System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining weather data; means for operating a generative model to predict solar power generation based on the obtained weather data; means for scheduling operation of high power consumers based on the predicted solar power generation; means for determining optimal timing of charging and discharging of energy storage devices; and means for communicating an optimized energy schedule based on the predicted solar power generation and energy consumption.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] Current solar power generation systems have unstable energy supplies depending on the weather and time of day, making it difficult to effectively utilize power within the home. High costs are also incurred during peak power usage times, making it difficult to reduce electricity bills. Furthermore, manually managing the operation schedules of high-power consumption devices and energy storage devices is time-consuming and inefficient. Therefore, there is a need for a system that can maximize solar power generation, reduce energy costs, and optimize power usage within the home. [Means for solving the problem]

[0005] The present invention provides a system that utilizes AI to acquire weather data, schedules the operation of high-power consumption devices based on predicted solar power generation, and determines the optimal timing for charging and discharging an energy storage device. Specifically, the system includes a means for acquiring weather data, a means for running a generative model that predicts solar power generation based on the acquired weather data, a means for scheduling the operation of high-power consumption devices, a means for determining the optimal timing for charging and discharging an energy storage device, a means for notifying an optimized energy schedule, a means for optimizing energy use based on an electricity rate plan, and a means for predicting and notifying the timing for maintenance of an energy generation device. This overcomes the instability of solar power supply, reduces energy costs, and improves the efficiency of power use.

[0006] "Weather data" refers to information about the weather, such as temperature, hours of sunshine, cloud cover, and wind speed, and is data used to predict the amount of solar power generation.

[0007] A "generative model" is a mathematical or statistical algorithm that uses AI to generate a specific output from input data.

[0008] "High-power appliances" are appliances that consume a lot of electricity in the home, such as washing machines and dishwashers.

[0009] "Scheduling operations" is the process of optimizing the operation times and sequences of high-power consumption devices.

[0010] An "energy storage device" is a device that stores electricity in the form of a battery or other device and supplies power when needed.

[0011] The "optimal timing for charging and discharging" is the most suitable time to charge and discharge the energy storage device to enable efficient power utilization.

[0012] An "energy schedule" is an optimal timetable for power usage that is created based on predicted power generation and power consumption.

[0013] An "energy rate plan" is an electricity consumption contract offered by an electricity supplier with different pricing structures, often with rates that vary depending on the time of day.

[0014] An "energy generating device" is a device that converts external energy into electricity, such as a solar panel.

[0015] "Maintenance timing" refers to the appropriate time for maintenance and inspection work to be carried out in order to maintain the functionality of the energy generation equipment. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

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

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] An embodiment of the present invention will be described in detail below. This system performs energy prediction and management to make the most efficient use of solar power generated in an ordinary home, and is composed of the following steps.

[0038] 1. User Initial Settings

[0039] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[0040] 2. Obtaining weather data

[0041] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[0042] 3. Generating an energy prediction model

[0043] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[0044] 4. Scheduling of high-power devices

[0045] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. An operation schedule is generated and notified to the device. The device then operates the target devices according to this schedule.

[0046] 5. Optimization of Energy Storage Devices

[0047] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[0048] 6. Optimizing electricity costs

[0049] Users input their electricity rate plan information into the terminal, and the server adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0050] 7. System Maintenance Notification

[0051] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance period is predicted, a notification is sent to the terminal. The user follows the notification and performs appropriate maintenance to ensure the long-term stable operation of the system.

[0052] Specific examples

[0053] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[0054] 1. The user inputs the desired time for using the washing machine into the terminal.

[0055] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[0056] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0057] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0058] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0059] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0060] This optimizes the operation of the washing machine using solar power, reducing energy costs and improving the efficiency of electricity use within the home.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user inputs information about the high-power appliances and energy storage devices in the home into the terminal. For example, the user registers the model name and planned usage time of a washing machine or dishwasher. The terminal then transmits this information to the server.

[0064] Step 2:

[0065] The server sends a request to the weather API to retrieve weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes the retrieved weather data and stores it in a database.

[0066] Step 3:

[0067] The server inputs the acquired weather data into a generative model to predict the amount of solar power generation for the next day. The generative model makes highly accurate predictions based on past data and acquired weather data. These prediction results are used for energy management.

[0068] Step 4:

[0069] The server calculates the optimal operating times for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. Taking into account the desired usage times input by the user, the server determines the most efficient time slots within that range. An operating schedule is generated.

[0070] Step 5:

[0071] The server notifies the terminal of the generated operation schedule. The terminal displays the operation schedule to the user and asks for confirmation. The terminal automatically starts operation of the equipment according to the scheduled time.

[0072] Step 6:

[0073] The server calculates the optimal charging and discharging timing for the energy storage device (e.g., a home battery). It sets it to supply power during times when power generation is high and to store power during times when power generation is low. This setting is sent to the home battery via the terminal.

[0074] Step 7:

[0075] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0076] Step 8:

[0077] The server analyzes the equipment's operational data and past failure data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal then displays the maintenance timing to the user.

[0078] Step 9:

[0079] Once all data and settings are collected, the system will automatically begin operation and optimize the operation of high-power consumption appliances and energy storage devices based on predicted solar power generation, enabling users to achieve more efficient energy use in their homes and reduce energy costs.

[0080] Example 1

[0081] 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."

[0082] As the adoption of solar power generation systems in general households increases, there is a need to maximize their power generation efficiency while optimizing power consumption. However, current systems lack the means to accurately predict solar power generation amounts by fully utilizing weather data, and the use of high-power-consuming devices and management of energy storage devices are not effectively carried out. Furthermore, they are not adequately able to optimize energy costs according to electricity rate plans. Furthermore, they lack the functionality to predict and notify when power generation systems need maintenance. This results in a decrease in the efficiency of power usage within the home, making it difficult to reduce energy costs.

[0083] 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.

[0084] In this invention, the server includes means for a user to input information about high-power consumption devices and energy storage devices in the home, means for acquiring weather data, means for operating a generative AI model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining optimal timing for charging and discharging the energy storage device, and means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption. This improves the accuracy of solar power generation predictions, enables efficient management of high-power consumption devices and energy storage devices, and enables improved efficiency of home power utilization and reduced energy costs.

[0085] "User" refers to an individual or household that uses the system.

[0086] "High-power household appliances" refers to household appliances such as washing machines and dishwashers that consume large amounts of electricity at once.

[0087] An "energy storage device" is a device that temporarily stores electricity generated within the home and supplies it when needed. A specific example is a home battery.

[0088] "Terminal" means an electronic device used by a user to enter information and receive information from a system. Examples include a smartphone or tablet.

[0089] "Server" refers to the computer system that manages the entire system and processes data and runs predictive models.

[0090] "Weather data" refers to data relating to weather conditions, such as temperature, hours of sunshine, cloud cover, and wind speed.

[0091] "Weather API" refers to a programmatic interface used to obtain weather data. An example is the OpenWeatherMap API.

[0092] A "generative AI model" refers to an artificial intelligence model that makes predictions and classifications based on acquired data. A specific example is a predictive model using TensorFlow.

[0093] "Scheduling" refers to planning and setting the operating times and timing of specific equipment based on predictive data.

[0094] "Optimization" refers to adjusting resource allocation and scheduling to maximize energy efficiency or minimize costs.

[0095] An "energy schedule" refers to a schedule that includes the operation plans of household appliances and energy storage devices.

[0096] "Electricity rate plan" means an electricity payment plan that a consumer enters into with an electricity supplier. Examples include flat-rate plans and time-of-use plans.

[0097] "Maintenance timing" refers to the specific timing when maintenance of a system or equipment is required.

[0098] This invention is a system for energy prediction and management to make the most efficient use of solar power generated in an average household, and operates in cooperation with the server, terminal, and user elements.

[0099] System Overview

[0100] User Preferences

[0101] The user launches a dedicated application using the device. From the settings screen within the application, they enter information about high-power consumption devices in the home (e.g., washing machine, dishwasher) and energy storage devices (e.g., home battery). Once this information is saved, the device sends it to the server. The server stores the received information in a database.

[0102] Obtaining weather data

[0103] The server periodically calls a weather API (e.g., OpenWeatherMap API) to obtain weather data (e.g., temperature, sunshine hours, cloud cover, wind speed), which is then stored in a database within the system.

[0104] Generate an energy forecasting model

[0105] The server runs a generative AI model (for example, a forecasting model using TensorFlow) based on the stored weather data to predict the amount of solar power generation for the next day. The forecast results are stored in a database.

[0106] Scheduling high power consumers

[0107] The user inputs the desired usage time of a high-power consumption device (e.g., a washing machine) on the device. The device then sends the desired usage time data to the server. The server calculates the optimal operation time for the high-power consumption device based on the predicted solar power generation data and the desired usage time, and generates an operation schedule. The generated schedule is notified to the device, which automatically starts operation of the device at the set time.

[0108] Energy storage device optimization

[0109] The server calculates the timing of charging and discharging the home battery based on the predicted power generation data. For example, it sets a schedule to charge at night (when power demand is low) and discharge in the morning when power generation is low. The calculation results are sent to the terminal, and instructions are sent to the home battery through the terminal.

[0110] Optimizing power costs

[0111] Users input their electricity plan information (e.g., flat-rate plan, time-of-use plan) into the device and send it to the server, which then runs an algorithm to optimize energy usage based on the plan and reschedules each device to avoid peak power hours.

[0112] System maintenance notification

[0113] The server analyzes the operational data of the home's solar power generation system and predicts when maintenance is required. The prediction results are sent to the terminal and displayed to the user. The user can then follow the notification to arrange for appropriate maintenance work.

[0114] Specific examples

[0115] For example, the process when the laundry is scheduled to be done in the morning of the next day will be described.

[0116] 1. The user inputs the desired time for using the washing machine into the terminal.

[0117] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[0118] 3. The server calculates the optimal time to run the washing machine based on the predicted power generation data. For example, it determines that the best time is between 2:00 PM and 4:00 PM, when the sunshine hours are the longest.

[0119] 4. The schedule is sent to the device, and the user confirms it. The device automatically starts the washing machine at the specified time.

[0120] 5. The server optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0121] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0122] Prompt Sentence Examples

[0123] "Based on the weather forecast for the next day obtained using a weather API, please predict the amount of solar power generation in the home for the next day and generate an optimal operation schedule for the washing machine, which is a high-power-consuming device. In this case, please create a schedule to operate the washing machine during the time period when power generation is highest."

[0124] This invention improves the efficiency of solar power generation in homes, reducing energy costs and realizing sustainable energy use.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: Initial User Setup

[0127] Input: The user inputs information about high-power consumption appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the home into the terminal.

[0128] Data processing / data calculation: The terminal formats the input information into a database and creates a data set that includes information set by the user (device manufacturer, model number, power consumption, etc.).

[0129] Output: The terminal sends the formatted data to the server.

[0130] Specific operation: The user opens the dedicated application, enters information about the home appliance and energy storage device on the settings screen, and presses the save button. The device then sends the information to the server.

[0131] Step 2: Obtaining weather data

[0132] Input: The server sends a request to the weather API.

[0133] Data processing / data calculation: As a response from the weather API, the server receives weather data such as temperature, sunshine hours, cloud cover, wind speed, etc. The server converts this data into an appropriate format and stores it in the database.

[0134] Output: Weather data is stored in a database on the server.

[0135] Specific operation: The server periodically accesses a weather API (e.g., OpenWeatherMap API) to obtain the necessary weather data.

[0136] Step 3: Generate an energy forecasting model

[0137] Input: The server retrieves the stored weather data.

[0138] Data processing / data calculation: A generative AI model (such as TensorFlow) is used to predict the amount of solar power generated for the next day. The model is input with training data and calculated to output the future amount of power generated.

[0139] Output: The predicted solar power generation data is stored in a database on the server.

[0140] How it works: The server retrieves weather data, uses a generative AI model to predict the next day's power generation, and stores the results.

[0141] Step 4: Scheduling high power consumers

[0142] Input: The user inputs the desired time for using the device into the terminal, and the desired time is sent from the terminal to the server. The server obtains the predicted power generation data.

[0143] Data processing / data calculation: The server compares the user's desired time with the predicted power generation amount and executes an algorithm to calculate the optimal operating time. It selects the time period with the longest sunshine hours and creates a schedule.

[0144] Output: The operation schedule is sent from the server to the terminal.

[0145] Specific operation: The user inputs the desired usage time into the application, and the server creates an optimal operation schedule based on that time period and notifies the device. The device then automatically starts operating the device according to that schedule.

[0146] Step 5: Optimizing the energy storage device

[0147] Input: The server retrieves the predicted energy yield data.

[0148] Data processing / data calculation: The server calculates the optimal charging and discharging timing based on the amount of electricity stored in the home battery and the predicted amount of power generation. For example, it calculates a schedule to charge electricity at night and discharge it in the morning.

[0149] Output: The optimized charging and discharging schedule is sent to the terminal, which then instructs the home battery.

[0150] Specific operation: The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal.

[0151] Step 6: Optimize your energy costs

[0152] Input: The user inputs the electricity rate plan into the device. The plan information is sent from the device to the server.

[0153] Data processing / data calculation: The server runs an algorithm to optimize energy usage based on the input electricity rate plan, for example concentrating operation during times when rates are low.

[0154] Output: The optimized schedule is sent to the terminal.

[0155] Specific operation: The user inputs an electricity rate plan, and the server readjusts the schedule based on that plan and notifies the terminal.

[0156] Step 7: System Maintenance Notification

[0157] Input: The server acquires operational data of the home solar power generation system.

[0158] Data processing / data calculation: The server analyzes operational data and runs algorithms to predict when maintenance will be required.

[0159] Output: The terminal is notified when maintenance is required.

[0160] Specific operation: The server predicts the need for maintenance based on operational data and notifies the user via the terminal.

[0161] (Application example 1)

[0162] 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."

[0163] Modern energy management systems aim to efficiently utilize solar power generation in homes and commercial facilities, but they currently have difficulty adapting to the efficient operation of high-power consumption equipment and production robots, which consume large amounts of energy in factories. Therefore, there is a need for systems that can optimize energy consumption throughout the factory and improve productivity. There is also a need for systems that can develop optimal operation schedules based on electricity rate plans and predict and notify maintenance timing.

[0164] 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.

[0165] In this invention, the server includes means for acquiring weather data, means for running a generative model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining the optimal timing for charging and discharging an energy storage device, means for generating and executing an operation schedule for optimizing the operation of an energy robot, and means for notifying the optimized energy schedule based on the predicted solar power generation and energy consumption. This makes it possible to optimize the operation of high-power consumption devices and robots in a factory to match solar power generation, thereby improving production efficiency while reducing energy costs.

[0166] "Means for obtaining weather data" means means for collecting current and future weather data using the weather API.

[0167] "Means for operating a generative model that predicts solar power generation" refers to means for running a generative AI model to predict the next day's solar power generation based on acquired weather data.

[0168] The "means for scheduling the operation of high-power consuming devices" is a means for calculating the optimal operation time of high-power consuming devices based on the predicted amount of solar power generation, and generating an operation schedule.

[0169] The "means for determining the optimal timing for charging and discharging the energy storage device" is a means for calculating the optimal timing for charging and discharging the home battery and transmitting operation instructions.

[0170] The "means for generating and executing an operation schedule for optimizing the operation of an energy robot" refers to a means for optimizing the operation schedule of the robot based on predicted solar power generation and energy consumption, and for operating the robot according to that schedule.

[0171] The "means for notifying an optimized energy schedule" is a means for notifying a user terminal of an energy schedule generated based on predicted solar power generation and energy consumption.

[0172] This invention is a system for managing energy in factories and optimizing the operation schedule of high-power-consuming equipment. This system collects weather data and uses it to predict solar power generation, enabling efficient energy use.

[0173] The server uses a weather API to obtain weather data, including temperature, sunshine hours, cloud cover, and wind speed, and runs a generative AI model based on this data to predict the amount of solar power generation for the next day.

[0174] Based on the predicted solar power generation, the server schedules the operation of high-power-consuming equipment in the factory, such as welding machines and processing machines. It calculates the optimal operating times and generates a schedule. Once the schedule is determined, the server notifies the terminal, and the terminal operates the high-power-consuming equipment.

[0175] In addition, the timing of charging and discharging energy storage devices (such as home batteries) is optimized to avoid peak energy consumption times and ensure that electricity is available during times when solar power generation is strongest.

[0176] Additionally, users can input their own electricity rate plan information into the device, and the server uses this information to avoid peak power hours and optimize energy usage, enabling efficient use of electricity while reducing energy costs.

[0177] The system consists of software for scheduling using the Python schedule library and for acquiring weather data using the Weather API. The factory's production robots and processing machines are linked to a networked environmental control system.

[0178] As a specific example, when optimizing the operation of a welding machine, the operation can be performed at the following timing: For example, the operation of the welding machine can be set from 2:00 PM to 4:00 PM based on weather data forecasts. Also, to avoid peak hours of energy consumption, the start of the welding machine can be scheduled during off-peak hours, achieving efficient energy consumption.

[0179] An example of a prompt sentence is, "Based on tomorrow's weather forecast, what is the optimal operating time for the welding machine?"

[0180] In this way, the energy prediction and management technology of the invention can be applied to the efficient operation of factory robots, thereby reducing energy consumption and improving productivity.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc., which is then used in subsequent forecasting models.

[0184] Input: Weather data request from the weather API

[0185] Data processing / calculation: weather data collection and filtering

[0186] Output: Weather data (temperature, sunshine hours, cloud cover, wind speed)

[0187] Step 2:

[0188] The server runs a prediction model (generative AI model) to predict the amount of solar power generation for the next day based on the acquired weather data. This model takes weather data as input and outputs the amount of power generation as a numerical value.

[0189] Input: Weather data

[0190] Data processing / calculation: Predicting power generation using weather data

[0191] Output: Predicted solar power generation (numerical data)

[0192] Step 3:

[0193] The server calculates the optimal operating time for high-power-consuming devices based on the predicted solar power generation amount and the user's desired usage time, and generates an operating schedule, which is then notified to the terminal.

[0194] Input: Forecasted solar power generation, desired usage time of the user

[0195] Data processing / calculation: Calculation of optimal driving time

[0196] Output: Schedule high-power consumption devices

[0197] Step 4:

[0198] The terminal operates the high-power consumption devices according to the operation schedule received from the server. The operation of the devices starts automatically and ends at the scheduled time.

[0199] Input: Operation schedule of high power consumption devices

[0200] Data processing / calculation: Issuing operation instructions for equipment

[0201] Output: Operating high-power devices

[0202] Step 5:

[0203] The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal, thereby optimizing the charging and discharging timing.

[0204] Input: Forecasted solar power generation, current energy storage status

[0205] Data processing / calculation: Optimization calculation of charge and discharge timing

[0206] Output: Charge and discharge timing instructions

[0207] Step 6:

[0208] Users input their electricity rate plan information into the device, and that information is sent to the server, which then optimizes energy usage and adjusts the schedule based on the plan.

[0209] Input: User's electricity plan

[0210] Data processing / calculation: Energy usage optimization based on electricity rate plans

[0211] Output: Adjusted energy schedule

[0212] Step 7:

[0213] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. The predicted timing is notified to the user via the terminal, and the user can then carry out the appropriate maintenance.

[0214] Input: Solar power system operation data

[0215] Data processing / calculation: Maintenance timing prediction

[0216] Output: Maintenance notification

[0217] 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.

[0218] The present invention will be described in detail below with reference to an embodiment thereof. This system performs energy forecasting and management for the most efficient use of solar power in a typical household, and also combines it with an emotion engine that recognizes the user's emotions.

[0219] 1. User Initial Settings

[0220] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[0221] 2. Obtaining weather data

[0222] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[0223] 3. Generating an energy prediction model

[0224] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[0225] 4. Scheduling of high-power devices

[0226] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[0227] 5. Optimization of Energy Storage Devices

[0228] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[0229] 6. Optimizing electricity costs

[0230] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0231] 7. System Maintenance Notification

[0232] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[0233] 8. Introducing the Emotion Engine

[0234] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[0235] 9. Emotion-based scheduling and notification optimization

[0236] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of energy-intensive appliances. It also optimizes notification methods based on the user's emotional state (for example, app notifications in a gentler tone).

[0237] Specific examples

[0238] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[0239] 1. The user inputs the desired time for using the washing machine into the terminal.

[0240] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[0241] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0242] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0243] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0244] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0245] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[0246] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[0247] In this way, the system not only optimizes the operation of high-power-consuming appliances and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, resulting in more efficient energy use within the home and reduced energy costs.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] A user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the terminal. The terminal then transmits the input information to the server.

[0251] Step 2:

[0252] The server sends a request to the weather API to get weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes this data and stores it in a database.

[0253] Step 3:

[0254] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The generative model makes predictions based on past data and acquired weather data. The results of this prediction are used for energy management.

[0255] Step 4:

[0256] The server calculates the optimal operating time for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. It also takes into account the desired usage times entered by the user and determines the most efficient time period within that range. The server generates an operating schedule and sends it to the terminal.

[0257] Step 5:

[0258] The terminal notifies the user of the operation schedule received from the server. The user checks the schedule and either approves it or requests a revision. After receiving the user's confirmation, the terminal automatically starts operating the equipment according to the operation schedule.

[0259] Step 6:

[0260] The server calculates the optimal charging and discharging timing for the home battery. This allows the battery to be charged during times when power generation is high and discharged during times when power generation is low. The server then sends these operation instructions to the terminal. The terminal then operates the home battery based on the received instructions.

[0261] Step 7:

[0262] Users input their electricity rate plan information into their device, which then sends this information to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0263] Step 8:

[0264] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal displays the notification content to the user and suggests appropriate maintenance.

[0265] Step 9:

[0266] When the emotion engine is installed, the device analyzes the user's voice and facial expression data in real time to determine their current emotional state. For example, if the user is feeling stressed, that information is sent to the server.

[0267] Step 10:

[0268] The server can adjust the schedule based on the user's emotional state. For example, if the user is feeling stressed, the server can delay the operation of the washing machine. The server can also optimize notification methods (such as the tone and content of notification sounds) according to the user's emotions.

[0269] For example, if the emotion engine detects that the user is feeling stressed the next morning, the server can adjust the washing machine's operating time to the afternoon to reduce the user's stress, optimizing energy efficiency while taking into account the user's emotional state.

[0270] Example 2

[0271] 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."

[0272] There is a need to maximize the efficiency of solar power generation in ordinary households. However, predicting power generation based on weather data and creating an optimal operation schedule for high-power-consuming devices linked to that forecast are complex, and adjusting the timing of charging and discharging energy storage devices is not easy. Furthermore, there is no established method for reducing electricity costs while optimizing energy use by taking into account the user's emotional state. Therefore, a system that can solve these multiple challenges in an integrated manner is needed.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0274] In this invention, the server includes a means for inputting information about household electrical appliances, a means for acquiring weather data, a means for running a generative model that predicts solar power generation based on the acquired weather data, a means for scheduling the operation of high-power consumption appliances based on the predicted solar power generation, a means for determining optimal timing for charging and discharging an energy storage device, a means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption, a means for acquiring and analyzing emotion data, and a means for adjusting the energy schedule based on the analyzed emotion data. This enables flexible energy scheduling that takes into account the user's emotional state while maximizing the utilization efficiency of solar power generation in the home. It also reduces energy costs and improves energy management throughout the home.

[0275] "Means for inputting information about household electrical appliances" refers to an interface or device that allows a user to input information about high-power consumption appliances and energy storage devices in the home into a terminal.

[0276] "Means of obtaining weather data" refers to the function for obtaining weather forecasts and current conditions data from online weather APIs, etc.

[0277] "Means for operating the generative model" refers to software or algorithms that operate an AI-based predictive model based on acquired weather data and estimate the amount of solar power generated the following day.

[0278] "Means for scheduling the operation of high-power-consuming devices" refers to a system that calculates the optimal operating times of high-power-consuming devices such as washing machines and dishwashers based on predicted power generation data and the user's desired usage times, and generates a schedule.

[0279] "Means for determining the optimal timing for charging and discharging an energy storage device" refers to a function that calculates the most efficient timing for charging and discharging an energy storage device such as a home battery.

[0280] The "means for notifying the optimized energy schedule" refers to a notification system for notifying the user of the calculated optimal energy schedule. Specifically, it includes a function for displaying the schedule through a terminal.

[0281] "Means for acquiring and analyzing emotional data" refers to sensors and analytical algorithms for acquiring and analyzing emotional data such as the user's voice and facial expressions to identify their current emotional state.

[0282] "Means for adjusting energy schedules based on emotional data" refers to a system for modifying and adjusting energy schedules based on the analyzed emotional state of a user, including actions such as delaying the operation of high-power consumption devices when stress levels are high.

[0283] This invention relates to an energy forecasting and management system for the most efficient use of solar power in homes. The system is further enhanced in flexibility and adaptability by incorporating an emotion engine that recognizes the user's emotions.

[0284] System Overview

[0285] The system consists of the following major hardware and software components:

[0286] server

[0287] Terminal (device operated by the user)

[0288] High-power consumption appliances (e.g. washing machines, dishwashers, etc.)

[0289] Energy storage devices (e.g. home batteries)

[0290] Weather API (to retrieve weather data)

[0291] Generative AI models (to predict solar power generation)

[0292] Emotion engine (to recognize and analyze user emotions)

[0293] Initial Setup

[0294] First, a user inputs information about high-power consumption appliances and energy storage devices in the home using a terminal, which is then sent to a server and stored in a database.

[0295] Obtaining weather data

[0296] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to predict solar power generation.

[0297] Energy Forecast

[0298] Based on the acquired weather data, the server runs a generative AI model to predict the amount of solar power generation for the next day. The prediction results are stored in a database and used in the next step to plan the operation of high-power consumption equipment and energy storage devices.

[0299] Scheduling

[0300] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the desired usage times set by the user. The calculated schedule is notified to the device and displayed to the user. The device can also automatically operate the devices according to this schedule.

[0301] Energy storage device optimization

[0302] The server calculates the optimal charging and discharging timing for the home battery, allowing users to avoid peak energy consumption times and use electricity during times when power generation is high. These operation instructions are sent to the home battery via the terminal.

[0303] Optimizing power costs

[0304] Users input their electricity plan information into their device. This information is sent to the server, which then optimizes energy usage based on the plan and adjusts the schedule to avoid peak power hours.

[0305] System maintenance notification

[0306] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. When the maintenance period approaches, the server sends a notification to the terminal and displays it to the user.

[0307] Introducing the Emotion Engine

[0308] The emotion engine uses sensors to capture the user's voice and facial expression data and analyzes their emotional state in real time. The analysis results are sent to the server and reflected in the energy schedule in the next step.

[0309] Emotion-Based Adjustment

[0310] The server adjusts the energy schedule based on the analyzed emotional data. For example, if the user is feeling stressed, it will adjust the operating time of high-power consumption devices later. Notification methods are also optimized according to the user's emotional state.

[0311] Specific examples

[0312] For example, if the user plans to do laundry the next morning, the process would be:

[0313] 1. The user inputs the desired time for using the washing machine into the terminal.

[0314] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative model to predict solar power generation.

[0315] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data and the desired usage time.

[0316] 4. The generated schedule is sent to the device, where the user can confirm it. The device then automatically starts the washing machine operation based on this schedule.

[0317] 5. The server also optimizes the timing of charging and discharging the home battery.

[0318] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0319] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[0320] 8. If the emotion engine detects stress in the user, the server will make adjustments such as delaying the operation time of the washing machine.

[0321] Through this process, the system not only optimizes the operation of high-power-consuming devices and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, thereby improving the efficiency of power use within the home and reducing energy costs.

[0322] Prompt Sentence Examples

[0323] For example, the system uses specific prompts such as, "I plan to do laundry the next morning. Therefore, please calculate the optimal washing machine operation schedule based on the predicted solar power generation amount. Also, please consider adjusting the operation time if the user feels stressed."

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1: Initial User Setup

[0326] The user uses the terminal to enter the following information:

[0327] High-power household appliances (e.g. washing machines, dishwashers)

[0328] Energy storage devices (e.g. home batteries)

[0329] input:

[0330] High power consumption device information

[0331] Energy Storage Device Information

[0332] output:

[0333] The terminal transmits this information to the server, which stores the received information in a database.

[0334] Specific behavior:

[0335] The user operates the terminal to enter the necessary information into the form and presses the send button to pass the information to the server, which receives the data and stores it in a database.

[0336] Step 2: Obtaining weather data

[0337] The server calls the weather API to retrieve current and future weather data.

[0338] input:

[0339] Weather API request

[0340] output:

[0341] Weather data such as temperature, sunshine hours, cloud cover, and wind speed

[0342] Specific behavior:

[0343] The server accesses the weather API, sends a request, and receives weather data in response, which is then stored locally or recorded in a database for analysis.

[0344] Step 3: Generate an energy forecasting model

[0345] The server uses a generated AI model based on the acquired weather data to predict the amount of solar power generation for the next day.

[0346] input:

[0347] Weather data

[0348] output:

[0349] Predicted solar power generation data

[0350] Specific behavior:

[0351] The server inputs the stored weather data into the generative AI model, which then calculates and predicts the amount of solar power generation for the next day. The prediction results are stored in a database.

[0352] Step 4: Scheduling high power consumers

[0353] The server calculates the optimal operating time for high-power consumption devices based on predicted solar power generation data and the user's desired usage times.

[0354] input:

[0355] Predicted solar power generation data

[0356] User's desired usage time

[0357] output:

[0358] Operation schedule for high power consumption devices

[0359] Specific behavior:

[0360] The server uses an algorithm to calculate the most efficient operating time, taking into account the user's desired time and solar power generation forecast data, and notifies the terminal of the calculation results.

[0361] Step 5: Optimizing the energy storage device

[0362] The server determines the optimal timing for charging and discharging the home battery.

[0363] input:

[0364] Solar power generation data

[0365] Residential energy consumption data

[0366] output:

[0367] Home battery charging and discharging timing

[0368] Specific behavior:

[0369] The server analyzes the solar power generation forecast data and the household's power consumption patterns to calculate the optimal timing for charging and discharging the home battery. The calculation results are sent to the terminal and instructions are sent to the home battery.

[0370] Step 6: Optimize your energy costs

[0371] Users input their electricity plan information into the device, and the server uses this information to optimize energy usage.

[0372] input:

[0373] Electricity rate plan information

[0374] output:

[0375] Optimized Energy Schedule

[0376] Specific behavior:

[0377] Users input their energy plan details via a device, and the server receives the data and stores it in a database. The server then uses this information to adjust energy usage schedules to avoid peak tariff periods.

[0378] Step 7: System Maintenance Notification

[0379] The server analyzes operational data from the solar power generation system and predicts and notifies users when maintenance is necessary.

[0380] input:

[0381] Power generation system operation data

[0382] output:

[0383] Maintenance Notification

[0384] Specific behavior:

[0385] The server periodically analyzes operational data to detect abnormalities and when maintenance is required. The detected information is notified to the terminal and displayed to the user.

[0386] Step 8: Implementing the Emotion Engine

[0387] The emotion engine acquires and analyzes the user's voice and facial expression data.

[0388] input:

[0389] Voice and facial expression data

[0390] output:

[0391] User emotional state data

[0392] Specific behavior:

[0393] The device or a dedicated device captures voice and facial expressions in real time, and the emotion engine processes the data to analyze the user's emotional state. The analysis results are then sent to a server.

[0394] Step 9: Emotional Adjustment

[0395] The server adjusts the energy schedule based on the user's emotional state.

[0396] input:

[0397] User emotional state data

[0398] output:

[0399] Adjusted Energy Schedule

[0400] Specific behavior:

[0401] The server receives the emotional state data and adjusts the operation schedule of high-power consumption devices when stress levels are high, etc. The adjusted schedule is sent to the terminal and notified to the user.

[0402] (Application example 2)

[0403] 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."

[0404] Conventional solar power generation systems mainly rely on weather data to predict power generation and schedule high-power-consuming equipment. However, these systems do not take into account the emotional state of the user, limiting their ability to optimize user experience and efficiency. Furthermore, resource management that ignores emotional aspects such as worker stress and fatigue can lead to reduced productivity and user dissatisfaction.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring and analyzing emotion data, means for adjusting the operation schedule of the high-power consumption devices based on the emotion data, and means for changing the content and method of notification based on the emotion data. This makes it possible to flexibly adjust the operation schedule of the high-power consumption devices according to the user's emotional state, thereby improving the user experience and achieving effective energy management.

[0406] "Means for acquiring weather data" refers to a combination of hardware and software for acquiring weather data in real time. Information is collected via the weather API.

[0407] The "means for operating a generative model to predict solar power generation" refers to algorithms and software for predicting solar power generation for the next day based on acquired weather data. A generative AI model is used.

[0408] The "means for scheduling the operation of high-power consuming devices" refers to scheduling algorithms and software for optimizing the operation time of high-power consuming devices based on the predicted amount of solar power generation.

[0409] The "means for determining the optimal timing for charging and discharging the energy storage device" refers to algorithms and software for optimally timing the charging and discharging of the home battery.

[0410] The "means for notifying the optimized energy schedule" refers to an interface and software for notifying the user of the scheduling results. A device such as a smartphone or tablet is used.

[0411] The "means for acquiring and analyzing emotional data" refers to an emotion recognition engine and software for acquiring and analyzing emotional data such as the user's voice and facial expressions in real time.

[0412] The "means for adjusting the operation schedule of high-power-consuming devices based on emotional data" refers to algorithms and software for adjusting the operation schedule of high-power-consuming devices in accordance with the user's emotional state based on the acquired emotional data.

[0413] The "means for changing the notification content and method based on emotional data" refers to algorithms and software for optimizing the notification content and method according to the user's emotional state.

[0414] The "means for inputting an electricity rate plan" refers to an interface and software that allows a user to input their electricity rate plan information into the system.

[0415] The "means for optimizing energy usage by avoiding peak power hours based on an electricity rate plan" refers to algorithms and software for optimizing energy usage by avoiding peak power hours based on input electricity rate plan information.

[0416] The "means for predicting and notifying the timing of necessary maintenance of an energy generating device" refers to an algorithm and software for analyzing operational data of the energy generating device, predicting the timing of necessary maintenance, and notifying the timing.

[0417] The system for implementing the present invention aims to improve the efficiency of energy management in homes and factories, and also takes into account the emotional state of the user. The detailed configuration and operation of this system will be described below.

[0418] Initial Setup

[0419] First, a user uses a terminal to input information about high-power-consuming devices (e.g., washing machines, welding robots) and energy storage devices (e.g., home batteries, factory batteries) in their homes or factories. This information includes the amount of power consumed by each device and the desired operating time.

[0420] Obtaining weather data

[0421] The server then uses a weather API (e.g., OpenWeatherMap API) to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to forecast solar power generation.

[0422] Generate an energy forecasting model

[0423] The server runs a generative AI model (e.g., TensorFlow, PyTorch) based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to operate power usage and storage devices in homes and factories.

[0424] Scheduling high power consumers

[0425] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[0426] Energy storage device optimization

[0427] The server calculates the optimal charging and discharging timing for the home or factory battery, allowing users to avoid peak energy consumption times and utilize power during periods of high power generation. Operation instructions are sent to the energy storage device via the terminal.

[0428] Optimizing power costs

[0429] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0430] System maintenance notification

[0431] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. As soon as the necessary maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[0432] Introducing the Emotion Engine

[0433] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[0434] Emotion-based scheduling and notification optimization

[0435] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of high-power devices. It also optimizes notification methods (e.g., app notifications in a gentler tone) according to the user's emotional state.

[0436] Specific examples

[0437] If the user plans to do laundry the next morning, the system works as follows:

[0438] 1. The user inputs the desired time for using the washing machine into the terminal.

[0439] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[0440] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0441] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0442] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0443] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0444] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[0445] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[0446] Prompt Sentence Examples

[0447] "Design an application that uses a generative AI model to generate an operation schedule to maximize the use of solar power generation in a factory for the next day. Acquire and integrate weather data (e.g., sunshine hours, wind speed). Calculate the optimal operation time for high-power consuming equipment in the factory and notify the user. Analyze the emotional state of workers using an emotion recognition engine and adjust the operation schedule if stress is detected. Calculate the optimal timing for charging and discharging the factory battery."

[0448] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0449] Step 1:

[0450] Users use a terminal to input information about high-power-consuming devices and energy storage devices in their homes or factories, including the amount of power each device consumes and the desired operating time. This input data is then stored in a database on the server.

[0451] Step 2:

[0452] The server uses a weather API (e.g., OpenWeatherMap API) to obtain current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is the basis for solar power generation forecasts. The obtained weather data is stored and processed within the server.

[0453] Step 3:

[0454] The server uses a generative AI model (e.g., TensorFlow, PyTorch) based on the stored weather data to predict the amount of solar power generation for the next day. The input data is the weather data, and the output data is the predicted amount of solar power generation. This forecast data is used for energy management.

[0455] Step 4:

[0456] The server calculates the optimal operation schedule for high-power consumption devices based on the acquired information on the devices and the predicted solar power generation data. For example, to minimize power consumption, it sets the devices to operate during the hours with the longest sunshine. This calculation is performed using an algorithm and output in the form of an operation schedule.

[0457] Step 5:

[0458] The server calculates the optimal charging and discharging timing for a home or industrial energy storage device. The input data is the predicted power generation and consumption pattern, and the output data is the optimal charging and discharging schedule. This schedule allows avoiding peak energy consumption.

[0459] Step 6:

[0460] Users input their electricity plan information using a terminal. This information is sent to the server and stored. The plan information is used to optimize energy schedules to avoid peak hours.

[0461] Step 7:

[0462] The server generates a schedule to optimize energy usage based on the input electricity rate plan. This calculation uses an algorithm to avoid peak hours. The output data is the optimized energy schedule.

[0463] Step 8:

[0464] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. It calculates the necessary maintenance timing and notifies the terminal. The input data is the operational data of the equipment, and the output data is the appropriate maintenance notification.

[0465] Step 9:

[0466] The emotion engine analyzes the user's voice and facial expression data sent from the device in real time to identify the user's current emotional state. The acquired emotional data is sent to the server for analysis. The input data is voice and facial expression data, and the output data is the user's emotional state.

[0467] Step 10:

[0468] The server adjusts the operation schedule based on the emotional data. For example, if the user is feeling stressed, the server can change the operation time of high-power consumption devices. The input data are the emotional state and the existing operation schedule, and the output data is the adjusted operation schedule.

[0469] Step 11:

[0470] The server adjusts the notification content and method based on the emotional data. For example, if the user feels like relaxing, the server may adjust the tone of the notification. The input data is the emotional state and existing notification settings, and the output data is the adjusted notification content.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] [Second embodiment]

[0475] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0476] 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.

[0477] 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).

[0478] 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.

[0479] 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.

[0480] 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).

[0481] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0482] 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.

[0483] 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.

[0484] 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.

[0485] 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.

[0486] 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."

[0487] An embodiment of the present invention will be described in detail below. This system performs energy prediction and management to make the most efficient use of solar power generated in an ordinary home, and is composed of the following steps.

[0488] 1. User Initial Settings

[0489] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[0490] 2. Obtaining weather data

[0491] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[0492] 3. Generating an energy prediction model

[0493] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[0494] 4. Scheduling of high-power devices

[0495] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. An operation schedule is generated and notified to the device. The device then operates the target devices according to this schedule.

[0496] 5. Optimization of Energy Storage Devices

[0497] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[0498] 6. Optimizing electricity costs

[0499] Users input their electricity rate plan information into the terminal, and the server adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0500] 7. System Maintenance Notification

[0501] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance period is predicted, a notification is sent to the terminal. The user follows the notification and performs appropriate maintenance to ensure the long-term stable operation of the system.

[0502] Specific examples

[0503] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[0504] 1. The user inputs the desired time for using the washing machine into the terminal.

[0505] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[0506] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0507] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0508] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0509] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0510] This optimizes the operation of the washing machine using solar power, reducing energy costs and improving the efficiency of electricity use within the home.

[0511] The processing flow will be explained below.

[0512] Step 1:

[0513] The user inputs information about the high-power appliances and energy storage devices in the home into the terminal. For example, the user registers the model name and planned usage time of a washing machine or dishwasher. The terminal then transmits this information to the server.

[0514] Step 2:

[0515] The server sends a request to the weather API to retrieve weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes the retrieved weather data and stores it in a database.

[0516] Step 3:

[0517] The server inputs the acquired weather data into a generative model to predict the amount of solar power generation for the next day. The generative model makes highly accurate predictions based on past data and acquired weather data. These prediction results are used for energy management.

[0518] Step 4:

[0519] The server calculates the optimal operating times for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. Taking into account the desired usage times input by the user, the server determines the most efficient time slots within that range. An operating schedule is generated.

[0520] Step 5:

[0521] The server notifies the terminal of the generated operation schedule. The terminal displays the operation schedule to the user and asks for confirmation. The terminal automatically starts operation of the equipment according to the scheduled time.

[0522] Step 6:

[0523] The server calculates the optimal charging and discharging timing for the energy storage device (e.g., a home battery). It sets it to supply power during times when power generation is high and to store power during times when power generation is low. This setting is sent to the home battery via the terminal.

[0524] Step 7:

[0525] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0526] Step 8:

[0527] The server analyzes the equipment's operational data and past failure data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal then displays the maintenance timing to the user.

[0528] Step 9:

[0529] Once all data and settings are collected, the system will automatically begin operation and optimize the operation of high-power consumption appliances and energy storage devices based on predicted solar power generation, enabling users to achieve more efficient energy use in their homes and reduce energy costs.

[0530] Example 1

[0531] 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."

[0532] As the adoption of solar power generation systems in general households increases, there is a need to maximize their power generation efficiency while optimizing power consumption. However, current systems lack the means to accurately predict solar power generation amounts by fully utilizing weather data, and the use of high-power-consuming devices and management of energy storage devices are not effectively carried out. Furthermore, they are not adequately able to optimize energy costs according to electricity rate plans. Furthermore, they lack the functionality to predict and notify when power generation systems need maintenance. This results in a decrease in the efficiency of power usage within the home, making it difficult to reduce energy costs.

[0533] 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.

[0534] In this invention, the server includes means for a user to input information about high-power consumption devices and energy storage devices in the home, means for acquiring weather data, means for operating a generative AI model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining optimal timing for charging and discharging the energy storage device, and means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption. This improves the accuracy of solar power generation predictions, enables efficient management of high-power consumption devices and energy storage devices, and enables improved efficiency of home power utilization and reduced energy costs.

[0535] "User" refers to an individual or household that uses the system.

[0536] "High-power household appliances" refers to household appliances such as washing machines and dishwashers that consume large amounts of electricity at once.

[0537] An "energy storage device" is a device that temporarily stores electricity generated within the home and supplies it when needed. A specific example is a home battery.

[0538] "Terminal" means an electronic device used by a user to enter information and receive information from a system. Examples include a smartphone or tablet.

[0539] "Server" refers to the computer system that manages the entire system and processes data and runs predictive models.

[0540] "Weather data" refers to data relating to weather conditions, such as temperature, hours of sunshine, cloud cover, and wind speed.

[0541] "Weather API" refers to a programmatic interface used to obtain weather data. An example is the OpenWeatherMap API.

[0542] A "generative AI model" refers to an artificial intelligence model that makes predictions and classifications based on acquired data. A specific example is a predictive model using TensorFlow.

[0543] "Scheduling" refers to planning and setting the operating times and timing of specific equipment based on predictive data.

[0544] "Optimization" refers to adjusting resource allocation and scheduling to maximize energy efficiency or minimize costs.

[0545] An "energy schedule" refers to a schedule that includes the operation plans of household appliances and energy storage devices.

[0546] "Electricity rate plan" means an electricity payment plan that a consumer enters into with an electricity supplier. Examples include flat-rate plans and time-of-use plans.

[0547] "Maintenance timing" refers to the specific timing when maintenance of a system or equipment is required.

[0548] This invention is a system for energy prediction and management to make the most efficient use of solar power generated in an average household, and operates in cooperation with the server, terminal, and user elements.

[0549] System Overview

[0550] User Preferences

[0551] The user launches a dedicated application using the device. From the settings screen within the application, they enter information about high-power consumption devices in the home (e.g., washing machine, dishwasher) and energy storage devices (e.g., home battery). Once this information is saved, the device sends it to the server. The server stores the received information in a database.

[0552] Obtaining weather data

[0553] The server periodically calls a weather API (e.g., OpenWeatherMap API) to obtain weather data (e.g., temperature, sunshine hours, cloud cover, wind speed), which is then stored in a database within the system.

[0554] Generate an energy forecasting model

[0555] The server runs a generative AI model (for example, a forecasting model using TensorFlow) based on the stored weather data to predict the amount of solar power generation for the next day. The forecast results are stored in a database.

[0556] Scheduling high power consumers

[0557] The user inputs the desired usage time of a high-power consumption device (e.g., a washing machine) on the device. The device then sends the desired usage time data to the server. The server calculates the optimal operation time for the high-power consumption device based on the predicted solar power generation data and the desired usage time, and generates an operation schedule. The generated schedule is notified to the device, which automatically starts operation of the device at the set time.

[0558] Energy storage device optimization

[0559] The server calculates the timing of charging and discharging the home battery based on the predicted power generation data. For example, it sets a schedule to charge at night (when power demand is low) and discharge in the morning when power generation is low. The calculation results are sent to the terminal, and instructions are sent to the home battery through the terminal.

[0560] Optimizing power costs

[0561] Users input their electricity plan information (e.g., flat-rate plan, time-of-use plan) into the device and send it to the server, which then runs an algorithm to optimize energy usage based on the plan and reschedules each device to avoid peak power hours.

[0562] System maintenance notification

[0563] The server analyzes the operational data of the home's solar power generation system and predicts when maintenance is required. The prediction results are sent to the terminal and displayed to the user. The user can then follow the notification to arrange for appropriate maintenance work.

[0564] Specific examples

[0565] For example, the process when the laundry is scheduled to be done in the morning of the next day will be described.

[0566] 1. The user inputs the desired time for using the washing machine into the terminal.

[0567] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[0568] 3. The server calculates the optimal time to run the washing machine based on the predicted power generation data. For example, it determines that the best time is between 2:00 PM and 4:00 PM, when the sunshine hours are the longest.

[0569] 4. The schedule is sent to the device, and the user confirms it. The device automatically starts the washing machine at the specified time.

[0570] 5. The server optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0571] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0572] Prompt Sentence Examples

[0573] "Based on the weather forecast for the next day obtained using a weather API, please predict the amount of solar power generation in the home for the next day and generate an optimal operation schedule for the washing machine, which is a high-power-consuming device. In this case, please create a schedule to operate the washing machine during the time period when power generation is highest."

[0574] This invention improves the efficiency of solar power generation in homes, reducing energy costs and realizing sustainable energy use.

[0575] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0576] Step 1: Initial User Setup

[0577] Input: The user inputs information about high-power consumption appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the home into the terminal.

[0578] Data processing / data calculation: The terminal formats the input information into a database and creates a data set that includes information set by the user (device manufacturer, model number, power consumption, etc.).

[0579] Output: The terminal sends the formatted data to the server.

[0580] Specific operation: The user opens the dedicated application, enters information about the home appliance and energy storage device on the settings screen, and presses the save button. The device then sends the information to the server.

[0581] Step 2: Obtaining weather data

[0582] Input: The server sends a request to the weather API.

[0583] Data processing / data calculation: As a response from the weather API, the server receives weather data such as temperature, sunshine hours, cloud cover, wind speed, etc. The server converts this data into an appropriate format and stores it in the database.

[0584] Output: Weather data is stored in a database on the server.

[0585] Specific operation: The server periodically accesses a weather API (e.g., OpenWeatherMap API) to obtain the necessary weather data.

[0586] Step 3: Generate an energy forecasting model

[0587] Input: The server retrieves the stored weather data.

[0588] Data processing / data calculation: A generative AI model (such as TensorFlow) is used to predict the amount of solar power generated for the next day. The model is input with training data and calculated to output the future amount of power generated.

[0589] Output: The predicted solar power generation data is stored in a database on the server.

[0590] How it works: The server retrieves weather data, uses a generative AI model to predict the next day's power generation, and stores the results.

[0591] Step 4: Scheduling high power consumers

[0592] Input: The user inputs the desired time for using the device into the terminal, and the desired time is sent from the terminal to the server. The server obtains the predicted power generation data.

[0593] Data processing / data calculation: The server compares the user's desired time with the predicted power generation amount and executes an algorithm to calculate the optimal operating time. It selects the time period with the longest sunshine hours and creates a schedule.

[0594] Output: The operation schedule is sent from the server to the terminal.

[0595] Specific operation: The user inputs the desired usage time into the application, and the server creates an optimal operation schedule based on that time period and notifies the device. The device then automatically starts operating the device according to that schedule.

[0596] Step 5: Optimizing the energy storage device

[0597] Input: The server retrieves the predicted energy yield data.

[0598] Data processing / data calculation: The server calculates the optimal charging and discharging timing based on the amount of electricity stored in the home battery and the predicted amount of power generation. For example, it calculates a schedule to charge electricity at night and discharge it in the morning.

[0599] Output: The optimized charging and discharging schedule is sent to the terminal, which then instructs the home battery.

[0600] Specific operation: The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal.

[0601] Step 6: Optimize your energy costs

[0602] Input: The user inputs the electricity rate plan into the device. The plan information is sent from the device to the server.

[0603] Data processing / data calculation: The server runs an algorithm to optimize energy usage based on the input electricity rate plan, for example concentrating operation during times when rates are low.

[0604] Output: The optimized schedule is sent to the terminal.

[0605] Specific operation: The user inputs an electricity rate plan, and the server readjusts the schedule based on that plan and notifies the terminal.

[0606] Step 7: System Maintenance Notification

[0607] Input: The server acquires operational data of the home solar power generation system.

[0608] Data processing / data calculation: The server analyzes operational data and runs algorithms to predict when maintenance will be required.

[0609] Output: The terminal is notified when maintenance is required.

[0610] Specific operation: The server predicts the need for maintenance based on operational data and notifies the user via the terminal.

[0611] (Application example 1)

[0612] 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."

[0613] Modern energy management systems aim to efficiently utilize solar power generation in homes and commercial facilities, but they currently have difficulty adapting to the efficient operation of high-power consumption equipment and production robots, which consume large amounts of energy in factories. Therefore, there is a need for systems that can optimize energy consumption throughout the factory and improve productivity. There is also a need for systems that can develop optimal operation schedules based on electricity rate plans and predict and notify maintenance timing.

[0614] 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.

[0615] In this invention, the server includes means for acquiring weather data, means for running a generative model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining the optimal timing for charging and discharging an energy storage device, means for generating and executing an operation schedule for optimizing the operation of an energy robot, and means for notifying the optimized energy schedule based on the predicted solar power generation and energy consumption. This makes it possible to optimize the operation of high-power consumption devices and robots in a factory to match solar power generation, thereby improving production efficiency while reducing energy costs.

[0616] "Means for obtaining weather data" means means for collecting current and future weather data using the weather API.

[0617] "Means for operating a generative model that predicts solar power generation" refers to means for running a generative AI model to predict the amount of solar power generation for the next day based on acquired weather data.

[0618] The "means for scheduling the operation of high-power consuming devices" is a means for calculating the optimal operation time of high-power consuming devices based on the predicted amount of solar power generation, and generating an operation schedule.

[0619] The "means for determining the optimal timing for charging and discharging the energy storage device" is a means for calculating the optimal timing for charging and discharging the home battery and transmitting operation instructions.

[0620] The "means for generating and executing an operation schedule for optimizing the operation of an energy robot" refers to a means for optimizing the operation schedule of the robot based on predicted solar power generation and energy consumption, and for operating the robot according to that schedule.

[0621] The "means for notifying an optimized energy schedule" is a means for notifying a user terminal of an energy schedule generated based on predicted solar power generation and energy consumption.

[0622] This invention is a system for managing energy in factories and optimizing the operation schedule of high-power-consuming equipment. This system collects weather data and uses it to predict solar power generation, enabling efficient energy use.

[0623] The server uses a weather API to obtain weather data, including temperature, sunshine hours, cloud cover, and wind speed, and runs a generative AI model based on this data to predict the amount of solar power generation for the next day.

[0624] Based on the predicted solar power generation, the server schedules the operation of high-power-consuming equipment in the factory, such as welding machines and processing machines. It calculates the optimal operating times and generates a schedule. Once the schedule is determined, the server notifies the terminal, and the terminal operates the high-power-consuming equipment.

[0625] In addition, the timing of charging and discharging energy storage devices (such as home batteries) is optimized to avoid peak energy consumption times and ensure that electricity is available during times when solar power generation is strongest.

[0626] Additionally, users can input their own electricity rate plan information into the device, and the server uses this information to avoid peak power hours and optimize energy usage, enabling efficient use of electricity while reducing energy costs.

[0627] The system consists of software for scheduling using the Python schedule library and for acquiring weather data using the Weather API. The factory's production robots and processing machines are linked to a networked environmental control system.

[0628] As a specific example, when optimizing the operation of a welding machine, the operation can be performed at the following timing: For example, the operation of the welding machine can be set from 2:00 PM to 4:00 PM based on weather data forecasts. Also, to avoid peak hours of energy consumption, the start of the welding machine can be scheduled during off-peak hours, achieving efficient energy consumption.

[0629] An example of a prompt sentence is, "Based on tomorrow's weather forecast, what is the optimal operating time for the welding machine?"

[0630] In this way, the energy prediction and management technology of the invention can be applied to the efficient operation of factory robots, thereby reducing energy consumption and improving productivity.

[0631] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0632] Step 1:

[0633] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc., which is then used in subsequent forecasting models.

[0634] Input: Weather data request from the weather API

[0635] Data processing / calculation: weather data collection and filtering

[0636] Output: Weather data (temperature, sunshine hours, cloud cover, wind speed)

[0637] Step 2:

[0638] The server runs a prediction model (generative AI model) to predict the amount of solar power generation for the next day based on the acquired weather data. This model takes weather data as input and outputs the amount of power generation as a numerical value.

[0639] Input: Weather data

[0640] Data processing / calculation: Predicting power generation using weather data

[0641] Output: Predicted solar power generation (numerical data)

[0642] Step 3:

[0643] The server calculates the optimal operating time for high-power-consuming devices based on the predicted solar power generation amount and the user's desired usage time, and generates an operating schedule, which is then notified to the terminal.

[0644] Input: Forecasted solar power generation, desired usage time of the user

[0645] Data processing / calculation: Calculation of optimal driving time

[0646] Output: Schedule high-power consumption devices

[0647] Step 4:

[0648] The terminal operates the high-power consumption devices according to the operation schedule received from the server. The operation of the devices starts automatically and ends at the scheduled time.

[0649] Input: Operation schedule of high power consumption devices

[0650] Data processing / calculation: Issuing operation instructions for equipment

[0651] Output: Operating high-power devices

[0652] Step 5:

[0653] The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal, thereby optimizing the charging and discharging timing.

[0654] Input: Forecasted solar power generation, current energy storage status

[0655] Data processing / calculation: Optimization calculation of charge and discharge timing

[0656] Output: Charge and discharge timing instructions

[0657] Step 6:

[0658] Users input their electricity rate plan information into the device, and that information is sent to the server, which then optimizes energy usage and adjusts the schedule based on the plan.

[0659] Input: User's electricity plan

[0660] Data processing / calculation: Energy usage optimization based on electricity rate plans

[0661] Output: Adjusted energy schedule

[0662] Step 7:

[0663] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. The predicted timing is notified to the user via the terminal, and the user can then carry out the appropriate maintenance.

[0664] Input: Solar power system operation data

[0665] Data processing / calculation: Maintenance timing prediction

[0666] Output: Maintenance notification

[0667] 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.

[0668] The present invention will be described in detail below with reference to an embodiment thereof. This system performs energy forecasting and management for the most efficient use of solar power in a typical household, and also combines it with an emotion engine that recognizes the user's emotions.

[0669] 1. User Initial Settings

[0670] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[0671] 2. Obtaining weather data

[0672] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[0673] 3. Generating an energy prediction model

[0674] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[0675] 4. Scheduling of high-power devices

[0676] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[0677] 5. Optimization of Energy Storage Devices

[0678] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[0679] 6. Optimizing electricity costs

[0680] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0681] 7. System Maintenance Notification

[0682] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[0683] 8. Introducing the Emotion Engine

[0684] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[0685] 9. Emotion-based scheduling and notification optimization

[0686] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of energy-intensive appliances. It also optimizes notification methods based on the user's emotional state (for example, app notifications in a gentler tone).

[0687] Specific examples

[0688] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[0689] 1. The user inputs the desired time for using the washing machine into the terminal.

[0690] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[0691] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0692] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0693] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0694] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0695] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[0696] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[0697] In this way, the system not only optimizes the operation of high-power-consuming appliances and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, resulting in more efficient energy use within the home and reduced energy costs.

[0698] The processing flow will be explained below.

[0699] Step 1:

[0700] A user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the terminal. The terminal then transmits the input information to the server.

[0701] Step 2:

[0702] The server sends a request to the weather API to get weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes this data and stores it in a database.

[0703] Step 3:

[0704] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The generative model makes predictions based on past data and acquired weather data. The results of this prediction are used for energy management.

[0705] Step 4:

[0706] The server calculates the optimal operating time for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. It also takes into account the desired usage times entered by the user and determines the most efficient time period within that range. The server generates an operating schedule and sends it to the terminal.

[0707] Step 5:

[0708] The terminal notifies the user of the operation schedule received from the server. The user checks the schedule and either approves it or requests a revision. After receiving the user's confirmation, the terminal automatically starts operating the equipment according to the operation schedule.

[0709] Step 6:

[0710] The server calculates the optimal charging and discharging timing for the home battery. This allows the battery to be charged during times when power generation is high and discharged during times when power generation is low. The server then sends these operation instructions to the terminal. The terminal then operates the home battery based on the received instructions.

[0711] Step 7:

[0712] Users input their electricity rate plan information into their device, which then sends this information to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0713] Step 8:

[0714] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal displays the notification content to the user and suggests appropriate maintenance.

[0715] Step 9:

[0716] When the emotion engine is installed, the device analyzes the user's voice and facial expression data in real time to determine their current emotional state. For example, if the user is feeling stressed, that information is sent to the server.

[0717] Step 10:

[0718] The server can adjust the schedule based on the user's emotional state. For example, if the user is feeling stressed, the server can delay the operation of the washing machine. The server can also optimize notification methods (such as the tone and content of notification sounds) according to the user's emotions.

[0719] For example, if the emotion engine detects that the user is feeling stressed the next morning, the server can adjust the washing machine's operating time to the afternoon to reduce the user's stress, optimizing energy efficiency while taking into account the user's emotional state.

[0720] Example 2

[0721] 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."

[0722] There is a need to maximize the efficiency of solar power generation in ordinary households. However, predicting power generation based on weather data and creating an optimal operation schedule for high-power-consuming devices linked to that forecast are complex, and adjusting the timing of charging and discharging energy storage devices is not easy. Furthermore, there is no established method for reducing electricity costs while optimizing energy use by taking into account the user's emotional state. Therefore, a system that can solve these multiple challenges in an integrated manner is needed.

[0723] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0724] In this invention, the server includes a means for inputting information about household electrical appliances, a means for acquiring weather data, a means for running a generative model that predicts solar power generation based on the acquired weather data, a means for scheduling the operation of high-power consumption appliances based on the predicted solar power generation, a means for determining optimal timing for charging and discharging an energy storage device, a means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption, a means for acquiring and analyzing emotion data, and a means for adjusting the energy schedule based on the analyzed emotion data. This enables flexible energy scheduling that takes into account the user's emotional state while maximizing the utilization efficiency of solar power generation in the home. It also reduces energy costs and improves energy management throughout the home.

[0725] "Means for inputting information about household electrical appliances" refers to an interface or device that allows a user to input information about high-power consumption appliances and energy storage devices in the home into a terminal.

[0726] "Means of obtaining weather data" refers to the function for obtaining weather forecasts and current conditions data from online weather APIs, etc.

[0727] "Means for operating the generative model" refers to software or algorithms that operate an AI-based predictive model based on acquired weather data and estimate the amount of solar power generated the following day.

[0728] "Means for scheduling the operation of high-power-consuming devices" refers to a system that calculates the optimal operating times of high-power-consuming devices such as washing machines and dishwashers based on predicted power generation data and the user's desired usage times, and generates a schedule.

[0729] "Means for determining the optimal timing for charging and discharging an energy storage device" refers to a function that calculates the most efficient timing for charging and discharging an energy storage device such as a home battery.

[0730] The "means for notifying the optimized energy schedule" refers to a notification system for notifying the user of the calculated optimal energy schedule. Specifically, it includes a function for displaying the schedule through a terminal.

[0731] "Means for acquiring and analyzing emotional data" refers to sensors and analytical algorithms for acquiring and analyzing emotional data such as the user's voice and facial expressions to identify their current emotional state.

[0732] "Means for adjusting energy schedules based on emotional data" refers to a system for modifying and adjusting energy schedules based on the analyzed emotional state of a user, including actions such as delaying the operation of high-power consumption devices when stress levels are high.

[0733] This invention relates to an energy forecasting and management system for the most efficient use of solar power in homes. The system is further enhanced in flexibility and adaptability by incorporating an emotion engine that recognizes the user's emotions.

[0734] System Overview

[0735] The system consists of the following major hardware and software components:

[0736] server

[0737] Terminal (device operated by the user)

[0738] High-power consumption appliances (e.g. washing machines, dishwashers, etc.)

[0739] Energy storage devices (e.g. home batteries)

[0740] Weather API (to retrieve weather data)

[0741] Generative AI models (to predict solar power generation)

[0742] Emotion engine (to recognize and analyze user emotions)

[0743] Initial Setup

[0744] First, a user inputs information about high-power consumption appliances and energy storage devices in the home using a terminal, which is then sent to a server and stored in a database.

[0745] Obtaining weather data

[0746] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to predict solar power generation.

[0747] Energy Forecast

[0748] Based on the acquired weather data, the server runs a generative AI model to predict the amount of solar power generation for the next day. The prediction results are stored in a database and used in the next step to plan the operation of high-power consumption equipment and energy storage devices.

[0749] Scheduling

[0750] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the desired usage times set by the user. The calculated schedule is notified to the device and displayed to the user. The device can also automatically operate the devices according to this schedule.

[0751] Energy storage device optimization

[0752] The server calculates the optimal charging and discharging timing for the home battery, allowing users to avoid peak energy consumption times and use electricity during times when power generation is high. These operation instructions are sent to the home battery via the terminal.

[0753] Optimizing power costs

[0754] Users input their electricity plan information into their device. This information is sent to the server, which then optimizes energy usage based on the plan and adjusts the schedule to avoid peak power hours.

[0755] System maintenance notification

[0756] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. When the maintenance period approaches, the server sends a notification to the terminal and displays it to the user.

[0757] Introducing the Emotion Engine

[0758] The emotion engine uses sensors to capture the user's voice and facial expression data and analyzes their emotional state in real time. The analysis results are sent to the server and reflected in the energy schedule in the next step.

[0759] Emotion-Based Adjustment

[0760] The server adjusts the energy schedule based on the analyzed emotional data. For example, if the user is feeling stressed, it will adjust the operating time of high-power consumption devices later. Notification methods are also optimized according to the user's emotional state.

[0761] Specific examples

[0762] For example, if the user plans to do laundry the next morning, the process would be:

[0763] 1. The user inputs the desired time for using the washing machine into the terminal.

[0764] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative model to predict solar power generation.

[0765] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data and the desired usage time.

[0766] 4. The generated schedule is sent to the device, where the user can confirm it. The device then automatically starts the washing machine operation based on this schedule.

[0767] 5. The server also optimizes the timing of charging and discharging the home battery.

[0768] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0769] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[0770] 8. If the emotion engine detects stress in the user, the server will make adjustments such as delaying the operation time of the washing machine.

[0771] Through this process, the system not only optimizes the operation of high-power-consuming devices and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, thereby improving the efficiency of power use within the home and reducing energy costs.

[0772] Prompt Sentence Examples

[0773] For example, the system uses specific prompts such as, "I plan to do laundry the next morning. Therefore, please calculate the optimal washing machine operation schedule based on the predicted solar power generation amount. Also, please consider adjusting the operation time if the user feels stressed."

[0774] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0775] Step 1: Initial User Setup

[0776] The user uses the terminal to enter the following information:

[0777] High-power household appliances (e.g. washing machines, dishwashers)

[0778] Energy storage devices (e.g. home batteries)

[0779] input:

[0780] High power consumption device information

[0781] Energy Storage Device Information

[0782] output:

[0783] The terminal transmits this information to the server, which stores the received information in a database.

[0784] Specific behavior:

[0785] The user operates the terminal to enter the necessary information into the form and presses the send button to pass the information to the server, which receives the data and stores it in a database.

[0786] Step 2: Obtaining weather data

[0787] The server calls the weather API to retrieve current and future weather data.

[0788] input:

[0789] Weather API request

[0790] output:

[0791] Weather data such as temperature, sunshine hours, cloud cover, and wind speed

[0792] Specific behavior:

[0793] The server accesses the weather API, sends a request, and receives weather data in response, which is then stored locally or recorded in a database for analysis.

[0794] Step 3: Generate an energy forecasting model

[0795] The server uses a generated AI model based on the acquired weather data to predict the amount of solar power generation for the next day.

[0796] input:

[0797] Weather data

[0798] output:

[0799] Predicted solar power generation data

[0800] Specific behavior:

[0801] The server inputs the stored weather data into the generative AI model, which then calculates and predicts the amount of solar power generation for the next day. The prediction results are stored in a database.

[0802] Step 4: Scheduling high power consumers

[0803] The server calculates the optimal operating time for high-power consumption devices based on predicted solar power generation data and the user's desired usage times.

[0804] input:

[0805] Predicted solar power generation data

[0806] User's desired usage time

[0807] output:

[0808] Operation schedule for high power consumption devices

[0809] Specific behavior:

[0810] The server uses an algorithm to calculate the most efficient operating time, taking into account the user's desired time and solar power generation forecast data, and notifies the terminal of the calculation results.

[0811] Step 5: Optimizing the energy storage device

[0812] The server determines the optimal timing for charging and discharging the home battery.

[0813] input:

[0814] Solar power generation data

[0815] Residential energy consumption data

[0816] output:

[0817] Home battery charging and discharging timing

[0818] Specific behavior:

[0819] The server analyzes the solar power generation forecast data and the household's power consumption patterns to calculate the optimal timing for charging and discharging the home battery. The calculation results are sent to the terminal and instructions are sent to the home battery.

[0820] Step 6: Optimize your energy costs

[0821] Users input their electricity plan information into the device, and the server uses this information to optimize energy usage.

[0822] input:

[0823] Electricity rate plan information

[0824] output:

[0825] Optimized Energy Schedule

[0826] Specific behavior:

[0827] Users input their energy plan details via a device, and the server receives the data and stores it in a database. The server then uses this information to adjust energy usage schedules to avoid peak tariff periods.

[0828] Step 7: System Maintenance Notification

[0829] The server analyzes operational data from the solar power generation system and predicts and notifies users when maintenance is necessary.

[0830] input:

[0831] Power generation system operation data

[0832] output:

[0833] Maintenance Notification

[0834] Specific behavior:

[0835] The server periodically analyzes operational data to detect abnormalities and when maintenance is required. The detected information is notified to the terminal and displayed to the user.

[0836] Step 8: Implementing the Emotion Engine

[0837] The emotion engine acquires and analyzes the user's voice and facial expression data.

[0838] input:

[0839] Voice and facial expression data

[0840] output:

[0841] User emotional state data

[0842] Specific behavior:

[0843] The device or a dedicated device captures voice and facial expressions in real time, and the emotion engine processes the data to analyze the user's emotional state. The analysis results are then sent to a server.

[0844] Step 9: Emotional Adjustment

[0845] The server adjusts the energy schedule based on the user's emotional state.

[0846] input:

[0847] User emotional state data

[0848] output:

[0849] Adjusted Energy Schedule

[0850] Specific behavior:

[0851] The server receives the emotional state data and adjusts the operation schedule of high-power consumption devices when stress levels are high, etc. The adjusted schedule is sent to the terminal and notified to the user.

[0852] (Application example 2)

[0853] 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."

[0854] Conventional solar power generation systems mainly rely on weather data to predict power generation and schedule high-power-consuming equipment. However, these systems do not take into account the emotional state of the user, limiting their ability to optimize user experience and efficiency. Furthermore, resource management that ignores emotional aspects such as worker stress and fatigue can lead to reduced productivity and user dissatisfaction.

[0855] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring and analyzing emotion data, means for adjusting the operation schedule of the high-power consumption devices based on the emotion data, and means for changing the content and method of notification based on the emotion data. This makes it possible to flexibly adjust the operation schedule of the high-power consumption devices according to the user's emotional state, thereby improving the user experience and achieving effective energy management.

[0856] "Means for acquiring weather data" refers to a combination of hardware and software for acquiring weather data in real time. Information is collected via the weather API.

[0857] The "means for operating a generative model to predict solar power generation" refers to algorithms and software for predicting solar power generation for the next day based on acquired weather data. A generative AI model is used.

[0858] The "means for scheduling the operation of high-power consuming devices" refers to scheduling algorithms and software for optimizing the operation time of high-power consuming devices based on the predicted amount of solar power generation.

[0859] The "means for determining the optimal timing for charging and discharging the energy storage device" refers to algorithms and software for optimally timing the charging and discharging of the home battery.

[0860] The "means for notifying the optimized energy schedule" refers to an interface and software for notifying the user of the scheduling results. A device such as a smartphone or tablet is used.

[0861] The "means for acquiring and analyzing emotional data" refers to an emotion recognition engine and software for acquiring and analyzing emotional data such as the user's voice and facial expressions in real time.

[0862] The "means for adjusting the operation schedule of high-power-consuming devices based on emotional data" refers to algorithms and software for adjusting the operation schedule of high-power-consuming devices in accordance with the user's emotional state based on the acquired emotional data.

[0863] The "means for changing the notification content and method based on emotional data" refers to algorithms and software for optimizing the notification content and method according to the user's emotional state.

[0864] The "means for inputting an electricity rate plan" refers to an interface and software that allows a user to input their electricity rate plan information into the system.

[0865] The "means for optimizing energy usage by avoiding peak power hours based on an electricity rate plan" refers to algorithms and software for optimizing energy usage by avoiding peak power hours based on input electricity rate plan information.

[0866] The "means for predicting and notifying the timing of necessary maintenance of an energy generating device" refers to an algorithm and software for analyzing operational data of the energy generating device, predicting the timing of necessary maintenance, and notifying the timing.

[0867] The system for implementing the present invention aims to improve the efficiency of energy management in homes and factories, and also takes into account the emotional state of the user. The detailed configuration and operation of this system will be described below.

[0868] Initial Setup

[0869] First, a user uses a terminal to input information about high-power-consuming devices (e.g., washing machines, welding robots) and energy storage devices (e.g., home batteries, factory batteries) in their homes or factories. This information includes the amount of power consumed by each device and the desired operating time.

[0870] Obtaining weather data

[0871] The server then uses a weather API (e.g., OpenWeatherMap API) to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to forecast solar power generation.

[0872] Generate an energy forecasting model

[0873] The server runs a generative AI model (e.g., TensorFlow, PyTorch) based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to operate power usage and storage devices in homes and factories.

[0874] Scheduling high power consumers

[0875] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[0876] Energy storage device optimization

[0877] The server calculates the optimal charging and discharging timing for the home or factory battery, allowing users to avoid peak energy consumption times and utilize power during periods of high power generation. Operation instructions are sent to the energy storage device via the terminal.

[0878] Optimizing power costs

[0879] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0880] System maintenance notification

[0881] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. As soon as the necessary maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[0882] Introducing the Emotion Engine

[0883] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[0884] Emotion-based scheduling and notification optimization

[0885] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of high-power devices. It also optimizes notification methods (e.g., app notifications in a gentler tone) according to the user's emotional state.

[0886] Specific examples

[0887] If the user plans to do laundry the next morning, the system works as follows:

[0888] 1. The user inputs the desired time for using the washing machine into the terminal.

[0889] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[0890] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0891] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0892] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0893] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0894] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[0895] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[0896] Prompt Sentence Examples

[0897] "Design an application that uses a generative AI model to generate an operation schedule to maximize the use of solar power generation in a factory for the next day. Acquire and integrate weather data (e.g., sunshine hours, wind speed). Calculate the optimal operation time for high-power consuming equipment in the factory and notify the user. Analyze the emotional state of workers using an emotion recognition engine and adjust the operation schedule if stress is detected. Calculate the optimal timing for charging and discharging the factory battery."

[0898] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0899] Step 1:

[0900] Users use a terminal to input information about high-power-consuming devices and energy storage devices in their homes or factories, including the amount of power each device consumes and the desired operating time. This input data is then stored in a database on the server.

[0901] Step 2:

[0902] The server uses a weather API (e.g., OpenWeatherMap API) to obtain current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is the basis for solar power generation forecasts. The obtained weather data is stored and processed within the server.

[0903] Step 3:

[0904] The server uses a generative AI model (e.g., TensorFlow, PyTorch) based on the stored weather data to predict the amount of solar power generation for the next day. The input data is the weather data, and the output data is the predicted amount of solar power generation. This forecast data is used for energy management.

[0905] Step 4:

[0906] The server calculates the optimal operation schedule for high-power consumption devices based on the acquired information on the devices and the predicted solar power generation data. For example, to minimize power consumption, it sets the devices to operate during the hours with the longest sunshine. This calculation is performed using an algorithm and output in the form of an operation schedule.

[0907] Step 5:

[0908] The server calculates the optimal charging and discharging timing for a home or industrial energy storage device. The input data is the predicted power generation and consumption pattern, and the output data is the optimal charging and discharging schedule. This schedule allows avoiding peak energy consumption.

[0909] Step 6:

[0910] Users input their electricity plan information using a terminal. This information is sent to the server and stored. The plan information is used to optimize energy schedules to avoid peak hours.

[0911] Step 7:

[0912] The server generates a schedule to optimize energy usage based on the input electricity rate plan. This calculation uses an algorithm to avoid peak hours. The output data is the optimized energy schedule.

[0913] Step 8:

[0914] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. It calculates the necessary maintenance timing and notifies the terminal. The input data is the operational data of the equipment, and the output data is the appropriate maintenance notification.

[0915] Step 9:

[0916] The emotion engine analyzes the user's voice and facial expression data sent from the device in real time to identify the user's current emotional state. The acquired emotional data is sent to the server for analysis. The input data is voice and facial expression data, and the output data is the user's emotional state.

[0917] Step 10:

[0918] The server adjusts the operation schedule based on the emotional data. For example, if the user is feeling stressed, the server can change the operation time of high-power consumption devices. The input data are the emotional state and the existing operation schedule, and the output data is the adjusted operation schedule.

[0919] Step 11:

[0920] The server adjusts the notification content and method based on the emotional data. For example, if the user feels like relaxing, the server may adjust the tone of the notification. The input data is the emotional state and existing notification settings, and the output data is the adjusted notification content.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] [Third embodiment]

[0925] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0926] 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.

[0927] 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).

[0928] 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.

[0929] 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.

[0930] 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).

[0931] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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."

[0937] An embodiment of the present invention will be described in detail below. This system performs energy prediction and management to make the most efficient use of solar power generated in an ordinary home, and is composed of the following steps.

[0938] 1. User Initial Settings

[0939] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[0940] 2. Obtaining weather data

[0941] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[0942] 3. Generating an energy prediction model

[0943] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[0944] 4. Scheduling of high-power devices

[0945] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. An operation schedule is generated and notified to the device. The device then operates the target devices according to this schedule.

[0946] 5. Optimization of Energy Storage Devices

[0947] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[0948] 6. Optimizing electricity costs

[0949] Users input their electricity rate plan information into the terminal, and the server adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0950] 7. System Maintenance Notification

[0951] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance period is predicted, a notification is sent to the terminal. The user follows the notification and performs appropriate maintenance to ensure the long-term stable operation of the system.

[0952] Specific examples

[0953] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[0954] 1. The user inputs the desired time for using the washing machine into the terminal.

[0955] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[0956] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[0957] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[0958] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[0959] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[0960] This optimizes the operation of the washing machine using solar power, reducing energy costs and improving the efficiency of electricity use within the home.

[0961] The processing flow will be explained below.

[0962] Step 1:

[0963] The user inputs information about the high-power appliances and energy storage devices in the home into the terminal. For example, the user registers the model name and planned usage time of a washing machine or dishwasher. The terminal then transmits this information to the server.

[0964] Step 2:

[0965] The server sends a request to the weather API to retrieve weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes the retrieved weather data and stores it in a database.

[0966] Step 3:

[0967] The server inputs the acquired weather data into a generative model to predict the amount of solar power generation for the next day. The generative model makes highly accurate predictions based on past data and acquired weather data. These prediction results are used for energy management.

[0968] Step 4:

[0969] The server calculates the optimal operating times for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. Taking into account the desired usage times input by the user, the server determines the most efficient time slots within that range. An operating schedule is generated.

[0970] Step 5:

[0971] The server notifies the terminal of the generated operation schedule. The terminal displays the operation schedule to the user and asks for confirmation. The terminal automatically starts operation of the equipment according to the scheduled time.

[0972] Step 6:

[0973] The server calculates the optimal charging and discharging timing for the energy storage device (e.g., a home battery). It sets it to supply power during times when power generation is high and to store power during times when power generation is low. This setting is sent to the home battery via the terminal.

[0974] Step 7:

[0975] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[0976] Step 8:

[0977] The server analyzes the equipment's operational data and past failure data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal then displays the maintenance timing to the user.

[0978] Step 9:

[0979] Once all data and settings are collected, the system will automatically begin operation and optimize the operation of high-power consumption appliances and energy storage devices based on predicted solar power generation, enabling users to achieve more efficient energy use in their homes and reduce energy costs.

[0980] Example 1

[0981] 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."

[0982] As the adoption of solar power generation systems in general households increases, there is a need to maximize their power generation efficiency while optimizing power consumption. However, current systems lack the means to accurately predict solar power generation amounts by fully utilizing weather data, and the use of high-power-consuming devices and management of energy storage devices are not effectively carried out. Furthermore, they are not adequately able to optimize energy costs according to electricity rate plans. Furthermore, they lack the functionality to predict and notify when power generation systems need maintenance. This results in a decrease in the efficiency of power usage within the home, making it difficult to reduce energy costs.

[0983] 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.

[0984] In this invention, the server includes means for a user to input information about high-power consumption devices and energy storage devices in the home, means for acquiring weather data, means for operating a generative AI model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining optimal timing for charging and discharging the energy storage device, and means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption. This improves the accuracy of solar power generation predictions, enables efficient management of high-power consumption devices and energy storage devices, and enables improved efficiency of home power utilization and reduced energy costs.

[0985] "User" refers to an individual or household that uses the system.

[0986] "High-power household appliances" refers to household appliances such as washing machines and dishwashers that consume large amounts of electricity at once.

[0987] An "energy storage device" is a device that temporarily stores electricity generated within the home and supplies it when needed. A specific example is a home battery.

[0988] "Terminal" means an electronic device used by a user to enter information and receive information from a system. Examples include a smartphone or tablet.

[0989] "Server" refers to the computer system that manages the entire system and processes data and runs predictive models.

[0990] "Weather data" refers to data relating to weather conditions, such as temperature, hours of sunshine, cloud cover, and wind speed.

[0991] "Weather API" refers to a programmatic interface used to obtain weather data. An example is the OpenWeatherMap API.

[0992] A "generative AI model" refers to an artificial intelligence model that makes predictions and classifications based on acquired data. A specific example is a predictive model using TensorFlow.

[0993] "Scheduling" refers to planning and setting the operating times and timing of specific equipment based on predictive data.

[0994] "Optimization" refers to adjusting resource allocation and scheduling to maximize energy efficiency or minimize costs.

[0995] An "energy schedule" refers to a schedule that includes the operation plans of household appliances and energy storage devices.

[0996] "Electricity rate plan" means an electricity payment plan that a consumer enters into with an electricity supplier. Examples include flat-rate plans and time-of-use plans.

[0997] "Maintenance timing" refers to the specific timing when maintenance of a system or equipment is required.

[0998] This invention is a system for energy prediction and management to make the most efficient use of solar power generated in an average household, and operates in cooperation with the server, terminal, and user elements.

[0999] System Overview

[1000] User Preferences

[1001] The user launches a dedicated application using the device. From the settings screen within the application, they enter information about high-power consumption devices in the home (e.g., washing machine, dishwasher) and energy storage devices (e.g., home battery). Once this information is saved, the device sends it to the server. The server stores the received information in a database.

[1002] Obtaining weather data

[1003] The server periodically calls a weather API (e.g., OpenWeatherMap API) to obtain weather data (e.g., temperature, sunshine hours, cloud cover, wind speed), which is then stored in a database within the system.

[1004] Generate an energy forecasting model

[1005] The server runs a generative AI model (for example, a forecasting model using TensorFlow) based on the stored weather data to predict the amount of solar power generation for the next day. The forecast results are stored in a database.

[1006] Scheduling high power consumers

[1007] The user inputs the desired usage time of a high-power consumption device (e.g., a washing machine) on the device. The device then sends the desired usage time data to the server. The server calculates the optimal operation time for the high-power consumption device based on the predicted solar power generation data and the desired usage time, and generates an operation schedule. The generated schedule is notified to the device, which automatically starts operation of the device at the set time.

[1008] Energy storage device optimization

[1009] The server calculates the timing of charging and discharging the home battery based on the predicted power generation data. For example, it sets a schedule to charge at night (when power demand is low) and discharge in the morning when power generation is low. The calculation results are sent to the terminal, and instructions are sent to the home battery through the terminal.

[1010] Optimizing power costs

[1011] Users input their electricity plan information (e.g., flat-rate plan, time-of-use plan) into the device and send it to the server, which then runs an algorithm to optimize energy usage based on the plan and reschedules each device to avoid peak power hours.

[1012] System maintenance notification

[1013] The server analyzes the operational data of the home's solar power generation system and predicts when maintenance is required. The prediction results are sent to the terminal and displayed to the user. The user can then follow the notification to arrange for appropriate maintenance work.

[1014] Specific examples

[1015] For example, the process when the laundry is scheduled to be done in the morning of the next day will be described.

[1016] 1. The user inputs the desired time for using the washing machine into the terminal.

[1017] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[1018] 3. The server calculates the optimal time to run the washing machine based on the predicted power generation data. For example, it determines that the best time is between 2:00 PM and 4:00 PM, when the sunshine hours are the longest.

[1019] 4. The schedule is sent to the device, and the user confirms it. The device automatically starts the washing machine at the specified time.

[1020] 5. The server optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1021] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1022] Prompt Sentence Examples

[1023] "Based on the weather forecast for the next day obtained using a weather API, please predict the amount of solar power generation in the home for the next day and generate an optimal operation schedule for the washing machine, which is a high-power-consuming device. In this case, please create a schedule to operate the washing machine during the time period when power generation is highest."

[1024] This invention improves the efficiency of solar power generation in homes, reducing energy costs and realizing sustainable energy use.

[1025] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1026] Step 1: Initial User Setup

[1027] Input: The user inputs information about high-power consumption appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the home into the terminal.

[1028] Data processing / data calculation: The terminal formats the input information into a database and creates a data set that includes information set by the user (device manufacturer, model number, power consumption, etc.).

[1029] Output: The terminal sends the formatted data to the server.

[1030] Specific operation: The user opens the dedicated application, enters information about the home appliance and energy storage device on the settings screen, and presses the save button. The device then sends the information to the server.

[1031] Step 2: Obtaining weather data

[1032] Input: The server sends a request to the weather API.

[1033] Data processing / data calculation: As a response from the weather API, the server receives weather data such as temperature, sunshine hours, cloud cover, wind speed, etc. The server converts this data into an appropriate format and stores it in the database.

[1034] Output: Weather data is stored in a database on the server.

[1035] Specific operation: The server periodically accesses a weather API (e.g., OpenWeatherMap API) to obtain the necessary weather data.

[1036] Step 3: Generate an energy forecasting model

[1037] Input: The server retrieves the stored weather data.

[1038] Data processing / data calculation: A generative AI model (such as TensorFlow) is used to predict the amount of solar power generated for the next day. The model is input with training data and calculated to output the future amount of power generated.

[1039] Output: The predicted solar power generation data is stored in a database on the server.

[1040] How it works: The server retrieves weather data, uses a generative AI model to predict the next day's power generation, and stores the results.

[1041] Step 4: Scheduling high power consumers

[1042] Input: The user inputs the desired time for using the device into the terminal, and the desired time is sent from the terminal to the server. The server obtains the predicted power generation data.

[1043] Data processing / data calculation: The server compares the user's desired time with the predicted power generation amount and executes an algorithm to calculate the optimal operating time. It selects the time period with the longest sunshine hours and creates a schedule.

[1044] Output: The operation schedule is sent from the server to the terminal.

[1045] Specific operation: The user inputs the desired usage time into the application, and the server creates an optimal operation schedule based on that time period and notifies the device. The device then automatically starts operating the device according to that schedule.

[1046] Step 5: Optimizing the energy storage device

[1047] Input: The server retrieves the predicted energy yield data.

[1048] Data processing / data calculation: The server calculates the optimal charging and discharging timing based on the amount of electricity stored in the home battery and the predicted amount of power generation. For example, it calculates a schedule to charge electricity at night and discharge it in the morning.

[1049] Output: The optimized charging and discharging schedule is sent to the terminal, which then instructs the home battery.

[1050] Specific operation: The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal.

[1051] Step 6: Optimize your energy costs

[1052] Input: The user inputs the electricity rate plan into the device. The plan information is sent from the device to the server.

[1053] Data processing / data calculation: The server runs an algorithm to optimize energy usage based on the input electricity rate plan, for example concentrating operation during times when rates are low.

[1054] Output: The optimized schedule is sent to the terminal.

[1055] Specific operation: The user inputs an electricity rate plan, and the server readjusts the schedule based on that plan and notifies the terminal.

[1056] Step 7: System Maintenance Notification

[1057] Input: The server acquires operational data of the home solar power generation system.

[1058] Data processing / data calculation: The server analyzes operational data and runs algorithms to predict when maintenance will be required.

[1059] Output: The terminal is notified when maintenance is required.

[1060] Specific operation: The server predicts the need for maintenance based on operational data and notifies the user via the terminal.

[1061] (Application example 1)

[1062] 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."

[1063] Modern energy management systems aim to efficiently utilize solar power generation in homes and commercial facilities, but they currently have difficulty adapting to the efficient operation of high-power consumption equipment and production robots, which consume large amounts of energy in factories. Therefore, there is a need for systems that can optimize energy consumption throughout the factory and improve productivity. There is also a need for systems that can develop optimal operation schedules based on electricity rate plans and predict and notify maintenance timing.

[1064] 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.

[1065] In this invention, the server includes means for acquiring weather data, means for running a generative model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining the optimal timing for charging and discharging an energy storage device, means for generating and executing an operation schedule for optimizing the operation of an energy robot, and means for notifying the optimized energy schedule based on the predicted solar power generation and energy consumption. This makes it possible to optimize the operation of high-power consumption devices and robots in a factory to match solar power generation, thereby improving production efficiency while reducing energy costs.

[1066] "Means for obtaining weather data" means means for collecting current and future weather data using the weather API.

[1067] "Means for operating a generative model that predicts solar power generation" refers to means for running a generative AI model to predict the amount of solar power generation for the next day based on acquired weather data.

[1068] The "means for scheduling the operation of high-power consuming devices" is a means for calculating the optimal operation time of high-power consuming devices based on the predicted amount of solar power generation, and generating an operation schedule.

[1069] The "means for determining the optimal timing for charging and discharging the energy storage device" is a means for calculating the optimal timing for charging and discharging the home battery and transmitting operation instructions.

[1070] The "means for generating and executing an operation schedule for optimizing the operation of an energy robot" refers to a means for optimizing the operation schedule of the robot based on predicted solar power generation and energy consumption, and for operating the robot according to that schedule.

[1071] The "means for notifying an optimized energy schedule" is a means for notifying a user terminal of an energy schedule generated based on predicted solar power generation and energy consumption.

[1072] This invention is a system for managing energy in factories and optimizing the operation schedule of high-power-consuming equipment. This system collects weather data and uses it to predict solar power generation, enabling efficient energy use.

[1073] The server uses a weather API to obtain weather data, including temperature, sunshine hours, cloud cover, and wind speed, and runs a generative AI model based on this data to predict the amount of solar power generation for the next day.

[1074] Based on the predicted solar power generation, the server schedules the operation of high-power-consuming equipment in the factory, such as welding machines and processing machines. It calculates the optimal operating times and generates a schedule. Once the schedule is determined, the server notifies the terminal, and the terminal operates the high-power-consuming equipment.

[1075] In addition, the timing of charging and discharging energy storage devices (such as home batteries) is optimized to avoid peak energy consumption times and ensure that electricity is available during times when solar power generation is strongest.

[1076] Additionally, users can input their own electricity rate plan information into the device, and the server uses this information to avoid peak power hours and optimize energy usage, enabling efficient use of electricity while reducing energy costs.

[1077] The system consists of software for scheduling using the Python schedule library and for acquiring weather data using the Weather API. The factory's production robots and processing machines are linked to a networked environmental control system.

[1078] As a specific example, when optimizing the operation of a welding machine, the operation can be performed at the following timing: For example, the operation of the welding machine can be set from 2:00 PM to 4:00 PM based on weather data forecasts. Also, to avoid peak hours of energy consumption, the start of the welding machine can be scheduled during off-peak hours, achieving efficient energy consumption.

[1079] An example of a prompt sentence is, "Based on tomorrow's weather forecast, what is the optimal operating time for the welding machine?"

[1080] In this way, the energy prediction and management technology of the invention can be applied to the efficient operation of factory robots, thereby reducing energy consumption and improving productivity.

[1081] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1082] Step 1:

[1083] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc., which is then used in subsequent forecasting models.

[1084] Input: Weather data request from the weather API

[1085] Data processing / calculation: weather data collection and filtering

[1086] Output: Weather data (temperature, sunshine hours, cloud cover, wind speed)

[1087] Step 2:

[1088] The server runs a prediction model (generative AI model) to predict the amount of solar power generation for the next day based on the acquired weather data. This model takes weather data as input and outputs the amount of power generation as a numerical value.

[1089] Input: Weather data

[1090] Data processing / calculation: Predicting power generation using weather data

[1091] Output: Predicted solar power generation (numerical data)

[1092] Step 3:

[1093] The server calculates the optimal operating time for high-power-consuming devices based on the predicted solar power generation amount and the user's desired usage time, and generates an operating schedule, which is then notified to the terminal.

[1094] Input: Forecasted solar power generation, desired usage time of the user

[1095] Data processing / calculation: Calculation of optimal driving time

[1096] Output: Schedule high-power consumption devices

[1097] Step 4:

[1098] The terminal operates the high-power consumption devices according to the operation schedule received from the server. The operation of the devices starts automatically and ends at the scheduled time.

[1099] Input: Operation schedule of high power consumption devices

[1100] Data processing / calculation: Issuing operation instructions for equipment

[1101] Output: Operating high-power devices

[1102] Step 5:

[1103] The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal, thereby optimizing the charging and discharging timing.

[1104] Input: Forecasted solar power generation, current energy storage status

[1105] Data processing / calculation: Optimization calculation of charge and discharge timing

[1106] Output: Charge and discharge timing instructions

[1107] Step 6:

[1108] Users input their electricity rate plan information into the device, and that information is sent to the server, which then optimizes energy usage and adjusts the schedule based on the plan.

[1109] Input: User's electricity plan

[1110] Data processing / calculation: Energy usage optimization based on electricity rate plans

[1111] Output: Adjusted energy schedule

[1112] Step 7:

[1113] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. The predicted timing is notified to the user via the terminal, and the user can then carry out the appropriate maintenance.

[1114] Input: Solar power system operation data

[1115] Data processing / calculation: Maintenance timing prediction

[1116] Output: Maintenance notification

[1117] 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.

[1118] The present invention will be described in detail below with reference to an embodiment thereof. This system performs energy forecasting and management for the most efficient use of solar power in a typical household, and also combines it with an emotion engine that recognizes the user's emotions.

[1119] 1. User Initial Settings

[1120] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[1121] 2. Obtaining weather data

[1122] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[1123] 3. Generating an energy prediction model

[1124] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[1125] 4. Scheduling of high-power devices

[1126] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[1127] 5. Optimization of Energy Storage Devices

[1128] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[1129] 6. Optimizing electricity costs

[1130] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1131] 7. System Maintenance Notification

[1132] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[1133] 8. Introducing the Emotion Engine

[1134] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[1135] 9. Emotion-based scheduling and notification optimization

[1136] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of energy-intensive appliances. It also optimizes notification methods based on the user's emotional state (for example, app notifications in a gentler tone).

[1137] Specific examples

[1138] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[1139] 1. The user inputs the desired time for using the washing machine into the terminal.

[1140] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[1141] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[1142] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[1143] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1144] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1145] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[1146] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[1147] In this way, the system not only optimizes the operation of high-power-consuming appliances and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, resulting in more efficient energy use within the home and reduced energy costs.

[1148] The processing flow will be explained below.

[1149] Step 1:

[1150] A user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the terminal. The terminal then transmits the input information to the server.

[1151] Step 2:

[1152] The server sends a request to the weather API to get weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes this data and stores it in a database.

[1153] Step 3:

[1154] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The generative model makes predictions based on past data and acquired weather data. The results of this prediction are used for energy management.

[1155] Step 4:

[1156] The server calculates the optimal operating time for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. It also takes into account the desired usage times entered by the user and determines the most efficient time period within that range. The server generates an operating schedule and sends it to the terminal.

[1157] Step 5:

[1158] The terminal notifies the user of the operation schedule received from the server. The user checks the schedule and either approves it or requests a revision. After receiving the user's confirmation, the terminal automatically starts operating the equipment according to the operation schedule.

[1159] Step 6:

[1160] The server calculates the optimal charging and discharging timing for the home battery. This allows the battery to be charged during times when power generation is high and discharged during times when power generation is low. The server then sends these operation instructions to the terminal. The terminal then operates the home battery based on the received instructions.

[1161] Step 7:

[1162] Users input their electricity rate plan information into their device, which then sends this information to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1163] Step 8:

[1164] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal displays the notification content to the user and suggests appropriate maintenance.

[1165] Step 9:

[1166] When the emotion engine is installed, the device analyzes the user's voice and facial expression data in real time to determine their current emotional state. For example, if the user is feeling stressed, that information is sent to the server.

[1167] Step 10:

[1168] The server can adjust the schedule based on the user's emotional state. For example, if the user is feeling stressed, the server can delay the operation of the washing machine. The server can also optimize notification methods (such as the tone and content of notification sounds) according to the user's emotions.

[1169] For example, if the emotion engine detects that the user is feeling stressed the next morning, the server can adjust the washing machine's operating time to the afternoon to reduce the user's stress, optimizing energy efficiency while taking into account the user's emotional state.

[1170] Example 2

[1171] 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."

[1172] There is a need to maximize the efficiency of solar power generation in ordinary households. However, predicting power generation based on weather data and creating an optimal operation schedule for high-power-consuming devices linked to that forecast are complex, and adjusting the timing of charging and discharging energy storage devices is not easy. Furthermore, there is no established method for reducing electricity costs while optimizing energy use by taking into account the user's emotional state. Therefore, a system that can solve these multiple challenges in an integrated manner is needed.

[1173] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1174] In this invention, the server includes a means for inputting information about household electrical appliances, a means for acquiring weather data, a means for running a generative model that predicts solar power generation based on the acquired weather data, a means for scheduling the operation of high-power consumption appliances based on the predicted solar power generation, a means for determining optimal timing for charging and discharging an energy storage device, a means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption, a means for acquiring and analyzing emotion data, and a means for adjusting the energy schedule based on the analyzed emotion data. This enables flexible energy scheduling that takes into account the user's emotional state while maximizing the utilization efficiency of solar power generation in the home. It also reduces energy costs and improves energy management throughout the home.

[1175] "Means for inputting information about household electrical appliances" refers to an interface or device that allows a user to input information about high-power consumption appliances and energy storage devices in the home into a terminal.

[1176] "Means of obtaining weather data" refers to the function for obtaining weather forecasts and current conditions data from online weather APIs, etc.

[1177] "Means for operating the generative model" refers to software or algorithms that operate an AI-based predictive model based on acquired weather data and estimate the amount of solar power generated the following day.

[1178] "Means for scheduling the operation of high-power-consuming devices" refers to a system that calculates the optimal operating times of high-power-consuming devices such as washing machines and dishwashers based on predicted power generation data and the user's desired usage times, and generates a schedule.

[1179] "Means for determining the optimal timing for charging and discharging an energy storage device" refers to a function that calculates the most efficient timing for charging and discharging an energy storage device such as a home battery.

[1180] The "means for notifying the optimized energy schedule" refers to a notification system for notifying the user of the calculated optimal energy schedule. Specifically, it includes a function for displaying the schedule through a terminal.

[1181] "Means for acquiring and analyzing emotional data" refers to sensors and analytical algorithms for acquiring and analyzing emotional data such as the user's voice and facial expressions to identify their current emotional state.

[1182] "Means for adjusting energy schedules based on emotional data" refers to a system for modifying and adjusting energy schedules based on the analyzed emotional state of a user, including actions such as delaying the operation of high-power consumption devices when stress levels are high.

[1183] This invention relates to an energy forecasting and management system for the most efficient use of solar power in homes. The system is further enhanced in flexibility and adaptability by incorporating an emotion engine that recognizes the user's emotions.

[1184] System Overview

[1185] The system consists of the following major hardware and software components:

[1186] server

[1187] Terminal (device operated by the user)

[1188] High-power consumption appliances (e.g. washing machines, dishwashers, etc.)

[1189] Energy storage devices (e.g. home batteries)

[1190] Weather API (to retrieve weather data)

[1191] Generative AI models (to predict solar power generation)

[1192] Emotion engine (to recognize and analyze user emotions)

[1193] Initial Setup

[1194] First, a user inputs information about high-power consumption appliances and energy storage devices in the home using a terminal, which is then sent to a server and stored in a database.

[1195] Obtaining weather data

[1196] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to predict solar power generation.

[1197] Energy Forecast

[1198] Based on the acquired weather data, the server runs a generative AI model to predict the amount of solar power generation for the next day. The prediction results are stored in a database and used in the next step to plan the operation of high-power consumption equipment and energy storage devices.

[1199] Scheduling

[1200] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the desired usage times set by the user. The calculated schedule is notified to the device and displayed to the user. The device can also automatically operate the devices according to this schedule.

[1201] Energy storage device optimization

[1202] The server calculates the optimal charging and discharging timing for the home battery, allowing users to avoid peak energy consumption times and use electricity during times when power generation is high. These operation instructions are sent to the home battery via the terminal.

[1203] Optimizing power costs

[1204] Users input their electricity plan information into their device. This information is sent to the server, which then optimizes energy usage based on the plan and adjusts the schedule to avoid peak power hours.

[1205] System maintenance notification

[1206] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. When the maintenance period approaches, the server sends a notification to the terminal and displays it to the user.

[1207] Introducing the Emotion Engine

[1208] The emotion engine uses sensors to capture the user's voice and facial expression data and analyzes their emotional state in real time. The analysis results are sent to the server and reflected in the energy schedule in the next step.

[1209] Emotion-Based Adjustment

[1210] The server adjusts the energy schedule based on the analyzed emotional data. For example, if the user is feeling stressed, it will adjust the operating time of high-power consumption devices later. Notification methods are also optimized according to the user's emotional state.

[1211] Specific examples

[1212] For example, if the user plans to do laundry the next morning, the process would be:

[1213] 1. The user inputs the desired time for using the washing machine into the terminal.

[1214] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative model to predict solar power generation.

[1215] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data and the desired usage time.

[1216] 4. The generated schedule is sent to the device, where the user can confirm it. The device then automatically starts the washing machine operation based on this schedule.

[1217] 5. The server also optimizes the timing of charging and discharging the home battery.

[1218] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1219] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[1220] 8. If the emotion engine detects stress in the user, the server will make adjustments such as delaying the operation time of the washing machine.

[1221] Through this process, the system not only optimizes the operation of high-power-consuming devices and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, thereby improving the efficiency of power use within the home and reducing energy costs.

[1222] Prompt Sentence Examples

[1223] For example, the system uses specific prompts such as, "I plan to do laundry the next morning. Therefore, please calculate the optimal washing machine operation schedule based on the predicted solar power generation amount. Also, please consider adjusting the operation time if the user feels stressed."

[1224] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1225] Step 1: Initial User Setup

[1226] The user uses the terminal to enter the following information:

[1227] High-power household appliances (e.g. washing machines, dishwashers)

[1228] Energy storage devices (e.g. home batteries)

[1229] input:

[1230] High power consumption device information

[1231] Energy Storage Device Information

[1232] output:

[1233] The terminal transmits this information to the server, which stores the received information in a database.

[1234] Specific behavior:

[1235] The user operates the terminal to enter the necessary information into the form and presses the send button to pass the information to the server, which receives the data and stores it in a database.

[1236] Step 2: Obtaining weather data

[1237] The server calls the weather API to retrieve current and future weather data.

[1238] input:

[1239] Weather API request

[1240] output:

[1241] Weather data such as temperature, sunshine hours, cloud cover, and wind speed

[1242] Specific behavior:

[1243] The server accesses the weather API, sends a request, and receives weather data in response, which is then stored locally or recorded in a database for analysis.

[1244] Step 3: Generate an energy forecasting model

[1245] The server uses a generated AI model based on the acquired weather data to predict the amount of solar power generation for the next day.

[1246] input:

[1247] Weather data

[1248] output:

[1249] Predicted solar power generation data

[1250] Specific behavior:

[1251] The server inputs the stored weather data into the generative AI model, which then calculates and predicts the amount of solar power generation for the next day. The prediction results are stored in a database.

[1252] Step 4: Scheduling high power consumers

[1253] The server calculates the optimal operating time for high-power consumption devices based on predicted solar power generation data and the user's desired usage times.

[1254] input:

[1255] Predicted solar power generation data

[1256] User's desired usage time

[1257] output:

[1258] Operation schedule for high power consumption devices

[1259] Specific behavior:

[1260] The server uses an algorithm to calculate the most efficient operating time, taking into account the user's desired time and solar power generation forecast data, and notifies the terminal of the calculation results.

[1261] Step 5: Optimizing the energy storage device

[1262] The server determines the optimal timing for charging and discharging the home battery.

[1263] input:

[1264] Solar power generation data

[1265] Residential energy consumption data

[1266] output:

[1267] Home battery charging and discharging timing

[1268] Specific behavior:

[1269] The server analyzes the solar power generation forecast data and the household's power consumption patterns to calculate the optimal timing for charging and discharging the home battery. The calculation results are sent to the terminal and instructions are sent to the home battery.

[1270] Step 6: Optimize your energy costs

[1271] Users input their electricity plan information into the device, and the server uses this information to optimize energy usage.

[1272] input:

[1273] Electricity rate plan information

[1274] output:

[1275] Optimized Energy Schedule

[1276] Specific behavior:

[1277] Users input their energy plan details via a device, and the server receives the data and stores it in a database. The server then uses this information to adjust energy usage schedules to avoid peak tariff periods.

[1278] Step 7: System Maintenance Notification

[1279] The server analyzes operational data from the solar power generation system and predicts and notifies users when maintenance is necessary.

[1280] input:

[1281] Power generation system operation data

[1282] output:

[1283] Maintenance Notification

[1284] Specific behavior:

[1285] The server periodically analyzes operational data to detect abnormalities and when maintenance is required. The detected information is notified to the terminal and displayed to the user.

[1286] Step 8: Implementing the Emotion Engine

[1287] The emotion engine acquires and analyzes the user's voice and facial expression data.

[1288] input:

[1289] Voice and facial expression data

[1290] output:

[1291] User emotional state data

[1292] Specific behavior:

[1293] The device or a dedicated device captures voice and facial expressions in real time, and the emotion engine processes the data to analyze the user's emotional state. The analysis results are then sent to a server.

[1294] Step 9: Emotional Adjustment

[1295] The server adjusts the energy schedule based on the user's emotional state.

[1296] input:

[1297] User emotional state data

[1298] output:

[1299] Adjusted Energy Schedule

[1300] Specific behavior:

[1301] The server receives the emotional state data and adjusts the operation schedule of high-power consumption devices when stress levels are high, etc. The adjusted schedule is sent to the terminal and notified to the user.

[1302] (Application example 2)

[1303] 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."

[1304] Conventional solar power generation systems mainly rely on weather data to predict power generation and schedule high-power-consuming equipment. However, these systems do not take into account the emotional state of the user, limiting their ability to optimize user experience and efficiency. Furthermore, resource management that ignores emotional aspects such as worker stress and fatigue can lead to reduced productivity and user dissatisfaction.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring and analyzing emotion data, means for adjusting the operation schedule of the high-power consumption devices based on the emotion data, and means for changing the content and method of notification based on the emotion data. This makes it possible to flexibly adjust the operation schedule of the high-power consumption devices according to the user's emotional state, thereby improving the user experience and achieving effective energy management.

[1306] "Means for acquiring weather data" refers to a combination of hardware and software for acquiring weather data in real time. Information is collected via the weather API.

[1307] The "means for operating a generative model to predict solar power generation" refers to algorithms and software for predicting solar power generation for the next day based on acquired weather data. A generative AI model is used.

[1308] The "means for scheduling the operation of high-power consuming devices" refers to scheduling algorithms and software for optimizing the operation time of high-power consuming devices based on the predicted amount of solar power generation.

[1309] The "means for determining the optimal timing for charging and discharging the energy storage device" refers to algorithms and software for optimally timing the charging and discharging of the home battery.

[1310] The "means for notifying the optimized energy schedule" refers to an interface and software for notifying the user of the scheduling results. A device such as a smartphone or tablet is used.

[1311] The "means for acquiring and analyzing emotional data" refers to an emotion recognition engine and software for acquiring and analyzing emotional data such as the user's voice and facial expressions in real time.

[1312] The "means for adjusting the operation schedule of high-power-consuming devices based on emotional data" refers to algorithms and software for adjusting the operation schedule of high-power-consuming devices in accordance with the user's emotional state based on the acquired emotional data.

[1313] The "means for changing the notification content and method based on emotional data" refers to algorithms and software for optimizing the notification content and method according to the user's emotional state.

[1314] The "means for inputting an electricity rate plan" refers to an interface and software that allows a user to input their electricity rate plan information into the system.

[1315] The "means for optimizing energy usage by avoiding peak power hours based on an electricity rate plan" refers to algorithms and software for optimizing energy usage by avoiding peak power hours based on input electricity rate plan information.

[1316] The "means for predicting and notifying the timing of necessary maintenance of an energy generating device" refers to an algorithm and software for analyzing operational data of the energy generating device, predicting the timing of necessary maintenance, and notifying the timing.

[1317] The system for implementing the present invention aims to improve the efficiency of energy management in homes and factories, and also takes into account the emotional state of the user. The detailed configuration and operation of this system will be described below.

[1318] Initial Setup

[1319] First, a user uses a terminal to input information about high-power-consuming devices (e.g., washing machines, welding robots) and energy storage devices (e.g., home batteries, factory batteries) in their homes or factories. This information includes the amount of power consumed by each device and the desired operating time.

[1320] Obtaining weather data

[1321] The server then uses a weather API (e.g., OpenWeatherMap API) to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to forecast solar power generation.

[1322] Generate an energy forecasting model

[1323] The server runs a generative AI model (e.g., TensorFlow, PyTorch) based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to operate power usage and storage devices in homes and factories.

[1324] Scheduling high power consumers

[1325] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[1326] Energy storage device optimization

[1327] The server calculates the optimal charging and discharging timing for the home or factory battery, allowing users to avoid peak energy consumption times and utilize power during periods of high power generation. Operation instructions are sent to the energy storage device via the terminal.

[1328] Optimizing power costs

[1329] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1330] System maintenance notification

[1331] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. As soon as the necessary maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[1332] Introducing the Emotion Engine

[1333] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[1334] Emotion-based scheduling and notification optimization

[1335] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of high-power devices. It also optimizes notification methods (e.g., app notifications in a gentler tone) according to the user's emotional state.

[1336] Specific examples

[1337] If the user plans to do laundry the next morning, the system works as follows:

[1338] 1. The user inputs the desired time for using the washing machine into the terminal.

[1339] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[1340] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[1341] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[1342] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1343] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1344] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[1345] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[1346] Prompt Sentence Examples

[1347] "Design an application that uses a generative AI model to generate an operation schedule to maximize the use of solar power generation in a factory for the next day. Acquire and integrate weather data (e.g., sunshine hours, wind speed). Calculate the optimal operation time for high-power consuming equipment in the factory and notify the user. Analyze the emotional state of workers using an emotion recognition engine and adjust the operation schedule if stress is detected. Calculate the optimal timing for charging and discharging the factory battery."

[1348] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1349] Step 1:

[1350] Users use a terminal to input information about high-power-consuming devices and energy storage devices in their homes or factories, including the amount of power each device consumes and the desired operating time. This input data is then stored in a database on the server.

[1351] Step 2:

[1352] The server uses a weather API (e.g., OpenWeatherMap API) to obtain current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is the basis for solar power generation forecasts. The obtained weather data is stored and processed within the server.

[1353] Step 3:

[1354] The server uses a generative AI model (e.g., TensorFlow, PyTorch) based on the stored weather data to predict the amount of solar power generation for the next day. The input data is the weather data, and the output data is the predicted amount of solar power generation. This forecast data is used for energy management.

[1355] Step 4:

[1356] The server calculates the optimal operation schedule for high-power consumption devices based on the acquired information on the devices and the predicted solar power generation data. For example, to minimize power consumption, it sets the devices to operate during the hours with the longest sunshine. This calculation is performed using an algorithm and output in the form of an operation schedule.

[1357] Step 5:

[1358] The server calculates the optimal charging and discharging timing for a home or industrial energy storage device. The input data is the predicted power generation and consumption pattern, and the output data is the optimal charging and discharging schedule. This schedule allows avoiding peak energy consumption.

[1359] Step 6:

[1360] Users input their electricity plan information using a terminal. This information is sent to the server and stored. The plan information is used to optimize energy schedules to avoid peak hours.

[1361] Step 7:

[1362] The server generates a schedule to optimize energy usage based on the input electricity rate plan. This calculation uses an algorithm to avoid peak hours. The output data is the optimized energy schedule.

[1363] Step 8:

[1364] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. It calculates the necessary maintenance timing and notifies the terminal. The input data is the operational data of the equipment, and the output data is the appropriate maintenance notification.

[1365] Step 9:

[1366] The emotion engine analyzes the user's voice and facial expression data sent from the device in real time to identify the user's current emotional state. The acquired emotional data is sent to the server for analysis. The input data is voice and facial expression data, and the output data is the user's emotional state.

[1367] Step 10:

[1368] The server adjusts the operation schedule based on the emotional data. For example, if the user is feeling stressed, the server can change the operation time of high-power consumption devices. The input data are the emotional state and the existing operation schedule, and the output data is the adjusted operation schedule.

[1369] Step 11:

[1370] The server adjusts the notification content and method based on the emotional data. For example, if the user feels like relaxing, the server may adjust the tone of the notification. The input data is the emotional state and existing notification settings, and the output data is the adjusted notification content.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] [Fourth embodiment]

[1375] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1376] 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.

[1377] 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).

[1378] 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.

[1379] 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.

[1380] 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).

[1381] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1382] 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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."

[1388] An embodiment of the present invention will be described in detail below. This system performs energy prediction and management to make the most efficient use of solar power generated in an ordinary home, and is composed of the following steps.

[1389] 1. User Initial Settings

[1390] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[1391] 2. Obtaining weather data

[1392] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[1393] 3. Generating an energy prediction model

[1394] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[1395] 4. Scheduling of high-power devices

[1396] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. An operation schedule is generated and notified to the device. The device then operates the target devices according to this schedule.

[1397] 5. Optimization of Energy Storage Devices

[1398] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[1399] 6. Optimizing electricity costs

[1400] Users input their electricity rate plan information into the terminal, and the server adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1401] 7. System Maintenance Notification

[1402] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance period is predicted, a notification is sent to the terminal. The user follows the notification and performs appropriate maintenance to ensure the long-term stable operation of the system.

[1403] Specific examples

[1404] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[1405] 1. The user inputs the desired time for using the washing machine into the terminal.

[1406] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[1407] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[1408] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[1409] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1410] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1411] This optimizes the operation of the washing machine using solar power, reducing energy costs and improving the efficiency of electricity use within the home.

[1412] The processing flow will be explained below.

[1413] Step 1:

[1414] The user inputs information about the high-power appliances and energy storage devices in the home into the terminal. For example, the user registers the model name and planned usage time of a washing machine or dishwasher. The terminal then transmits this information to the server.

[1415] Step 2:

[1416] The server sends a request to the weather API to retrieve weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes the retrieved weather data and stores it in a database.

[1417] Step 3:

[1418] The server inputs the acquired weather data into a generative model to predict the amount of solar power generation for the next day. The generative model makes highly accurate predictions based on past data and acquired weather data. These prediction results are used for energy management.

[1419] Step 4:

[1420] The server calculates the optimal operating times for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. Taking into account the desired usage times input by the user, the server determines the most efficient time slots within that range. An operating schedule is generated.

[1421] Step 5:

[1422] The server notifies the terminal of the generated operation schedule. The terminal displays the operation schedule to the user and asks for confirmation. The terminal automatically starts operation of the equipment according to the scheduled time.

[1423] Step 6:

[1424] The server calculates the optimal charging and discharging timing for the energy storage device (e.g., a home battery). It sets it to supply power during times when power generation is high and to store power during times when power generation is low. This setting is sent to the home battery via the terminal.

[1425] Step 7:

[1426] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1427] Step 8:

[1428] The server analyzes the equipment's operational data and past failure data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal then displays the maintenance timing to the user.

[1429] Step 9:

[1430] Once all data and settings are collected, the system will automatically begin operation and optimize the operation of high-power consumption appliances and energy storage devices based on predicted solar power generation, enabling users to achieve more efficient energy use in their homes and reduce energy costs.

[1431] Example 1

[1432] 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."

[1433] As the adoption of solar power generation systems in general households increases, there is a need to maximize their power generation efficiency while optimizing power consumption. However, current systems lack the means to accurately predict solar power generation amounts by fully utilizing weather data, and the use of high-power-consuming devices and management of energy storage devices are not effectively carried out. Furthermore, they are not adequately able to optimize energy costs according to electricity rate plans. Furthermore, they lack the functionality to predict and notify when power generation systems need maintenance. This results in a decrease in the efficiency of power usage within the home, making it difficult to reduce energy costs.

[1434] 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.

[1435] In this invention, the server includes means for a user to input information about high-power consumption devices and energy storage devices in the home, means for acquiring weather data, means for operating a generative AI model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining optimal timing for charging and discharging the energy storage device, and means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption. This improves the accuracy of solar power generation predictions, enables efficient management of high-power consumption devices and energy storage devices, and enables improved efficiency of home power utilization and reduced energy costs.

[1436] "User" refers to an individual or household that uses the system.

[1437] "High-power household appliances" refers to household appliances such as washing machines and dishwashers that consume large amounts of electricity at once.

[1438] An "energy storage device" is a device that temporarily stores electricity generated within the home and supplies it when needed. A specific example is a home battery.

[1439] "Terminal" means an electronic device used by a user to enter information and receive information from a system. Examples include a smartphone or tablet.

[1440] "Server" refers to the computer system that manages the entire system and processes data and runs predictive models.

[1441] "Weather data" refers to data relating to weather conditions, such as temperature, hours of sunshine, cloud cover, and wind speed.

[1442] "Weather API" refers to a programmatic interface used to obtain weather data. An example is the OpenWeatherMap API.

[1443] A "generative AI model" refers to an artificial intelligence model that makes predictions and classifications based on acquired data. A specific example is a predictive model using TensorFlow.

[1444] "Scheduling" refers to planning and setting the operating times and timing of specific equipment based on predictive data.

[1445] "Optimization" refers to adjusting resource allocation and scheduling to maximize energy efficiency or minimize costs.

[1446] An "energy schedule" refers to a schedule that includes the operation plans of household appliances and energy storage devices.

[1447] "Electricity rate plan" means an electricity payment plan that a consumer enters into with an electricity supplier. Examples include flat-rate plans and time-of-use plans.

[1448] "Maintenance timing" refers to the specific timing when maintenance of a system or equipment is required.

[1449] This invention is a system for energy prediction and management to make the most efficient use of solar power generated in an average household, and operates in cooperation with the server, terminal, and user elements.

[1450] System Overview

[1451] User Preferences

[1452] The user launches a dedicated application using the device. From the settings screen within the application, they enter information about high-power consumption devices in the home (e.g., washing machine, dishwasher) and energy storage devices (e.g., home battery). Once this information is saved, the device sends it to the server. The server stores the received information in a database.

[1453] Obtaining weather data

[1454] The server periodically calls a weather API (e.g., OpenWeatherMap API) to obtain weather data (e.g., temperature, sunshine hours, cloud cover, wind speed), which is then stored in a database within the system.

[1455] Generate an energy forecasting model

[1456] The server runs a generative AI model (for example, a forecasting model using TensorFlow) based on the stored weather data to predict the amount of solar power generation for the next day. The forecast results are stored in a database.

[1457] Scheduling high power consumers

[1458] The user inputs the desired usage time of a high-power consumption device (e.g., a washing machine) on the device. The device then sends the desired usage time data to the server. The server calculates the optimal operation time for the high-power consumption device based on the predicted solar power generation data and the desired usage time, and generates an operation schedule. The generated schedule is notified to the device, which automatically starts operation of the device at the set time.

[1459] Energy storage device optimization

[1460] The server calculates the timing of charging and discharging the home battery based on the predicted power generation data. For example, it sets a schedule to charge at night (when power demand is low) and discharge in the morning when power generation is low. The calculation results are sent to the terminal, and instructions are sent to the home battery through the terminal.

[1461] Optimizing power costs

[1462] Users input their electricity plan information (e.g., flat-rate plan, time-of-use plan) into the device and send it to the server, which then runs an algorithm to optimize energy usage based on the plan and reschedules each device to avoid peak power hours.

[1463] System maintenance notification

[1464] The server analyzes the operational data of the home's solar power generation system and predicts when maintenance is required. The prediction results are sent to the terminal and displayed to the user. The user can then follow the notification to arrange for appropriate maintenance work.

[1465] Specific examples

[1466] For example, the process when the laundry is scheduled to be done in the morning of the next day will be described.

[1467] 1. The user inputs the desired time for using the washing machine into the terminal.

[1468] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[1469] 3. The server calculates the optimal time to run the washing machine based on the predicted power generation data. For example, it determines that the best time is between 2:00 PM and 4:00 PM, when the sunshine hours are the longest.

[1470] 4. The schedule is sent to the device, and the user confirms it. The device automatically starts the washing machine at the specified time.

[1471] 5. The server optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1472] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1473] Prompt Sentence Examples

[1474] "Based on the weather forecast for the next day obtained using a weather API, please predict the amount of solar power generation in the home for the next day and generate an optimal operation schedule for the washing machine, which is a high-power-consuming device. In this case, please create a schedule to operate the washing machine during the time period when power generation is highest."

[1475] This invention improves the efficiency of solar power generation in homes, reducing energy costs and realizing sustainable energy use.

[1476] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1477] Step 1: Initial User Setup

[1478] Input: The user inputs information about high-power consumption appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the home into the terminal.

[1479] Data processing / data calculation: The terminal formats the input information into a database and creates a data set that includes information set by the user (device manufacturer, model number, power consumption, etc.).

[1480] Output: The terminal sends the formatted data to the server.

[1481] Specific operation: The user opens the dedicated application, enters information about the home appliance and energy storage device on the settings screen, and presses the save button. The device then sends the information to the server.

[1482] Step 2: Obtaining weather data

[1483] Input: The server sends a request to the weather API.

[1484] Data processing / data calculation: As a response from the weather API, the server receives weather data such as temperature, sunshine hours, cloud cover, wind speed, etc. The server converts this data into an appropriate format and stores it in the database.

[1485] Output: Weather data is stored in a database on the server.

[1486] Specific operation: The server periodically accesses a weather API (e.g., OpenWeatherMap API) to obtain the necessary weather data.

[1487] Step 3: Generate an energy forecasting model

[1488] Input: The server retrieves the stored weather data.

[1489] Data processing / data calculation: A generative AI model (such as TensorFlow) is used to predict the amount of solar power generated for the next day. The model is input with training data and calculated to output the future amount of power generated.

[1490] Output: The predicted solar power generation data is stored in a database on the server.

[1491] How it works: The server retrieves weather data, uses a generative AI model to predict the next day's power generation, and stores the results.

[1492] Step 4: Scheduling high power consumers

[1493] Input: The user inputs the desired time for using the device into the terminal, and the desired time is sent from the terminal to the server. The server obtains the predicted power generation data.

[1494] Data processing / data calculation: The server compares the user's desired time with the predicted power generation amount and executes an algorithm to calculate the optimal operating time. It selects the time period with the longest sunshine hours and creates a schedule.

[1495] Output: The operation schedule is sent from the server to the terminal.

[1496] Specific operation: The user inputs the desired usage time into the application, and the server creates an optimal operation schedule based on that time period and notifies the device. The device then automatically starts operating the device according to that schedule.

[1497] Step 5: Optimizing the energy storage device

[1498] Input: The server retrieves the predicted energy yield data.

[1499] Data processing / data calculation: The server calculates the optimal charging and discharging timing based on the amount of electricity stored in the home battery and the predicted amount of power generation. For example, it calculates a schedule to charge electricity at night and discharge it in the morning.

[1500] Output: The optimized charging and discharging schedule is sent to the terminal, which then instructs the home battery.

[1501] Specific operation: The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal.

[1502] Step 6: Optimize your energy costs

[1503] Input: The user inputs the electricity rate plan into the device. The plan information is sent from the device to the server.

[1504] Data processing / data calculation: The server runs an algorithm to optimize energy usage based on the input electricity rate plan, for example concentrating operation during times when rates are low.

[1505] Output: The optimized schedule is sent to the terminal.

[1506] Specific operation: The user inputs an electricity rate plan, and the server readjusts the schedule based on that plan and notifies the terminal.

[1507] Step 7: System Maintenance Notification

[1508] Input: The server acquires operational data of the home solar power generation system.

[1509] Data processing / data calculation: The server analyzes operational data and runs algorithms to predict when maintenance will be required.

[1510] Output: The terminal is notified when maintenance is required.

[1511] Specific operation: The server predicts the need for maintenance based on operational data and notifies the user via the terminal.

[1512] (Application example 1)

[1513] 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."

[1514] Modern energy management systems aim to efficiently utilize solar power generation in homes and commercial facilities, but they currently have difficulty adapting to the efficient operation of high-power consumption equipment and production robots, which consume large amounts of energy in factories. Therefore, there is a need for systems that can optimize energy consumption throughout the factory and improve productivity. There is also a need for systems that can develop optimal operation schedules based on electricity rate plans and predict and notify maintenance timing.

[1515] 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.

[1516] In this invention, the server includes means for acquiring weather data, means for running a generative model that predicts solar power generation based on the acquired weather data, means for scheduling the operation of high-power consumption devices based on the predicted solar power generation, means for determining the optimal timing for charging and discharging an energy storage device, means for generating and executing an operation schedule for optimizing the operation of an energy robot, and means for notifying the optimized energy schedule based on the predicted solar power generation and energy consumption. This makes it possible to optimize the operation of high-power consumption devices and robots in a factory to match solar power generation, thereby improving production efficiency while reducing energy costs.

[1517] "Means for obtaining weather data" means means for collecting current and future weather data using the weather API.

[1518] "Means for operating a generative model that predicts solar power generation" refers to means for running a generative AI model to predict the amount of solar power generation for the next day based on acquired weather data.

[1519] The "means for scheduling the operation of high-power consuming devices" is a means for calculating the optimal operation time of high-power consuming devices based on the predicted amount of solar power generation, and generating an operation schedule.

[1520] The "means for determining the optimal timing for charging and discharging the energy storage device" is a means for calculating the optimal timing for charging and discharging the home battery and transmitting operation instructions.

[1521] The "means for generating and executing an operation schedule for optimizing the operation of an energy robot" refers to a means for optimizing the operation schedule of the robot based on predicted solar power generation and energy consumption, and for operating the robot according to that schedule.

[1522] The "means for notifying an optimized energy schedule" is a means for notifying a user terminal of an energy schedule generated based on predicted solar power generation and energy consumption.

[1523] This invention is a system for managing energy in factories and optimizing the operation schedule of high-power-consuming equipment. This system collects weather data and uses it to predict solar power generation, enabling efficient energy use.

[1524] The server uses a weather API to obtain weather data, including temperature, sunshine hours, cloud cover, and wind speed, and runs a generative AI model based on this data to predict the amount of solar power generation for the next day.

[1525] Based on the predicted solar power generation, the server schedules the operation of high-power-consuming equipment in the factory, such as welding machines and processing machines. It calculates the optimal operating times and generates a schedule. Once the schedule is determined, the server notifies the terminal, and the terminal operates the high-power-consuming equipment.

[1526] In addition, the timing of charging and discharging energy storage devices (such as home batteries) is optimized to avoid peak energy consumption times and ensure that electricity is available during times when solar power generation is strongest.

[1527] Additionally, users can input their own electricity rate plan information into the device, and the server uses this information to avoid peak power hours and optimize energy usage, enabling efficient use of electricity while reducing energy costs.

[1528] The system consists of software for scheduling using the Python schedule library and for acquiring weather data using the Weather API. The factory's production robots and processing machines are linked to a networked environmental control system.

[1529] As a specific example, when optimizing the operation of a welding machine, the operation can be performed at the following timing: For example, the operation of the welding machine can be set from 2:00 PM to 4:00 PM based on weather data forecasts. Also, to avoid peak hours of energy consumption, the start of the welding machine can be scheduled during off-peak hours, achieving efficient energy consumption.

[1530] An example of a prompt sentence is, "Based on tomorrow's weather forecast, what is the optimal operating time for the welding machine?"

[1531] In this way, the energy prediction and management technology of the invention can be applied to the efficient operation of factory robots, thereby reducing energy consumption and improving productivity.

[1532] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1533] Step 1:

[1534] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc., which is then used in subsequent forecasting models.

[1535] Input: Weather data request from the weather API

[1536] Data processing / calculation: weather data collection and filtering

[1537] Output: Weather data (temperature, sunshine hours, cloud cover, wind speed)

[1538] Step 2:

[1539] The server runs a prediction model (generative AI model) to predict the amount of solar power generation for the next day based on the acquired weather data. This model takes weather data as input and outputs the amount of power generation as a numerical value.

[1540] Input: Weather data

[1541] Data processing / calculation: Predicting power generation using weather data

[1542] Output: Predicted solar power generation (numerical data)

[1543] Step 3:

[1544] The server calculates the optimal operating time for high-power-consuming devices based on the predicted solar power generation amount and the user's desired usage time, and generates an operating schedule, which is then notified to the terminal.

[1545] Input: Forecasted solar power generation, desired usage time of the user

[1546] Data processing / calculation: Calculation of optimal driving time

[1547] Output: Schedule high-power consumption devices

[1548] Step 4:

[1549] The terminal operates the high-power consumption devices according to the operation schedule received from the server. The operation of the devices starts automatically and ends at the scheduled time.

[1550] Input: Operation schedule of high power consumption devices

[1551] Data processing / calculation: Issuing operation instructions for equipment

[1552] Output: Operating high-power devices

[1553] Step 5:

[1554] The server calculates the optimal charging and discharging timing for the home battery and sends instructions via the terminal, thereby optimizing the charging and discharging timing.

[1555] Input: Forecasted solar power generation, current energy storage status

[1556] Data processing / calculation: Optimization calculation of charge and discharge timing

[1557] Output: Charge and discharge timing instructions

[1558] Step 6:

[1559] Users input their electricity rate plan information into the device, and that information is sent to the server, which then optimizes energy usage and adjusts the schedule based on the plan.

[1560] Input: User's electricity plan

[1561] Data processing / calculation: Energy usage optimization based on electricity rate plans

[1562] Output: Adjusted energy schedule

[1563] Step 7:

[1564] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. The predicted timing is notified to the user via the terminal, and the user can then carry out the appropriate maintenance.

[1565] Input: Solar power system operation data

[1566] Data processing / calculation: Maintenance timing prediction

[1567] Output: Maintenance notification

[1568] 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.

[1569] The present invention will be described in detail below with reference to an embodiment thereof. This system performs energy forecasting and management for the most efficient use of solar power in a typical household, and also combines it with an emotion engine that recognizes the user's emotions.

[1570] 1. User Initial Settings

[1571] The user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) using a terminal, and the system acquires information about the appliances to be controlled.

[1572] 2. Obtaining weather data

[1573] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This weather data is used to forecast solar power generation.

[1574] 3. Generating an energy prediction model

[1575] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to control the use of electricity within the home and the operation of storage devices.

[1576] 4. Scheduling of high-power devices

[1577] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[1578] 5. Optimization of Energy Storage Devices

[1579] The server calculates the optimal charging and discharging timing for the home battery, allowing it to avoid peak energy consumption times and use electricity during times when power generation is high. Operation instructions are sent to the home battery via the terminal.

[1580] 6. Optimizing electricity costs

[1581] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1582] 7. System Maintenance Notification

[1583] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. As soon as the required maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[1584] 8. Introducing the Emotion Engine

[1585] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[1586] 9. Emotion-based scheduling and notification optimization

[1587] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of energy-intensive appliances. It also optimizes notification methods based on the user's emotional state (for example, app notifications in a gentler tone).

[1588] Specific examples

[1589] For example, if the user plans to do laundry in the morning of the next day, the process is as follows.

[1590] 1. The user inputs the desired time for using the washing machine into the terminal.

[1591] 2. The server obtains the weather forecast for the next day from the weather API and predicts the amount of solar power generation using the generative model.

[1592] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[1593] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[1594] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1595] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1596] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[1597] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[1598] In this way, the system not only optimizes the operation of high-power-consuming appliances and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, resulting in more efficient energy use within the home and reduced energy costs.

[1599] The processing flow will be explained below.

[1600] Step 1:

[1601] A user inputs information about high-power-consuming appliances (e.g., washing machines, dishwashers) and energy storage devices (e.g., home batteries) in the terminal. The terminal then transmits the input information to the server.

[1602] Step 2:

[1603] The server sends a request to the weather API to get weather data for the next day, including temperature, sunshine hours, cloud cover, wind speed, etc. The server analyzes this data and stores it in a database.

[1604] Step 3:

[1605] The server runs a generative model based on the acquired weather data to predict the amount of solar power generated for the next day. The generative model makes predictions based on past data and acquired weather data. The results of this prediction are used for energy management.

[1606] Step 4:

[1607] The server calculates the optimal operating time for high-power-consuming devices (such as washing machines) based on the predicted solar power generation data. It also takes into account the desired usage times entered by the user and determines the most efficient time period within that range. The server generates an operating schedule and sends it to the terminal.

[1608] Step 5:

[1609] The terminal notifies the user of the operation schedule received from the server. The user checks the schedule and either approves it or requests a revision. After receiving the user's confirmation, the terminal automatically starts operating the equipment according to the operation schedule.

[1610] Step 6:

[1611] The server calculates the optimal charging and discharging timing for the home battery. This allows the battery to be charged during times when power generation is high and discharged during times when power generation is low. The server then sends these operation instructions to the terminal. The terminal then operates the home battery based on the received instructions.

[1612] Step 7:

[1613] Users input their electricity rate plan information into their device, which then sends this information to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1614] Step 8:

[1615] The server analyzes the equipment's operational data to manage the solar power generation system and predict the timing of maintenance. When necessary maintenance is predicted, the server sends a maintenance notification to the terminal. The terminal displays the notification content to the user and suggests appropriate maintenance.

[1616] Step 9:

[1617] When the emotion engine is installed, the device analyzes the user's voice and facial expression data in real time to determine their current emotional state. For example, if the user is feeling stressed, that information is sent to the server.

[1618] Step 10:

[1619] The server can adjust the schedule based on the user's emotional state. For example, if the user is feeling stressed, the server can delay the operation of the washing machine. The server can also optimize notification methods (such as the tone and content of notification sounds) according to the user's emotions.

[1620] For example, if the emotion engine detects that the user is feeling stressed the next morning, the server can adjust the washing machine's operating time to the afternoon to reduce the user's stress, optimizing energy efficiency while taking into account the user's emotional state.

[1621] Example 2

[1622] 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."

[1623] There is a need to maximize the efficiency of solar power generation in ordinary households. However, predicting power generation based on weather data and creating an optimal operation schedule for high-power-consuming devices linked to that forecast are complex, and adjusting the timing of charging and discharging energy storage devices is not easy. Furthermore, there is no established method for reducing electricity costs while optimizing energy use by taking into account the user's emotional state. Therefore, a system that can solve these multiple challenges in an integrated manner is needed.

[1624] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1625] In this invention, the server includes a means for inputting information about household electrical appliances, a means for acquiring weather data, a means for running a generative model that predicts solar power generation based on the acquired weather data, a means for scheduling the operation of high-power consumption appliances based on the predicted solar power generation, a means for determining optimal timing for charging and discharging an energy storage device, a means for notifying an optimized energy schedule based on the predicted solar power generation and energy consumption, a means for acquiring and analyzing emotion data, and a means for adjusting the energy schedule based on the analyzed emotion data. This enables flexible energy scheduling that takes into account the user's emotional state while maximizing the utilization efficiency of solar power generation in the home. It also reduces energy costs and improves energy management throughout the home.

[1626] "Means for inputting information about household electrical appliances" refers to an interface or device that allows a user to input information about high-power consumption appliances and energy storage devices in the home into a terminal.

[1627] "Means of obtaining weather data" refers to the function for obtaining weather forecasts and current conditions data from online weather APIs, etc.

[1628] "Means for operating the generative model" refers to software or algorithms that operate an AI-based predictive model based on acquired weather data and estimate the amount of solar power generated the following day.

[1629] "Means for scheduling the operation of high-power-consuming devices" refers to a system that calculates the optimal operating times of high-power-consuming devices such as washing machines and dishwashers based on predicted power generation data and the user's desired usage times, and generates a schedule.

[1630] "Means for determining the optimal timing for charging and discharging an energy storage device" refers to a function that calculates the most efficient timing for charging and discharging an energy storage device such as a home battery.

[1631] The "means for notifying the optimized energy schedule" refers to a notification system for notifying the user of the calculated optimal energy schedule. Specifically, it includes a function for displaying the schedule through a terminal.

[1632] "Means for acquiring and analyzing emotional data" refers to sensors and analytical algorithms for acquiring and analyzing emotional data such as the user's voice and facial expressions to identify their current emotional state.

[1633] "Means for adjusting energy schedules based on emotional data" refers to a system for modifying and adjusting energy schedules based on the analyzed emotional state of a user, including actions such as delaying the operation of high-power consumption devices when stress levels are high.

[1634] This invention relates to an energy forecasting and management system for the most efficient use of solar power in homes. The system is further enhanced in flexibility and adaptability by incorporating an emotion engine that recognizes the user's emotions.

[1635] System Overview

[1636] The system consists of the following major hardware and software components:

[1637] server

[1638] Terminal (device operated by the user)

[1639] High-power consumption appliances (e.g. washing machines, dishwashers, etc.)

[1640] Energy storage devices (e.g. home batteries)

[1641] Weather API (to retrieve weather data)

[1642] Generative AI models (to predict solar power generation)

[1643] Emotion engine (to recognize and analyze user emotions)

[1644] Initial Setup

[1645] First, a user inputs information about high-power consumption appliances and energy storage devices in the home using a terminal, which is then sent to a server and stored in a database.

[1646] Obtaining weather data

[1647] The server uses a weather API to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to predict solar power generation.

[1648] Energy Forecast

[1649] Based on the acquired weather data, the server runs a generative AI model to predict the amount of solar power generation for the next day. The prediction results are stored in a database and used in the next step to plan the operation of high-power consumption equipment and energy storage devices.

[1650] Scheduling

[1651] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the desired usage times set by the user. The calculated schedule is notified to the device and displayed to the user. The device can also automatically operate the devices according to this schedule.

[1652] Energy storage device optimization

[1653] The server calculates the optimal charging and discharging timing for the home battery, allowing users to avoid peak energy consumption times and use electricity during times when power generation is high. These operation instructions are sent to the home battery via the terminal.

[1654] Optimizing power costs

[1655] Users input their electricity plan information into their device. This information is sent to the server, which then optimizes energy usage based on the plan and adjusts the schedule to avoid peak power hours.

[1656] System maintenance notification

[1657] The server analyzes the operational data of the solar power generation system and predicts when maintenance is required. When the maintenance period approaches, the server sends a notification to the terminal and displays it to the user.

[1658] Introducing the Emotion Engine

[1659] The emotion engine uses sensors to capture the user's voice and facial expression data and analyzes their emotional state in real time. The analysis results are sent to the server and reflected in the energy schedule in the next step.

[1660] Emotion-Based Adjustment

[1661] The server adjusts the energy schedule based on the analyzed emotional data. For example, if the user is feeling stressed, it will adjust the operating time of high-power consumption devices later. Notification methods are also optimized according to the user's emotional state.

[1662] Specific examples

[1663] For example, if the user plans to do laundry the next morning, the process would be:

[1664] 1. The user inputs the desired time for using the washing machine into the terminal.

[1665] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative model to predict solar power generation.

[1666] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data and the desired usage time.

[1667] 4. The generated schedule is sent to the device, where the user can confirm it. The device then automatically starts the washing machine operation based on this schedule.

[1668] 5. The server also optimizes the timing of charging and discharging the home battery.

[1669] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1670] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[1671] 8. If the emotion engine detects stress in the user, the server will make adjustments such as delaying the operation time of the washing machine.

[1672] Through this process, the system not only optimizes the operation of high-power-consuming devices and energy storage devices based on predicted solar power generation, but also makes flexible adjustments that take into account the user's emotional state, thereby improving the efficiency of power use within the home and reducing energy costs.

[1673] Prompt Sentence Examples

[1674] For example, the system uses specific prompts such as, "I plan to do laundry the next morning. Therefore, please calculate the optimal washing machine operation schedule based on the predicted solar power generation amount. Also, please consider adjusting the operation time if the user feels stressed."

[1675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1676] Step 1: Initial User Setup

[1677] The user uses the terminal to enter the following information:

[1678] High-power household appliances (e.g. washing machines, dishwashers)

[1679] Energy storage devices (e.g. home batteries)

[1680] input:

[1681] High power consumption device information

[1682] Energy Storage Device Information

[1683] output:

[1684] The terminal transmits this information to the server, which stores the received information in a database.

[1685] Specific behavior:

[1686] The user operates the terminal to enter the necessary information into the form and presses the send button to pass the information to the server, which receives the data and stores it in a database.

[1687] Step 2: Obtaining weather data

[1688] The server calls the weather API to retrieve current and future weather data.

[1689] input:

[1690] Weather API request

[1691] output:

[1692] Weather data such as temperature, sunshine hours, cloud cover, and wind speed

[1693] Specific behavior:

[1694] The server accesses the weather API, sends a request, and receives weather data in response, which is then stored locally or recorded in a database for analysis.

[1695] Step 3: Generate an energy forecasting model

[1696] The server uses a generated AI model based on the acquired weather data to predict the amount of solar power generation for the next day.

[1697] input:

[1698] Weather data

[1699] output:

[1700] Predicted solar power generation data

[1701] Specific behavior:

[1702] The server inputs the stored weather data into the generative AI model, which then calculates and predicts the amount of solar power generation for the next day. The prediction results are stored in a database.

[1703] Step 4: Scheduling high power consumers

[1704] The server calculates the optimal operating time for high-power consumption devices based on predicted solar power generation data and the user's desired usage times.

[1705] input:

[1706] Predicted solar power generation data

[1707] User's desired usage time

[1708] output:

[1709] Operation schedule for high power consumption devices

[1710] Specific behavior:

[1711] The server uses an algorithm to calculate the most efficient operating time, taking into account the user's desired time and solar power generation forecast data, and notifies the terminal of the calculation results.

[1712] Step 5: Optimizing the energy storage device

[1713] The server determines the optimal timing for charging and discharging the home battery.

[1714] input:

[1715] Solar power generation data

[1716] Residential energy consumption data

[1717] output:

[1718] Home battery charging and discharging timing

[1719] Specific behavior:

[1720] The server analyzes the solar power generation forecast data and the household's power consumption patterns to calculate the optimal timing for charging and discharging the home battery. The calculation results are sent to the terminal and instructions are sent to the home battery.

[1721] Step 6: Optimize your energy costs

[1722] Users input their electricity plan information into the device, and the server uses this information to optimize energy usage.

[1723] input:

[1724] Electricity rate plan information

[1725] output:

[1726] Optimized Energy Schedule

[1727] Specific behavior:

[1728] Users input their energy plan details via a device, and the server receives the data and stores it in a database. The server then uses this information to adjust energy usage schedules to avoid peak tariff periods.

[1729] Step 7: System Maintenance Notification

[1730] The server analyzes operational data from the solar power generation system and predicts and notifies users when maintenance is necessary.

[1731] input:

[1732] Power generation system operation data

[1733] output:

[1734] Maintenance Notification

[1735] Specific behavior:

[1736] The server periodically analyzes operational data to detect abnormalities and when maintenance is required. The detected information is notified to the terminal and displayed to the user.

[1737] Step 8: Implementing the Emotion Engine

[1738] The emotion engine acquires and analyzes the user's voice and facial expression data.

[1739] input:

[1740] Voice and facial expression data

[1741] output:

[1742] User emotional state data

[1743] Specific behavior:

[1744] The device or a dedicated device captures voice and facial expressions in real time, and the emotion engine processes the data to analyze the user's emotional state. The analysis results are then sent to a server.

[1745] Step 9: Emotional Adjustment

[1746] The server adjusts the energy schedule based on the user's emotional state.

[1747] input:

[1748] User emotional state data

[1749] output:

[1750] Adjusted Energy Schedule

[1751] Specific behavior:

[1752] The server receives the emotional state data and adjusts the operation schedule of high-power consumption devices when stress levels are high, etc. The adjusted schedule is sent to the terminal and notified to the user.

[1753] (Application example 2)

[1754] 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."

[1755] Conventional solar power generation systems mainly rely on weather data to predict power generation and schedule high-power-consuming equipment. However, these systems do not take into account the emotional state of the user, limiting their ability to optimize user experience and efficiency. Furthermore, resource management that ignores emotional aspects such as worker stress and fatigue can lead to reduced productivity and user dissatisfaction.

[1756] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring and analyzing emotion data, means for adjusting the operation schedule of the high-power consumption devices based on the emotion data, and means for changing the content and method of notification based on the emotion data. This makes it possible to flexibly adjust the operation schedule of the high-power consumption devices according to the user's emotional state, thereby improving the user experience and achieving effective energy management.

[1757] "Means for acquiring weather data" refers to a combination of hardware and software for acquiring weather data in real time. Information is collected via the weather API.

[1758] The "means for operating a generative model to predict solar power generation" refers to algorithms and software for predicting solar power generation for the next day based on acquired weather data. A generative AI model is used.

[1759] The "means for scheduling the operation of high-power consuming devices" refers to scheduling algorithms and software for optimizing the operation time of high-power consuming devices based on the predicted amount of solar power generation.

[1760] The "means for determining the optimal timing for charging and discharging the energy storage device" refers to algorithms and software for optimally timing the charging and discharging of the home battery.

[1761] The "means for notifying the optimized energy schedule" refers to an interface and software for notifying the user of the scheduling results. A device such as a smartphone or tablet is used.

[1762] The "means for acquiring and analyzing emotional data" refers to an emotion recognition engine and software for acquiring and analyzing emotional data such as the user's voice and facial expressions in real time.

[1763] The "means for adjusting the operation schedule of high-power-consuming devices based on emotional data" refers to algorithms and software for adjusting the operation schedule of high-power-consuming devices in accordance with the user's emotional state based on the acquired emotional data.

[1764] The "means for changing the notification content and method based on emotional data" refers to algorithms and software for optimizing the notification content and method according to the user's emotional state.

[1765] The "means for inputting an electricity rate plan" refers to an interface and software that allows a user to input their electricity rate plan information into the system.

[1766] The "means for optimizing energy usage by avoiding peak power hours based on an electricity rate plan" refers to algorithms and software for optimizing energy usage by avoiding peak power hours based on input electricity rate plan information.

[1767] The "means for predicting and notifying the timing of necessary maintenance of an energy generating device" refers to an algorithm and software for analyzing operational data of the energy generating device, predicting the timing of necessary maintenance, and notifying the timing.

[1768] The system for implementing the present invention aims to improve the efficiency of energy management in homes and factories, and also takes into account the emotional state of the user. The detailed configuration and operation of this system will be described below.

[1769] Initial Setup

[1770] First, a user uses a terminal to input information about high-power-consuming devices (e.g., washing machines, welding robots) and energy storage devices (e.g., home batteries, factory batteries) in their homes or factories. This information includes the amount of power consumed by each device and the desired operating time.

[1771] Obtaining weather data

[1772] The server then uses a weather API (e.g., OpenWeatherMap API) to retrieve current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is used to forecast solar power generation.

[1773] Generate an energy forecasting model

[1774] The server runs a generative AI model (e.g., TensorFlow, PyTorch) based on the acquired weather data to predict the amount of solar power generated for the next day. The prediction results are used to operate power usage and storage devices in homes and factories.

[1775] Scheduling high power consumers

[1776] The server calculates the optimal operating time for high-power consumption devices based on the predicted solar power generation data and the user's desired usage times. Taking into account the desired usage times entered by the user, the server determines the most efficient time period within that range. An operation schedule is generated and notified to the device. The device operates the target devices according to this schedule.

[1777] Energy storage device optimization

[1778] The server calculates the optimal charging and discharging timing for the home or factory battery, allowing users to avoid peak energy consumption times and utilize power during periods of high power generation. Operation instructions are sent to the energy storage device via the terminal.

[1779] Optimizing power costs

[1780] Users input their electricity rate plan information into the device. The device receives this information and sends it to the server. The server then adjusts the schedule to avoid peak power hours in order to optimize energy usage based on the electricity rate plan.

[1781] System maintenance notification

[1782] The server analyzes the operational data of the equipment to manage the solar power generation system and energy generation equipment and predict the timing of maintenance. As soon as the necessary maintenance time is predicted, the server sends a maintenance notification to the terminal. The terminal displays the maintenance timing to the user.

[1783] Introducing the Emotion Engine

[1784] The emotion engine analyzes the user's voice and facial expression data in real time to identify their current emotional state. For example, if the user is feeling stressed, the engine sends this information to the server.

[1785] Emotion-based scheduling and notification optimization

[1786] The server adjusts the schedule based on the user's emotional state. For example, if the user wants to relax, it can delay the operation of high-power devices. It also optimizes notification methods (e.g., app notifications in a gentler tone) according to the user's emotional state.

[1787] Specific examples

[1788] If the user plans to do laundry the next morning, the system works as follows:

[1789] 1. The user inputs the desired time for using the washing machine into the terminal.

[1790] 2. The server obtains the weather forecast for the next day from the weather API and uses the generative AI model to predict solar power generation.

[1791] 3. The server calculates the optimal operating time for the washing machine based on the predicted power generation data. For example, if it determines that the most efficient time is between 2:00 and 4:00 p.m., when the sunshine hours are the longest, it will schedule the washing machine to run during this time period.

[1792] 4. The schedule is sent to the device, the user confirms it, and the device automatically starts the washing machine.

[1793] 5. The server also optimizes the timing of charging and discharging the home battery, for example, by setting it to charge at night and discharge in the morning when power generation is low.

[1794] 6. If the user has entered an energy plan, the server takes that into account and modifies the schedule to avoid peak electricity prices.

[1795] 7. If the system detects the need for maintenance, the terminal will notify the user of the appropriate maintenance.

[1796] 8. If the emotion engine detects stress in the user, the server will adjust the washing machine, such as delaying its running time, thereby reducing the burden on the user while maintaining energy efficiency.

[1797] Prompt Sentence Examples

[1798] "Design an application that uses a generative AI model to generate an operation schedule to maximize the use of solar power generation in a factory for the next day. Acquire and integrate weather data (e.g., sunshine hours, wind speed). Calculate the optimal operation time for high-power consuming equipment in the factory and notify the user. Analyze the emotional state of workers using an emotion recognition engine and adjust the operation schedule if stress is detected. Calculate the optimal timing for charging and discharging the factory battery."

[1799] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1800] Step 1:

[1801] Users use a terminal to input information about high-power-consuming devices and energy storage devices in their homes or factories, including the amount of power each device consumes and the desired operating time. This input data is then stored in a database on the server.

[1802] Step 2:

[1803] The server uses a weather API (e.g., OpenWeatherMap API) to obtain current and future weather data, including temperature, sunshine hours, cloud cover, wind speed, etc. This data is the basis for solar power generation forecasts. The obtained weather data is stored and processed within the server.

[1804] Step 3:

[1805] The server uses a generative AI mode...

Claims

1. a means for acquiring weather data; A means for operating a generative model that predicts solar power generation based on the acquired weather data; means for scheduling operation of high power consuming devices based on the predicted solar power generation; means for determining optimal timing for charging and discharging the energy storage device; means for notifying an optimized energy schedule based on predicted solar power generation and energy consumption; A system including:

2. a means for inputting an electricity rate plan; A means for optimizing energy usage by avoiding peak power hours based on an input power rate plan; The system of claim 1 further comprising:

3. 10. The system of claim 1, further comprising means for predicting and notifying when maintenance of the energy generating device is required.

Images