homes and businesses, it is difficult to understand consumption patterns and specific costs. Furthermore, it is often difficult to take appropriate measures to prevent energy waste and increased costs. Furthermore, optimizing contract plans and switching to energy-saving modes is done manually, making effective energy management difficult.

[0531] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0532] In this invention, the server includes a means for collecting infrastructure usage information, a means for analyzing the collected infrastructure usage information using a big data analysis tool to predict usage patterns and costs, a means for sending alerts to user devices based on the prediction results, a means for using an energy company's API to optimize infrastructure service contract plans, and a means for sending instructions to apply energy-saving modes to home appliances, thereby enabling visualization and optimization of energy consumption and automatic energy-saving measures.

[0533] "Infrastructure usage information" refers to usage data related to infrastructure services such as electricity, water, gas, and communications.

[0534] "Means of collection" refers to technologies including sensors and APIs for obtaining information from smart meters, communication devices, etc.

[0535] "Big data analysis tools" are software and frameworks for processing and analyzing huge data sets, including Spark and Hadoop.

[0536] "Usage patterns" are data that indicate trends in the use of energy, etc. at specific times or under specific conditions.

[0537] "Cost forecasting" refers to estimating future charges based on future energy and other usage.

[0538] An "alert" is a message that notifies the user based on a specific condition or prediction result.

[0539] "User devices" refer to terminals and applications used by users, including smartphones and PCs.

[0540] An "energy company API" is an interface for accessing data and services offered by energy providers.

[0541] "Contract plan optimization" is the process of proposing or changing the most cost-effective energy plan based on the user's consumption patterns.

[0542] "Energy saving mode" is a setting that switches home appliances to a specific operating state to reduce energy consumption.

[0543] "Home appliances" are electronic devices used in the home, such as heating and cooling equipment and lighting.

[0544] "Means for sending instructions to home appliances" refers to the communication technology and protocols used to transmit instructions from the server to home appliances. Examples include Wi-Fi and Bluetooth.

[0545] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[0546] 1. Program Generation

[0547] The server generates a program that contains the following main modules:

[0548] 1. Infrastructure usage information collection module

[0549] 2. Data Analysis Module

[0550] 3. Alert Delivery Module

[0551] 4. Contract plan optimization module

[0552] 5. Energy-saving mode application module

[0553] 2. Explain the program's processing in natural language

[0554] Collection of infrastructure usage information

[0555] The server collects data in real time from meters such as smart electricity bills, water meters, and gas meters using the meter's API. For example, the server retrieves electricity usage data every minute and stores it in a relational database such as MySQL or PostgreSQL.

[0556] Data analysis

[0557] The server analyzes the collected data using big data analytics tools (e.g., Spark, Hadoop) to identify seasonal usage patterns and peak periods. The analysis results are used to predict the next peak period and potential cost increases. For example, the server uses data from the past year to predict peak usage times in a particular month with an accuracy of over 80%.

[0558] Alert delivery

[0559] The server then sends alerts to the user based on the analysis results. Twilio's SMS API or Firebase Cloud Messaging are often used for alert delivery. For example, the server might send a notification to the user's smartphone saying, "Power usage will soon reach its peak. Please take measures to reduce energy consumption."

[0560] Optimizing contract plans

[0561] The server compares the analysis results with the user's current contract plan and suggests changing to the optimal plan. It also uses the energy company's API to obtain the user's usage history and the optimal plan. For example, the server might send the user a message saying, "We have a new plan that offers lower rates during peak hours. We recommend you change to it."

[0562] Applying energy saving mode

[0563] The device receives instructions from the server and automatically adjusts its settings. For example, if an air conditioner receives an instruction to "change the set temperature from 24 degrees to 26 degrees," it will automatically change the setting and reduce power consumption. This is done using smart device integration software such as Home Assistant and Google Home for IoT control.

[0564] Specific examples

[0565] Below are some concrete examples and examples of prompts for the generative AI model:

[0566] Example 1: Increased electricity consumption in summer

[0567] 1. Data Collection:

[0568] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[0569] 2. Data Analysis:

[0570] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[0571] 3. Alert Delivery:

[0572] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[0573] 4. Plan optimization:

[0574] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[0575] 5. Apply energy saving mode:

[0576] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[0577] Example prompts for generative AI models

[0578] Describe the system's program in natural language. Include the following elements:

[0579] Use the server, terminal, and user as subjects

[0580] Specific hardware and software names for each process

[0581] Data collection, data analysis, alert distribution, contract plan optimization, energy saving mode application

[0582] Specific examples of events

[0583] What the program does

[0584] 1. Data collection: The server collects usage information from smart electricity bills and gas meters.

[0585] 2. Data analysis: The server analyzes the data using Hadoop or Spark.

[0586] 3. Alert delivery: The server sends an alert via Twilio or Firebase

[0587] 4. Optimizing contract plans: The server uses the energy company's API to propose the optimal plan.

[0588] 5. Applying power saving mode: The device switches to power saving mode using Home Assistant

[0589] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0590] Divide the program processing flow into processing steps

[0591] Step 1:

[0592] Step 2:

[0593] Step 3:

[0594] Step 4:

[0595] Step 5:

[0596] Detailed explanation of each processing step

[0597] Step 1:

[0598] The server collects infrastructure usage information, including electricity, water, and gas usage. As input, it uses real-time data from smart electricity bills, water meters, and gas meters. As output, this data is stored in a relational database, such as MySQL or PostgreSQL. Specifically, the server calls a remote API every minute to retrieve data from each meter.

[0599] Step 2:

[0600] The server analyzes the collected data using big data analysis tools. The data collected in step 1 is used as input. The output generates forecast data that identifies seasonal usage patterns and peak periods. Specifically, the server runs batch processing overnight and performs time series analysis using past data sets.

[0601] Step 3:

[0602] The server sends an alert to the user device based on the prediction results. The analysis results from step 2 are used as input. The output is a notification sent to the user's smartphone or computer. Specifically, the server generates a notification using Twilio's SMS API or Firebase Cloud Messaging and sends it to the user device.

[0603] Step 4:

[0604] The server compares the analysis results with the current contract plan and proposes a change to the optimal plan. The input uses the user's current contract plan information and the analysis results from step 2. The output is a proposal for the optimal energy plan for the user. Specifically, the server accesses the energy company's API, obtains the optimal rate plan information, and notifies the user.

[0605] Step 5:

[0606] The device receives instructions from the server and applies energy-saving mode. The instruction information from the server is used as input. The output is a change to the settings of the home appliance. Specifically, the device (e.g., air conditioner) automatically changes the set temperature and switches to energy-saving mode. This process uses smart device integration software such as Home Assistant or Google Home.

[0607] This allows for efficient energy management and automated energy saving measures.

[0608] (Application example 1)

[0609] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0610] In recent years, energy consumption by factory equipment and robots has increased, resulting in increased operating costs. There is a need to efficiently manage this energy consumption and reduce costs. However, current management systems are unable to collect and analyze energy usage information in real time, making it difficult to predict peak energy consumption. Furthermore, automation for optimizing infrastructure service contract plans and applying energy-saving modes has not been fully achieved. As a result, efficient energy management in factories has yet to be achieved.

[0611] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0612] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected energy consumption data and predicting peak energy consumption of specific equipment or robots, and means for optimizing energy consumption by applying an energy-saving mode during peak times. This makes it possible to monitor energy consumption in a factory in real time, propose a change to an optimal contract plan, and automatically apply an energy-saving mode.

[0613] "Infrastructure usage information" refers to data on the energy consumption of each device and robot within a factory, such as data obtained from electricity meters and gas meters.

[0614] "Means of collection" is a general term for hardware and software used to collect data in real time from electricity meters, water meters, gas meters, communication devices, etc.

[0615] The "analytical means" refers to algorithms and computer systems that analyze energy consumption patterns and predict future consumption peaks based on collected infrastructure usage information.

[0616] The "prediction method" refers to a calculation method and platform that uses past data to analyze consumption patterns and estimate peak energy consumption during specific times and situations.

[0617] "Means for sending alerts" are communications means and software for sending notifications to users based on the results of the analysis and predictions.

[0618] The "means for optimizing contract plans" is a system that analyzes the contents of the current infrastructure service contract and proposes or automatically applies the most suitable rate plan or service plan to the user.

[0619] The "means for sending instructions to terminals to apply energy-saving mode" refers to a control system that sends energy-saving mode instructions generated on the server side to various terminals (e.g., robots and devices) to automatically perform operations to reduce energy consumption.

[0620] The "energy saving mode" is an operating mode in which a particular device or robot minimizes energy consumption, and includes, for example, settings such as reducing the operating speed or turning off the power when not in operation.

[0621] This invention is a system for efficiently managing energy consumption in factories and reducing operational costs. The system consists of a server, terminals, and users. The server collects and analyzes infrastructure usage information in real time, and automatically proposes optimal contract plans and applies energy-saving modes.

[0622] System Overview

[0623] 1. Collection of infrastructure usage information

[0624] The server collects energy consumption data from various measuring devices in the factory (e.g., electricity meters, gas meters, temperature sensors, etc.), allowing the system to grasp in real time how much energy each piece of equipment and robot is consuming.

[0625] 2. Data Analysis

[0626] The server uses data processing libraries such as pandas and numpy to analyze the collected data. Algorithms for predicting energy consumption patterns and detecting outliers are used for the analysis. Specifically, machine learning models such as random forests are used to predict consumption peaks.

[0627] 3. Alert delivery

[0628] Based on the analysis results, the server will send an alert to the user if energy consumption is expected to exceed a certain threshold, which can be achieved using a notification system such as Pushbullet.

[0629] 4. Optimizing your contract plan

[0630] The server analyzes the current infrastructure service contract based on the energy consumption data and proposes changes to the optimal contract plan, which may result in cost savings for the user.

[0631] 5. Applying energy saving mode

[0632] The server sends instructions to specific equipment or robots to enter energy-saving mode, and the devices that receive these instructions automatically apply energy-saving settings, such as reducing their operating speed or turning off the power during non-operating hours.

[0633] Program processing explanation

[0634] The server first collects information from various measurement devices, then analyzes the collected data and predicts peak energy consumption using machine learning models such as random forests. For example, libraries such as pandas and numpy are used to preprocess and analyze the data.

[0635] If the system predicts that energy consumption will exceed the threshold, Pushbullet will be used to send an alert to the user, allowing the user to take appropriate measures. The server will also suggest optimizing the contract plan and send instructions to enter energy-saving mode. Devices that receive this instruction will automatically change their settings and begin taking actions to reduce energy consumption.

[0636] Examples and prompts

[0637] As a concrete example, consider a factory where peak energy consumption is predicted to occur between 10:00 AM and 2:00 PM on Mondays. To apply energy saving mode during this time, the server generates the following prompt:

[0638] Example prompt sentence:

[0639] "Please set your system to apply energy saving mode from 10:00 AM to 2:00 PM tomorrow."

[0640] As described above, by introducing this system, it will be possible to efficiently manage energy consumption and reduce costs in factories.

[0641] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0642] Step 1:

[0643] The server collects energy consumption data in real time from various measuring devices installed in the factory (e.g., electricity meters, gas meters, temperature sensors). This data includes the instantaneous electricity and gas consumption of each piece of equipment and robot. The server accumulates this data by hour and creates a data set for analysis.

[0644] Input: Real-time energy consumption data

[0645] Output: Hourly accumulated energy consumption dataset

[0646] Step 2:

[0647] The server analyzes the collected energy consumption data using data processing libraries such as pandas and numpy, and applies machine learning algorithms (e.g., random forests) to analyze consumption patterns, thereby forecasting hourly energy consumption and identifying peak consumption periods.

[0648] Input: Energy consumption dataset accumulated by hour

[0649] Output: A forecasting model to identify consumption peaks

[0650] Step 3:

[0651] The server then sends an alert to the user when energy consumption is expected to exceed a threshold based on the predicted peak consumption data. This alert is sent to the user in real time using a notification system such as Pushbullet.

[0652] Input: A forecast model to identify consumption peaks

[0653] Output: Energy consumption peak alert

[0654] Step 4:

[0655] The server analyzes the current infrastructure service contract plans and proposes the optimal contract plan based on the energy consumption data, and sends the proposal to the user as a notification.

[0656] Input: Energy consumption data, current contract plan information

[0657] Output: Proposal of the best contract plan

[0658] Step 5:

[0659] The server sends instructions to specific equipment or robots to enter energy-saving mode. The terminals (e.g., robots) that receive these instructions automatically change their operating settings to energy-saving settings, such as slowing down the operating speed or turning off the power during non-operating hours.

[0660] Input: Energy saving mode instruction

[0661] Output: Change the device's operating settings to apply power saving mode

[0662] The specific operation is as follows:

[0663] Example: The server predicts that the peak energy consumption period is from 10:00 AM to 2:00 PM on Mondays. Based on this prediction, it generates energy-saving mode instructions and sends them to the associated robots. The robots receive these instructions, reduce their operating speed, and automatically turn off their power during non-operating hours if necessary. This process optimizes power usage during peak energy consumption periods.

[0664] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0665] This invention combines a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes with an emotion engine that recognizes user emotions. This system consists of a server, terminals, users, and an emotion engine.

[0666] System Overview

[0667] The following elements play a key role in this system:

[0668] 1. Collection of infrastructure usage information

[0669] The server collects real-time infrastructure usage information from smart electricity bills, water meters, gas meters, and communication devices, allowing for detailed understanding of users' consumption patterns.

[0670] 2. Data Analysis

[0671] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[0672] 3. Alert delivery

[0673] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[0674] 4. Optimizing your contract plan

[0675] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[0676] 5. Applying energy saving mode

[0677] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[0678] 6. Introducing the Emotion Engine

[0679] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information, enabling optimal responses according to the user's emotional state.

[0680] Specific examples

[0681] Example 1: Increased electricity consumption in summer and utilization of emotion engine

[0682] 1. Data Collection

[0683] The server collects electricity consumption data that indicates high air conditioner usage from June to August, while the emotion engine collects user emotion data from smart devices.

[0684] 2. Data Analysis

[0685] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[0686] 3. Alert delivery

[0687] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[0688] 4. Optimizing your contract plan

[0689] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[0690] 5. Applying energy saving mode

[0691] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server. The emotion engine gives instructions on temperature settings that take comfort into consideration.

[0692] Example 2: Increased gas consumption in winter and the use of emotion engines

[0693] 1. Data Collection

[0694] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February, and the emotion engine collects information from smart devices that indicate a user's sensitivity to cold.

[0695] 2. Data Analysis

[0696] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year. The emotion engine evaluates the user's emotional state and identifies discomfort due to the cold.

[0697] 3. Alert delivery

[0698] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak, urging them to take appropriate measures. The emotion engine will adjust the content of the alert to take into account the user's emotions.

[0699] 4. Optimizing your contract plan

[0700] The server checks the user's gas company plan and suggests switching to a special winter discount plan. The emotion engine adjusts the suggestion to reassure the user.

[0701] 5. Applying energy saving mode

[0702] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode according to instructions from the server. The emotion engine gives instructions on temperature settings that prioritize the user's comfort.

[0703] In this way, the system of the present invention provides a series of processes for monitoring and optimizing users' infrastructure usage in real time. Furthermore, by combining it with an emotion engine, it is possible to optimize responses according to the user's emotional state, further improving the user experience.

[0704] The processing flow will be explained below.

[0705] Step 1:

[0706] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[0707] Step 2:

[0708] The emotion engine collects emotion data from users' smart devices (e.g., smartphones and wearable devices), including physiological and behavioral data such as heart rate, facial expression recognition, and voice tone.

[0709] Step 3:

[0710] The server analyzes collected infrastructure usage information to identify seasonal usage patterns and lifecycle fluctuations, thereby predicting upcoming peak periods and identifying potential cost increases.

[0711] Step 4:

[0712] The emotion engine analyzes the collected emotion data to determine the user's emotional state, for example, whether the user is stressed by high temperatures or uncomfortable by cold temperatures.

[0713] Step 5:

[0714] Based on the analysis, the server identifies periods when usage costs are expected to be high, for example, when air conditioning use increases in the summer and electricity consumption peaks.

[0715] Step 6:

[0716] The server creates alerts for identified events and prepares to send them to the user. The content of the alerts is adjusted based on the analysis results of the emotion engine. For example, if the user is feeling stressed, the alert wording will be changed to a gentler tone.

[0717] Step 7:

[0718] The server sends alerts to users via email or smartphone app notifications, such as "Power consumption is expected to increase due to air conditioning use next week. Please check your settings to keep cool and save energy."

[0719] Step 8:

[0720] The server checks the user's current contract plan and considers whether there is an optimal plan available. It compares this with the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction.

[0721] Step 9:

[0722] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[0723] Step 10:

[0724] Based on the predicted data and the user's emotional state, the server sends an instruction to the terminal to apply an energy-saving mode, for example, adjusting the temperature setting of the air conditioner to be comfortable and energy-efficient.

[0725] Step 11:

[0726] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[0727] Step 12:

[0728] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[0729] Step 13:

[0730] The emotion engine monitors the user's reactions to notifications and acceptance of suggestions, assessing changes in their emotional state and providing feedback to improve the quality of future alerts and energy-saving mode instructions.

[0731] Example 2

[0732] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0733] Conventional systems that collect and analyze infrastructure usage information and issue alerts have the problem of being unable to respond optimally while taking into account the user's emotional state. For example, if a user receives a harsh alert when they are feeling stressed, it may actually increase their discomfort. Furthermore, changes to contract plans or the application of energy-saving modes do not take into account the user's emotional state, which can make them less likely to agree or reduce their comfort. This presents a challenge in making infrastructure use more efficient.

[0734] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to the user based on the prediction results, means for optimizing a contract plan for infrastructure services, means for sending an instruction to apply an energy-saving mode to the terminal, means for collecting and analyzing user emotion data and associating the emotion data with the infrastructure usage information, and means for generating an appropriate alert and a proposal to change the contract plan according to the user's emotional state using a generative AI model. This makes it possible to optimize infrastructure usage while taking the user's emotional state into consideration, thereby achieving both user comfort and efficient resource management.

[0735] "Infrastructure usage information" is data on the usage of infrastructure services such as electricity, water, gas, and communications.

[0736] The "collection means" refers to a means for acquiring infrastructure usage information in real time using a data measurement device or a communication device.

[0737] "Analysis tools" refers to data analysis tools and algorithms used to generate usage patterns and cost forecasts based on collected infrastructure usage information.

[0738] The "alert sending means" is a means for sending a notification to the user by email, SMS, or other means based on the prediction results.

[0739] The "contract plan optimization means" is a means for checking the user's contract plan and proposing and applying a change to the most suitable plan.

[0740] The "energy saving mode instruction means" is a means for instructing application of the energy saving mode based on the infrastructure usage information.

[0741] "Terminals" refers to home appliances such as air conditioners and heaters, as well as other IoT devices.

[0742] "Emotion data" is data that indicates the user's emotional state, and is information collected from audio, video, text, and the like.

[0743] "Means for collecting and analyzing emotional data" refers to tools and algorithms for collecting and analyzing emotional data from audio, video, etc.

[0744] A "generative AI model" is an artificial intelligence model used to generate appropriate alerts and suggestions based on the user's emotional state.

[0745] A "prompt sentence" is text data that is input into a generative AI model to specify the content and tone of the sentence to be generated.

[0746] This invention combines a system that collects and analyzes infrastructure usage information to send alerts to users at appropriate times, optimizes contract plans, and applies energy-saving modes, with a mechanism that takes into account user emotion data. This system is composed of a server, terminals, users, and an emotion engine.

[0747] How the system is implemented

[0748] 1. Collection of infrastructure usage information

[0749] The server collects infrastructure usage information in real time from smart electricity bills, water meters, gas meters, and communication devices. This data collection is performed using data measurement devices and communication devices.

[0750] The server streams the collected data using Amazon Web Services (AWS) Kinesis Data Streams, stores it temporarily, and then stores it in a database such as Amazon RDS or Google Cloud SQL.

[0751] 2. Data Analysis

[0752] The server uses Python's pandas library to preprocess the data and perform seasonal decomposition to identify seasonality and trends.

[0753] Additionally, we use scikit-learn predictive models (e.g., linear regression and random forest) to predict the next peak period and evaluate fluctuations in consumption patterns.

[0754] 3. Alert delivery

[0755] The server then uses the predictions to identify when usage costs will be high and sends alerts to users via email or SMS using SMTP or the Twilio API.

[0756] The emotion engine analyzes the emotion data and tailors the wording of the alert to the user's emotional state.

[0757] 4. Optimizing your contract plan

[0758] The server checks the user's contract plan information and searches the database for the most suitable plan.

[0759] Users are sent emails and push notifications with proposals for changes to their contract plans, which are empathetically worded using a generative AI model to make them more likely to be accepted.

[0760] 5. Applying energy saving mode

[0761] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[0762] The device (e.g., an air conditioner or heater) automatically adjusts the set temperature and switches to energy-saving mode according to the received instructions.

[0763] The emotion engine analyzes the user's emotion data and instructs them to change settings within a range that does not impair comfort.

[0764] 6. Introducing the Emotion Engine

[0765] The server uses an emotion engine to collect emotion data from smartphones and smart speakers, specifically analyzing emotions from audio and video data.

[0766] The emotion engine uses TensorFlow and PyTorch emotion analysis models to assess users' real-time emotional state, and emotion data is correlated with infrastructure usage information and stored in a database.

[0767] Specific examples

[0768] Increased electricity consumption in summer and utilization of emotion engine

[0769] The server collects data showing that air conditioner usage is high from June to August, and the emotion engine collects emotional data showing stress levels caused by high temperatures.

[0770] The server predicts that power consumption will peak in mid-July, and when sending an alert based on that prediction, the emotion engine adjusts the wording.

[0771] When optimizing contract plans, the server proposes the optimal plan, and the emotion engine generates empathetic proposals.

[0772] When energy-saving mode is applied, the device follows the server's instructions to raise the set temperature by 2 degrees, and the emotion engine also takes comfort into consideration.

[0773] Increased gas consumption in winter and the use of emotion engines

[0774] The server collects data showing that heating appliances are used more frequently from December to February. The emotion engine collects emotion data showing discomfort due to cold weather.

[0775] The server predicts that gas consumption will peak at the end of January, and when it sends an alert in mid-December, the emotion engine adjusts the content.

[0776] When optimizing contract plans, a special discount plan for the winter season is proposed, and the emotion engine generates a reassuring proposal.

[0777] When applying the energy-saving mode, the terminal adjusts the set temperature to an appropriate level according to the server's instructions, and the emotion engine takes into account the user's comfort.

[0778] Prompt Sentence Examples

[0779] Summer energy consumption alert: "Electricity consumption is expected to peak in mid-July. We recommend taking precautions in advance, such as adjusting your air conditioner temperature setting."

[0780] Winter gas consumption alert: "Gas consumption is expected to peak at the end of January. Please check your heating settings in advance and consider using energy-saving modes."

[0781] As described above, the present invention can be implemented using the following method. First, infrastructure usage information is collected in real time using a data measurement device or a communication device. Next, the collected data is processed by an analysis device to predict usage patterns and costs. Then, based on the prediction results, an alert is sent, and instructions are given to optimize the contract plan or apply an energy-saving mode. Furthermore, by combining an emotion engine that collects and analyzes user emotion data and using a generative AI model to generate appropriate alerts and suggestions according to the user's emotional state, it becomes possible to achieve both user comfort and efficient resource management.

[0782] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0783] Step 1: Collecting infrastructure usage information

[0784] The server connects to smart electricity meters, water meters, gas meters, and communication devices to collect data in real time.

[0785] Input: Real-time data from data measurement equipment.

[0786] Output: Streamed infrastructure usage information.

[0787] How it works: The server streams this data using AWS Kinesis Data Streams and stores it temporarily. The streaming data is periodically aggregated and stored in a database such as Amazon RDS or Google Cloud SQL.

[0788] Step 2: Data analysis

[0789] The server preprocesses the collected data and converts it into a format that is easy to analyze, for example by imputing missing values ​​and checking for outliers.

[0790] Input: Infrastructure usage information from streaming data.

[0791] Output: A dataset that can be analyzed.

[0792] How it works: The server preprocesses the data using Python's pandas library, then performs seasonal decomposition to identify seasonality and trends, and uses scikit-learn predictive models (e.g., linear regression and random forest) to forecast fluctuations in consumption patterns.

[0793] Step 3: Alert Delivery

[0794] Based on the prediction results, the server identifies when usage costs will be high and sends an alert to the user.

[0795] Input: Analysis results from the predictive model.

[0796] Output: The alert message to send to the user.

[0797] Specific operation: The server uses SMTP or Twilio API to send predictive alerts to users via email or SMS, and adjusts the wording of the alert text based on the user's emotional data analyzed by the emotion engine.

[0798] Step 4: Optimize your plan

[0799] The server checks the user's contract plan and proposes changing to the most suitable plan.

[0800] Input: User contract plan information and infrastructure usage information.

[0801] Output: Optimal plan suggestion message.

[0802] Specific operation: The server uses the contract plan API to compare plans and select the most cost-effective plan. The generative AI model uses an emotion engine to generate empathetic recommendations and send them to the user.

[0803] Step 5: Apply Energy Saving Mode

[0804] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[0805] Input: Predicted results and consumption pattern data.

[0806] Output: Energy saving mode instruction message.

[0807] Specific operation: The device (e.g., air conditioner or heater) receives instructions from the server and automatically adjusts the set temperature. It also uses the emotion engine to instruct the device to change the settings within a range that does not impair the user's comfort.

[0808] Step 6: Implementing the Emotion Engine

[0809] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information.

[0810] Input: Audio and video data, text data.

[0811] Output: Analyzed data about the user's emotional state.

[0812] Specific operation: The server collects audio and video data from smartphones and smart speakers, and evaluates user emotions in real time using emotion analysis models in TensorFlow and PyTorch. The emotion data is associated with infrastructure usage information and stored in a database, and the results are used as feedback for subsequent processing (sending alerts, optimizing contract plans, instructing energy-saving modes).

[0813] (Application example 2)

[0814] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0815] In modern factories and facilities, optimizing energy use and managing costs are important issues. Furthermore, it is known that workers' emotional states have a significant impact on productivity and work efficiency, but systems that comprehensively manage these factors have yet to be fully developed. Conventional systems focus on monitoring and optimizing energy consumption and do not take into account workers' emotional states, making it difficult to improve overall efficiency. Furthermore, selecting an efficient energy contract plan and applying energy-saving modes are often performed manually, making it difficult to respond in a timely manner. The purpose of this invention is to provide a system that comprehensively manages energy consumption and workers' emotional states, providing an efficient and comfortable work environment.

[0816] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0817] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to a user based on the prediction results, means for optimizing an infrastructure service contract plan, means for sending an instruction to apply an energy-saving mode to a terminal, means for collecting and analyzing user emotion data, and means for adjusting the wording of the alert and the energy-saving mode settings based on the emotion data. This enables the optimization of energy usage and the emotional state of workers to be managed in an integrated manner, thereby providing an efficient and comfortable work environment.

[0818] "Infrastructure usage information" refers to data on energy consumption such as electricity, water, and gas at factories and facilities.

[0819] "Means of collection" refers to the equipment and methods for collecting information on infrastructure usage through measuring devices such as sensors and meters.

[0820] "Means for analyzing and generating usage patterns and cost projections" refers to algorithms and software used to analyze collected data and predict trends in energy usage and future consumption costs.

[0821] "Means for sending alerts to users based on prediction results" refers to a mechanism for sending warnings or notifications to users based on analysis results.

[0822] "Means for optimizing contract plans" refers to a system or method that selects the optimal energy contract plan based on analyzed data and automatically changes it as necessary.

[0823] "Means for sending instructions to terminals to apply energy-saving mode" refers to a mechanism for sending settings to reduce energy consumption as commands to each terminal and changing the operating mode accordingly.

[0824] "User emotion data" refers to data that indicates the stress level and emotional state of a worker or user.

[0825] "Means for collecting and analyzing emotional data" refers to technologies and methods for collecting and analyzing the emotional state of workers and users using sensors and emotion recognition software.

[0826] "Means for adjusting alert wording and energy-saving mode settings based on emotional data" refers to a mechanism that appropriately adjusts notification content and energy settings for users based on collected emotional data.

[0827] "System" refers to a collection of devices and software that includes all of the above means and operates in conjunction with one another.

[0828] overview

[0829] The system that realizes this invention consists of a server, a terminal, a user, and an emotion engine. The server collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. The emotion engine also collects user emotion data and takes appropriate action accordingly.

[0830] Hardware and software used

[0831] Hardware: Factory robots, servers, smart sensors (electricity, water, gas, etc.), smart glasses (for workers)

[0832] Software: Data analysis software (e.g., Amazon SageMaker), emotion engine (e.g., Google Cloud Emotion AI), alert distribution system (e.g., Twilio)

[0833] Data collection and analysis

[0834] The server collects real-time consumption data on electricity, water, gas, etc. from smart sensors in the factory. In addition, worker emotion data is collected through smart glasses. This data is analyzed using data analysis software (e.g., Amazon SageMaker) on the server to predict energy consumption patterns and future consumption costs.

[0835] Alert generation and notification

[0836] The server generates timely alerts based on the prediction results. This uses an alert distribution system (e.g., Twilio) to notify users and workers of important events, allowing them to take proactive measures. In addition, an emotion engine (e.g., Google Cloud Emotion AI) adjusts the content of the alerts according to the user's emotional state.

[0837] Optimizing contract plans

[0838] The server then proposes the optimal energy contract plan based on the analyzed data and automatically changes it, allowing users to reduce unnecessary costs.

[0839] Applying energy saving mode

[0840] Factory robots and other devices switch to energy-saving mode in response to instructions from the server. For example, during times of high energy consumption, they automatically change their operating settings to reduce consumption. The emotion engine adjusts the energy-saving mode while taking into account the user's emotional state and ensuring comfort.

[0841] Specific examples

[0842] Example 1: Increase in summer electricity consumption and utilization of emotion engine

[0843] 1. Data Collection

[0844] The server collects electricity consumption data that indicates high air conditioner usage from June to August, and the emotion engine collects user emotion data from smart glasses.

[0845] 2. Data Analysis

[0846] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[0847] 3. Alert delivery

[0848] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[0849] 4. Optimizing your contract plan

[0850] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[0851] 5. Applying energy saving mode

[0852] Terminals such as factory robots automatically raise the set temperature by 2 degrees and switch to energy-saving mode in response to instructions from the server. The emotion engine also takes comfort into consideration when instructing the temperature setting.

[0853] Prompt Sentence Examples

[0854] "Analyze the power consumption data in the factory and predict peak periods this week."

[0855] "Analyze the emotional data of Worker A and identify his stress level and its contributing factors."

[0856] "Based on your consumption patterns, suggest and automatically apply the most suitable energy contract plan."

[0857] In this way, the present invention provides a system that manages infrastructure usage information and emotion data in an integrated manner, and aims to use energy efficiently and optimize the working environment.

[0858] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0859] Step 1:

[0860] The server collects real-time infrastructure usage information from smart sensors (electricity, water, gas, etc.) within the factory.

[0861] Input: Data from smart sensors (electricity, water, gas consumption information)

[0862] Processing: Various consumption data is collected on the server and stored in a database.

[0863] Output: Infrastructure usage data set

[0864] Step 2:

[0865] The server collects the user's (worker's) emotional data through smart glasses.

[0866] Input: Emotion data from smart glasses (worker's facial expressions and voice)

[0867] Processing: Emotion data is analyzed by an emotion engine (e.g., Google Cloud Emotion AI) to assess the worker's stress and emotional state.

[0868] Output: Emotion analysis results

[0869] Step 3:

[0870] The server analyzes the collected infrastructure usage information using data analysis software (e.g., Amazon SageMaker) to predict energy consumption patterns and future consumption costs.

[0871] Input: Infrastructure usage data set

[0872] Processing: Run data analysis algorithms to predict trends and peak periods in energy consumption.

[0873] Output: Energy consumption prediction results

[0874] Step 4:

[0875] The server generates an alert for the user based on the emotion analysis results and the energy consumption prediction results, and sends it using an alert delivery system (e.g., Twilio).

[0876] Input: Sentiment analysis results, energy consumption prediction results

[0877] Processing: The alert generation algorithm determines what to notify the user, adjusting the wording of the alert based on sentiment data.

[0878] Output: Alert message (e.g. "Power consumption is expected to reach a peak. Please take measures.")

[0879] Step 5:

[0880] Based on the analysis results, the server optimizes the user's energy contract plan.

[0881] Input: Energy consumption forecast results

[0882] Processing: Select the optimal plan and automatically change the contract plan if necessary.

[0883] Output: Optimized energy contract plan information

[0884] Step 6:

[0885] The server sends instructions to various terminals (factory robots and equipment) to apply energy-saving mode.

[0886] Input: Energy consumption prediction results, emotion analysis results

[0887] Processing: Determines energy-saving mode settings and issues instructions to various devices. Adjusts settings based on emotional data, taking comfort into account.

[0888] Output: Energy saving mode instruction message (e.g. "Raise the set temperature by 2 degrees to switch to energy saving mode.")

[0889] Step 7:

[0890] The terminal (factory robot) receives instructions from the server and switches to energy-saving mode.

[0891] Input: Power saving mode instruction message from the server

[0892] Action: Automatically change operating settings and apply energy saving mode

[0893] Output: Energy saving operation state

[0894] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0895] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0896] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0897] [Third embodiment]

[0898] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0899] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0900] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0901] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0902] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0903] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0904] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0905] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0906] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0907] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0908] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0909] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0910] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[0911] System Overview

[0912] The following elements play a key role in this system:

[0913] 1. Collection of infrastructure usage information

[0914] The server collects real-time usage information from smart electricity bills, water meters, gas meters, communication devices, etc. This allows for a detailed understanding of users' consumption patterns.

[0915] 2. Data Analysis

[0916] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[0917] 3. Alert delivery

[0918] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[0919] 4. Optimizing your contract plan

[0920] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[0921] 5. Applying energy saving mode

[0922] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[0923] Specific examples

[0924] Example 1: Increased electricity consumption in summer

[0925] 1. Data Collection

[0926] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[0927] 2. Data Analysis

[0928] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[0929] 3. Alert delivery

[0930] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[0931] 4. Optimizing your contract plan

[0932] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[0933] 5. Applying energy saving mode

[0934] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[0935] Example 2: Increased gas consumption in winter

[0936] 1. Data Collection

[0937] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February.

[0938] 2. Data Analysis

[0939] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year.

[0940] 3. Alert delivery

[0941] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak and urging them to take measures.

[0942] 4. Optimizing your contract plan

[0943] The server checks the user's gas company plan and suggests changing to a special discount plan for the winter season.

[0944] 5. Applying energy saving mode

[0945] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode in response to instructions from the server.

[0946] In this way, the system of the present invention provides a set of processes for monitoring and optimizing users' infrastructure usage in real time, thereby enabling users to achieve efficient and cost-effective infrastructure usage.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[0950] Step 2:

[0951] The server analyzes the collected infrastructure usage information. This involves applying algorithms that use historical data to identify seasonal and event usage patterns and then predict future usage and costs. For example, it analyzes patterns that indicate increased gas consumption for heating in the winter (December to February).

[0952] Step 3:

[0953] Based on the analysis results, the server identifies when usage costs are expected to increase at a specific time, creates an alert for the identified event, and prepares to send the alert to the user.

[0954] Step 4:

[0955] The server sends an alert to the user via email or the notification function of a smartphone app. For example, it could send an alert stating, "Power consumption is expected to increase due to air conditioning use next week."

[0956] Step 5:

[0957] The server checks the user's current contract plan and considers whether an optimal plan is available. It compares the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction. For example, it investigates whether a plan that offers reduced charges during specific peak hours is applicable.

[0958] Step 6:

[0959] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[0960] Step 7:

[0961] The server sends instructions to the terminal to apply an energy-saving mode based on the forecast data and the cost reduction policy, for example, to automatically adjust the temperature setting of the air conditioner.

[0962] Step 8:

[0963] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[0964] Step 9:

[0965] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[0966] Example 1

[0967] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0968] In today's world, where energy consumption is increasing in homes and businesses, it is difficult to understand consumption patterns and specific costs. Furthermore, it is often difficult to take appropriate measures to prevent energy waste and increased costs. Furthermore, optimizing contract plans and switching to energy-saving modes is done manually, making effective energy management difficult.

[0969] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0970] In this invention, the server includes a means for collecting infrastructure usage information, a means for analyzing the collected infrastructure usage information using a big data analysis tool to predict usage patterns and costs, a means for sending alerts to user devices based on the prediction results, a means for using an energy company's API to optimize infrastructure service contract plans, and a means for sending instructions to apply energy-saving modes to home appliances, thereby enabling visualization and optimization of energy consumption and automatic energy-saving measures.

[0971] "Infrastructure usage information" refers to usage data related to infrastructure services such as electricity, water, gas, and communications.

[0972] "Means of collection" refers to technologies including sensors and APIs for obtaining information from smart meters, communication devices, etc.

[0973] "Big data analysis tools" are software and frameworks for processing and analyzing huge data sets, including Spark and Hadoop.

[0974] "Usage patterns" are data that indicate trends in the use of energy, etc. at specific times or under specific conditions.

[0975] "Cost forecasting" refers to estimating future charges based on future energy and other usage.

[0976] An "alert" is a message that notifies the user based on a specific condition or prediction result.

[0977] "User devices" refer to terminals and applications used by users, including smartphones and PCs.

[0978] An "energy company API" is an interface for accessing data and services offered by energy providers.

[0979] "Contract plan optimization" is the process of proposing or changing the most cost-effective energy plan based on the user's consumption patterns.

[0980] "Energy saving mode" is a setting that switches home appliances to a specific operating state to reduce energy consumption.

[0981] "Home appliances" are electronic devices used in the home, such as heating and cooling equipment and lighting.

[0982] "Means for sending instructions to home appliances" refers to the communication technology and protocols used to transmit instructions from the server to home appliances. Examples include Wi-Fi and Bluetooth.

[0983] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[0984] 1. Program Generation

[0985] The server generates a program that contains the following main modules:

[0986] 1. Infrastructure usage information collection module

[0987] 2. Data Analysis Module

[0988] 3. Alert Delivery Module

[0989] 4. Contract plan optimization module

[0990] 5. Energy-saving mode application module

[0991] 2. Explain the program's processing in natural language

[0992] Collection of infrastructure usage information

[0993] The server collects data in real time from meters such as smart electricity bills, water meters, and gas meters using the meter's API. For example, the server retrieves electricity usage data every minute and stores it in a relational database such as MySQL or PostgreSQL.

[0994] Data analysis

[0995] The server analyzes the collected data using big data analytics tools (e.g., Spark, Hadoop) to identify seasonal usage patterns and peak periods. The analysis results are used to predict the next peak period and potential cost increases. For example, the server uses data from the past year to predict peak usage times in a particular month with an accuracy of over 80%.

[0996] Alert delivery

[0997] The server then sends alerts to the user based on the analysis results. Twilio's SMS API or Firebase Cloud Messaging are often used for alert delivery. For example, the server might send a notification to the user's smartphone saying, "Power usage will soon reach its peak. Please take measures to reduce energy consumption."

[0998] Optimizing contract plans

[0999] The server compares the analysis results with the user's current contract plan and suggests changing to the optimal plan. It also uses the energy company's API to obtain the user's usage history and the optimal plan. For example, the server might send the user a message saying, "We have a new plan that offers lower rates during peak hours. We recommend you change to it."

[1000] Applying energy saving mode

[1001] The device receives instructions from the server and automatically adjusts its settings. For example, if an air conditioner receives an instruction to "change the set temperature from 24 degrees to 26 degrees," it will automatically change the setting and reduce power consumption. This is done using smart device integration software such as Home Assistant and Google Home for IoT control.

[1002] Specific examples

[1003] Below are some concrete examples and examples of prompts for the generative AI model:

[1004] Example 1: Increased electricity consumption in summer

[1005] 1. Data Collection:

[1006] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[1007] 2. Data Analysis:

[1008] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[1009] 3. Alert Delivery:

[1010] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[1011] 4. Plan optimization:

[1012] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[1013] 5. Apply energy saving mode:

[1014] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[1015] Example prompts for generative AI models

[1016] Describe the system's program in natural language. Include the following elements:

[1017] Use the server, terminal, and user as subjects

[1018] Specific hardware and software names for each process

[1019] Data collection, data analysis, alert distribution, contract plan optimization, energy saving mode application

[1020] Specific examples of events

[1021] What the program does

[1022] 1. Data collection: The server collects usage information from smart electricity bills and gas meters.

[1023] 2. Data analysis: The server analyzes the data using Hadoop or Spark.

[1024] 3. Alert delivery: The server sends an alert via Twilio or Firebase

[1025] 4. Optimizing contract plans: The server uses the energy company's API to propose the optimal plan.

[1026] 5. Applying power saving mode: The device switches to power saving mode using Home Assistant

[1027] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1028] Divide the program processing flow into processing steps

[1029] Step 1:

[1030] Step 2:

[1031] Step 3:

[1032] Step 4:

[1033] Step 5:

[1034] Detailed explanation of each processing step

[1035] Step 1:

[1036] The server collects infrastructure usage information, including electricity, water, and gas usage. As input, it uses real-time data from smart electricity bills, water meters, and gas meters. As output, this data is stored in a relational database, such as MySQL or PostgreSQL. Specifically, the server calls a remote API every minute to retrieve data from each meter.

[1037] Step 2:

[1038] The server analyzes the collected data using big data analysis tools. The data collected in step 1 is used as input. The output generates forecast data that identifies seasonal usage patterns and peak periods. Specifically, the server runs batch processing overnight and performs time series analysis using past data sets.

[1039] Step 3:

[1040] The server sends an alert to the user device based on the prediction results. The analysis results from step 2 are used as input. The output is a notification sent to the user's smartphone or computer. Specifically, the server generates a notification using Twilio's SMS API or Firebase Cloud Messaging and sends it to the user device.

[1041] Step 4:

[1042] The server compares the analysis results with the current contract plan and proposes a change to the optimal plan. The input uses the user's current contract plan information and the analysis results from step 2. The output is a proposal for the optimal energy plan for the user. Specifically, the server accesses the energy company's API, obtains the optimal rate plan information, and notifies the user.

[1043] Step 5:

[1044] The device receives instructions from the server and applies energy-saving mode. The instruction information from the server is used as input. The output is a change to the settings of the home appliance. Specifically, the device (e.g., air conditioner) automatically changes the set temperature and switches to energy-saving mode. This process uses smart device integration software such as Home Assistant or Google Home.

[1045] This allows for efficient energy management and automated energy saving measures.

[1046] (Application example 1)

[1047] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1048] In recent years, energy consumption by factory equipment and robots has increased, resulting in increased operating costs. There is a need to efficiently manage this energy consumption and reduce costs. However, current management systems are unable to collect and analyze energy usage information in real time, making it difficult to predict peak energy consumption. Furthermore, automation for optimizing infrastructure service contract plans and applying energy-saving modes has not been fully achieved. As a result, efficient energy management in factories has yet to be achieved.

[1049] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1050] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected energy consumption data and predicting peak energy consumption of specific equipment or robots, and means for optimizing energy consumption by applying an energy-saving mode during peak times. This makes it possible to monitor energy consumption in a factory in real time, propose a change to an optimal contract plan, and automatically apply an energy-saving mode.

[1051] "Infrastructure usage information" refers to data on the energy consumption of each device and robot within a factory, such as data obtained from electricity meters and gas meters.

[1052] "Means of collection" is a general term for hardware and software used to collect data in real time from electricity meters, water meters, gas meters, communication devices, etc.

[1053] The "analytical means" refers to algorithms and computer systems that analyze energy consumption patterns and predict future consumption peaks based on collected infrastructure usage information.

[1054] The "prediction method" refers to a calculation method and platform that uses past data to analyze consumption patterns and estimate peak energy consumption during specific times and situations.

[1055] "Means for sending alerts" are communications means and software for sending notifications to users based on the results of the analysis and predictions.

[1056] The "means for optimizing contract plans" is a system that analyzes the contents of the current infrastructure service contract and proposes or automatically applies the most suitable rate plan or service plan to the user.

[1057] The "means for sending instructions to terminals to apply energy-saving mode" refers to a control system that sends energy-saving mode instructions generated on the server side to various terminals (e.g., robots and devices) to automatically perform operations to reduce energy consumption.

[1058] The "energy saving mode" is an operating mode in which a particular device or robot minimizes energy consumption, and includes, for example, settings such as reducing the operating speed or turning off the power when not in operation.

[1059] This invention is a system for efficiently managing energy consumption in factories and reducing operational costs. The system consists of a server, terminals, and users. The server collects and analyzes infrastructure usage information in real time, and automatically proposes optimal contract plans and applies energy-saving modes.

[1060] System Overview

[1061] 1. Collection of infrastructure usage information

[1062] The server collects energy consumption data from various measuring devices in the factory (e.g., electricity meters, gas meters, temperature sensors, etc.), allowing the system to grasp in real time how much energy each piece of equipment and robot is consuming.

[1063] 2. Data Analysis

[1064] The server uses data processing libraries such as pandas and numpy to analyze the collected data. Algorithms for predicting energy consumption patterns and detecting outliers are used for the analysis. Specifically, machine learning models such as random forests are used to predict consumption peaks.

[1065] 3. Alert delivery

[1066] Based on the analysis results, the server will send an alert to the user if energy consumption is expected to exceed a certain threshold, which can be achieved using a notification system such as Pushbullet.

[1067] 4. Optimizing your contract plan

[1068] The server analyzes the current infrastructure service contract based on the energy consumption data and proposes changes to the optimal contract plan, which may result in cost savings for the user.

[1069] 5. Applying energy saving mode

[1070] The server sends instructions to specific equipment or robots to enter energy-saving mode, and the devices that receive these instructions automatically apply energy-saving settings, such as reducing their operating speed or turning off the power during non-operating hours.

[1071] Program processing explanation

[1072] The server first collects information from various measurement devices, then analyzes the collected data and predicts peak energy consumption using machine learning models such as random forests. For example, libraries such as pandas and numpy are used to preprocess and analyze the data.

[1073] If the system predicts that energy consumption will exceed the threshold, Pushbullet will be used to send an alert to the user, allowing the user to take appropriate measures. The server will also suggest optimizing the contract plan and send instructions to enter energy-saving mode. Devices that receive this instruction will automatically change their settings and begin taking actions to reduce energy consumption.

[1074] Examples and prompts

[1075] As a concrete example, consider a factory where peak energy consumption is predicted to occur between 10:00 AM and 2:00 PM on Mondays. To apply energy saving mode during this time, the server generates the following prompt:

[1076] Example prompt sentence:

[1077] "Please set your system to apply energy saving mode from 10:00 AM to 2:00 PM tomorrow."

[1078] As described above, by introducing this system, it will be possible to efficiently manage energy consumption and reduce costs in factories.

[1079] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1080] Step 1:

[1081] The server collects energy consumption data in real time from various measuring devices installed in the factory (e.g., electricity meters, gas meters, temperature sensors). This data includes the instantaneous electricity and gas consumption of each piece of equipment and robot. The server accumulates this data by hour and creates a data set for analysis.

[1082] Input: Real-time energy consumption data

[1083] Output: Hourly accumulated energy consumption dataset

[1084] Step 2:

[1085] The server analyzes the collected energy consumption data using data processing libraries such as pandas and numpy, and applies machine learning algorithms (e.g., random forests) to analyze consumption patterns, thereby forecasting hourly energy consumption and identifying peak consumption periods.

[1086] Input: Energy consumption dataset accumulated by hour

[1087] Output: A forecasting model to identify consumption peaks

[1088] Step 3:

[1089] The server then sends an alert to the user when energy consumption is expected to exceed a threshold based on the predicted peak consumption data. This alert is sent to the user in real time using a notification system such as Pushbullet.

[1090] Input: A forecast model to identify consumption peaks

[1091] Output: Energy consumption peak alert

[1092] Step 4:

[1093] The server analyzes the current infrastructure service contract plans and proposes the optimal contract plan based on the energy consumption data, and sends the proposal to the user as a notification.

[1094] Input: Energy consumption data, current contract plan information

[1095] Output: Proposal of the best contract plan

[1096] Step 5:

[1097] The server sends instructions to specific equipment or robots to enter energy-saving mode. The terminals (e.g., robots) that receive these instructions automatically change their operating settings to energy-saving settings, such as slowing down the operating speed or turning off the power during non-operating hours.

[1098] Input: Energy saving mode instruction

[1099] Output: Change the device's operating settings to apply power saving mode

[1100] The specific operation is as follows:

[1101] Example: The server predicts that the peak energy consumption period is from 10:00 AM to 2:00 PM on Mondays. Based on this prediction, it generates energy-saving mode instructions and sends them to the associated robots. The robots receive these instructions, reduce their operating speed, and automatically turn off their power during non-operating hours if necessary. This process optimizes power usage during peak energy consumption periods.

[1102] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1103] This invention combines a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes with an emotion engine that recognizes user emotions. This system consists of a server, terminals, users, and an emotion engine.

[1104] System Overview

[1105] The following elements play a key role in this system:

[1106] 1. Collection of infrastructure usage information

[1107] The server collects real-time infrastructure usage information from smart electricity bills, water meters, gas meters, and communication devices, allowing for detailed understanding of users' consumption patterns.

[1108] 2. Data Analysis

[1109] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[1110] 3. Alert delivery

[1111] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[1112] 4. Optimizing your contract plan

[1113] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[1114] 5. Applying energy saving mode

[1115] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[1116] 6. Introducing the Emotion Engine

[1117] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information, enabling optimal responses according to the user's emotional state.

[1118] Specific examples

[1119] Example 1: Increased electricity consumption in summer and utilization of emotion engine

[1120] 1. Data Collection

[1121] The server collects electricity consumption data that indicates high air conditioner usage from June to August, while the emotion engine collects user emotion data from smart devices.

[1122] 2. Data Analysis

[1123] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[1124] 3. Alert delivery

[1125] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[1126] 4. Optimizing your contract plan

[1127] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[1128] 5. Applying energy saving mode

[1129] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server. The emotion engine gives instructions on temperature settings that take comfort into consideration.

[1130] Example 2: Increased gas consumption in winter and the use of emotion engines

[1131] 1. Data Collection

[1132] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February, and the emotion engine collects information from smart devices that indicate a user's sensitivity to cold.

[1133] 2. Data Analysis

[1134] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year. The emotion engine evaluates the user's emotional state and identifies discomfort due to the cold.

[1135] 3. Alert delivery

[1136] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak, urging them to take appropriate measures. The emotion engine will adjust the content of the alert to take into account the user's emotions.

[1137] 4. Optimizing your contract plan

[1138] The server checks the user's gas company plan and suggests switching to a special winter discount plan. The emotion engine adjusts the suggestion to reassure the user.

[1139] 5. Applying energy saving mode

[1140] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode according to instructions from the server. The emotion engine gives instructions on temperature settings that prioritize the user's comfort.

[1141] In this way, the system of the present invention provides a series of processes for monitoring and optimizing users' infrastructure usage in real time. Furthermore, by combining it with an emotion engine, it is possible to optimize responses according to the user's emotional state, further improving the user experience.

[1142] The processing flow will be explained below.

[1143] Step 1:

[1144] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[1145] Step 2:

[1146] The emotion engine collects emotion data from users' smart devices (e.g., smartphones and wearable devices), including physiological and behavioral data such as heart rate, facial expression recognition, and voice tone.

[1147] Step 3:

[1148] The server analyzes collected infrastructure usage information to identify seasonal usage patterns and lifecycle fluctuations, thereby predicting upcoming peak periods and identifying potential cost increases.

[1149] Step 4:

[1150] The emotion engine analyzes the collected emotion data to determine the user's emotional state, for example, whether the user is stressed by high temperatures or uncomfortable by cold temperatures.

[1151] Step 5:

[1152] Based on the analysis, the server identifies periods when usage costs are expected to be high, for example, when air conditioning use increases in the summer and electricity consumption peaks.

[1153] Step 6:

[1154] The server creates alerts for identified events and prepares to send them to the user. The content of the alerts is adjusted based on the analysis results of the emotion engine. For example, if the user is feeling stressed, the alert wording will be changed to a gentler tone.

[1155] Step 7:

[1156] The server sends alerts to users via email or smartphone app notifications, such as "Power consumption is expected to increase due to air conditioning use next week. Please check your settings to keep cool and save energy."

[1157] Step 8:

[1158] The server checks the user's current contract plan and considers whether there is an optimal plan available. It compares this with the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction.

[1159] Step 9:

[1160] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[1161] Step 10:

[1162] Based on the predicted data and the user's emotional state, the server sends an instruction to the terminal to apply an energy-saving mode, for example, adjusting the temperature setting of the air conditioner to be comfortable and energy-efficient.

[1163] Step 11:

[1164] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[1165] Step 12:

[1166] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[1167] Step 13:

[1168] The emotion engine monitors the user's reactions to notifications and acceptance of suggestions, assessing changes in their emotional state and providing feedback to improve the quality of future alerts and energy-saving mode instructions.

[1169] Example 2

[1170] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1171] Conventional systems that collect and analyze infrastructure usage information and issue alerts have the problem of being unable to respond optimally while taking into account the user's emotional state. For example, if a user receives a harsh alert when they are feeling stressed, it may actually increase their discomfort. Furthermore, changes to contract plans or the application of energy-saving modes do not take into account the user's emotional state, which can make them less likely to agree or reduce their comfort. This presents a challenge in making infrastructure use more efficient.

[1172] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to the user based on the prediction results, means for optimizing a contract plan for infrastructure services, means for sending an instruction to apply an energy-saving mode to the terminal, means for collecting and analyzing user emotion data and associating the emotion data with the infrastructure usage information, and means for generating an appropriate alert and a proposal to change the contract plan according to the user's emotional state using a generative AI model. This makes it possible to optimize infrastructure usage while taking the user's emotional state into consideration, thereby achieving both user comfort and efficient resource management.

[1173] "Infrastructure usage information" is data on the usage of infrastructure services such as electricity, water, gas, and communications.

[1174] The "collection means" refers to a means for acquiring infrastructure usage information in real time using a data measurement device or a communication device.

[1175] "Analysis tools" refers to data analysis tools and algorithms used to generate usage patterns and cost forecasts based on collected infrastructure usage information.

[1176] The "alert sending means" is a means for sending a notification to the user by email, SMS, or other means based on the prediction results.

[1177] The "contract plan optimization means" is a means for checking the user's contract plan and proposing and applying a change to the most suitable plan.

[1178] The "energy saving mode instruction means" is a means for instructing application of the energy saving mode based on the infrastructure usage information.

[1179] "Terminals" refers to home appliances such as air conditioners and heaters, as well as other IoT devices.

[1180] "Emotion data" is data that indicates the user's emotional state, and is information collected from audio, video, text, and the like.

[1181] "Means for collecting and analyzing emotional data" refers to tools and algorithms for collecting and analyzing emotional data from audio, video, etc.

[1182] A "generative AI model" is an artificial intelligence model used to generate appropriate alerts and suggestions based on the user's emotional state.

[1183] A "prompt sentence" is text data that is input into a generative AI model to specify the content and tone of the sentence to be generated.

[1184] This invention combines a system that collects and analyzes infrastructure usage information to send alerts to users at appropriate times, optimizes contract plans, and applies energy-saving modes, with a mechanism that takes into account user emotion data. This system is composed of a server, terminals, users, and an emotion engine.

[1185] How the system is implemented

[1186] 1. Collection of infrastructure usage information

[1187] The server collects infrastructure usage information in real time from smart electricity bills, water meters, gas meters, and communication devices. This data collection is performed using data measurement devices and communication devices.

[1188] The server streams the collected data using Amazon Web Services (AWS) Kinesis Data Streams, stores it temporarily, and then stores it in a database such as Amazon RDS or Google Cloud SQL.

[1189] 2. Data Analysis

[1190] The server uses Python's pandas library to preprocess the data and perform seasonal decomposition to identify seasonality and trends.

[1191] Additionally, we use scikit-learn predictive models (e.g., linear regression and random forest) to predict the next peak period and evaluate fluctuations in consumption patterns.

[1192] 3. Alert delivery

[1193] The server then uses the predictions to identify when usage costs will be high and sends alerts to users via email or SMS using SMTP or the Twilio API.

[1194] The emotion engine analyzes the emotion data and tailors the wording of the alert to the user's emotional state.

[1195] 4. Optimizing your contract plan

[1196] The server checks the user's contract plan information and searches the database for the most suitable plan.

[1197] Users are sent emails and push notifications with proposals for changes to their contract plans, which are empathetically worded using a generative AI model to make them more likely to be accepted.

[1198] 5. Applying energy saving mode

[1199] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[1200] The device (e.g., an air conditioner or heater) automatically adjusts the set temperature and switches to energy-saving mode according to the received instructions.

[1201] The emotion engine analyzes the user's emotion data and instructs them to change settings within a range that does not impair comfort.

[1202] 6. Introducing the Emotion Engine

[1203] The server uses an emotion engine to collect emotion data from smartphones and smart speakers, specifically analyzing emotions from audio and video data.

[1204] The emotion engine uses TensorFlow and PyTorch emotion analysis models to assess users' real-time emotional state, and emotion data is correlated with infrastructure usage information and stored in a database.

[1205] Specific examples

[1206] Increased electricity consumption in summer and utilization of emotion engine

[1207] The server collects data showing that air conditioner usage is high from June to August, and the emotion engine collects emotional data showing stress levels caused by high temperatures.

[1208] The server predicts that power consumption will peak in mid-July, and when sending an alert based on that prediction, the emotion engine adjusts the wording.

[1209] When optimizing contract plans, the server proposes the optimal plan, and the emotion engine generates empathetic proposals.

[1210] When energy-saving mode is applied, the device follows the server's instructions to raise the set temperature by 2 degrees, and the emotion engine also takes comfort into consideration.

[1211] Increased gas consumption in winter and the use of emotion engines

[1212] The server collects data showing that heating appliances are used more frequently from December to February. The emotion engine collects emotion data showing discomfort due to cold weather.

[1213] The server predicts that gas consumption will peak at the end of January, and when it sends an alert in mid-December, the emotion engine adjusts the content.

[1214] When optimizing contract plans, a special discount plan for the winter season is proposed, and the emotion engine generates a reassuring proposal.

[1215] When applying the energy-saving mode, the terminal adjusts the set temperature to an appropriate level according to the server's instructions, and the emotion engine takes into account the user's comfort.

[1216] Prompt Sentence Examples

[1217] Summer energy consumption alert: "Electricity consumption is expected to peak in mid-July. We recommend taking precautions in advance, such as adjusting your air conditioner temperature setting."

[1218] Winter gas consumption alert: "Gas consumption is expected to peak at the end of January. Please check your heating settings in advance and consider using energy-saving modes."

[1219] As described above, the present invention can be implemented using the following method. First, infrastructure usage information is collected in real time using a data measurement device or a communication device. Next, the collected data is processed by an analysis device to predict usage patterns and costs. Then, based on the prediction results, an alert is sent, and instructions are given to optimize the contract plan or apply an energy-saving mode. Furthermore, by combining an emotion engine that collects and analyzes user emotion data and using a generative AI model to generate appropriate alerts and suggestions according to the user's emotional state, it becomes possible to achieve both user comfort and efficient resource management.

[1220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1221] Step 1: Collecting infrastructure usage information

[1222] The server connects to smart electricity meters, water meters, gas meters, and communication devices to collect data in real time.

[1223] Input: Real-time data from data measurement equipment.

[1224] Output: Streamed infrastructure usage information.

[1225] How it works: The server streams this data using AWS Kinesis Data Streams and stores it temporarily. The streaming data is periodically aggregated and stored in a database such as Amazon RDS or Google Cloud SQL.

[1226] Step 2: Data analysis

[1227] The server preprocesses the collected data and converts it into a format that is easy to analyze, for example by imputing missing values ​​and checking for outliers.

[1228] Input: Infrastructure usage information from streaming data.

[1229] Output: A dataset that can be analyzed.

[1230] How it works: The server preprocesses the data using Python's pandas library, then performs seasonal decomposition to identify seasonality and trends, and uses scikit-learn predictive models (e.g., linear regression and random forest) to forecast fluctuations in consumption patterns.

[1231] Step 3: Alert Delivery

[1232] Based on the prediction results, the server identifies when usage costs will be high and sends an alert to the user.

[1233] Input: Analysis results from the predictive model.

[1234] Output: The alert message to send to the user.

[1235] Specific operation: The server uses SMTP or Twilio API to send predictive alerts to users via email or SMS, and adjusts the wording of the alert text based on the user's emotional data analyzed by the emotion engine.

[1236] Step 4: Optimize your plan

[1237] The server checks the user's contract plan and proposes changing to the most suitable plan.

[1238] Input: User contract plan information and infrastructure usage information.

[1239] Output: Optimal plan suggestion message.

[1240] Specific operation: The server uses the contract plan API to compare plans and select the most cost-effective plan. The generative AI model uses an emotion engine to generate empathetic recommendations and send them to the user.

[1241] Step 5: Apply Energy Saving Mode

[1242] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[1243] Input: Predicted results and consumption pattern data.

[1244] Output: Energy saving mode instruction message.

[1245] Specific operation: The device (e.g., air conditioner or heater) receives instructions from the server and automatically adjusts the set temperature. It also uses the emotion engine to instruct the device to change the settings within a range that does not impair the user's comfort.

[1246] Step 6: Implementing the Emotion Engine

[1247] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information.

[1248] Input: Audio and video data, text data.

[1249] Output: Analyzed data about the user's emotional state.

[1250] Specific operation: The server collects audio and video data from smartphones and smart speakers, and evaluates user emotions in real time using emotion analysis models in TensorFlow and PyTorch. The emotion data is associated with infrastructure usage information and stored in a database, and the results are used as feedback for subsequent processing (sending alerts, optimizing contract plans, instructing energy-saving modes).

[1251] (Application example 2)

[1252] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1253] In modern factories and facilities, optimizing energy use and managing costs are important issues. Furthermore, it is known that workers' emotional states have a significant impact on productivity and work efficiency, but systems that comprehensively manage these factors have yet to be fully developed. Conventional systems focus on monitoring and optimizing energy consumption and do not take into account workers' emotional states, making it difficult to improve overall efficiency. Furthermore, selecting an efficient energy contract plan and applying energy-saving modes are often performed manually, making it difficult to respond in a timely manner. The purpose of this invention is to provide a system that comprehensively manages energy consumption and workers' emotional states, providing an efficient and comfortable work environment.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1255] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to a user based on the prediction results, means for optimizing an infrastructure service contract plan, means for sending an instruction to apply an energy-saving mode to a terminal, means for collecting and analyzing user emotion data, and means for adjusting the wording of the alert and the energy-saving mode settings based on the emotion data. This enables the optimization of energy usage and the emotional state of workers to be managed in an integrated manner, thereby providing an efficient and comfortable work environment.

[1256] "Infrastructure usage information" refers to data on energy consumption such as electricity, water, and gas at factories and facilities.

[1257] "Means of collection" refers to the equipment and methods for collecting information on infrastructure usage through measuring devices such as sensors and meters.

[1258] "Means for analyzing and generating usage patterns and cost projections" refers to algorithms and software used to analyze collected data and predict trends in energy usage and future consumption costs.

[1259] "Means for sending alerts to users based on prediction results" refers to a mechanism for sending warnings or notifications to users based on analysis results.

[1260] "Means for optimizing contract plans" refers to a system or method that selects the optimal energy contract plan based on analyzed data and automatically changes it as necessary.

[1261] "Means for sending instructions to terminals to apply energy-saving mode" refers to a mechanism for sending settings to reduce energy consumption as commands to each terminal and changing the operating mode accordingly.

[1262] "User emotion data" refers to data that indicates the stress level and emotional state of a worker or user.

[1263] "Means for collecting and analyzing emotional data" refers to technologies and methods for collecting and analyzing the emotional state of workers and users using sensors and emotion recognition software.

[1264] "Means for adjusting alert wording and energy-saving mode settings based on emotional data" refers to a mechanism that appropriately adjusts notification content and energy settings for users based on collected emotional data.

[1265] "System" refers to a collection of devices and software that includes all of the above means and operates in conjunction with one another.

[1266] overview

[1267] The system that realizes this invention consists of a server, a terminal, a user, and an emotion engine. The server collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. The emotion engine also collects user emotion data and takes appropriate action accordingly.

[1268] Hardware and software used

[1269] Hardware: Factory robots, servers, smart sensors (electricity, water, gas, etc.), smart glasses (for workers)

[1270] Software: Data analysis software (e.g., Amazon SageMaker), emotion engine (e.g., Google Cloud Emotion AI), alert distribution system (e.g., Twilio)

[1271] Data collection and analysis

[1272] The server collects real-time consumption data on electricity, water, gas, etc. from smart sensors in the factory. In addition, worker emotion data is collected through smart glasses. This data is analyzed using data analysis software (e.g., Amazon SageMaker) on the server to predict energy consumption patterns and future consumption costs.

[1273] Alert generation and notification

[1274] The server generates timely alerts based on the prediction results. This uses an alert distribution system (e.g., Twilio) to notify users and workers of important events, allowing them to take proactive measures. In addition, an emotion engine (e.g., Google Cloud Emotion AI) adjusts the content of the alerts according to the user's emotional state.

[1275] Optimizing contract plans

[1276] The server then proposes the optimal energy contract plan based on the analyzed data and automatically changes it, allowing users to reduce unnecessary costs.

[1277] Applying energy saving mode

[1278] Factory robots and other devices switch to energy-saving mode in response to instructions from the server. For example, during times of high energy consumption, they automatically change their operating settings to reduce consumption. The emotion engine adjusts the energy-saving mode while taking into account the user's emotional state and ensuring comfort.

[1279] Specific examples

[1280] Example 1: Increase in summer electricity consumption and utilization of emotion engine

[1281] 1. Data Collection

[1282] The server collects electricity consumption data that indicates high air conditioner usage from June to August, and the emotion engine collects user emotion data from smart glasses.

[1283] 2. Data Analysis

[1284] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[1285] 3. Alert delivery

[1286] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[1287] 4. Optimizing your contract plan

[1288] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[1289] 5. Applying energy saving mode

[1290] Terminals such as factory robots automatically raise the set temperature by 2 degrees and switch to energy-saving mode in response to instructions from the server. The emotion engine also takes comfort into consideration when instructing the temperature setting.

[1291] Prompt Sentence Examples

[1292] "Analyze the power consumption data in the factory and predict peak periods this week."

[1293] "Analyze the emotional data of Worker A and identify his stress level and its contributing factors."

[1294] "Based on your consumption patterns, suggest and automatically apply the most suitable energy contract plan."

[1295] In this way, the present invention provides a system that manages infrastructure usage information and emotion data in an integrated manner, and aims to use energy efficiently and optimize the working environment.

[1296] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1297] Step 1:

[1298] The server collects real-time infrastructure usage information from smart sensors (electricity, water, gas, etc.) within the factory.

[1299] Input: Data from smart sensors (electricity, water, gas consumption information)

[1300] Processing: Various consumption data is collected on the server and stored in a database.

[1301] Output: Infrastructure usage data set

[1302] Step 2:

[1303] The server collects the user's (worker's) emotional data through smart glasses.

[1304] Input: Emotion data from smart glasses (worker's facial expressions and voice)

[1305] Processing: Emotion data is analyzed by an emotion engine (e.g., Google Cloud Emotion AI) to assess the worker's stress and emotional state.

[1306] Output: Emotion analysis results

[1307] Step 3:

[1308] The server analyzes the collected infrastructure usage information using data analysis software (e.g., Amazon SageMaker) to predict energy consumption patterns and future consumption costs.

[1309] Input: Infrastructure usage data set

[1310] Processing: Run data analysis algorithms to predict trends and peak periods in energy consumption.

[1311] Output: Energy consumption prediction results

[1312] Step 4:

[1313] The server generates an alert for the user based on the emotion analysis results and the energy consumption prediction results, and sends it using an alert delivery system (e.g., Twilio).

[1314] Input: Sentiment analysis results, energy consumption prediction results

[1315] Processing: The alert generation algorithm determines what to notify the user, adjusting the wording of the alert based on sentiment data.

[1316] Output: Alert message (e.g. "Power consumption is expected to reach a peak. Please take measures.")

[1317] Step 5:

[1318] Based on the analysis results, the server optimizes the user's energy contract plan.

[1319] Input: Energy consumption forecast results

[1320] Processing: Select the optimal plan and automatically change the contract plan if necessary.

[1321] Output: Optimized energy contract plan information

[1322] Step 6:

[1323] The server sends instructions to various terminals (factory robots and equipment) to apply energy-saving mode.

[1324] Input: Energy consumption prediction results, emotion analysis results

[1325] Processing: Determines energy-saving mode settings and issues instructions to various devices. Adjusts settings based on emotional data, taking comfort into account.

[1326] Output: Energy saving mode instruction message (e.g. "Raise the set temperature by 2 degrees to switch to energy saving mode.")

[1327] Step 7:

[1328] The terminal (factory robot) receives instructions from the server and switches to energy-saving mode.

[1329] Input: Power saving mode instruction message from the server

[1330] Action: Automatically change operating settings and apply energy saving mode

[1331] Output: Energy saving operation state

[1332] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1333] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1334] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1335] [Fourth embodiment]

[1336] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1337] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1338] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1339] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1340] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1341] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1342] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1343] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1344] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1345] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1346] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1347] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1348] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1349] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[1350] System Overview

[1351] The following elements play a key role in this system:

[1352] 1. Collection of infrastructure usage information

[1353] The server collects real-time usage information from smart electricity bills, water meters, gas meters, communication devices, etc. This allows for a detailed understanding of users' consumption patterns.

[1354] 2. Data Analysis

[1355] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[1356] 3. Alert delivery

[1357] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[1358] 4. Optimizing your contract plan

[1359] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[1360] 5. Applying energy saving mode

[1361] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[1362] Specific examples

[1363] Example 1: Increased electricity consumption in summer

[1364] 1. Data Collection

[1365] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[1366] 2. Data Analysis

[1367] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[1368] 3. Alert delivery

[1369] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[1370] 4. Optimizing your contract plan

[1371] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[1372] 5. Applying energy saving mode

[1373] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[1374] Example 2: Increased gas consumption in winter

[1375] 1. Data Collection

[1376] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February.

[1377] 2. Data Analysis

[1378] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year.

[1379] 3. Alert delivery

[1380] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak and urging them to take measures.

[1381] 4. Optimizing your contract plan

[1382] The server checks the user's gas company plan and suggests changing to a special discount plan for the winter season.

[1383] 5. Applying energy saving mode

[1384] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode in response to instructions from the server.

[1385] In this way, the system of the present invention provides a set of processes for monitoring and optimizing users' infrastructure usage in real time, thereby enabling users to achieve efficient and cost-effective infrastructure usage.

[1386] The processing flow will be explained below.

[1387] Step 1:

[1388] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[1389] Step 2:

[1390] The server analyzes the collected infrastructure usage information. This involves applying algorithms that use historical data to identify seasonal and event usage patterns and then predict future usage and costs. For example, it analyzes patterns that indicate increased gas consumption for heating in the winter (December to February).

[1391] Step 3:

[1392] Based on the analysis results, the server identifies when usage costs are expected to increase at a specific time, creates an alert for the identified event, and prepares to send the alert to the user.

[1393] Step 4:

[1394] The server sends an alert to the user via email or the notification function of a smartphone app. For example, it could send an alert stating, "Power consumption is expected to increase due to air conditioning use next week."

[1395] Step 5:

[1396] The server checks the user's current contract plan and considers whether an optimal plan is available. It compares the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction. For example, it investigates whether a plan that offers reduced charges during specific peak hours is applicable.

[1397] Step 6:

[1398] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[1399] Step 7:

[1400] The server sends instructions to the terminal to apply an energy-saving mode based on the forecast data and the cost reduction policy, for example, to automatically adjust the temperature setting of the air conditioner.

[1401] Step 8:

[1402] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[1403] Step 9:

[1404] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[1405] Example 1

[1406] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1407] In today's world, where energy consumption is increasing in homes and businesses, it is difficult to understand consumption patterns and specific costs. Furthermore, it is often difficult to take appropriate measures to prevent energy waste and increased costs. Furthermore, optimizing contract plans and switching to energy-saving modes is done manually, making effective energy management difficult.

[1408] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1409] In this invention, the server includes a means for collecting infrastructure usage information, a means for analyzing the collected infrastructure usage information using a big data analysis tool to predict usage patterns and costs, a means for sending alerts to user devices based on the prediction results, a means for using an energy company's API to optimize infrastructure service contract plans, and a means for sending instructions to apply energy-saving modes to home appliances, thereby enabling visualization and optimization of energy consumption and automatic energy-saving measures.

[1410] "Infrastructure usage information" refers to usage data related to infrastructure services such as electricity, water, gas, and communications.

[1411] "Means of collection" refers to technologies including sensors and APIs for obtaining information from smart meters, communication devices, etc.

[1412] "Big data analysis tools" are software and frameworks for processing and analyzing huge data sets, including Spark and Hadoop.

[1413] "Usage patterns" are data that indicate trends in the use of energy, etc. at specific times or under specific conditions.

[1414] "Cost forecasting" refers to estimating future charges based on future energy and other usage.

[1415] An "alert" is a message that notifies the user based on a specific condition or prediction result.

[1416] "User devices" refer to terminals and applications used by users, including smartphones and PCs.

[1417] An "energy company API" is an interface for accessing data and services offered by energy providers.

[1418] "Contract plan optimization" is the process of proposing or changing the most cost-effective energy plan based on the user's consumption patterns.

[1419] "Energy saving mode" is a setting that switches home appliances to a specific operating state to reduce energy consumption.

[1420] "Home appliances" are electronic devices used in the home, such as heating and cooling equipment and lighting.

[1421] "Means for sending instructions to home appliances" refers to the communication technology and protocols used to transmit instructions from the server to home appliances. Examples include Wi-Fi and Bluetooth.

[1422] This invention is a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. This system consists of a server, terminals, and users.

[1423] 1. Program Generation

[1424] The server generates a program that contains the following main modules:

[1425] 1. Infrastructure usage information collection module

[1426] 2. Data Analysis Module

[1427] 3. Alert Delivery Module

[1428] 4. Contract plan optimization module

[1429] 5. Energy-saving mode application module

[1430] 2. Explain the program's processing in natural language

[1431] Collection of infrastructure usage information

[1432] The server collects data in real time from meters such as smart electricity bills, water meters, and gas meters using the meter's API. For example, the server retrieves electricity usage data every minute and stores it in a relational database such as MySQL or PostgreSQL.

[1433] Data analysis

[1434] The server analyzes the collected data using big data analytics tools (e.g., Spark, Hadoop) to identify seasonal usage patterns and peak periods. The analysis results are used to predict the next peak period and potential cost increases. For example, the server uses data from the past year to predict peak usage times in a particular month with an accuracy of over 80%.

[1435] Alert delivery

[1436] The server then sends alerts to the user based on the analysis results. Twilio's SMS API or Firebase Cloud Messaging are often used for alert delivery. For example, the server might send a notification to the user's smartphone saying, "Power usage will soon reach its peak. Please take measures to reduce energy consumption."

[1437] Optimizing contract plans

[1438] The server compares the analysis results with the user's current contract plan and suggests changing to the optimal plan. It also uses the energy company's API to obtain the user's usage history and the optimal plan. For example, the server might send the user a message saying, "We have a new plan that offers lower rates during peak hours. We recommend you change to it."

[1439] Applying energy saving mode

[1440] The device receives instructions from the server and automatically adjusts its settings. For example, if an air conditioner receives an instruction to "change the set temperature from 24 degrees to 26 degrees," it will automatically change the setting and reduce power consumption. This is done using smart device integration software such as Home Assistant and Google Home for IoT control.

[1441] Specific examples

[1442] Below are some concrete examples and examples of prompts for the generative AI model:

[1443] Example 1: Increased electricity consumption in summer

[1444] 1. Data Collection:

[1445] The server collects power consumption data that indicates that air conditioners are used more frequently from June to August.

[1446] 2. Data Analysis:

[1447] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year.

[1448] 3. Alert Delivery:

[1449] The server will send an alert to users in early July informing them that power consumption is expected to peak, urging them to take measures.

[1450] 4. Plan optimization:

[1451] The server checks the user's power company plan and suggests changing to a plan that reduces charges during specific peak hours.

[1452] 5. Apply energy saving mode:

[1453] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server.

[1454] Example prompts for generative AI models

[1455] Describe the system's program in natural language. Include the following elements:

[1456] Use the server, terminal, and user as subjects

[1457] Specific hardware and software names for each process

[1458] Data collection, data analysis, alert distribution, contract plan optimization, energy saving mode application

[1459] Specific examples of events

[1460] What the program does

[1461] 1. Data collection: The server collects usage information from smart electricity bills and gas meters.

[1462] 2. Data analysis: The server analyzes the data using Hadoop or Spark.

[1463] 3. Alert delivery: The server sends an alert via Twilio or Firebase

[1464] 4. Optimizing contract plans: The server uses the energy company's API to propose the optimal plan.

[1465] 5. Applying power saving mode: The device switches to power saving mode using Home Assistant

[1466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1467] Divide the program processing flow into processing steps

[1468] Step 1:

[1469] Step 2:

[1470] Step 3:

[1471] Step 4:

[1472] Step 5:

[1473] Detailed explanation of each processing step

[1474] Step 1:

[1475] The server collects infrastructure usage information, including electricity, water, and gas usage. As input, it uses real-time data from smart electricity bills, water meters, and gas meters. As output, this data is stored in a relational database, such as MySQL or PostgreSQL. Specifically, the server calls a remote API every minute to retrieve data from each meter.

[1476] Step 2:

[1477] The server analyzes the collected data using big data analysis tools. The data collected in step 1 is used as input. The output generates forecast data that identifies seasonal usage patterns and peak periods. Specifically, the server runs batch processing overnight and performs time series analysis using past data sets.

[1478] Step 3:

[1479] The server sends an alert to the user device based on the prediction results. The analysis results from step 2 are used as input. The output is a notification sent to the user's smartphone or computer. Specifically, the server generates a notification using Twilio's SMS API or Firebase Cloud Messaging and sends it to the user device.

[1480] Step 4:

[1481] The server compares the analysis results with the current contract plan and proposes a change to the optimal plan. The input uses the user's current contract plan information and the analysis results from step 2. The output is a proposal for the optimal energy plan for the user. Specifically, the server accesses the energy company's API, obtains the optimal rate plan information, and notifies the user.

[1482] Step 5:

[1483] The device receives instructions from the server and applies energy-saving mode. The instruction information from the server is used as input. The output is a change to the settings of the home appliance. Specifically, the device (e.g., air conditioner) automatically changes the set temperature and switches to energy-saving mode. This process uses smart device integration software such as Home Assistant or Google Home.

[1484] This allows for efficient energy management and automated energy saving measures.

[1485] (Application example 1)

[1486] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1487] In recent years, energy consumption by factory equipment and robots has increased, resulting in increased operating costs. There is a need to efficiently manage this energy consumption and reduce costs. However, current management systems are unable to collect and analyze energy usage information in real time, making it difficult to predict peak energy consumption. Furthermore, automation for optimizing infrastructure service contract plans and applying energy-saving modes has not been fully achieved. As a result, efficient energy management in factories has yet to be achieved.

[1488] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1489] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected energy consumption data and predicting peak energy consumption of specific equipment or robots, and means for optimizing energy consumption by applying an energy-saving mode during peak times. This makes it possible to monitor energy consumption in a factory in real time, propose a change to an optimal contract plan, and automatically apply an energy-saving mode.

[1490] "Infrastructure usage information" refers to data on the energy consumption of each device and robot within a factory, such as data obtained from electricity meters and gas meters.

[1491] "Means of collection" is a general term for hardware and software used to collect data in real time from electricity meters, water meters, gas meters, communication devices, etc.

[1492] The "analytical means" refers to algorithms and computer systems that analyze energy consumption patterns and predict future consumption peaks based on collected infrastructure usage information.

[1493] The "prediction method" refers to a calculation method and platform that uses past data to analyze consumption patterns and estimate peak energy consumption during specific times and situations.

[1494] "Means for sending alerts" are communications means and software for sending notifications to users based on the results of the analysis and predictions.

[1495] The "means for optimizing contract plans" is a system that analyzes the contents of the current infrastructure service contract and proposes or automatically applies the most suitable rate plan or service plan to the user.

[1496] The "means for sending instructions to terminals to apply energy-saving mode" refers to a control system that sends energy-saving mode instructions generated on the server side to various terminals (e.g., robots and devices) to automatically perform operations to reduce energy consumption.

[1497] The "energy saving mode" is an operating mode in which a particular device or robot minimizes energy consumption, and includes, for example, settings such as reducing the operating speed or turning off the power when not in operation.

[1498] This invention is a system for efficiently managing energy consumption in factories and reducing operational costs. The system consists of a server, terminals, and users. The server collects and analyzes infrastructure usage information in real time, and automatically proposes optimal contract plans and applies energy-saving modes.

[1499] System Overview

[1500] 1. Collection of infrastructure usage information

[1501] The server collects energy consumption data from various measuring devices in the factory (e.g., electricity meters, gas meters, temperature sensors, etc.), allowing the system to grasp in real time how much energy each piece of equipment and robot is consuming.

[1502] 2. Data Analysis

[1503] The server uses data processing libraries such as pandas and numpy to analyze the collected data. Algorithms for predicting energy consumption patterns and detecting outliers are used for the analysis. Specifically, machine learning models such as random forests are used to predict consumption peaks.

[1504] 3. Alert delivery

[1505] Based on the analysis results, the server will send an alert to the user if energy consumption is expected to exceed a certain threshold, which can be achieved using a notification system such as Pushbullet.

[1506] 4. Optimizing your contract plan

[1507] The server analyzes the current infrastructure service contract based on the energy consumption data and proposes changes to the optimal contract plan, which may result in cost savings for the user.

[1508] 5. Applying energy saving mode

[1509] The server sends instructions to specific equipment or robots to enter energy-saving mode, and the devices that receive these instructions automatically apply energy-saving settings, such as reducing their operating speed or turning off the power during non-operating hours.

[1510] Program processing explanation

[1511] The server first collects information from various measurement devices, then analyzes the collected data and predicts peak energy consumption using machine learning models such as random forests. For example, libraries such as pandas and numpy are used to preprocess and analyze the data.

[1512] If the system predicts that energy consumption will exceed the threshold, Pushbullet will be used to send an alert to the user, allowing the user to take appropriate measures. The server will also suggest optimizing the contract plan and send instructions to enter energy-saving mode. Devices that receive this instruction will automatically change their settings and begin taking actions to reduce energy consumption.

[1513] Examples and prompts

[1514] As a concrete example, consider a factory where peak energy consumption is predicted to occur between 10:00 AM and 2:00 PM on Mondays. To apply energy saving mode during this time, the server generates the following prompt:

[1515] Example prompt sentence:

[1516] "Please set your system to apply energy saving mode from 10:00 AM to 2:00 PM tomorrow."

[1517] As described above, by introducing this system, it will be possible to efficiently manage energy consumption and reduce costs in factories.

[1518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1519] Step 1:

[1520] The server collects energy consumption data in real time from various measuring devices installed in the factory (e.g., electricity meters, gas meters, temperature sensors). This data includes the instantaneous electricity and gas consumption of each piece of equipment and robot. The server accumulates this data by hour and creates a data set for analysis.

[1521] Input: Real-time energy consumption data

[1522] Output: Hourly accumulated energy consumption dataset

[1523] Step 2:

[1524] The server analyzes the collected energy consumption data using data processing libraries such as pandas and numpy, and applies machine learning algorithms (e.g., random forests) to analyze consumption patterns, thereby forecasting hourly energy consumption and identifying peak consumption periods.

[1525] Input: Energy consumption dataset accumulated by hour

[1526] Output: A forecasting model to identify consumption peaks

[1527] Step 3:

[1528] The server then sends an alert to the user when energy consumption is expected to exceed a threshold based on the predicted peak consumption data. This alert is sent to the user in real time using a notification system such as Pushbullet.

[1529] Input: A forecast model to identify consumption peaks

[1530] Output: Energy consumption peak alert

[1531] Step 4:

[1532] The server analyzes the current infrastructure service contract plans and proposes the optimal contract plan based on the energy consumption data, and sends the proposal to the user as a notification.

[1533] Input: Energy consumption data, current contract plan information

[1534] Output: Proposal of the best contract plan

[1535] Step 5:

[1536] The server sends instructions to specific equipment or robots to enter energy-saving mode. The terminals (e.g., robots) that receive these instructions automatically change their operating settings to energy-saving settings, such as slowing down the operating speed or turning off the power during non-operating hours.

[1537] Input: Energy saving mode instruction

[1538] Output: Change the device's operating settings to apply power saving mode

[1539] The specific operation is as follows:

[1540] Example: The server predicts that the peak energy consumption period is from 10:00 AM to 2:00 PM on Mondays. Based on this prediction, it generates energy-saving mode instructions and sends them to the associated robots. The robots receive these instructions, reduce their operating speed, and automatically turn off their power during non-operating hours if necessary. This process optimizes power usage during peak energy consumption periods.

[1541] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1542] This invention combines a system that collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes with an emotion engine that recognizes user emotions. This system consists of a server, terminals, users, and an emotion engine.

[1543] System Overview

[1544] The following elements play a key role in this system:

[1545] 1. Collection of infrastructure usage information

[1546] The server collects real-time infrastructure usage information from smart electricity bills, water meters, gas meters, and communication devices, allowing for detailed understanding of users' consumption patterns.

[1547] 2. Data Analysis

[1548] The server analyzes the collected data to identify seasonal usage patterns and general lifecycle fluctuations, which helps predict upcoming peak periods and identify potential cost increases.

[1549] 3. Alert delivery

[1550] Based on the analysis results, the server identifies periods when usage costs are predicted to increase and sends a timely alert to the user, allowing the user to take measures in advance.

[1551] 4. Optimizing your contract plan

[1552] The server checks the user's current contract plan and proposes or automatically applies changes to the optimal plan, allowing the user to reduce costs.

[1553] 5. Applying energy saving mode

[1554] The device automatically applies energy-saving modes in response to instructions from the server, for example by adjusting the temperature setting of the air conditioner to an appropriate level to reduce unnecessary power consumption.

[1555] 6. Introducing the Emotion Engine

[1556] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information, enabling optimal responses according to the user's emotional state.

[1557] Specific examples

[1558] Example 1: Increased electricity consumption in summer and utilization of emotion engine

[1559] 1. Data Collection

[1560] The server collects electricity consumption data that indicates high air conditioner usage from June to August, while the emotion engine collects user emotion data from smart devices.

[1561] 2. Data Analysis

[1562] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[1563] 3. Alert delivery

[1564] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[1565] 4. Optimizing your contract plan

[1566] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[1567] 5. Applying energy saving mode

[1568] The terminal (air conditioner) automatically raises the set temperature by 2 degrees and switches to energy-saving mode in response to instructions from the server. The emotion engine gives instructions on temperature settings that take comfort into consideration.

[1569] Example 2: Increased gas consumption in winter and the use of emotion engines

[1570] 1. Data Collection

[1571] The server collects gas consumption data that indicates that heating appliances are used more frequently from December to February, and the emotion engine collects information from smart devices that indicate a user's sensitivity to cold.

[1572] 2. Data Analysis

[1573] The server analyzes the collected data and predicts that gas consumption will peak at the end of January each year. The emotion engine evaluates the user's emotional state and identifies discomfort due to the cold.

[1574] 3. Alert delivery

[1575] The server will send an alert to users in mid-December informing them that gas consumption is expected to peak, urging them to take appropriate measures. The emotion engine will adjust the content of the alert to take into account the user's emotions.

[1576] 4. Optimizing your contract plan

[1577] The server checks the user's gas company plan and suggests switching to a special winter discount plan. The emotion engine adjusts the suggestion to reassure the user.

[1578] 5. Applying energy saving mode

[1579] The terminal (heating appliance) adjusts the set temperature to an appropriate level and switches to energy-saving mode according to instructions from the server. The emotion engine gives instructions on temperature settings that prioritize the user's comfort.

[1580] In this way, the system of the present invention provides a series of processes for monitoring and optimizing users' infrastructure usage in real time. Furthermore, by combining it with an emotion engine, it is possible to optimize responses according to the user's emotional state, further improving the user experience.

[1581] The processing flow will be explained below.

[1582] Step 1:

[1583] The server collects real-time infrastructure usage information from smart electricity meters, water meters, gas meters, and communication devices, including capturing daily consumption data and storing it in a database, such as 24-hour electricity consumption, water consumption, gas consumption, and communication data volume.

[1584] Step 2:

[1585] The emotion engine collects emotion data from users' smart devices (e.g., smartphones and wearable devices), including physiological and behavioral data such as heart rate, facial expression recognition, and voice tone.

[1586] Step 3:

[1587] The server analyzes collected infrastructure usage information to identify seasonal usage patterns and lifecycle fluctuations, thereby predicting upcoming peak periods and identifying potential cost increases.

[1588] Step 4:

[1589] The emotion engine analyzes the collected emotion data to determine the user's emotional state, for example, whether the user is stressed by high temperatures or uncomfortable by cold temperatures.

[1590] Step 5:

[1591] Based on the analysis, the server identifies periods when usage costs are expected to be high, for example, when air conditioning use increases in the summer and electricity consumption peaks.

[1592] Step 6:

[1593] The server creates alerts for identified events and prepares to send them to the user. The content of the alerts is adjusted based on the analysis results of the emotion engine. For example, if the user is feeling stressed, the alert wording will be changed to a gentler tone.

[1594] Step 7:

[1595] The server sends alerts to users via email or smartphone app notifications, such as "Power consumption is expected to increase due to air conditioning use next week. Please check your settings to keep cool and save energy."

[1596] Step 8:

[1597] The server checks the user's current contract plan and considers whether there is an optimal plan available. It compares this with the collected and analyzed usage information and searches for the most suitable plan from the perspective of cost reduction.

[1598] Step 9:

[1599] The server sends an alert to the user proposing the optimal plan change, and if the user accepts the proposal, the contract plan is automatically changed. For example, if the server proposes changing to a "seasonal special discount plan," and if the user accepts, the server will proceed with the change procedure with the power company.

[1600] Step 10:

[1601] Based on the predicted data and the user's emotional state, the server sends an instruction to the terminal to apply an energy-saving mode, for example, adjusting the temperature setting of the air conditioner to be comfortable and energy-efficient.

[1602] Step 11:

[1603] Terminals (such as air conditioners and heaters) receive instructions from the server and automatically switch to energy-saving mode. For example, an air conditioner will raise the set temperature by 2 degrees and enter energy-saving mode.

[1604] Step 12:

[1605] The server monitors the results of the device's energy-saving mode in real time, evaluates its effectiveness, and collects data such as power consumption after the energy-saving mode is applied to analyze whether the optimization was successful.

[1606] Step 13:

[1607] The emotion engine monitors the user's reactions to notifications and acceptance of suggestions, assessing changes in their emotional state and providing feedback to improve the quality of future alerts and energy-saving mode instructions.

[1608] Example 2

[1609] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1610] Conventional systems that collect and analyze infrastructure usage information and issue alerts have the problem of being unable to respond optimally while taking into account the user's emotional state. For example, if a user receives a harsh alert when they are feeling stressed, it may actually increase their discomfort. Furthermore, changes to contract plans or the application of energy-saving modes do not take into account the user's emotional state, which can make them less likely to agree or reduce their comfort. This presents a challenge in making infrastructure use more efficient.

[1611] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to the user based on the prediction results, means for optimizing a contract plan for infrastructure services, means for sending an instruction to apply an energy-saving mode to the terminal, means for collecting and analyzing user emotion data and associating the emotion data with the infrastructure usage information, and means for generating an appropriate alert and a proposal to change the contract plan according to the user's emotional state using a generative AI model. This makes it possible to optimize infrastructure usage while taking the user's emotional state into consideration, thereby achieving both user comfort and efficient resource management.

[1612] "Infrastructure usage information" is data on the usage of infrastructure services such as electricity, water, gas, and communications.

[1613] The "collection means" refers to a means for acquiring infrastructure usage information in real time using a data measurement device or a communication device.

[1614] "Analysis tools" refers to data analysis tools and algorithms used to generate usage patterns and cost forecasts based on collected infrastructure usage information.

[1615] The "alert sending means" is a means for sending a notification to the user by email, SMS, or other means based on the prediction results.

[1616] The "contract plan optimization means" is a means for checking the user's contract plan and proposing and applying a change to the most suitable plan.

[1617] The "energy saving mode instruction means" is a means for instructing application of the energy saving mode based on the infrastructure usage information.

[1618] "Terminals" refers to home appliances such as air conditioners and heaters, as well as other IoT devices.

[1619] "Emotion data" is data that indicates the user's emotional state, and is information collected from audio, video, text, and the like.

[1620] "Means for collecting and analyzing emotional data" refers to tools and algorithms for collecting and analyzing emotional data from audio, video, etc.

[1621] A "generative AI model" is an artificial intelligence model used to generate appropriate alerts and suggestions based on the user's emotional state.

[1622] A "prompt sentence" is text data that is input into a generative AI model to specify the content and tone of the sentence to be generated.

[1623] This invention combines a system that collects and analyzes infrastructure usage information to send alerts to users at appropriate times, optimizes contract plans, and applies energy-saving modes, with a mechanism that takes into account user emotion data. This system is composed of a server, terminals, users, and an emotion engine.

[1624] How the system is implemented

[1625] 1. Collection of infrastructure usage information

[1626] The server collects infrastructure usage information in real time from smart electricity bills, water meters, gas meters, and communication devices. This data collection is performed using data measurement devices and communication devices.

[1627] The server streams the collected data using Amazon Web Services (AWS) Kinesis Data Streams, stores it temporarily, and then stores it in a database such as Amazon RDS or Google Cloud SQL.

[1628] 2. Data Analysis

[1629] The server uses Python's pandas library to preprocess the data and perform seasonal decomposition to identify seasonality and trends.

[1630] Additionally, we use scikit-learn predictive models (e.g., linear regression and random forest) to predict the next peak period and evaluate fluctuations in consumption patterns.

[1631] 3. Alert delivery

[1632] The server then uses the predictions to identify when usage costs will be high and sends alerts to users via email or SMS using SMTP or the Twilio API.

[1633] The emotion engine analyzes the emotion data and tailors the wording of the alert to the user's emotional state.

[1634] 4. Optimizing your contract plan

[1635] The server checks the user's contract plan information and searches the database for the most suitable plan.

[1636] Users are sent emails and push notifications with proposals for changes to their contract plans, which are empathetically worded using a generative AI model to make them more likely to be accepted.

[1637] 5. Applying energy saving mode

[1638] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[1639] The device (e.g., an air conditioner or heater) automatically adjusts the set temperature and switches to energy-saving mode according to the received instructions.

[1640] The emotion engine analyzes the user's emotion data and instructs them to change settings within a range that does not impair comfort.

[1641] 6. Introducing the Emotion Engine

[1642] The server uses an emotion engine to collect emotion data from smartphones and smart speakers, specifically analyzing emotions from audio and video data.

[1643] The emotion engine uses TensorFlow and PyTorch emotion analysis models to assess users' real-time emotional state, and emotion data is correlated with infrastructure usage information and stored in a database.

[1644] Specific examples

[1645] Increased electricity consumption in summer and utilization of emotion engine

[1646] The server collects data showing that air conditioner usage is high from June to August, and the emotion engine collects emotional data showing stress levels caused by high temperatures.

[1647] The server predicts that power consumption will peak in mid-July, and when sending an alert based on that prediction, the emotion engine adjusts the wording.

[1648] When optimizing contract plans, the server proposes the optimal plan, and the emotion engine generates empathetic proposals.

[1649] When energy-saving mode is applied, the device follows the server's instructions to raise the set temperature by 2 degrees, and the emotion engine also takes comfort into consideration.

[1650] Increased gas consumption in winter and the use of emotion engines

[1651] The server collects data showing that heating appliances are used more frequently from December to February. The emotion engine collects emotion data showing discomfort due to cold weather.

[1652] The server predicts that gas consumption will peak at the end of January, and when it sends an alert in mid-December, the emotion engine adjusts the content.

[1653] When optimizing contract plans, a special discount plan for the winter season is proposed, and the emotion engine generates a reassuring proposal.

[1654] When applying the energy-saving mode, the terminal adjusts the set temperature to an appropriate level according to the server's instructions, and the emotion engine takes into account the user's comfort.

[1655] Prompt Sentence Examples

[1656] Summer energy consumption alert: "Electricity consumption is expected to peak in mid-July. We recommend taking precautions in advance, such as adjusting your air conditioner temperature setting."

[1657] Winter gas consumption alert: "Gas consumption is expected to peak at the end of January. Please check your heating settings in advance and consider using energy-saving modes."

[1658] As described above, the present invention can be implemented using the following method. First, infrastructure usage information is collected in real time using a data measurement device or a communication device. Next, the collected data is processed by an analysis device to predict usage patterns and costs. Then, based on the prediction results, an alert is sent, and instructions are given to optimize the contract plan or apply an energy-saving mode. Furthermore, by combining an emotion engine that collects and analyzes user emotion data and using a generative AI model to generate appropriate alerts and suggestions according to the user's emotional state, it becomes possible to achieve both user comfort and efficient resource management.

[1659] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1660] Step 1: Collecting infrastructure usage information

[1661] The server connects to smart electricity meters, water meters, gas meters, and communication devices to collect data in real time.

[1662] Input: Real-time data from data measurement equipment.

[1663] Output: Streamed infrastructure usage information.

[1664] How it works: The server streams this data using AWS Kinesis Data Streams and stores it temporarily. The streaming data is periodically aggregated and stored in a database such as Amazon RDS or Google Cloud SQL.

[1665] Step 2: Data analysis

[1666] The server preprocesses the collected data and converts it into a format that is easy to analyze, for example by imputing missing values ​​and checking for outliers.

[1667] Input: Infrastructure usage information from streaming data.

[1668] Output: A dataset that can be analyzed.

[1669] How it works: The server preprocesses the data using Python's pandas library, then performs seasonal decomposition to identify seasonality and trends, and uses scikit-learn predictive models (e.g., linear regression and random forest) to forecast fluctuations in consumption patterns.

[1670] Step 3: Alert Delivery

[1671] Based on the prediction results, the server identifies when usage costs will be high and sends an alert to the user.

[1672] Input: Analysis results from the predictive model.

[1673] Output: The alert message to send to the user.

[1674] Specific operation: The server uses SMTP or Twilio API to send predictive alerts to users via email or SMS, and adjusts the wording of the alert text based on the user's emotional data analyzed by the emotion engine.

[1675] Step 4: Optimize your plan

[1676] The server checks the user's contract plan and proposes changing to the most suitable plan.

[1677] Input: User contract plan information and infrastructure usage information.

[1678] Output: Optimal plan suggestion message.

[1679] Specific operation: The server uses the contract plan API to compare plans and select the most cost-effective plan. The generative AI model uses an emotion engine to generate empathetic recommendations and send them to the user.

[1680] Step 5: Apply Energy Saving Mode

[1681] The server transmits an instruction to the terminal to switch to an energy saving mode based on the consumption pattern and the prediction result.

[1682] Input: Predicted results and consumption pattern data.

[1683] Output: Energy saving mode instruction message.

[1684] Specific operation: The device (e.g., air conditioner or heater) receives instructions from the server and automatically adjusts the set temperature. It also uses the emotion engine to instruct the device to change the settings within a range that does not impair the user's comfort.

[1685] Step 6: Implementing the Emotion Engine

[1686] The server uses an emotion engine to collect and analyze user emotion data and associate it with infrastructure usage information.

[1687] Input: Audio and video data, text data.

[1688] Output: Analyzed data about the user's emotional state.

[1689] Specific operation: The server collects audio and video data from smartphones and smart speakers, and evaluates user emotions in real time using emotion analysis models in TensorFlow and PyTorch. The emotion data is associated with infrastructure usage information and stored in a database, and the results are used as feedback for subsequent processing (sending alerts, optimizing contract plans, instructing energy-saving modes).

[1690] (Application example 2)

[1691] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1692] In modern factories and facilities, optimizing energy use and managing costs are important issues. Furthermore, it is known that workers' emotional states have a significant impact on productivity and work efficiency, but systems that comprehensively manage these factors have yet to be fully developed. Conventional systems focus on monitoring and optimizing energy consumption and do not take into account workers' emotional states, making it difficult to improve overall efficiency. Furthermore, selecting an efficient energy contract plan and applying energy-saving modes are often performed manually, making it difficult to respond in a timely manner. The purpose of this invention is to provide a system that comprehensively manages energy consumption and workers' emotional states, providing an efficient and comfortable work environment.

[1693] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1694] In this invention, the server includes means for collecting infrastructure usage information, means for analyzing the collected infrastructure usage information and predicting usage patterns and costs, means for sending an alert to a user based on the prediction results, means for optimizing an infrastructure service contract plan, means for sending an instruction to apply an energy-saving mode to a terminal, means for collecting and analyzing user emotion data, and means for adjusting the wording of the alert and the energy-saving mode settings based on the emotion data. This enables the optimization of energy usage and the emotional state of workers to be managed in an integrated manner, thereby providing an efficient and comfortable work environment.

[1695] "Infrastructure usage information" refers to data on energy consumption such as electricity, water, and gas at factories and facilities.

[1696] "Means of collection" refers to the equipment and methods for collecting information on infrastructure usage through measuring devices such as sensors and meters.

[1697] "Means for analyzing and generating usage patterns and cost projections" refers to algorithms and software used to analyze collected data and predict trends in energy usage and future consumption costs.

[1698] "Means for sending alerts to users based on prediction results" refers to a mechanism for sending warnings or notifications to users based on analysis results.

[1699] "Means for optimizing contract plans" refers to a system or method that selects the optimal energy contract plan based on analyzed data and automatically changes it as necessary.

[1700] "Means for sending instructions to terminals to apply energy-saving mode" refers to a mechanism for sending settings to reduce energy consumption as commands to each terminal and changing the operating mode accordingly.

[1701] "User emotion data" refers to data that indicates the stress level and emotional state of a worker or user.

[1702] "Means for collecting and analyzing emotional data" refers to technologies and methods for collecting and analyzing the emotional state of workers and users using sensors and emotion recognition software.

[1703] "Means for adjusting alert wording and energy-saving mode settings based on emotional data" refers to a mechanism that appropriately adjusts notification content and energy settings for users based on collected emotional data.

[1704] "System" refers to a collection of devices and software that includes all of the above means and operates in conjunction with one another.

[1705] overview

[1706] The system that realizes this invention consists of a server, a terminal, a user, and an emotion engine. The server collects and analyzes infrastructure usage information, issues alerts at appropriate times, automatically changes contract plans, and applies energy-saving modes. The emotion engine also collects user emotion data and takes appropriate action accordingly.

[1707] Hardware and software used

[1708] Hardware: Factory robots, servers, smart sensors (electricity, water, gas, etc.), smart glasses (for workers)

[1709] Software: Data analysis software (e.g., Amazon SageMaker), emotion engine (e.g., Google Cloud Emotion AI), alert distribution system (e.g., Twilio)

[1710] Data collection and analysis

[1711] The server collects real-time consumption data on electricity, water, gas, etc. from smart sensors in the factory. In addition, worker emotion data is collected through smart glasses. This data is analyzed using data analysis software (e.g., Amazon SageMaker) on the server to predict energy consumption patterns and future consumption costs.

[1712] Alert generation and notification

[1713] The server generates timely alerts based on the prediction results. This uses an alert distribution system (e.g., Twilio) to notify users and workers of important events, allowing them to take proactive measures. In addition, an emotion engine (e.g., Google Cloud Emotion AI) adjusts the content of the alerts according to the user's emotional state.

[1714] Optimizing contract plans

[1715] The server then proposes the optimal energy contract plan based on the analyzed data and automatically changes it, allowing users to reduce unnecessary costs.

[1716] Applying energy saving mode

[1717] Factory robots and other devices switch to energy-saving mode in response to instructions from the server. For example, during times of high energy consumption, they automatically change their operating settings to reduce consumption. The emotion engine adjusts the energy-saving mode while taking into account the user's emotional state and ensuring comfort.

[1718] Specific examples

[1719] Example 1: Increase in summer electricity consumption and utilization of emotion engine

[1720] 1. Data Collection

[1721] The server collects electricity consumption data that indicates high air conditioner usage from June to August, and the emotion engine collects user emotion data from smart glasses.

[1722] 2. Data Analysis

[1723] The server analyzes the collected data and predicts that power consumption will peak in mid-July each year, and the emotion engine identifies when users are stressed due to high temperatures.

[1724] 3. Alert delivery

[1725] The server sends an alert to the user in early July stating that power consumption is expected to peak, urging them to take measures. The emotion engine adjusts the wording of the alert to be gentle, since the user is in a stressful state.

[1726] 4. Optimizing your contract plan

[1727] The server checks the user's electricity plan and proposes a plan that reduces charges during certain peak hours. The emotion engine generates a more empathetic proposal to make it easier for the user to accept.

[1728] 5. Applying energy saving mode

[1729] Terminals such as factory robots automatically raise the set temperature by 2 degrees and switch to energy-saving mode in response to instructions from the server. The emotion engine also takes comfort into consideration when instructing the temperature setting.

[1730] Prompt Sentence Examples

[1731] "Analyze the power consumption data in the factory and predict peak periods this week."

[1732] "Analyze the emotional data of Worker A and identify his stress level and its contributing factors."

[1733] "Based on your consumption patterns, suggest and automatically apply the most suitable energy contract plan."

[1734] In this way, the present invention provides a system that manages infrastructure usage information and emotion data in an integrated manner, and aims to use energy efficiently and optimize the working environment.

[1735] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1736] Step 1:

[1737] The server collects real-time infrastructure usage information from smart sensors (electricity, water, gas, etc.) within the factory.

[1738] Input: Data from smart sensors (electricity, water, gas consumption information)

[1739] Processing: Various consumption data is collected on the server and stored in a database.

[1740] Output: Infrastructure usage data set

[1741] Step 2:

[1742] The server collects the user's (worker's) emotional data through smart glasses.

[1743] Input: Emotion data from smart glasses (worker's facial expressions and voice)

[1744] Processing: Emotion data is analyzed by an emotion engine (e.g., Google Cloud Emotion AI) to assess the worker's stress and emotional state.

[1745] Output: Emotion analysis results

[1746] Step 3:

[1747] The server analyzes the collected infrastructure usage information using data analysis software (e.g., Amazon SageMaker) to predict energy consumption patterns and future consumption costs.

[1748] Input: Infrastructure usage data set

[1749] Processing: Run data analysis algorithms to predict trends and peak periods in energy consumption.

[1750] Output: Energy consumption prediction results

[1751] Step 4:

[1752] The server generates an alert for the user based on the emotion analysis results and the energy consumption prediction results, and sends it using an alert delivery system (e.g., Twilio).

[1753] Input: Sentiment analysis results, energy consumption prediction results

[1754] Processing: The alert generation algorithm determines what to notify the user, adjusting the wording of the alert based on sentiment data.

[1755] Output: Alert message (e.g. "Power consumption is expected to reach a peak. Please take measures.")

[1756] Step 5:

[1757] Based on the analysis results, the server optimizes the user's energy contract plan.

[1758] Input: Energy consumption forecast results

[1759] Processing: Select the optimal plan and automatically change the contract plan if necessary.

[1760] Output: Optimized energy contract plan information

[1761] Step 6:

[1762] The server sends instructions to various terminals (factory robots and equipment) to apply energy-saving mode.

[1763] Input: Energy consumption prediction results, emotion analysis results

[1764] Processing: Determines energy-saving mode settings and issues instructions to various devices. Adjusts settings based on emotional data, taking comfort into account.

[1765] Output: Energy saving mode instruction message (e.g. "Raise the set temperature by 2 degrees to switch to energy saving mode.")

[1766] Step 7:

[1767] The terminal (factory robot) receives instructions from the server and switches to energy-saving mode.

[1768] Input: Power saving mode instruction message from the server

[1769] Action: Automatically change operating settings and apply energy saving mode

[1770] Output: Energy saving operation state

[1771] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1772] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1773] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1774] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1775] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1776] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1777] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1778] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1779] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1780] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1781] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1782] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1783] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1784] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1785] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1786] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1787] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1788] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1789] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1790] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1791] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1792] The following is further disclosed regarding the above embodiment.

[1793] (Claim 1)

[1794] a means of collecting infrastructure usage information;

[1795] a means for analyzing the collected infrastructure usage information to generate usage patterns and cost predictions;

[1796] means for sending an alert to a user based on the prediction result;

[1797] A means for optimizing infrastructure service contract plans;

[1798] means for sending an instruction to the terminal to apply an energy saving mode;

[1799] A system including:

[1800] (Claim 2)

[1801] 2. The system of claim 1, wherein the means for collecting infrastructure usage information acquires data from electricity meters, water meters, gas meters, and communication devices.

[1802] (Claim 3)

[1803] 2. The system according to claim 1, wherein the terminal that receives the instruction to apply the energy saving mode automatically changes the operation settings of the home appliance.

[1804] "Example 1"

[1805] (Claim 1)

[1806] a means of collecting infrastructure usage information;

[1807] A means for analyzing the collected infrastructure usage information using a big data analysis tool to predict usage patterns and costs;

[1808] means for sending an alert to a user device based on the prediction result;

[1809] A means to use energy companies' APIs to optimize infrastructure service contract plans;

[1810] means for transmitting an instruction to the home appliance to apply an energy saving mode;

[1811] A system including:

[1812] (Claim 2)

[1813] 10. The system of claim 1, wherein the means for collecting infrastructure usage information acquires data from metering and communication devices.

[1814] (Claim 3)

[1815] 2. The system according to claim 1, wherein the home appliance that receives the instruction to apply the energy-saving mode automatically changes its operation settings.

[1816] "Application Example 1"

[1817] (Claim 1)

[1818] a means of collecting infrastructure usage information;

[1819] a means for analyzing the collected infrastructure usage information to generate usage patterns and cost predictions;

[1820] means for sending an alert to a user based on the prediction result;

[1821] A means for optimizing infrastructure service contract plans;

[1822] means for sending an instruction to the terminal to apply an energy saving mode;

[1823] A means for analyzing the collected energy consumption data and predicting peak energy consumption of a particular piece of equipment or robot;

[1824] a means of optimizing energy consumption by applying energy saving modes during peak hours;

[1825] A system including:

[1826] (Claim 2)

[1827] 2. The system according to claim 1, wherein the means for collecting infrastructure usage information acquires and analyzes data from electricity meters, water meters, gas meters, and communication devices.

[1828] (Claim 3)

[1829] 2. The system according to claim 1, wherein the terminal that receives the instruction to apply the energy saving mode automatically changes the operation settings of the industrial equipment.

[1830] "Example 2: Combining Emotion Engines"

[1831] (Claim 1)

[1832] a means of collecting infrastructure usage information;

[1833] a means for analyzing the collected infrastructure usage information to generate usage patterns and cost predictions;

[1834] means for sending an alert to a user based on the prediction result;

[1835] A means for optimizing infrastructure service contract plans;

[1836] means for sending an instruction to the terminal to apply an energy saving mode;

[1837] means for collecting and analyzing user emotion data and associating the emotion data with the infrastructure usage information;

[1838] A means for generating an appropriate alert and a contract plan change proposal according to the user's emotional state using a generative AI model;

[1839] A system including:

[1840] (Claim 2)

[1841] 2. The system of claim 1, wherein the means for collecting infrastructure usage information acquires data from data measurement devices and communication devices.

[1842] (Claim 3)

[1843] 2. The system according to claim 1, wherein the terminal that receives the instruction to apply the energy saving mode automatically changes the operation settings of the electronic device.

[1844] "Application example 2 when combining emotion engines"

[1845] (Claim 1)

[1846] a means of collecting infrastructure usage information;

[1847] a means for analyzing the collected infrastructure usage information to generate usage patterns and cost predictions;

[1848] means for sending an alert to a user based on the prediction result;

[1849] A means for optimizing infrastructure service contract plans;

[1850] means for sending an instruction to the terminal to apply an energy saving mode;

[1851] A means for collecting and analyzing user emotion data;

[1852] A means to adjust alert wording and energy saving mode settings based on emotion data; and

[1853] A system including:

[1854] (Claim 2)

[1855] 10. The system of claim 1, wherein the means for collecting infrastructure usage information acquires data from metering devices and communication equipment.

[1856] (Claim 3)

[1857] 2. The system according to claim 1, wherein the terminal that receives the instruction to apply the energy saving mode automatically changes the operation settings of the device. [Explanation of symbols]

[1858] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting infrastructure usage information; a means for analyzing the collected infrastructure usage information to generate usage patterns and cost predictions; means for sending an alert to a user based on the prediction result; A means for optimizing infrastructure service contract plans; means for sending an instruction to the terminal to apply an energy saving mode; A system including:

2. 2. The system of claim 1, wherein the means for collecting infrastructure usage information acquires data from electricity meters, water meters, gas meters, and communication devices.

3. The system according to claim 1 , wherein the terminal that receives the instruction to apply the energy saving mode automatically changes the operation settings of the home appliance.

Images