System

Abstract

A system is provided.SOLUTION: A system includes means for collecting attribute information and power usage data from a user via a terminal, means for preprocessing the collected attribute information and power usage data, means for generating an optimal power saving method using a generated AI model using the preprocessed data, means for notifying the user's terminal of the generated power saving method, means for collecting and evaluating feedback from the user, and means for giving a reward to the user based on the evaluation.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] Currently, there is a need to reduce household electricity consumption in order to achieve carbon neutrality. However, the characteristics and electricity usage of each household are different, and uniform energy-saving measures cannot be sufficiently effective. In addition, there is a lack of a system in place to receive specific and effective suggestions for individual households to voluntarily take energy-saving actions. Furthermore, there is a problem in that appropriate feedback and incentives are not provided for regular energy-saving actions, which means that continuous energy-saving actions are not promoted. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system that collects attribute information and power usage data from users via their devices. The collected attribute information and power usage data are then preprocessed and analyzed using a generative AI model to generate optimal power-saving methods for each user. The system then notifies the user of the generated power-saving methods via their device, and collects and evaluates feedback from the user. By rewarding the user based on the evaluation, the system motivates the user to continuously take energy-saving actions. Furthermore, the generative AI model is trained and updated using the collected data, creating a system that can always provide advice based on the latest information.

[0006] A "terminal" is a communication device used by a user, such as a smartphone, tablet, or PC.

[0007] "Attribute information" refers to information such as the user's family structure, type of residence, and types of home appliances owned.

[0008] "Electricity usage data" refers to data relating to the amount of electricity consumed and patterns of electricity usage in a user's home.

[0009] "Preprocessing" refers to performing data transformations on the collected data, such as imputing missing values, scaling, and encoding categorical variables.

[0010] A "generative AI model" is a machine learning model that uses artificial intelligence technology to analyze data and generate appropriate energy-saving methods.

[0011] "Power saving methods" are specific suggestions for actions that users can take to reduce power consumption.

[0012] "Notifying" refers to sending the generated power saving method to the user's device using a means such as a push notification.

[0013] "Feedback" refers to users providing their opinions and results on the energy-saving measures they have implemented.

[0014] "Evaluating" means analyzing user feedback and energy usage data to measure the effectiveness of energy-saving measures.

[0015] "Rewards" are incentives provided based on the energy-saving measures taken by users, and can include in-app currency and physical prizes.

[0016] "Training" refers to learning from newly collected data to improve a generative AI model.

[0017] "Updating" refers to applying a generative AI model that has been improved through training to the system. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions based on household power usage.

[0040] First, the user launches the Eco Electricity app via a device such as a smartphone, tablet, or PC. The user enters attribute information (e.g., family composition, type of residence, and types of home appliances owned) into the app. Additionally, household electricity usage data is periodically sent to the server from the user's smart meter or IoT device.

[0041] The server receives the collected attribute information and energy usage data. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0042] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. The generated power-saving methods are presented to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[0043] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[0044] Specific examples

[0045] Example 1: For a user living alone

[0046] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0047] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[0048] The generative AI model analyzes this data and generates a power-saving method such as, "If you raise the air conditioner's temperature setting by 1 degree in the morning, you can save 5,000 yen on your electricity bill per year."

[0049] The server will push this proposal to the user's device.

[0050] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effectiveness of the suggestions.

[0051] The server evaluates the amount of electricity used and awards a reward to the user.

[0052] Example 2: Family users

[0053] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0054] Data collected by the server: This includes the fact that the user's family uses the most electricity in the evening, regular laundry and cooking schedules, etc.

[0055] The generative AI model analyzes this data and generates a power-saving method such as, "After dinner, use LED lighting, which consumes less energy. This will save you about 3,000 yen a year."

[0056] The server will push this proposal to the user's device.

[0057] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0058] The server evaluates the amount of electricity used and awards a reward to the user.

[0059] In this example, users receive personalized, reliable energy-saving suggestions without asking any direct questions, and can implement them in a few easy steps. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting.

[0063] Step 2:

[0064] The terminal sends the input attribute information to the server, which receives the attribute information and stores it in a database.

[0065] Step 3:

[0066] The server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[0067] Step 4:

[0068] The server preprocesses the collected attribute information and electricity usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0069] Step 5:

[0070] The server inputs the preprocessed data into a generative AI model, which analyzes the user's energy usage patterns and attribute information to generate optimal energy-saving methods.

[0071] Step 6:

[0072] The server sends the generated power-saving methods to the device as a push notification, and the user receives the notification via the device and confirms the proposed power-saving measures.

[0073] Step 7:

[0074] The user implements the suggested energy-saving measures (e.g., changing the air conditioner's temperature setting or switching to LED lighting).

[0075] Step 8:

[0076] The server collects feedback on the energy-saving measures taken by users, who can provide feedback via the app.

[0077] Step 9:

[0078] The server analyzes the power usage data and feedback to evaluate the effectiveness of the implemented power saving measures, such as the degree of reduction in power consumption.

[0079] Step 10:

[0080] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[0081] Step 11:

[0082] The server continuously collects new data to train and update the generative AI model, improving the model's accuracy and providing the latest power-saving suggestions to users.

[0083] Example 1

[0084] 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."

[0085] As household electricity consumption increases, finding appropriate energy-saving methods is an important challenge. However, it is difficult for ordinary users to find individually optimized energy-saving methods. Furthermore, a system is needed to quantitatively evaluate the effectiveness of energy-saving methods and encourage continuous energy-saving behavior. Furthermore, appropriate feedback and rewards are required to continuously improve user behavior.

[0086] 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.

[0087] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving methods to their terminals, means for collecting and evaluating feedback from users, means for rewarding the users based on the evaluation, and means for continuously training and updating the generative AI model. This allows users to receive individually optimized power-saving suggestions and adopt the power-saving methods as actionable actions. Furthermore, the effectiveness of the proposed power-saving methods is evaluated, and rewards are awarded to the users, thereby encouraging sustainable energy-saving behavior.

[0088] "Terminal" refers to a device used by a user, including smartphones, tablets, PCs, etc.

[0089] "Attribute information" is personal, static data about a user, including information such as family composition, type of residence, and types of home appliances owned.

[0090] "Electricity usage data" is data that shows the electricity consumption status in a user's home, and is time-series data collected from smart meters and IoT devices.

[0091] "Preprocessing" refers to processes for improving the quality of collected data, including missing value imputation, scaling, and encoding of categorical variables.

[0092] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate optimal suggestions and predictions for a specific purpose.

[0093] "Power-saving methods" are specific actions that users can take to reduce electricity consumption at home, such as changing the temperature setting on their air conditioner or using LED lighting.

[0094] "Notification" is a means of informing the user of power saving methods and other information generated by the server by sending it to the user's terminal.

[0095] "Feedback" is information about the implementation details and results that the user provides to the server, and is data about the implementation status and effectiveness of the proposed power saving method.

[0096] "Evaluation" is the process of determining the effectiveness of proposed energy conservation methods based on collected feedback and additional energy usage data.

[0097] "Rewards" are incentives that users receive as a result of implementing the suggested energy-saving methods, and can include in-app currency or physical prizes.

[0098] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions according to the power usage situation in a home. The system is implemented as follows.

[0099] First, the user launches the dedicated Eco Electricity app via a device such as a smartphone, tablet, or PC. The user then fills in a form within the app with attribute information such as family composition, type of residence, and types of home appliances owned. This initial input is important data for understanding the user's electricity consumption patterns.

[0100] The device then collects real-time energy usage data from smart meters and connected IoT devices, and transmits the collected data to a server at regular intervals using a standard communication protocol.

[0101] The server preprocesses the received attribute information and electricity usage data by creating a data frame using Python's pandas library, imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0102] Generative AI models are built using libraries such as TensorFlow and PyTorch, and analyze input data to generate optimal power-saving methods. For example, here are some specific examples:

[0103] Example 1: For users living alone

[0104] User: A company employee in his 20s who lives alone in an apartment and uses a refrigerator, air conditioner, washing machine, and microwave.

[0105] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[0106] Energy-saving suggestion from a generative AI model: "By raising the air conditioner temperature setting by 1 degree in the morning, you can save 5,000 yen in electricity bills per year."

[0107] The server sends this proposal to the user's device via a push notification.

[0108] The user follows the suggestions and changes the air conditioner's temperature setting.

[0109] Example prompt sentence:

[0110] "I'm a company employee in my 20s who lives alone and uses a refrigerator, air conditioner, washing machine, and microwave. I'm away from home from 7:00 AM to 6:00 PM, so I'd like to reduce the frequency of using the air conditioner. Please tell me some ways to save on electricity bills."

[0111] In addition, the server collects feedback from users and evaluates the implementation results of the proposed energy-saving methods. Based on the evaluation results, users are given rewards such as in-app currency and real prizes, which encourages users to continue energy-saving behavior.

[0112] The server continuously trains the generative AI model with newly collected data to improve its accuracy, a process that ensures users always receive the most up-to-date and optimal energy-saving suggestions.

[0113] Throughout the system, users simply receive individually optimized energy saving suggestions that can be implemented through concrete actions.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] Users launch the Eco Electricity App on a device such as a smartphone or tablet and enter attribute information such as family composition, type of residence, and types of home appliances they own.

[0117] Input: User's family structure, residence type, and types of appliances owned

[0118] Output: The entered attribute information is sent to the server.

[0119] What happens: A user enters information using a form within the app and presses the submit button, which sends this information to the server.

[0120] Step 2:

[0121] The terminal collects electricity usage data from smart meters and connected IoT devices and sends it to a server at regular intervals.

[0122] Input: Domestic electricity usage data (data from smart meters and IoT devices)

[0123] Output: Collected electricity usage data is stored on the server.

[0124] Specific operation: The terminal periodically communicates with smart meters and IoT devices, acquires electricity usage data, and sends it to a server.

[0125] Step 3:

[0126] The server preprocesses the received attribute information and electricity usage data by imputing missing values, scaling, and encoding categorical variables using the Python pandas library.

[0127] Input: Attribute information, electricity usage data

[0128] Output: Preprocessed data

[0129] What it does: The server runs a Python script to impute missing values ​​in attribute information and electricity usage data, scale it, and convert categorical variables to numeric values ​​as needed.

[0130] Step 4:

[0131] The server inputs the preprocessed data into a generative AI model, a machine learning model using TensorFlow and PyTorch, which analyzes the data and generates optimal power-saving strategies.

[0132] Input: Preprocessed data

[0133] Output: Best way to save power

[0134] How it works: The server feeds data to a generative AI model, which then generates optimal power-saving strategies based on learned patterns.

[0135] Step 5:

[0136] The server sends the generated power saving method to the user's device as a push notification.

[0137] Input: Best way to save energy

[0138] Output: Push notification to the user's device

[0139] Specific operation: The server converts the power saving method into JSON format and sends it to the user's device using the push notification service.

[0140] Step 6:

[0141] The user checks the suggestions and implements specific power saving methods.

[0142] Input: Power saving method received via push notification

[0143] Output: Actual energy-saving measures taken (e.g., raising the air conditioner temperature setting by 1 degree)

[0144] Specific behavior: The user receives a notification through the app, implements the suggested power-saving measures, and checks the results.

[0145] Step 7:

[0146] The server collects feedback from users and evaluates the proposed power saving methods.

[0147] Input: User-entered feedback, latest energy usage data

[0148] Output: Power saving effect evaluation result

[0149] Specific operation: The server analyzes the user's feedback form and power usage data to evaluate the effectiveness of the power saving suggestions.

[0150] Step 8:

[0151] The server rewards users based on the evaluation results, which are provided as in-app currency or physical prizes.

[0152] Input: Evaluation result

[0153] Output: Reward added to user account

[0154] Specific operation: The server calculates the user's reward based on the evaluation results and credits the reward to the user's account.

[0155] Step 9:

[0156] The server continuously trains the generative AI model with new data it collects, which improves the model's accuracy.

[0157] Input: New power usage data, feedback data

[0158] Output: An updated generative AI model

[0159] What it does: The server retrains the generative AI model with newly collected data to improve the model's performance.

[0160] (Application example 1)

[0161] 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."

[0162] This invention relates to a system that makes appropriate energy-saving suggestions based on the store's power usage, and aims to solve the problem that conventional energy-saving methods are abstract and do not provide specific guidelines for action. In addition, by establishing an evaluation and reward system based on user feedback, the system encourages users to continue energy-saving behavior.

[0163] 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.

[0164] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving methods, means for collecting and evaluating feedback from users, means for rewarding users based on the evaluation, and means for providing optimal power-saving methods in real time based on the store's power usage status and power usage data. This makes it possible to provide specific and feasible power-saving suggestions to stores in real time, effectively encouraging users to take energy-saving actions.

[0165] A "terminal" is an electronic device, such as a smartphone, tablet, or PC, that allows a user to input and receive information.

[0166] "Attribute information" refers to information about an individual or household, such as the user's family structure, type of residence, and types of home appliances owned.

[0167] "Electricity usage data" refers to information about electricity consumption collected from smart meters and IoT devices.

[0168] "Preprocessing" refers to operations that process collected data, such as imputing missing values, scaling, and encoding categorical variables.

[0169] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to analyze a user's electricity usage patterns and attribute information to generate optimal energy-saving methods.

[0170] "Power saving methods" are specific suggestions or courses of action that users can take to reduce their electricity consumption.

[0171] "Notification" refers to sending the generated power saving method to the user's device in the form of a push notification or message.

[0172] "Feedback" refers to the user returning actual behavioral data and opinions to the server after following the suggestions.

[0173] "Evaluation" refers to analyzing the effectiveness of the energy-saving measures implemented based on feedback collected from users.

[0174] "Rewards" are incentives such as in-app currency or physical prizes provided to users.

[0175] "Real-time" means that analysis and recommendations are made immediately after data is collected, with results communicated to users almost instantly.

[0176] A "store" is a business office or facility for selling goods or providing services.

[0177] "Power usage data" is detailed data on power consumption in a store by hour.

[0178] "Power saving suggestions" are specific advice for reducing power consumption provided to users based on the analysis of collected data and the generated AI model.

[0179] This invention relates to a system that makes energy-saving suggestions based on the electricity usage status of a store. A user launches an eco-electricity management app using a device such as a smartphone or tablet, and inputs attribute information about the store (e.g., store size, business format, and types of electrical equipment used) into the app. In addition, the store's electricity usage data is periodically sent to a server from smart meters and IoT devices.

[0180] The server receives the attribute information and power usage data collected via the device. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0181] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. This generative AI model uses machine learning frameworks such as TensorFlow and PyTorch. The generated power-saving methods are provided to the user as specific, actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[0182] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[0183] Specific examples

[0184] Example 1: A store in a shopping mall

[0185] User: A store owner in a shopping mall who uses a lot of air conditioning, lighting, and electronics.

[0186] Data collected by the server: Store electricity usage graph, business hours, and information on home appliances being used.

[0187] The generative AI model analyzes this data and generates a suggestion such as, "By raising the air conditioner temperature by 2 degrees after closing, you can save 2,000 yen per month on electricity."

[0188] The server will send a push notification of this proposal to the manager's smartphone.

[0189] The manager follows the suggestions, changes the air conditioning settings and checks the effect.

[0190] Prompt Sentence Examples

[0191] "Generate optimal energy-saving methods based on store power consumption data."

[0192] "Please analyze this data and provide specific energy-saving suggestions: e.g., adjusting the air conditioner temperature setting after closing time."

[0193] This allows stores to receive specific and actionable energy-saving suggestions in real time, effectively encouraging users to take energy-saving actions.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] Data collection

[0197] Users launch the eco-electricity management app on their smartphones, tablets, or other devices and enter their store's attribute information (e.g., store size, business format, and types of electrical equipment used). In addition, the store's electricity usage data is periodically sent to the server from smart meters and IoT devices.

[0198] Input: User attribute information, electricity usage data

[0199] Output: User attribute information and power usage data stored on the server

[0200] Step 2:

[0201] Data Preprocessing

[0202] The server preprocesses the collected attribute information and electricity usage data, including imputing missing values, scaling, and encoding categorical variables.

[0203] Input: Raw user demographic information and electricity usage data

[0204] Output: Preprocessed user attribute information and electricity usage data

[0205] Specific behaviors: missing value imputation, data normalization, categorical variable encoding

[0206] Step 3:

[0207] Input to generative AI models

[0208] The server inputs the preprocessed data into a generative AI model, which is built using a machine learning framework (e.g., TensorFlow or PyTorch).

[0209] Input: Preprocessed user demographic information and electricity usage data

[0210] Output: Analysis results from the generative AI model

[0211] Specific operations: Data analysis, pattern recognition, and generation of power saving methods

[0212] Step 4:

[0213] Generate specific energy-saving methods

[0214] The generative AI model analyzes the user's energy usage patterns and attribute information to generate optimal energy-saving methods, which are then sent to the server as specific, actionable suggestions.

[0215] Input: Preprocessed data

[0216] Output: Specific power saving methods

[0217] Specific operations: Generate power saving methods and confirm the proposed contents

[0218] Step 5:

[0219] notification

[0220] The server sends the generated power saving methods to the user's device as a push notification, allowing the user to review the suggestions and take specific actions.

[0221] Input: Specific energy saving methods

[0222] Output: Push notification sent to user device

[0223] Specific behavior: Creating and sending a push notification

[0224] Step 6:

[0225] Gathering and evaluating feedback

[0226] The server collects feedback from users and evaluates the effectiveness of the implemented power saving measures.

[0227] Input: User feedback

[0228] Output: Evaluation result

[0229] Specific actions: Analyzing feedback and evaluating effectiveness

[0230] Step 7:

[0231] Rewarding

[0232] Based on their ratings, users are rewarded with in-app currency, physical prizes, and other rewards. The generative AI model is continually trained with new data to improve its accuracy.

[0233] Input: Evaluation result

[0234] Output: Reward, updated generative AI model

[0235] Specific operations: Calculating and awarding rewards, training and updating generative AI models

[0236] 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.

[0237] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation in a home.

[0238] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[0239] The device sends the input attribute information and emotion data to a server, which receives this information and stores it in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[0240] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model.

[0241] The generative AI model analyzes the user's power usage patterns, attribute information, and emotional data to generate optimal power-saving methods for each user. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can then review the suggestions and take specific actions.

[0242] Furthermore, the server collects feedback from users and not only evaluates the effectiveness of the implemented power-saving measures, but also evaluates the emotional aspects of the feedback using an emotion engine. This evaluation is a comprehensive evaluation that includes the degree of power consumption reduction and the user's emotional response. Based on this evaluation, users are given rewards such as in-app currency and real prizes.

[0243] The generative AI model is also continually trained with new data to improve its accuracy, ensuring that advice is always based on the most up-to-date information and that personalized energy-saving suggestions take into account the user's emotional state.

[0244] Specific examples

[0245] Example 1: For a user living alone

[0246] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0247] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, peak hours of power usage, and emotional data (e.g., stress levels, mood states).

[0248] The generative AI model analyzes this data and generates energy-saving suggestions, such as "Raising the air conditioner temperature setting by 1 degree in the morning will save you 5,000 yen in electricity bills per year." At the same time, the emotion engine takes into account the user's stress level and adjusts the suggestions to be made during times when stress is lower.

[0249] The server will push this proposal to the user's device.

[0250] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect of the suggestions.

[0251] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0252] Example 2: Family users

[0253] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0254] Data collected by the server: Includes the fact that the user's family consumes the most electricity in the evening, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[0255] The generative AI model analyzes this data and generates energy-saving suggestions such as, "Use LED lighting, which consumes less energy, after dinner. This will save you about 3,000 yen a year." The emotion engine takes into account the emotional state of the entire family and makes suggestions at the most acceptable times.

[0256] The server will push this proposal to the user's device.

[0257] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0258] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0259] This example allows users to receive personalized energy-saving suggestions that take their emotional state into account without asking any direct questions, and implement them in a simple process. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and emotional data (e.g., current mood, stress level) as initial settings.

[0263] Step 2:

[0264] The device sends the input attribute information and emotion data to the server, which receives the attribute information and emotion data and stores them in a database.

[0265] Step 3:

[0266] The server periodically collects electricity usage data from smart meters and IoT devices, including information on household electricity consumption and usage patterns by time of day.

[0267] Step 4:

[0268] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0269] Step 5:

[0270] The server inputs the preprocessed data into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate individually optimized energy-saving methods.

[0271] Step 6:

[0272] The server sends the generated power-saving methods to the device as push notifications. The emotion engine adjusts the timing and content of the suggestions based on the user's emotional state.

[0273] Step 7:

[0274] The user can check the push notification via their device and take specific actions to save energy, such as changing the temperature setting of the air conditioner or doing laundry at a specific time.

[0275] Step 8:

[0276] The server collects user feedback along with emotional data, and users can provide feedback such as their feelings and perceived stress levels through the app.

[0277] Step 9:

[0278] The server analyzes the collected feedback and power usage data to evaluate the effectiveness of the implemented energy-saving measures, based on a comprehensive evaluation that includes the degree of reduction in power consumption and the user's emotional response.

[0279] Step 10:

[0280] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[0281] Step 11:

[0282] The server continuously collects new data to train and update the generative AI model and emotion engine, improving the model's accuracy and providing the latest energy-saving suggestions.

[0283] Example 2

[0284] 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."

[0285] In modern homes, reducing power consumption is an important issue for environmental protection and energy cost reduction. However, it is difficult for users to understand their own power usage patterns and find optimal ways to save power. In addition, there is a demand for energy-saving suggestions that take emotional factors into account, but until now, no system has existed that can achieve this.

[0286] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for collecting emotion data, means for preprocessing the collected attribute information, power usage data, and emotion data, means for generating an optimal power-saving method using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving method, means for collecting and evaluating feedback from the user, means for rewarding the user based on the evaluation, and means for retraining the generative AI model. This enables highly accurate power-saving suggestions that take into account the user's individual power usage pattern and emotional state.

[0287] "Terminal" refers to a device used by a user to input information or receive notifications, and specifically includes smartphones, tablets, and personal computers.

[0288] "Attribute information" refers to information about the user's lifestyle and environment, such as the user's family structure, type of residence, and types of home appliances owned.

[0289] "Electricity usage data" refers to information such as household electricity consumption and usage patterns by time of day obtained through smart meters and IoT devices.

[0290] "Emotional data" refers to information about a user's emotional state, such as their stress level or mood, and is obtained through the app's camera, microphone, or text input.

[0291] "Preprocessing" refers to the process of converting collected data into a format that is easier to analyze, and specifically includes imputing missing data, scaling numerical data, and encoding categorical variables.

[0292] "Generative AI model" refers to an artificial intelligence model used to analyze collected data and generate optimal energy-saving methods for each user.

[0293] "Power saving method" refers to a specific and feasible method for reducing power consumption that is provided based on a user's power usage pattern.

[0294] "Notification" refers to the act of notifying the user's device of the power saving method generated by the server, and specifically includes push notifications.

[0295] "Feedback" refers to the act of a user providing information such as the results of implementing a proposed energy-saving method and their impressions.

[0296] "Evaluation" refers to the act of analyzing the effectiveness of implemented energy-saving measures and users' emotional reactions based on feedback collected from users.

[0297] "Rewards" refer to incentives such as in-app currency or real prizes given to users based on the evaluation results.

[0298] "Retraining" refers to the act of retraining a generative AI model using newly collected data in order to improve its accuracy.

[0299] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation in a home. Specifically, the system is implemented in the following manner.

[0300] System configuration

[0301] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[0302] The device sends the input attribute information and emotion data to a server. The server receives this information and stores it in a database, such as MySQL or MongoDB. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes household electricity consumption and usage patterns by time of day.

[0303] The server preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. Python libraries (e.g., Pandas, Scikit-learn) are used for preprocessing.

[0304] The preprocessed data is input into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate optimal energy-saving methods for each user. This analysis is performed using deep learning frameworks (e.g., TensorFlow, PyTorch).

[0305] The generated power-saving methods are provided to the user as specific and actionable suggestions, and the server sends these power-saving methods to the user's device as push notifications using a notification service such as Firebase Cloud Messaging (FCM).

[0306] Users can review the suggestions and take specific actions. They also provide feedback within the app, such as the effectiveness of the suggestions and their impressions. The server receives this feedback and evaluates it. The evaluation includes analyzing the collected emotional data with an emotion engine.

[0307] Based on the feedback, the server can reward the user, which can include in-app currency or physical prizes.

[0308] The generative AI model is also continually trained with new data to improve its accuracy, ensuring that advice is always based on the most up-to-date information and that personalized energy-saving suggestions take into account the user's emotional state.

[0309] Specific examples

[0310] Example 1: For a user living alone

[0311] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0312] Data collected by the server: Attribute information such as being away from home between 7am and 6pm, frequency of air conditioning use, peak hours of electricity usage, and emotional data (e.g., stress level, mood state).

[0313] Based on this data, the generative AI model suggests, "Raising the air conditioner temperature setting by 1 degree in the morning will save 5,000 yen in electricity bills per year." The emotion engine takes into account the user's stress level and makes suggestions for times when stress is low.

[0314] The server sends a push notification of this proposal to the user's device.

[0315] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect.

[0316] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0317] Example 2: Family users

[0318] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0319] Data collected by the server: Attribute information such as which hours of the day a family uses the most electricity, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[0320] Based on this data, the generative AI model suggests, "Using LED lighting after dinner, which consumes less energy, can save approximately 3,000 yen per year." The model makes this suggestion at the most receptive timing, taking into account the emotional state of the entire family.

[0321] The server sends a push notification of this proposal to the user's device.

[0322] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0323] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0324] This allows users to receive individually optimized energy-saving suggestions that take into account their emotional state without asking any direct questions, and implement them in a simple procedure. Furthermore, continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0326] Step 1:

[0327] Users launch the Eco Electricity app using a device such as a smartphone, tablet, or PC. On the initial setup screen, users enter attribute information such as family composition, type of residence, and the types of appliances used. Users can also provide emotional data using the app's camera, microphone, or text input. Inputs include attribute information and emotional data, and the output is data that the device sends to the server.

[0328] As a specific operation, after the user has finished inputting, he or she presses the "send" button.

[0329] Step 2:

[0330] The terminal transmits the attribute information and emotion data entered by the user to the server via the Internet. The input data includes the user's attribute information and emotion data, and the output data is delivered to the server.

[0331] Specifically, the device uses Wi-Fi or mobile data communication to send data to the server's API as a POST request.

[0332] Step 3:

[0333] The server receives the attribute information and emotion data and stores them in a database, such as MySQL or MongoDB. The input is the received data, and the output is the attribute information and emotion data stored in the database.

[0334] Specifically, the server receives the data in JSON format and inserts it into the appropriate table or collection.

[0335] Step 4:

[0336] The server periodically collects household electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day. The input is electricity usage data from the smart meters, and the output is electricity usage data accumulated by the server.

[0337] Specifically, the server uses an API to send a data acquisition request to the smart meter every 30 minutes.

[0338] Step 5:

[0339] The server preprocesses the collected attribute information, emotion data, and power usage data. Preprocessing includes imputing missing data, scaling numerical data, encoding categorical variables, etc. The input is the various collected and stored data, and the output is the preprocessed data.

[0340] Specifically, it uses Python's Pandas and Scikit-learn libraries to cleanse and transform data.

[0341] Step 6:

[0342] The preprocessed data is input into a generative AI model, which uses this data to generate optimal power-saving methods for each user. The input is the preprocessed data, and the output is the optimal power-saving method.

[0343] Specifically, it runs deep learning models using TensorFlow and PyTorch to generate user-specific power-saving suggestions.

[0344] Step 7:

[0345] The generated power saving method is sent from the server to the user's device as a push notification. The input is the generated power saving method, and the output is a notification displayed on the user's device.

[0346] Specifically, it sends a message using a notification service such as Firebase Cloud Messaging (FCM).

[0347] Step 8:

[0348] The user checks the received power-saving suggestions and takes specific actions according to the suggestions. The input is the power-saving suggestions displayed on the terminal, and the output is the actual power-saving actions.

[0349] Specific actions include following suggestions such as raising the air conditioner's set temperature by 1 degree or switching to LED lighting.

[0350] Step 9:

[0351] The server collects feedback from users and evaluates the effectiveness of the implemented power-saving measures. The evaluation also analyzes emotional feedback using an emotion engine. The input is user feedback data, and the output is the evaluation result.

[0352] Specifically, the server collects opinions and feedback through a feedback form and runs a Python script to analyze them.

[0353] Step 10:

[0354] The server retrains the generative AI model to improve its accuracy, updating it with newly collected data, with the new data as input and the retrained model as output.

[0355] Specifically, it periodically inputs new data into the model in batches and runs a script to retrain it.

[0356] (Application example 2)

[0357] 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."

[0358] Optimizing energy consumption is an urgent issue in modern homes and brick-and-mortar stores, but existing energy-saving suggestion systems have problems with low suggestion acceptance and implementation rates because they do not fully consider the user's emotional state or individual attribute information. Furthermore, there are insufficient means to properly evaluate user feedback and improve the accuracy of generative AI models through continuous training.

[0359] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for preprocessing the collected attribute information and power usage data, means for generating an optimal power-saving method using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving method, means for collecting and preprocessing the user's emotional data, means for analyzing the emotional data to optimize the timing of the notification of the suggestion, means for collecting and evaluating feedback from the user, and means for rewarding the user based on the evaluation. This enables individually optimized power-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, by training and updating the generative AI model based on continuous feedback, the system always provides the latest and most accurate suggestions.

[0360] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[0361] "Attribute information" refers to information such as the user's family composition, type of residence, and types of home appliances owned.

[0362] "Electricity usage data" refers to data on electricity consumption within homes and stores and usage patterns by time of day, collected from smart meters and IoT devices.

[0363] "Preprocessing" is the process of preparing collected data by completing missing data, scaling numerical data, encoding categorical variables, etc.

[0364] A "generative AI model" is an artificial intelligence model that analyzes data, finds complex patterns and relationships, and generates optimal energy-saving methods.

[0365] "Power saving methods" refers to specific techniques and proposals for reducing power consumption.

[0366] "Feedback" is data obtained from users regarding the effectiveness of implemented energy saving suggestions and their emotional reactions.

[0367] "Rewards" are incentives such as in-app currency or physical prizes that are given to users after they put the suggested energy-saving methods into practice and their effectiveness is confirmed.

[0368] "Emotional data" refers to data that indicates the user's emotional state, such as stress level or mood.

[0369] The "Emotion Engine" is an artificial intelligence system that analyzes collected emotional data and optimizes the timing of notification suggestions.

[0370] This invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation of a home or a brick-and-mortar store. Detailed embodiments of this system will be described below.

[0371] First, the user launches the Eco Electricity app on a device such as a smartphone, tablet, or PC. During initial setup, attribute information (e.g., family composition, residence type, and types of appliances owned) and electricity usage data are collected from the user via the device. The user also provides emotional data via the app's camera, microphone, and text input.

[0372] The device sends this information to a server, which stores the received attribute information and emotion data in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes electricity consumption in homes and stores and usage patterns by time of day.

[0373] The server then preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model to generate optimal energy-saving methods based on the user's energy usage patterns, attribute information, and emotion data.

[0374] The generated power-saving methods are notified to the device as specific and actionable suggestions. These suggestions are notified at appropriate times by the emotion engine, taking into account the user's emotional state. The server then sends these power-saving methods to the user's device as push notifications, allowing the user to confirm the suggestions and take specific actions.

[0375] The server also collects user feedback and evaluates the effectiveness of the app, based on a comprehensive evaluation that includes the degree of energy consumption reduction and the user's emotional response. Based on this evaluation, users are rewarded with in-app currency or real prizes.

[0376] Additionally, the generative AI model is continually trained with new data to improve its accuracy, ensuring that it always delivers the most up-to-date and accurate recommendations.

[0377] As a concrete example, let us consider the case of a coffee shop.

[0378] For example, if the user is a coffee shop manager, the server collects business hours, peak power usage, and staff emotional data (e.g., stress levels during busy hours). The generative AI model generates suggestions such as, "By reducing the store's lighting by half between 10:00 and 11:00 a.m., when there are fewer customers, you can save 2,000 yen per month on electricity." The emotion engine takes into account the emotional state of the staff and notifies them at times when stress is low. The server sends a push notification of this suggestion to the manager's smartphone, who then consults with the staff and adjusts the lighting. The server then evaluates the change in power usage and confirms the power-saving effect. The manager is rewarded with in-app currency as a success reward.

[0379] An example of a prompt would be, "Consider power usage data and emotion data and generate the optimal energy-saving method for a coffee shop. For example, reduce the lights by half between 10:00 and 11:00 AM." By inputting this prompt into the generative AI model, the corresponding energy-saving suggestion will be generated.

[0380] As described above, this system enables individually optimized energy-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, continuous feedback and model training enable the system to always provide the latest and most accurate suggestions.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] Users launch the Eco Electric app on their smartphone, tablet, PC, or other device. During the initial setup, users enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and also provide emotional data (e.g., stress level, mood state).

[0384] Input: Attribute information, emotion data

[0385] Output: Attribute information and emotion data are saved on the device.

[0386] Step 2:

[0387] The device sends the collected attribute information and emotion data to the server. It also periodically collects electricity usage data from smart meters and IoT devices within the home or physical store and sends it to the server.

[0388] Input: attribute information, emotion data, power usage data

[0389] Output: Attribute information, emotion data, and power usage data are stored on the server.

[0390] Step 3:

[0391] The server preprocesses the received attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0392] Input: attribute information, emotion data, power usage data

[0393] Output: Preprocessed data

[0394] Step 4:

[0395] The server inputs the preprocessed data into a generative AI model, which generates optimal energy-saving methods based on the user's power usage patterns, attribute information, and emotional data.

[0396] Input: Preprocessed data

[0397] Output: Best way to save power

[0398] Step 5:

[0399] The server sends the generated power-saving methods to the user's device as push notifications, with the emotion engine providing the notifications at appropriate times, taking into account the user's emotional state.

[0400] Input: Optimal power saving method, emotional data

[0401] Output: Push notification of power saving suggestions

[0402] Step 6:

[0403] Users can check the energy-saving suggestions sent to their device and take specific actions, such as adjusting lighting or changing air conditioning settings.

[0404] Input: Push notification of power saving suggestions

[0405] Output: Energy saving actions taken

[0406] Step 7:

[0407] The server collects feedback from users and evaluates the effectiveness of the implemented energy-saving measures, including the degree of reduction in power consumption and the user's emotional response.

[0408] Input: Feedback data

[0409] Output: Evaluation result

[0410] Step 8:

[0411] The server rewards the user (e.g., in-app currency, real prizes) based on the evaluation results.

[0412] Input: Evaluation result

[0413] Output: Reward granted

[0414] Step 9:

[0415] The server uses the preprocessed data and feedback data to train and update the generative AI model, and this continuous training improves the accuracy of the generative AI model.

[0416] Input: Preprocessed data, feedback data

[0417] Output: An updated generative AI model

[0418] 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.

[0419] 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.

[0420] 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.

[0421] [Second embodiment]

[0422] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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."

[0434] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions based on household power usage.

[0435] First, the user launches the Eco Electricity app via a device such as a smartphone, tablet, or PC. The user enters attribute information (e.g., family composition, type of residence, and types of home appliances owned) into the app. Additionally, household electricity usage data is periodically sent to the server from the user's smart meter or IoT device.

[0436] The server receives the collected attribute information and energy usage data. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0437] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[0438] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[0439] Specific examples

[0440] Example 1: For a user living alone

[0441] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0442] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[0443] The generative AI model analyzes this data and generates a power-saving method such as, "If you raise the air conditioner's temperature setting by 1 degree in the morning, you can save 5,000 yen on your electricity bill per year."

[0444] The server will push this proposal to the user's device.

[0445] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effectiveness of the suggestions.

[0446] The server evaluates the amount of electricity used and awards a reward to the user.

[0447] Example 2: Family users

[0448] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0449] Data collected by the server: This includes the fact that the user's family uses the most electricity in the evenings, regular laundry and cooking schedules, etc.

[0450] The generative AI model analyzes this data and generates a power-saving method such as, "After dinner, use LED lighting, which consumes less energy. This will save you about 3,000 yen a year."

[0451] The server will push this proposal to the user's device.

[0452] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0453] The server evaluates the amount of electricity used and awards a reward to the user.

[0454] In this example, users receive personalized, reliable energy-saving suggestions without asking any direct questions, and can implement them in a few easy steps. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0455] The processing flow will be explained below.

[0456] Step 1:

[0457] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting.

[0458] Step 2:

[0459] The terminal sends the input attribute information to the server, which receives the attribute information and stores it in a database.

[0460] Step 3:

[0461] The server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[0462] Step 4:

[0463] The server preprocesses the collected attribute information and electricity usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0464] Step 5:

[0465] The server inputs the preprocessed data into a generative AI model, which analyzes the user's power usage patterns and attribute information to generate optimal energy-saving methods.

[0466] Step 6:

[0467] The server sends the generated power-saving methods to the device as a push notification, and the user receives the notification via the device and confirms the proposed power-saving measures.

[0468] Step 7:

[0469] The user implements the suggested energy-saving measures (e.g., changing the air conditioner's temperature setting or switching to LED lighting).

[0470] Step 8:

[0471] The server collects feedback on the energy-saving measures taken by users, who can provide feedback via the app.

[0472] Step 9:

[0473] The server analyzes the power usage data and feedback to evaluate the effectiveness of the implemented power saving measures, such as the degree of reduction in power consumption.

[0474] Step 10:

[0475] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[0476] Step 11:

[0477] The server continuously collects new data to train and update the generative AI model, improving the model's accuracy and providing the latest power-saving suggestions to the user.

[0478] Example 1

[0479] 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."

[0480] As household electricity consumption increases, finding appropriate energy-saving methods is an important challenge. However, it is difficult for ordinary users to find individually optimized energy-saving methods. Furthermore, a system is needed to quantitatively evaluate the effectiveness of energy-saving methods and encourage continuous energy-saving behavior. Furthermore, appropriate feedback and rewards are required to continuously improve user behavior.

[0481] 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.

[0482] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving methods to their terminals, means for collecting and evaluating feedback from users, means for rewarding the users based on the evaluation, and means for continuously training and updating the generative AI model. This allows users to receive individually optimized power-saving suggestions and adopt the power-saving methods as actionable actions. Furthermore, the effectiveness of the proposed power-saving methods is evaluated, and rewards are awarded to the users, thereby encouraging sustainable energy-saving behavior.

[0483] "Terminal" refers to a device used by a user, including smartphones, tablets, PCs, etc.

[0484] "Attribute information" is personal, static data about a user, including information such as family composition, type of residence, and types of home appliances owned.

[0485] "Electricity usage data" is data that shows the electricity consumption status in a user's home, and is time-series data collected from smart meters and IoT devices.

[0486] "Preprocessing" refers to processes for improving the quality of collected data, including missing value imputation, scaling, and encoding of categorical variables.

[0487] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate optimal suggestions and predictions for a specific purpose.

[0488] "Power-saving methods" are specific actions that users can take to reduce electricity consumption at home, such as changing the temperature setting on their air conditioner or using LED lighting.

[0489] "Notification" is a means of informing the user of power saving methods and other information generated by the server by sending it to the user's terminal.

[0490] "Feedback" is information about the implementation details and results that the user provides to the server, and is data about the implementation status and effectiveness of the proposed power saving method.

[0491] "Evaluation" is the process of determining the effectiveness of proposed energy conservation methods based on collected feedback and additional energy usage data.

[0492] "Rewards" are incentives that users receive as a result of implementing the suggested energy-saving methods, and can include in-app currency or physical prizes.

[0493] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions according to the power usage situation in a home. The system is implemented as follows.

[0494] First, the user launches the dedicated Eco Electricity app via a device such as a smartphone, tablet, or PC. The user then fills in a form within the app with attribute information such as family composition, type of residence, and types of home appliances owned. This initial input is important data for understanding the user's electricity consumption patterns.

[0495] The device then collects real-time energy usage data from smart meters and connected IoT devices, and transmits the collected data to a server at regular intervals using a standard communication protocol.

[0496] The server preprocesses the received attribute information and electricity usage data by creating a data frame using Python's pandas library, imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0497] Generative AI models are built using libraries such as TensorFlow and PyTorch, and analyze input data to generate optimal power-saving methods. For example, here are some specific examples:

[0498] Example 1: For users living alone

[0499] User: A company employee in his 20s who lives alone in an apartment and uses a refrigerator, air conditioner, washing machine, and microwave.

[0500] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[0501] Energy-saving suggestion from a generative AI model: "By raising the air conditioner temperature setting by 1 degree in the morning, you can save 5,000 yen in electricity bills per year."

[0502] The server sends this proposal to the user's device via a push notification.

[0503] The user follows the suggestions and changes the air conditioner's temperature setting.

[0504] Example prompt sentence:

[0505] "I'm a company employee in my 20s who lives alone and uses a refrigerator, air conditioner, washing machine, and microwave. I'm away from home from 7:00 AM to 6:00 PM, so I'd like to reduce the frequency of using the air conditioner. Please tell me some ways to save on electricity bills."

[0506] Furthermore, the server collects feedback from users and evaluates the results of the proposed energy-saving methods. Based on the evaluation results, users are given rewards such as in-app currency and real prizes, which encourages users to continue energy-saving behavior.

[0507] The server continuously trains the generative AI model with newly collected data to improve its accuracy, a process that ensures users always receive the most up-to-date and optimal energy-saving suggestions.

[0508] Throughout the system, users simply receive individually optimized energy saving suggestions that can be implemented through concrete actions.

[0509] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0510] Step 1:

[0511] Users launch the Eco Electricity App on a device such as a smartphone or tablet and enter attribute information such as family composition, type of residence, and types of home appliances they own.

[0512] Input: User's family structure, residence type, and types of appliances owned

[0513] Output: The entered attribute information is sent to the server.

[0514] What happens: A user enters information using a form within the app and presses the submit button, which sends this information to the server.

[0515] Step 2:

[0516] The terminal collects electricity usage data from smart meters and connected IoT devices and sends it to a server at regular intervals.

[0517] Input: Domestic electricity usage data (data from smart meters and IoT devices)

[0518] Output: Collected electricity usage data is stored on the server.

[0519] Specific operation: The terminal periodically communicates with smart meters and IoT devices, acquires electricity usage data, and sends it to a server.

[0520] Step 3:

[0521] The server preprocesses the received attribute information and electricity usage data by imputing missing values, scaling, and encoding categorical variables using the Python pandas library.

[0522] Input: Attribute information, electricity usage data

[0523] Output: Preprocessed data

[0524] What it does: The server runs a Python script to impute missing values ​​in attribute information and electricity usage data, scale it, and convert categorical variables to numeric values ​​as needed.

[0525] Step 4:

[0526] The server inputs the preprocessed data into a generative AI model, a machine learning model using TensorFlow and PyTorch, which analyzes the data and generates optimal power-saving strategies.

[0527] Input: Preprocessed data

[0528] Output: Best way to save power

[0529] How it works: The server feeds data to a generative AI model, which then generates optimal power-saving strategies based on learned patterns.

[0530] Step 5:

[0531] The server sends the generated power saving method to the user's device as a push notification.

[0532] Input: Best way to save energy

[0533] Output: Push notification to the user's device

[0534] Specific operation: The server converts the power saving method into JSON format and sends it to the user's device using the push notification service.

[0535] Step 6:

[0536] The user checks the suggestions and implements specific power saving methods.

[0537] Input: Power saving method received via push notification

[0538] Output: Actual energy-saving measures taken (e.g., raising the air conditioner temperature setting by 1 degree)

[0539] Specific behavior: The user receives a notification through the app, implements the suggested power-saving measures, and checks the results.

[0540] Step 7:

[0541] The server collects feedback from users and evaluates the proposed power saving methods.

[0542] Input: User-entered feedback, latest energy usage data

[0543] Output: Power saving effect evaluation result

[0544] Specific operation: The server analyzes the user's feedback form and power usage data to evaluate the effectiveness of the power saving suggestions.

[0545] Step 8:

[0546] The server rewards users based on the evaluation results, which are provided as in-app currency or physical prizes.

[0547] Input: Evaluation result

[0548] Output: Reward added to user account

[0549] Specific operation: The server calculates the user's reward based on the evaluation results and credits the reward to the user's account.

[0550] Step 9:

[0551] The server continuously trains the generative AI model with new data it collects, which improves the model's accuracy.

[0552] Input: New electricity usage data, feedback data

[0553] Output: An updated generative AI model

[0554] What it does: The server retrains the generative AI model with newly collected data to improve the model's performance.

[0555] (Application example 1)

[0556] 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."

[0557] This invention relates to a system that makes appropriate energy-saving suggestions based on the store's power usage, and aims to solve the problem that conventional energy-saving methods are abstract and do not provide specific guidelines for action. In addition, by establishing an evaluation and reward system based on user feedback, the system encourages users to continue energy-saving behavior.

[0558] 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.

[0559] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving methods, means for collecting and evaluating feedback from users, means for rewarding users based on the evaluation, and means for providing optimal power-saving methods in real time based on the store's power usage status and power usage data. This makes it possible to provide specific and feasible power-saving suggestions to stores in real time, effectively encouraging users to take energy-saving actions.

[0560] A "terminal" is an electronic device, such as a smartphone, tablet, or PC, that allows a user to input and receive information.

[0561] "Attribute information" refers to information about an individual or household, such as the user's family structure, type of residence, and types of home appliances owned.

[0562] "Electricity usage data" refers to information about electricity consumption collected from smart meters and IoT devices.

[0563] "Preprocessing" refers to operations that process collected data, such as imputing missing values, scaling, and encoding categorical variables.

[0564] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to analyze a user's electricity usage patterns and attribute information to generate optimal energy-saving methods.

[0565] "Power saving methods" are specific suggestions or courses of action that users can take to reduce their electricity consumption.

[0566] "Notification" refers to sending the generated power saving method to the user's device in the form of a push notification or message.

[0567] "Feedback" refers to the user returning actual behavioral data and opinions to the server after following the suggestions.

[0568] "Evaluation" refers to analyzing the effectiveness of the energy-saving measures implemented based on feedback collected from users.

[0569] "Rewards" are incentives such as in-app currency or physical prizes provided to users.

[0570] "Real-time" means that analysis and recommendations are made immediately after data is collected, with results communicated to users almost instantly.

[0571] A "store" is a business office or facility for selling goods or providing services.

[0572] "Power usage data" is detailed data on power consumption in a store by hour.

[0573] "Power saving suggestions" are specific advice for reducing power consumption provided to users based on the analysis of collected data and the generated AI model.

[0574] This invention relates to a system that makes energy-saving suggestions based on the electricity usage status of a store. A user launches an eco-electricity management app using a device such as a smartphone or tablet, and inputs attribute information about the store (e.g., store size, business format, and types of electrical equipment used) into the app. In addition, the store's electricity usage data is periodically sent to a server from smart meters and IoT devices.

[0575] The server receives the attribute information and energy usage data collected via the device. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0576] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. This generative AI model uses machine learning frameworks such as TensorFlow and PyTorch. The generated power-saving methods are provided to the user as specific, actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[0577] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[0578] Specific examples

[0579] Example 1: A store in a shopping mall

[0580] User: A store owner in a shopping mall who uses a lot of air conditioning, lighting, and electronics.

[0581] Data collected by the server: Store electricity usage graph, business hours, and information on home appliances being used.

[0582] The generative AI model analyzes this data and generates a suggestion such as, "By raising the air conditioner temperature by 2 degrees after closing, you can save 2,000 yen per month on electricity."

[0583] The server will send a push notification of this proposal to the manager's smartphone.

[0584] The manager follows the suggestions, changes the air conditioning settings and checks the effect.

[0585] Prompt Sentence Examples

[0586] "Generate optimal energy-saving methods based on store power consumption data."

[0587] "Please analyze this data and provide specific energy-saving suggestions: e.g., adjusting the air conditioner temperature setting after closing time."

[0588] This allows stores to receive specific and actionable energy-saving suggestions in real time, effectively encouraging users to take energy-saving actions.

[0589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0590] Step 1:

[0591] Data collection

[0592] Users launch the eco-electricity management app on their smartphones, tablets, or other devices and enter their store's attribute information (e.g., store size, business format, and types of electrical equipment used). In addition, the store's electricity usage data is periodically sent to the server from smart meters and IoT devices.

[0593] Input: User attribute information, electricity usage data

[0594] Output: User attribute information and power usage data stored on the server

[0595] Step 2:

[0596] Data Preprocessing

[0597] The server preprocesses the collected attribute information and electricity usage data, including imputing missing values, scaling, and encoding categorical variables.

[0598] Input: Raw user demographic information and electricity usage data

[0599] Output: Preprocessed user attribute information and electricity usage data

[0600] Specific behaviors: missing value imputation, data normalization, categorical variable encoding

[0601] Step 3:

[0602] Input to generative AI models

[0603] The server inputs the preprocessed data into a generative AI model, which is built using a machine learning framework (e.g., TensorFlow or PyTorch).

[0604] Input: Preprocessed user demographic information and electricity usage data

[0605] Output: Analysis results from the generative AI model

[0606] Specific operations: Data analysis, pattern recognition, and generation of power saving methods

[0607] Step 4:

[0608] Generate specific energy-saving methods

[0609] The generative AI model analyzes the user's energy usage patterns and attribute information to generate optimal energy-saving methods, which are then sent to the server as specific, actionable suggestions.

[0610] Input: Preprocessed data

[0611] Output: Specific power saving methods

[0612] Specific operations: Generate power saving methods and confirm the proposed contents

[0613] Step 5:

[0614] notification

[0615] The server sends the generated power saving methods to the user's device as a push notification, allowing the user to review the suggestions and take specific actions.

[0616] Input: Specific energy saving methods

[0617] Output: Push notification sent to user device

[0618] Specific behavior: Creating and sending a push notification

[0619] Step 6:

[0620] Gathering and evaluating feedback

[0621] The server collects feedback from users and evaluates the effectiveness of the implemented power saving measures.

[0622] Input: User feedback

[0623] Output: Evaluation result

[0624] Specific actions: Analyzing feedback and evaluating effectiveness

[0625] Step 7:

[0626] Rewarding

[0627] Based on their ratings, users are rewarded with in-app currency, physical prizes, and other rewards. The generative AI model is continually trained with new data to improve its accuracy.

[0628] Input: Evaluation result

[0629] Output: Reward, updated generative AI model

[0630] Specific operations: Calculating and awarding rewards, training and updating generative AI models

[0631] 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.

[0632] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the electricity usage situation in a home.

[0633] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[0634] The device sends the input attribute information and emotion data to a server, which receives this information and stores it in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[0635] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model.

[0636] The generative AI model analyzes the user's power usage patterns, attribute information, and emotional data to generate optimal power-saving methods for each user. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can then review the suggestions and take specific actions.

[0637] Furthermore, the server collects feedback from users and not only evaluates the effectiveness of the implemented power-saving measures, but also evaluates the emotional aspects of the feedback using an emotion engine. This evaluation is a comprehensive evaluation that includes the degree of power consumption reduction and the user's emotional response. Based on this evaluation, users are given rewards such as in-app currency and real prizes.

[0638] The generative AI model is also continually trained with new data to improve its accuracy, ensuring that advice is always based on the most up-to-date information and that personalized energy-saving suggestions take into account the user's emotional state.

[0639] Specific examples

[0640] Example 1: For a user living alone

[0641] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0642] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, peak hours of power usage, and emotional data (e.g., stress levels, mood states).

[0643] The generative AI model analyzes this data and generates energy-saving suggestions, such as "Raising the air conditioner temperature setting by 1 degree in the morning will save you 5,000 yen in electricity bills per year." At the same time, the emotion engine takes into account the user's stress level and adjusts the suggestions to be made during times when stress is lower.

[0644] The server will push this proposal to the user's device.

[0645] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect of the suggestions.

[0646] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0647] Example 2: Family users

[0648] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0649] Data collected by the server: Includes the fact that the user's family consumes the most electricity in the evening, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[0650] The generative AI model analyzes this data and generates energy-saving suggestions such as, "Use LED lighting, which consumes less energy, after dinner. This will save you about 3,000 yen a year." The emotion engine takes into account the emotional state of the entire family and makes suggestions at the most acceptable times.

[0651] The server will push this proposal to the user's device.

[0652] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0653] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0654] This example allows users to receive personalized energy-saving suggestions that take their emotional state into account without asking any direct questions, and implement them in a simple procedure. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0655] The processing flow will be explained below.

[0656] Step 1:

[0657] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and emotional data (e.g., current mood, stress level) as initial settings.

[0658] Step 2:

[0659] The device sends the input attribute information and emotion data to the server, which receives the attribute information and emotion data and stores them in a database.

[0660] Step 3:

[0661] The server periodically collects electricity usage data from smart meters and IoT devices, including information on household electricity consumption and usage patterns by time of day.

[0662] Step 4:

[0663] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0664] Step 5:

[0665] The server inputs the preprocessed data into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate individually optimized energy-saving methods.

[0666] Step 6:

[0667] The server sends the generated power-saving methods to the device as push notifications. The emotion engine adjusts the timing and content of the suggestions based on the user's emotional state.

[0668] Step 7:

[0669] The user checks the push notification via their device and takes specific action to save energy, such as changing the air conditioner temperature setting or doing laundry at a specific time.

[0670] Step 8:

[0671] The server collects user feedback along with emotional data, and users can provide feedback such as their feelings and perceived stress levels through the app.

[0672] Step 9:

[0673] The server analyzes the collected feedback and power usage data to evaluate the effectiveness of the implemented energy-saving measures, based on a comprehensive evaluation that includes the degree of reduction in power consumption and the user's emotional response.

[0674] Step 10:

[0675] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[0676] Step 11:

[0677] The server continuously collects new data to train and update the generative AI model and emotion engine, improving the model's accuracy and providing the latest energy-saving suggestions.

[0678] Example 2

[0679] 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."

[0680] In modern homes, reducing power consumption is an important issue for environmental protection and energy cost reduction. However, it is difficult for users to understand their own power usage patterns and find optimal ways to save power. In addition, there is a demand for energy-saving suggestions that take emotional factors into account, but until now, no system has existed that can achieve this.

[0681] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for collecting emotion data, means for preprocessing the collected attribute information, power usage data, and emotion data, means for generating an optimal power-saving method using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving method, means for collecting and evaluating feedback from the user, means for rewarding the user based on the evaluation, and means for retraining the generative AI model. This enables highly accurate power-saving suggestions that take into account the user's individual power usage pattern and emotional state.

[0682] "Terminal" refers to a device used by a user to input information or receive notifications, and specifically includes smartphones, tablets, and personal computers.

[0683] "Attribute information" refers to information about the user's lifestyle and environment, such as the user's family structure, type of residence, and types of home appliances owned.

[0684] "Electricity usage data" refers to information such as household electricity consumption and usage patterns by time of day obtained through smart meters and IoT devices.

[0685] "Emotional data" refers to information about a user's emotional state, such as their stress level or mood, and is obtained through the app's camera, microphone, or text input.

[0686] "Preprocessing" refers to the process of converting collected data into a format that is easier to analyze, and specifically includes imputing missing data, scaling numerical data, and encoding categorical variables.

[0687] "Generative AI model" refers to an artificial intelligence model used to analyze collected data and generate optimal energy-saving methods for each user.

[0688] "Power saving method" refers to a specific and feasible method for reducing power consumption that is provided based on a user's power usage pattern.

[0689] "Notification" refers to the act of notifying the user's device of the power saving method generated by the server, and specifically includes push notifications.

[0690] "Feedback" refers to the act of a user providing information such as the results of implementing a proposed energy-saving method and their impressions.

[0691] "Evaluation" refers to the act of analyzing the effectiveness of implemented energy-saving measures and users' emotional reactions based on feedback collected from users.

[0692] "Rewards" refer to incentives such as in-app currency or real prizes given to users based on the evaluation results.

[0693] "Retraining" refers to the act of retraining a generative AI model using newly collected data in order to improve its accuracy.

[0694] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation in a home. Specifically, the system is implemented in the following manner.

[0695] System configuration

[0696] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[0697] The device sends the input attribute information and emotion data to a server. The server receives this information and stores it in a database, such as MySQL or MongoDB. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes household electricity consumption and usage patterns by time of day.

[0698] The server preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. Python libraries (e.g., Pandas, Scikit-learn) are used for preprocessing.

[0699] The preprocessed data is input into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate optimal energy-saving methods for each user. This analysis is performed using deep learning frameworks (e.g., TensorFlow, PyTorch).

[0700] The generated power-saving methods are provided to the user as specific and actionable suggestions, and the server sends these power-saving methods to the user's device as push notifications using a notification service such as Firebase Cloud Messaging (FCM).

[0701] Users can check the suggestions and take specific actions. They also provide feedback within the app, such as the effectiveness of the suggestions and their impressions. The server receives this feedback and evaluates it. The evaluation includes analyzing the collected emotional data with an emotion engine.

[0702] Based on the feedback, the server can reward the user, which can include in-app currency or physical prizes.

[0703] The generative AI model is also continually trained with new data to improve its accuracy, ensuring advice is always based on the most up-to-date information and personalized energy-saving suggestions that take into account the user's emotional state.

[0704] Specific examples

[0705] Example 1: For a user living alone

[0706] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0707] Data collected by the server: Attribute information such as being away from home between 7am and 6pm, frequency of air conditioning use, peak hours of electricity usage, and emotional data (e.g., stress level, mood state).

[0708] Based on this data, the generative AI model suggests, "Raising the air conditioner temperature setting by 1 degree in the morning will save 5,000 yen in electricity bills per year." The emotion engine takes into account the user's stress level and makes suggestions for times when stress is low.

[0709] The server sends a push notification of this proposal to the user's device.

[0710] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect.

[0711] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0712] Example 2: Family users

[0713] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0714] Data collected by the server: Attribute information such as which hours of the day a family uses the most electricity, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[0715] Based on this data, the generative AI model suggests, "Using LED lighting after dinner, which consumes less energy, can save approximately 3,000 yen per year." The model makes this suggestion at the most receptive timing, taking into account the emotional state of the entire family.

[0716] The server sends a push notification of this proposal to the user's device.

[0717] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0718] The server evaluates the power consumption and emotion data and awards a reward to the user.

[0719] This allows users to receive individually optimized energy-saving suggestions that take into account their emotional state without asking any direct questions, and implement them in a simple procedure. In addition, continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] Users launch the Eco Electricity app using a device such as a smartphone, tablet, or PC. On the initial setup screen, users enter attribute information such as family composition, type of residence, and the types of appliances used. Users can also provide emotional data using the app's camera, microphone, or text input. Inputs include attribute information and emotional data, and the output is data that the device sends to the server.

[0723] As a specific operation, after the user has finished inputting, he or she presses the "send" button.

[0724] Step 2:

[0725] The terminal transmits the attribute information and emotion data entered by the user to the server via the Internet. The input data includes the user's attribute information and emotion data, and the output data is delivered to the server.

[0726] Specifically, the device uses Wi-Fi or mobile data communication to send data to the server's API as a POST request.

[0727] Step 3:

[0728] The server receives the attribute information and emotion data and stores them in a database, such as MySQL or MongoDB. The input is the received data, and the output is the attribute information and emotion data stored in the database.

[0729] Specifically, the server receives the data in JSON format and inserts it into the appropriate table or collection.

[0730] Step 4:

[0731] The server periodically collects household electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day. The input is electricity usage data from the smart meters, and the output is electricity usage data accumulated by the server.

[0732] Specifically, the server uses an API to send a data acquisition request to the smart meter every 30 minutes.

[0733] Step 5:

[0734] The server preprocesses the collected attribute information, emotion data, and power usage data. Preprocessing includes imputing missing data, scaling numerical data, encoding categorical variables, etc. The input is the various collected and stored data, and the output is the preprocessed data.

[0735] Specifically, it uses Python's Pandas and Scikit-learn libraries to cleanse and transform data.

[0736] Step 6:

[0737] The preprocessed data is input into a generative AI model, which uses this data to generate optimal power-saving methods for each user. The input is the preprocessed data, and the output is the optimal power-saving method.

[0738] Specifically, it runs deep learning models using TensorFlow and PyTorch to generate user-specific power-saving suggestions.

[0739] Step 7:

[0740] The generated power saving method is sent from the server to the user's device as a push notification. The input is the generated power saving method, and the output is a notification displayed on the user's device.

[0741] Specifically, it sends a message using a notification service such as Firebase Cloud Messaging (FCM).

[0742] Step 8:

[0743] The user checks the received power-saving suggestions and takes specific actions according to the suggestions. The input is the power-saving suggestions displayed on the terminal, and the output is the actual power-saving actions.

[0744] Specific actions include following suggestions such as raising the air conditioner's set temperature by 1 degree or switching to LED lighting.

[0745] Step 9:

[0746] The server collects feedback from users and evaluates the effectiveness of the implemented power-saving measures. The evaluation also analyzes emotional feedback using an emotion engine. The input is user feedback data, and the output is the evaluation result.

[0747] Specifically, the server collects opinions and feedback through a feedback form and runs a Python script to analyze them.

[0748] Step 10:

[0749] The server retrains the generative AI model to improve its accuracy, updating it with newly collected data, with the new data as input and the retrained model as output.

[0750] Specifically, it periodically inputs new data into the model in batches and runs a script to retrain it.

[0751] (Application example 2)

[0752] 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."

[0753] Optimizing energy consumption is an urgent issue in modern homes and brick-and-mortar stores, but existing energy-saving suggestion systems have problems with low suggestion acceptance and implementation rates because they do not fully consider the user's emotional state or individual attribute information. Furthermore, there are insufficient means to properly evaluate user feedback and improve the accuracy of generative AI models through continuous training.

[0754] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for preprocessing the collected attribute information and power usage data, means for generating an optimal power-saving method using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving method, means for collecting and preprocessing the user's emotional data, means for analyzing the emotional data to optimize the timing of the notification of the suggestion, means for collecting and evaluating feedback from the user, and means for rewarding the user based on the evaluation. This enables individually optimized power-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, by training and updating the generative AI model based on continuous feedback, the system always provides the latest and most accurate suggestions.

[0755] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[0756] "Attribute information" refers to information such as the user's family composition, type of residence, and types of home appliances owned.

[0757] "Electricity usage data" refers to data on electricity consumption within homes and stores and usage patterns by time of day, collected from smart meters and IoT devices.

[0758] "Preprocessing" is the process of preparing collected data by completing missing data, scaling numerical data, encoding categorical variables, etc.

[0759] A "generative AI model" is an artificial intelligence model that analyzes data, finds complex patterns and relationships, and generates optimal energy-saving methods.

[0760] "Power saving methods" refers to specific techniques and proposals for reducing power consumption.

[0761] "Feedback" is data obtained from users regarding the effectiveness of implemented energy saving suggestions and their emotional reactions.

[0762] "Rewards" are incentives such as in-app currency or physical prizes that are given to users after they put the suggested energy-saving methods into practice and their effectiveness is confirmed.

[0763] "Emotional data" refers to data that indicates the user's emotional state, such as stress level or mood.

[0764] The "Emotion Engine" is an artificial intelligence system that analyzes collected emotional data and optimizes the timing of notification suggestions.

[0765] This invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation of a home or a brick-and-mortar store. Detailed embodiments of this system will be described below.

[0766] First, the user launches the Eco Electricity app on a device such as a smartphone, tablet, or PC. During initial setup, attribute information (e.g., family composition, residence type, and types of appliances owned) and electricity usage data are collected from the user via the device. The user also provides emotional data via the app's camera, microphone, and text input.

[0767] The device sends this information to a server, which stores the received attribute information and emotion data in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes electricity consumption in homes and stores and usage patterns by time of day.

[0768] The server then preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model to generate optimal energy-saving methods based on the user's energy usage patterns, attribute information, and emotion data.

[0769] The generated power-saving methods are notified to the device as specific and actionable suggestions. These suggestions are notified at appropriate times by the emotion engine, taking into account the user's emotional state. The server then sends these power-saving methods to the user's device as push notifications, allowing the user to confirm the suggestions and take specific actions.

[0770] The server also collects user feedback and evaluates the effectiveness of the app, based on a comprehensive evaluation that includes the degree of energy consumption reduction and the user's emotional response. Based on this evaluation, users are rewarded with in-app currency or real prizes.

[0771] Additionally, the generative AI model is continually trained with new data to improve its accuracy, ensuring that it always delivers the most up-to-date and accurate recommendations.

[0772] As a concrete example, let us consider the case of a coffee shop.

[0773] For example, if the user is a coffee shop manager, the server collects business hours, peak power usage, and staff emotional data (e.g., stress levels during busy hours). The generative AI model generates suggestions such as, "By reducing the store's lighting by half between 10:00 and 11:00 a.m., when there are fewer customers, you can save 2,000 yen per month on electricity." The emotion engine takes into account the emotional state of the staff and notifies them at times when stress is low. The server sends a push notification of this suggestion to the manager's smartphone, who then consults with the staff and adjusts the lighting. The server then evaluates the change in power usage and confirms the power-saving effect. The manager is rewarded with in-app currency as a success reward.

[0774] An example of a prompt would be, "Consider power usage data and emotion data and generate the optimal energy-saving method for a coffee shop. For example, reduce the lights by half between 10:00 and 11:00 AM." By inputting this prompt into the generative AI model, the corresponding energy-saving suggestion will be generated.

[0775] As described above, this system enables individually optimized energy-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, continuous feedback and model training enable the system to always provide the latest and most accurate suggestions.

[0776] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0777] Step 1:

[0778] Users launch the Eco Electric app on their smartphone, tablet, PC, or other device. During the initial setup, users enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and also provide emotional data (e.g., stress level, mood state).

[0779] Input: Attribute information, emotion data

[0780] Output: Attribute information and emotion data are saved on the device.

[0781] Step 2:

[0782] The device sends the collected attribute information and emotion data to the server. It also periodically collects electricity usage data from smart meters and IoT devices within the home or physical store and sends it to the server.

[0783] Input: attribute information, emotion data, power usage data

[0784] Output: Attribute information, emotion data, and power usage data are stored on the server.

[0785] Step 3:

[0786] The server preprocesses the received attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0787] Input: attribute information, emotion data, power usage data

[0788] Output: Preprocessed data

[0789] Step 4:

[0790] The server inputs the preprocessed data into a generative AI model, which generates optimal energy-saving methods based on the user's power usage patterns, attribute information, and emotional data.

[0791] Input: Preprocessed data

[0792] Output: Best way to save power

[0793] Step 5:

[0794] The server sends the generated power-saving methods to the user's device as push notifications, with the emotion engine providing the notifications at appropriate times, taking into account the user's emotional state.

[0795] Input: Optimal power saving method, emotional data

[0796] Output: Push notification of power saving suggestions

[0797] Step 6:

[0798] Users can check the energy-saving suggestions sent to their device and take specific actions, such as adjusting lighting or changing air conditioning settings.

[0799] Input: Push notification of power saving suggestions

[0800] Output: Energy saving actions taken

[0801] Step 7:

[0802] The server collects feedback from users and evaluates the effectiveness of the implemented energy-saving measures, including the degree of reduction in power consumption and the user's emotional response.

[0803] Input: Feedback data

[0804] Output: Evaluation result

[0805] Step 8:

[0806] The server rewards the user (e.g., in-app currency, real prizes) based on the evaluation results.

[0807] Input: Evaluation result

[0808] Output: Reward granted

[0809] Step 9:

[0810] The server uses the preprocessed data and feedback data to train and update the generative AI model, and this continuous training improves the accuracy of the generative AI model.

[0811] Input: Preprocessed data, feedback data

[0812] Output: An updated generative AI model

[0813] 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.

[0814] 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.

[0815] 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.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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."

[0829] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions based on household power usage.

[0830] First, the user launches the Eco Electricity app via a device such as a smartphone, tablet, or PC. The user enters attribute information (e.g., family composition, type of residence, and types of home appliances owned) into the app. Additionally, household electricity usage data is periodically sent to the server from the user's smart meter or IoT device.

[0831] The server receives the collected attribute information and energy usage data. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0832] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[0833] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[0834] Specific examples

[0835] Example 1: For a user living alone

[0836] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[0837] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[0838] The generative AI model analyzes this data and generates a power-saving method such as, "If you raise the air conditioner's temperature setting by 1 degree in the morning, you can save 5,000 yen on your electricity bill per year."

[0839] The server will push this proposal to the user's device.

[0840] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effectiveness of the suggestions.

[0841] The server evaluates the amount of electricity used and awards a reward to the user.

[0842] Example 2: Family users

[0843] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[0844] Data collected by the server: This includes the fact that the user's family uses the most electricity in the evenings, regular laundry and cooking schedules, etc.

[0845] The generative AI model analyzes this data and generates a power-saving method such as, "After dinner, use LED lighting, which consumes less energy. This will save you about 3,000 yen a year."

[0846] The server will push this proposal to the user's device.

[0847] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[0848] The server evaluates the amount of electricity used and awards a reward to the user.

[0849] In this example, users receive personalized, reliable energy-saving suggestions without asking any direct questions, and can implement them in a few easy steps. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[0850] The processing flow will be explained below.

[0851] Step 1:

[0852] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting.

[0853] Step 2:

[0854] The terminal sends the input attribute information to the server, which receives the attribute information and stores it in a database.

[0855] Step 3:

[0856] The server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[0857] Step 4:

[0858] The server preprocesses the collected attribute information and electricity usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[0859] Step 5:

[0860] The server inputs the preprocessed data into a generative AI model, which analyzes the user's power usage patterns and attribute information to generate optimal energy-saving methods.

[0861] Step 6:

[0862] The server sends the generated power-saving methods to the device as a push notification, and the user receives the notification via the device and confirms the proposed power-saving measures.

[0863] Step 7:

[0864] The user implements the suggested energy-saving measures (e.g., changing the air conditioner's temperature setting or switching to LED lighting).

[0865] Step 8:

[0866] The server collects feedback on the energy-saving measures taken by users, who can provide feedback via the app.

[0867] Step 9:

[0868] The server analyzes the power usage data and feedback to evaluate the effectiveness of the implemented power saving measures, such as the degree of reduction in power consumption.

[0869] Step 10:

[0870] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[0871] Step 11:

[0872] The server continuously collects new data to train and update the generative AI model, improving the model's accuracy and providing the latest power-saving suggestions to the user.

[0873] Example 1

[0874] 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."

[0875] As household electricity consumption increases, finding appropriate energy-saving methods is an important challenge. However, it is difficult for ordinary users to find individually optimized energy-saving methods. Furthermore, a system is needed to quantitatively evaluate the effectiveness of energy-saving methods and encourage continuous energy-saving behavior. Furthermore, appropriate feedback and rewards are required to continuously improve user behavior.

[0876] 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.

[0877] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving methods to their terminals, means for collecting and evaluating feedback from users, means for rewarding the users based on the evaluation, and means for continuously training and updating the generative AI model. This allows users to receive individually optimized power-saving suggestions and adopt the power-saving methods as actionable actions. Furthermore, the effectiveness of the proposed power-saving methods is evaluated, and rewards are awarded to the users, thereby encouraging sustainable energy-saving behavior.

[0878] "Terminal" refers to a device used by a user, including smartphones, tablets, PCs, etc.

[0879] "Attribute information" is personal, static data about a user, including information such as family composition, type of residence, and types of home appliances owned.

[0880] "Electricity usage data" is data that shows the electricity consumption status in a user's home, and is time-series data collected from smart meters and IoT devices.

[0881] "Preprocessing" refers to processes for improving the quality of collected data, including missing value imputation, scaling, and encoding of categorical variables.

[0882] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate optimal suggestions and predictions for a specific purpose.

[0883] "Power-saving methods" are specific actions that users can take to reduce electricity consumption at home, such as changing the temperature setting on their air conditioner or using LED lighting.

[0884] "Notification" is a means of informing the user of power saving methods and other information generated by the server by sending it to the user's terminal.

[0885] "Feedback" is information about the implementation details and results that the user provides to the server, and is data about the implementation status and effectiveness of the proposed power saving method.

[0886] "Evaluation" is the process of determining the effectiveness of proposed energy conservation methods based on collected feedback and additional energy usage data.

[0887] "Rewards" are incentives that users receive as a result of implementing the suggested energy-saving methods, and can include in-app currency or physical prizes.

[0888] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions according to the power usage situation in a home. The system is implemented as follows.

[0889] First, the user launches the dedicated Eco Electricity app via a device such as a smartphone, tablet, or PC. The user then fills in a form within the app with attribute information such as family composition, type of residence, and types of home appliances owned. This initial input is important data for understanding the user's electricity consumption patterns.

[0890] The device then collects real-time energy usage data from smart meters and connected IoT devices, and transmits the collected data to a server at regular intervals using a standard communication protocol.

[0891] The server preprocesses the received attribute information and electricity usage data by creating a data frame using Python's pandas library, imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0892] Generative AI models are built using libraries such as TensorFlow and PyTorch, and analyze input data to generate optimal power-saving methods. For example, here are some specific examples:

[0893] Example 1: For users living alone

[0894] User: A company employee in his 20s who lives alone in an apartment and uses a refrigerator, air conditioner, washing machine, and microwave.

[0895] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[0896] Energy-saving suggestion from a generative AI model: "By raising the air conditioner temperature setting by 1 degree in the morning, you can save 5,000 yen in electricity bills per year."

[0897] The server sends this proposal to the user's device via a push notification.

[0898] The user follows the suggestions and changes the air conditioner's temperature setting.

[0899] Example prompt sentence:

[0900] "I'm a company employee in my 20s who lives alone and uses a refrigerator, air conditioner, washing machine, and microwave. I'm away from home from 7:00 AM to 6:00 PM, so I'd like to reduce the frequency of using the air conditioner. Please tell me some ways to save on electricity bills."

[0901] Furthermore, the server collects feedback from users and evaluates the results of the proposed energy-saving methods. Based on the evaluation results, users are given rewards such as in-app currency and real prizes, which encourages users to continue energy-saving behavior.

[0902] The server continuously trains the generative AI model with newly collected data to improve its accuracy, a process that ensures users always receive the most up-to-date and optimal energy-saving suggestions.

[0903] Throughout the system, users simply receive individually optimized energy saving suggestions that can be implemented through concrete actions.

[0904] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0905] Step 1:

[0906] Users launch the Eco Electricity App on a device such as a smartphone or tablet and enter attribute information such as family composition, type of residence, and types of home appliances they own.

[0907] Input: User's family structure, residence type, and types of appliances owned

[0908] Output: The entered attribute information is sent to the server.

[0909] What happens: A user enters information using a form within the app and presses the submit button, which sends this information to the server.

[0910] Step 2:

[0911] The terminal collects electricity usage data from smart meters and connected IoT devices and sends it to a server at regular intervals.

[0912] Input: Domestic electricity usage data (data from smart meters and IoT devices)

[0913] Output: Collected electricity usage data is stored on the server.

[0914] Specific operation: The terminal periodically communicates with smart meters and IoT devices, acquires electricity usage data, and sends it to a server.

[0915] Step 3:

[0916] The server preprocesses the received attribute information and electricity usage data by imputing missing values, scaling, and encoding categorical variables using the Python pandas library.

[0917] Input: Attribute information, electricity usage data

[0918] Output: Preprocessed data

[0919] What it does: The server runs a Python script to impute missing values ​​in attribute information and electricity usage data, scale it, and convert categorical variables to numeric values ​​as needed.

[0920] Step 4:

[0921] The server inputs the preprocessed data into a generative AI model, a machine learning model using TensorFlow and PyTorch, which analyzes the data and generates optimal power-saving strategies.

[0922] Input: Preprocessed data

[0923] Output: Best way to save power

[0924] How it works: The server feeds data to a generative AI model, which then generates optimal power-saving strategies based on learned patterns.

[0925] Step 5:

[0926] The server sends the generated power saving method to the user's device as a push notification.

[0927] Input: Best way to save energy

[0928] Output: Push notification to the user's device

[0929] Specific operation: The server converts the power saving method into JSON format and sends it to the user's device using the push notification service.

[0930] Step 6:

[0931] The user checks the suggestions and implements specific power saving methods.

[0932] Input: Power saving method received via push notification

[0933] Output: Actual energy-saving measures taken (e.g., raising the air conditioner temperature setting by 1 degree)

[0934] Specific behavior: The user receives a notification through the app, implements the suggested power-saving measures, and checks the results.

[0935] Step 7:

[0936] The server collects feedback from users and evaluates the proposed power saving methods.

[0937] Input: User-entered feedback, latest energy usage data

[0938] Output: Power saving effect evaluation result

[0939] Specific operation: The server analyzes the user's feedback form and power usage data to evaluate the effectiveness of the power saving suggestions.

[0940] Step 8:

[0941] The server rewards users based on the evaluation results, which are provided as in-app currency or physical prizes.

[0942] Input: Evaluation result

[0943] Output: Reward added to user account

[0944] Specific operation: The server calculates the user's reward based on the evaluation results and credits the reward to the user's account.

[0945] Step 9:

[0946] The server continuously trains the generative AI model with new data it collects, which improves the model's accuracy.

[0947] Input: New electricity usage data, feedback data

[0948] Output: An updated generative AI model

[0949] What it does: The server retrains the generative AI model with newly collected data to improve the model's performance.

[0950] (Application example 1)

[0951] 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."

[0952] This invention relates to a system that makes appropriate energy-saving suggestions based on the store's power usage, and aims to solve the problem that conventional energy-saving methods are abstract and do not provide specific guidelines for action. In addition, by establishing an evaluation and reward system based on user feedback, the system encourages users to continue energy-saving behavior.

[0953] 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.

[0954] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving methods, means for collecting and evaluating feedback from users, means for rewarding users based on the evaluation, and means for providing optimal power-saving methods in real time based on the store's power usage status and power usage data. This makes it possible to provide specific and feasible power-saving suggestions to stores in real time, effectively encouraging users to take energy-saving actions.

[0955] A "terminal" is an electronic device, such as a smartphone, tablet, or PC, that allows a user to input and receive information.

[0956] "Attribute information" refers to information about an individual or household, such as the user's family structure, type of residence, and types of home appliances owned.

[0957] "Electricity usage data" refers to information about electricity consumption collected from smart meters and IoT devices.

[0958] "Preprocessing" refers to operations that process collected data, such as imputing missing values, scaling, and encoding categorical variables.

[0959] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to analyze a user's electricity usage patterns and attribute information to generate optimal energy-saving methods.

[0960] "Power saving methods" are specific suggestions or courses of action that users can take to reduce their electricity consumption.

[0961] "Notification" refers to sending the generated power saving method to the user's device in the form of a push notification or message.

[0962] "Feedback" refers to the user returning actual behavioral data and opinions to the server after following the suggestions.

[0963] "Evaluation" refers to analyzing the effectiveness of the energy-saving measures implemented based on feedback collected from users.

[0964] "Rewards" are incentives such as in-app currency or physical prizes provided to users.

[0965] "Real-time" means that analysis and recommendations are made immediately after data is collected, with results communicated to users almost instantly.

[0966] A "store" is a business office or facility for selling goods or providing services.

[0967] "Power usage data" is detailed data on power consumption in a store by hour.

[0968] "Power saving suggestions" are specific advice for reducing power consumption provided to users based on the analysis of collected data and the generated AI model.

[0969] This invention relates to a system that makes energy-saving suggestions based on the electricity usage status of a store. A user launches an eco-electricity management app using a device such as a smartphone or tablet, and inputs attribute information about the store (e.g., store size, business format, and types of electrical equipment used) into the app. In addition, the store's electricity usage data is periodically sent to a server from smart meters and IoT devices.

[0970] The server receives the attribute information and energy usage data collected via the device. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[0971] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. This generative AI model uses machine learning frameworks such as TensorFlow and PyTorch. The generated power-saving methods are provided to the user as specific, actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[0972] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[0973] Specific examples

[0974] Example 1: A store in a shopping mall

[0975] User: A store owner in a shopping mall who uses a lot of air conditioning, lighting, and electronics.

[0976] Data collected by the server: Store electricity usage graph, business hours, and information on home appliances being used.

[0977] The generative AI model analyzes this data and generates a suggestion such as, "By raising the air conditioner temperature by 2 degrees after closing, you can save 2,000 yen per month on electricity."

[0978] The server will send a push notification of this proposal to the manager's smartphone.

[0979] The manager follows the suggestions, changes the air conditioning settings and checks the effect.

[0980] Prompt Sentence Examples

[0981] "Generate optimal energy-saving methods based on store power consumption data."

[0982] "Please analyze this data and provide specific energy-saving suggestions: e.g., adjusting the air conditioner temperature setting after closing time."

[0983] This allows stores to receive specific and actionable energy-saving suggestions in real time, effectively encouraging users to take energy-saving actions.

[0984] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0985] Step 1:

[0986] Data collection

[0987] Users launch the eco-electricity management app on their smartphones, tablets, or other devices and enter their store's attribute information (e.g., store size, business format, and types of electrical equipment used). In addition, the store's electricity usage data is periodically sent to the server from smart meters and IoT devices.

[0988] Input: User attribute information, electricity usage data

[0989] Output: User attribute information and power usage data stored on the server

[0990] Step 2:

[0991] Data Preprocessing

[0992] The server preprocesses the collected attribute information and electricity usage data, including imputing missing values, scaling, and encoding categorical variables.

[0993] Input: Raw user demographic information and electricity usage data

[0994] Output: Preprocessed user attribute information and electricity usage data

[0995] Specific behaviors: missing value imputation, data normalization, categorical variable encoding

[0996] Step 3:

[0997] Input to generative AI models

[0998] The server inputs the preprocessed data into a generative AI model, which is built using a machine learning framework (e.g., TensorFlow or PyTorch).

[0999] Input: Preprocessed user demographic information and electricity usage data

[1000] Output: Analysis results from the generative AI model

[1001] Specific operations: Data analysis, pattern recognition, and generation of power saving methods

[1002] Step 4:

[1003] Generate specific energy-saving methods

[1004] The generative AI model analyzes the user's energy usage patterns and attribute information to generate optimal energy-saving methods, which are then sent to the server as specific, actionable suggestions.

[1005] Input: Preprocessed data

[1006] Output: Specific power saving methods

[1007] Specific operations: Generate power saving methods and confirm the proposed contents

[1008] Step 5:

[1009] notification

[1010] The server sends the generated power saving methods to the user's device as a push notification, allowing the user to review the suggestions and take specific actions.

[1011] Input: Specific energy saving methods

[1012] Output: Push notification sent to user device

[1013] Specific behavior: Creating and sending a push notification

[1014] Step 6:

[1015] Gathering and evaluating feedback

[1016] The server collects feedback from users and evaluates the effectiveness of the implemented power saving measures.

[1017] Input: User feedback

[1018] Output: Evaluation result

[1019] Specific actions: Analyzing feedback and evaluating effectiveness

[1020] Step 7:

[1021] Rewarding

[1022] Based on their ratings, users are rewarded with in-app currency, physical prizes, and other rewards. The generative AI model is continually trained with new data to improve its accuracy.

[1023] Input: Evaluation result

[1024] Output: Reward, updated generative AI model

[1025] Specific operations: Calculating and awarding rewards, training and updating generative AI models

[1026] 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.

[1027] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the electricity usage situation in a home.

[1028] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[1029] The device sends the input attribute information and emotion data to a server, which receives this information and stores it in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[1030] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model.

[1031] The generative AI model analyzes the user's power usage patterns, attribute information, and emotional data to generate optimal power-saving methods for each user. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can then review the suggestions and take specific actions.

[1032] Furthermore, the server collects feedback from users and not only evaluates the effectiveness of the implemented power-saving measures, but also evaluates the emotional aspects of the feedback using an emotion engine. This evaluation is a comprehensive evaluation that includes the degree of power consumption reduction and the user's emotional response. Based on this evaluation, users are given rewards such as in-app currency and real prizes.

[1033] The generative AI model is also continually trained with new data to improve its accuracy, ensuring that advice is always based on the most up-to-date information and that personalized energy-saving suggestions take into account the user's emotional state.

[1034] Specific examples

[1035] Example 1: For a user living alone

[1036] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[1037] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, peak hours of power usage, and emotional data (e.g., stress levels, mood states).

[1038] The generative AI model analyzes this data and generates energy-saving suggestions, such as "Raising the air conditioner temperature setting by 1 degree in the morning will save you 5,000 yen in electricity bills per year." At the same time, the emotion engine takes into account the user's stress level and adjusts the suggestions to be made during times when stress is lower.

[1039] The server will push this proposal to the user's device.

[1040] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect of the suggestions.

[1041] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1042] Example 2: Family users

[1043] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[1044] Data collected by the server: Includes the fact that the user's family consumes the most electricity in the evening, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[1045] The generative AI model analyzes this data and generates energy-saving suggestions such as, "Use LED lighting, which consumes less energy, after dinner. This will save you about 3,000 yen a year." The emotion engine takes into account the emotional state of the entire family and makes suggestions at the most acceptable times.

[1046] The server will push this proposal to the user's device.

[1047] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[1048] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1049] This example allows users to receive personalized energy-saving suggestions that take their emotional state into account without asking any direct questions, and implement them in a simple process. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[1050] The processing flow will be explained below.

[1051] Step 1:

[1052] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and emotional data (e.g., current mood, stress level) as initial settings.

[1053] Step 2:

[1054] The device sends the input attribute information and emotion data to the server, which receives the attribute information and emotion data and stores them in a database.

[1055] Step 3:

[1056] The server periodically collects electricity usage data from smart meters and IoT devices, including information on household electricity consumption and usage patterns by time of day.

[1057] Step 4:

[1058] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[1059] Step 5:

[1060] The server inputs the preprocessed data into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate individually optimized energy-saving methods.

[1061] Step 6:

[1062] The server sends the generated power-saving methods to the device as push notifications. The emotion engine adjusts the timing and content of the suggestions based on the user's emotional state.

[1063] Step 7:

[1064] The user can check the push notification via their device and take specific actions to save energy, such as changing the temperature setting of the air conditioner or doing laundry at a specific time.

[1065] Step 8:

[1066] The server collects user feedback along with emotional data, and users can provide feedback such as their feelings and perceived stress levels through the app.

[1067] Step 9:

[1068] The server analyzes the collected feedback and power usage data to evaluate the effectiveness of the implemented energy-saving measures, based on a comprehensive evaluation that includes the degree of reduction in power consumption and the user's emotional response.

[1069] Step 10:

[1070] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[1071] Step 11:

[1072] The server continuously collects new data to train and update the generative AI model and emotion engine, improving the model's accuracy and providing the latest energy-saving suggestions.

[1073] Example 2

[1074] 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."

[1075] In modern homes, reducing power consumption is an important issue for environmental protection and energy cost reduction. However, it is difficult for users to understand their own power usage patterns and find optimal ways to save power. In addition, there is a demand for energy-saving suggestions that take emotional factors into account, but until now, no system has existed that can achieve this.

[1076] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for collecting emotion data, means for preprocessing the collected attribute information, power usage data, and emotion data, means for generating an optimal power-saving method using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving method, means for collecting and evaluating feedback from the user, means for rewarding the user based on the evaluation, and means for retraining the generative AI model. This enables highly accurate power-saving suggestions that take into account the user's individual power usage pattern and emotional state.

[1077] "Terminal" refers to a device used by a user to input information or receive notifications, and specifically includes smartphones, tablets, and personal computers.

[1078] "Attribute information" refers to information about the user's lifestyle and environment, such as the user's family structure, type of residence, and types of home appliances owned.

[1079] "Electricity usage data" refers to information such as household electricity consumption and usage patterns by time of day obtained through smart meters and IoT devices.

[1080] "Emotional data" refers to information about a user's emotional state, such as their stress level or mood, and is obtained through the app's camera, microphone, or text input.

[1081] "Preprocessing" refers to the process of converting collected data into a format that is easier to analyze, and specifically includes imputing missing data, scaling numerical data, and encoding categorical variables.

[1082] "Generative AI model" refers to an artificial intelligence model used to analyze collected data and generate optimal energy-saving methods for each user.

[1083] "Power saving method" refers to a specific and feasible method for reducing power consumption that is provided based on a user's power usage pattern.

[1084] "Notification" refers to the act of notifying the user's device of the power saving method generated by the server, and specifically includes push notifications.

[1085] "Feedback" refers to the act of a user providing information such as the results of implementing a proposed energy-saving method and their impressions.

[1086] "Evaluation" refers to the act of analyzing the effectiveness of implemented energy-saving measures and users' emotional reactions based on feedback collected from users.

[1087] "Rewards" refer to incentives such as in-app currency or real prizes given to users based on the evaluation results.

[1088] "Retraining" refers to the act of retraining a generative AI model using newly collected data in order to improve its accuracy.

[1089] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation in a home. Specifically, the system is implemented in the following manner.

[1090] System configuration

[1091] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[1092] The device sends the input attribute information and emotion data to a server. The server receives this information and stores it in a database, such as MySQL or MongoDB. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes household electricity consumption and usage patterns by time of day.

[1093] The server preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. Python libraries (e.g., Pandas, Scikit-learn) are used for preprocessing.

[1094] The preprocessed data is input into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate optimal energy-saving methods for each user. This analysis is performed using deep learning frameworks (e.g., TensorFlow, PyTorch).

[1095] The generated power-saving methods are provided to the user as specific and actionable suggestions, and the server sends these power-saving methods to the user's device as push notifications using a notification service such as Firebase Cloud Messaging (FCM).

[1096] Users can review the suggestions and take specific actions. They also provide feedback within the app, such as the effectiveness of the suggestions and their impressions. The server receives this feedback and evaluates it. The evaluation includes analyzing the collected emotional data with an emotion engine.

[1097] Based on the feedback, the server can reward the user, which can include in-app currency or physical prizes.

[1098] The generative AI model is also continually trained with new data to improve its accuracy, ensuring that advice is always based on the most up-to-date information and that personalized energy-saving suggestions take into account the user's emotional state.

[1099] Specific examples

[1100] Example 1: For a user living alone

[1101] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[1102] Data collected by the server: Attribute information such as being away from home between 7am and 6pm, frequency of air conditioning use, peak hours of electricity usage, and emotional data (e.g., stress level, mood state).

[1103] Based on this data, the generative AI model suggests, "Raising the air conditioner temperature setting by 1 degree in the morning will save 5,000 yen in electricity bills per year." The emotion engine takes into account the user's stress level and makes suggestions for times when stress is low.

[1104] The server sends a push notification of this proposal to the user's device.

[1105] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect.

[1106] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1107] Example 2: Family users

[1108] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[1109] Data collected by the server: Attribute information such as which hours of the day a family uses the most electricity, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[1110] Based on this data, the generative AI model suggests, "Using LED lighting after dinner, which consumes less energy, can save approximately 3,000 yen per year." The model makes this suggestion at the most receptive timing, taking into account the emotional state of the entire family.

[1111] The server sends a push notification of this proposal to the user's device.

[1112] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[1113] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1114] This allows users to receive individually optimized energy-saving suggestions that take into account their emotional state without asking any direct questions, and implement them in a simple procedure. In addition, continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[1115] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1116] Step 1:

[1117] Users launch the Eco Electricity app using a device such as a smartphone, tablet, or PC. On the initial setup screen, users enter attribute information such as family composition, type of residence, and the types of appliances used. Users can also provide emotional data using the app's camera, microphone, or text input. Inputs include attribute information and emotional data, and the output is data that the device sends to the server.

[1118] As a specific operation, after the user has finished inputting, he or she presses the "send" button.

[1119] Step 2:

[1120] The terminal transmits the attribute information and emotion data entered by the user to the server via the Internet. The input data includes the user's attribute information and emotion data, and the output data is delivered to the server.

[1121] Specifically, the device uses Wi-Fi or mobile data communication to send data to the server's API as a POST request.

[1122] Step 3:

[1123] The server receives the attribute information and emotion data and stores them in a database, such as MySQL or MongoDB. The input is the received data, and the output is the attribute information and emotion data stored in the database.

[1124] Specifically, the server receives the data in JSON format and inserts it into the appropriate table or collection.

[1125] Step 4:

[1126] The server periodically collects household electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day. The input is electricity usage data from the smart meters, and the output is electricity usage data accumulated by the server.

[1127] Specifically, the server uses an API to send a data acquisition request to the smart meter every 30 minutes.

[1128] Step 5:

[1129] The server preprocesses the collected attribute information, emotion data, and power usage data. Preprocessing includes imputing missing data, scaling numerical data, encoding categorical variables, etc. The input is the various collected and stored data, and the output is the preprocessed data.

[1130] Specifically, it uses Python's Pandas and Scikit-learn libraries to cleanse and transform data.

[1131] Step 6:

[1132] The preprocessed data is input into a generative AI model, which uses this data to generate optimal power-saving methods for each user. The input is the preprocessed data, and the output is the optimal power-saving method.

[1133] Specifically, it runs deep learning models using TensorFlow and PyTorch to generate user-specific power-saving suggestions.

[1134] Step 7:

[1135] The generated power saving method is sent from the server to the user's device as a push notification. The input is the generated power saving method, and the output is a notification displayed on the user's device.

[1136] Specifically, it sends a message using a notification service such as Firebase Cloud Messaging (FCM).

[1137] Step 8:

[1138] The user checks the received power-saving suggestions and takes specific actions according to the suggestions. The input is the power-saving suggestions displayed on the terminal, and the output is the actual power-saving actions.

[1139] Specific actions include following suggestions such as raising the air conditioner's set temperature by 1 degree or switching to LED lighting.

[1140] Step 9:

[1141] The server collects feedback from users and evaluates the effectiveness of the implemented power-saving measures. The evaluation also analyzes emotional feedback using an emotion engine. The input is user feedback data, and the output is the evaluation result.

[1142] Specifically, the server collects opinions and feedback through a feedback form and runs a Python script to analyze them.

[1143] Step 10:

[1144] The server retrains the generative AI model to improve its accuracy, updating it with newly collected data, with the new data as input and the retrained model as output.

[1145] Specifically, it periodically inputs new data into the model in batches and runs a script to retrain it.

[1146] (Application example 2)

[1147] 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."

[1148] Optimizing energy consumption is an urgent issue in modern homes and brick-and-mortar stores, but existing energy-saving suggestion systems have problems with low suggestion acceptance and implementation rates because they do not fully consider the user's emotional state or individual attribute information. Furthermore, there are insufficient means to properly evaluate user feedback and improve the accuracy of generative AI models through continuous training.

[1149] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for preprocessing the collected attribute information and power usage data, means for generating an optimal power-saving method using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving method, means for collecting and preprocessing user emotion data, means for analyzing the emotion data to optimize the timing of the notification of the suggestion, means for collecting and evaluating feedback from the user, and means for rewarding the user based on the evaluation. This enables individually optimized power-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, by training and updating the generative AI model based on continuous feedback, the system always provides the latest and most accurate suggestions.

[1150] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[1151] "Attribute information" refers to information such as the user's family composition, type of residence, and types of home appliances owned.

[1152] "Electricity usage data" refers to data on electricity consumption within homes and stores and usage patterns by time of day, collected from smart meters and IoT devices.

[1153] "Preprocessing" is the process of preparing collected data by completing missing data, scaling numerical data, encoding categorical variables, etc.

[1154] A "generative AI model" is an artificial intelligence model that analyzes data, finds complex patterns and relationships, and generates optimal energy-saving methods.

[1155] "Power saving methods" refers to specific techniques and proposals for reducing power consumption.

[1156] "Feedback" is data obtained from users regarding the effectiveness of implemented energy saving suggestions and their emotional reactions.

[1157] "Rewards" are incentives such as in-app currency or physical prizes that are given to users after they put the suggested energy-saving methods into practice and their effectiveness is confirmed.

[1158] "Emotional data" refers to data that indicates the user's emotional state, such as stress level or mood.

[1159] The "Emotion Engine" is an artificial intelligence system that analyzes collected emotional data and optimizes the timing of notification suggestions.

[1160] This invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation of a home or a brick-and-mortar store. Detailed embodiments of this system will be described below.

[1161] First, the user launches the Eco Electricity app on a device such as a smartphone, tablet, or PC. During initial setup, attribute information (e.g., family composition, residence type, and types of appliances owned) and electricity usage data are collected from the user via the device. The user also provides emotional data via the app's camera, microphone, and text input.

[1162] The device sends this information to a server, which stores the received attribute information and emotion data in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes electricity consumption in homes and stores and usage patterns by time of day.

[1163] The server then preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model to generate optimal energy-saving methods based on the user's energy usage patterns, attribute information, and emotion data.

[1164] The generated power-saving methods are notified to the device as specific and actionable suggestions. These suggestions are notified at appropriate times by the emotion engine, taking into account the user's emotional state. The server then sends these power-saving methods to the user's device as push notifications, allowing the user to confirm the suggestions and take specific actions.

[1165] The server also collects user feedback and evaluates the effectiveness of the app, based on a comprehensive evaluation that includes the degree of energy consumption reduction and the user's emotional response. Based on this evaluation, users are rewarded with in-app currency or real prizes.

[1166] Additionally, the generative AI model is continually trained with new data to improve its accuracy, ensuring that it always delivers the most up-to-date and accurate recommendations.

[1167] As a concrete example, let us consider the case of a coffee shop.

[1168] For example, if the user is a coffee shop manager, the server collects business hours, peak power usage, and staff emotional data (e.g., stress levels during busy hours). The generative AI model generates suggestions such as, "By reducing the store's lighting by half between 10:00 and 11:00 a.m., when there are fewer customers, you can save 2,000 yen per month on electricity." The emotion engine takes into account the emotional state of the staff and notifies them at times when stress is low. The server sends a push notification of this suggestion to the manager's smartphone, who then consults with the staff and adjusts the lighting. The server then evaluates the change in power usage and confirms the power-saving effect. The manager is rewarded with in-app currency as a success reward.

[1169] An example of a prompt would be, "Consider power usage data and emotion data and generate the optimal energy-saving method for a coffee shop. For example, reduce the lights by half between 10:00 and 11:00 AM." By inputting this prompt into the generative AI model, the corresponding energy-saving suggestion will be generated.

[1170] As described above, this system enables individually optimized energy-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, continuous feedback and model training enable the system to always provide the latest and most accurate suggestions.

[1171] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1172] Step 1:

[1173] Users launch the Eco Electric app on their smartphone, tablet, PC, or other device. During the initial setup, users enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and also provide emotional data (e.g., stress level, mood state).

[1174] Input: attribute information, emotion data

[1175] Output: Attribute information and emotion data are saved on the device.

[1176] Step 2:

[1177] The device sends the collected attribute information and emotion data to the server. It also periodically collects electricity usage data from smart meters and IoT devices within the home or physical store and sends it to the server.

[1178] Input: Attribute information, emotion data, power usage data

[1179] Output: Attribute information, emotion data, and power usage data are stored on the server.

[1180] Step 3:

[1181] The server preprocesses the received attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[1182] Input: Attribute information, emotion data, power usage data

[1183] Output: Preprocessed data

[1184] Step 4:

[1185] The server inputs the preprocessed data into a generative AI model, which generates optimal energy-saving methods based on the user's power usage patterns, attribute information, and emotional data.

[1186] Input: Preprocessed data

[1187] Output: Best way to save power

[1188] Step 5:

[1189] The server sends the generated power-saving methods to the user's device as push notifications, with the emotion engine providing the notifications at appropriate times, taking into account the user's emotional state.

[1190] Input: Optimal power saving method, emotional data

[1191] Output: Push notification of power saving suggestions

[1192] Step 6:

[1193] Users can check the energy-saving suggestions sent to their device and take specific actions, such as adjusting lighting or changing air conditioning settings.

[1194] Input: Push notification of power saving suggestions

[1195] Output: Energy saving actions taken

[1196] Step 7:

[1197] The server collects feedback from users and evaluates the effectiveness of the implemented energy-saving measures, including the degree of reduction in power consumption and the user's emotional response.

[1198] Input: Feedback data

[1199] Output: Evaluation result

[1200] Step 8:

[1201] The server rewards the user (e.g., in-app currency, real prizes) based on the evaluation results.

[1202] Input: Evaluation result

[1203] Output: Reward granted

[1204] Step 9:

[1205] The server uses the preprocessed data and feedback data to train and update the generative AI model, and this continuous training improves the accuracy of the generative AI model.

[1206] Input: Preprocessed data, feedback data

[1207] Output: An updated generative AI model

[1208] 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.

[1209] 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.

[1210] 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.

[1211] [Fourth embodiment]

[1212] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1213] 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.

[1214] 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).

[1215] 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.

[1216] 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.

[1217] 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).

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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."

[1225] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions based on household power usage.

[1226] First, the user launches the Eco Electricity app via a device such as a smartphone, tablet, or PC. The user enters attribute information (e.g., family composition, type of residence, and types of home appliances owned) into the app. Additionally, household electricity usage data is periodically sent to the server from the user's smart meter or IoT device.

[1227] The server receives the collected attribute information and energy usage data. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[1228] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[1229] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[1230] Specific examples

[1231] Example 1: For a user living alone

[1232] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[1233] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[1234] The generative AI model analyzes this data and generates a power-saving method such as, "If you raise the air conditioner's temperature setting by 1 degree in the morning, you can save 5,000 yen on your electricity bill per year."

[1235] The server will push this proposal to the user's device.

[1236] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effectiveness of the suggestions.

[1237] The server evaluates the amount of electricity used and awards a reward to the user.

[1238] Example 2: For family users

[1239] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[1240] Data collected by the server: This includes the fact that the user's family uses the most electricity in the evening, regular laundry and cooking schedules, etc.

[1241] The generative AI model analyzes this data and generates a power-saving method such as, "After dinner, use LED lighting, which consumes less energy. This will save you about 3,000 yen a year."

[1242] The server will push this proposal to the user's device.

[1243] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[1244] The server evaluates the amount of electricity used and awards a reward to the user.

[1245] In this example, users receive personalized, reliable energy-saving suggestions without asking any direct questions, and can implement them in a few easy steps. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[1246] The processing flow will be explained below.

[1247] Step 1:

[1248] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting.

[1249] Step 2:

[1250] The terminal sends the input attribute information to the server, which receives the attribute information and stores it in a database.

[1251] Step 3:

[1252] The server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[1253] Step 4:

[1254] The server preprocesses the collected attribute information and electricity usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[1255] Step 5:

[1256] The server inputs the preprocessed data into a generative AI model, which analyzes the user's power usage patterns and attribute information to generate optimal energy-saving methods.

[1257] Step 6:

[1258] The server sends the generated power-saving methods to the device as a push notification, and the user receives the notification via the device and confirms the proposed power-saving measures.

[1259] Step 7:

[1260] The user implements the suggested energy-saving measures (e.g., changing the air conditioner's temperature setting or switching to LED lighting).

[1261] Step 8:

[1262] The server collects feedback on the energy-saving measures taken by users, who can provide feedback via the app.

[1263] Step 9:

[1264] The server analyzes the power usage data and feedback to evaluate the effectiveness of the implemented power saving measures, such as the degree of reduction in power consumption.

[1265] Step 10:

[1266] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[1267] Step 11:

[1268] The server continuously collects new data to train and update the generative AI model, improving the model's accuracy and providing the latest power-saving suggestions to users.

[1269] Example 1

[1270] 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."

[1271] As household electricity consumption increases, finding appropriate energy-saving methods is an important challenge. However, it is difficult for ordinary users to find individually optimized energy-saving methods. Furthermore, a system is needed to quantitatively evaluate the effectiveness of energy-saving methods and encourage continuous energy-saving behavior. Furthermore, appropriate feedback and rewards are required to continuously improve user behavior.

[1272] 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.

[1273] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving methods to their terminals, means for collecting and evaluating feedback from users, means for rewarding the users based on the evaluation, and means for continuously training and updating the generative AI model. This allows users to receive individually optimized power-saving suggestions and adopt the power-saving methods as actionable actions. Furthermore, the effectiveness of the proposed power-saving methods is evaluated, and rewards are awarded to the users, thereby encouraging sustainable energy-saving behavior.

[1274] "Terminal" refers to a device used by a user, including smartphones, tablets, PCs, etc.

[1275] "Attribute information" is personal, static data about a user, including information such as family composition, type of residence, and types of home appliances owned.

[1276] "Electricity usage data" is data that shows the electricity consumption status in a user's home, and is time-series data collected from smart meters and IoT devices.

[1277] "Preprocessing" refers to processes for improving the quality of collected data, including missing value imputation, scaling, and encoding of categorical variables.

[1278] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate optimal suggestions and predictions for a specific purpose.

[1279] "Power-saving methods" are specific actions that users can take to reduce electricity consumption at home, such as changing the temperature setting on their air conditioner or using LED lighting.

[1280] "Notification" is a means of informing the user of power saving methods and other information generated by the server by sending it to the user's terminal.

[1281] "Feedback" is information about the implementation details and results that the user provides to the server, and is data about the implementation status and effectiveness of the proposed power saving method.

[1282] "Evaluation" is the process of determining the effectiveness of proposed energy conservation methods based on collected feedback and additional energy usage data.

[1283] "Rewards" are incentives that users receive as a result of implementing the suggested energy-saving methods, and can include in-app currency or physical prizes.

[1284] The present invention relates to a system that uses a terminal, a server, and a generative AI model to make appropriate energy-saving suggestions according to the power usage situation in a home. The system is implemented as follows.

[1285] First, the user launches the dedicated Eco Electricity app via a device such as a smartphone, tablet, or PC. The user then fills in a form within the app with attribute information such as family composition, type of residence, and types of home appliances owned. This initial input is important data for understanding the user's electricity consumption patterns.

[1286] The device then collects real-time energy usage data from smart meters and connected IoT devices, and transmits the collected data to a server at regular intervals. This data collection is carried out using a common communication protocol.

[1287] The server preprocesses the received attribute information and electricity usage data by creating a data frame using Python's pandas library, imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[1288] Generative AI models are built using libraries such as TensorFlow and PyTorch, and analyze input data to generate optimal power-saving methods. For example,

[1289] Example 1: For a user living alone

[1290] User: A company employee in his 20s who lives alone in an apartment and uses a refrigerator, air conditioner, washing machine, and microwave.

[1291] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, and peak hours for electricity usage.

[1292] Energy-saving suggestion from a generative AI model: "By raising the air conditioner temperature setting by 1 degree in the morning, you can save 5,000 yen in electricity bills per year."

[1293] The server sends this proposal to the user's device via a push notification.

[1294] The user follows the suggestions and changes the air conditioner's temperature setting.

[1295] Example prompt sentence:

[1296] "I'm a company employee in my 20s who lives alone and uses a refrigerator, air conditioner, washing machine, and microwave. I'm away from home from 7:00 AM to 6:00 PM, so I'd like to reduce the frequency of using the air conditioner. Please tell me some ways to save on electricity bills."

[1297] Furthermore, the server collects feedback from users and evaluates the results of the proposed energy-saving methods. Based on the evaluation results, users are given rewards such as in-app currency and real prizes, which encourages users to continue energy-saving behavior.

[1298] The server continuously trains the generative AI model with newly collected data to improve its accuracy, a process that ensures users always receive the most up-to-date and optimal energy-saving suggestions.

[1299] Throughout the system, users simply receive individually optimized energy saving suggestions that can be implemented through concrete actions.

[1300] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1301] Step 1:

[1302] Users launch the Eco Electricity App on a device such as a smartphone or tablet and enter attribute information such as family composition, type of residence, and types of home appliances they own.

[1303] Input: User's family structure, residence type, and types of appliances owned

[1304] Output: The entered attribute information is sent to the server.

[1305] What happens: A user enters information using a form within the app and presses the submit button, which sends this information to the server.

[1306] Step 2:

[1307] The terminal collects electricity usage data from smart meters and connected IoT devices and sends it to a server at regular intervals.

[1308] Input: Domestic electricity usage data (data from smart meters and IoT devices)

[1309] Output: Collected electricity usage data is stored on the server.

[1310] Specific operation: The terminal periodically communicates with smart meters and IoT devices, acquires electricity usage data, and sends it to a server.

[1311] Step 3:

[1312] The server preprocesses the received attribute information and electricity usage data by imputing missing values, scaling, and encoding categorical variables using the Python pandas library.

[1313] Input: Attribute information, electricity usage data

[1314] Output: Preprocessed data

[1315] What it does: The server runs a Python script to impute missing values ​​in attribute information and electricity usage data, scale it, and convert categorical variables to numeric values ​​as needed.

[1316] Step 4:

[1317] The server inputs the preprocessed data into a generative AI model, a machine learning model using TensorFlow and PyTorch, which analyzes the data and generates optimal power-saving strategies.

[1318] Input: Preprocessed data

[1319] Output: Best way to save power

[1320] How it works: The server feeds data to a generative AI model, which then generates optimal power-saving strategies based on learned patterns.

[1321] Step 5:

[1322] The server sends the generated power saving method to the user's device as a push notification.

[1323] Input: Best way to save energy

[1324] Output: Push notification to the user's device

[1325] Specific operation: The server converts the power saving method into JSON format and sends it to the user's device using the push notification service.

[1326] Step 6:

[1327] The user checks the suggestions and implements specific power saving methods.

[1328] Input: Power saving method received via push notification

[1329] Output: Actual energy-saving measures taken (e.g., raising the air conditioner temperature setting by 1 degree)

[1330] Specific behavior: The user receives a notification through the app, implements the suggested power-saving measures, and checks the results.

[1331] Step 7:

[1332] The server collects feedback from users and evaluates the proposed power saving methods.

[1333] Input: User-entered feedback, latest energy usage data

[1334] Output: Power saving effect evaluation result

[1335] Specific operation: The server analyzes the user's feedback form and power usage data to evaluate the effectiveness of the power saving suggestions.

[1336] Step 8:

[1337] The server rewards users based on the evaluation results, which are provided as in-app currency or physical prizes.

[1338] Input: Evaluation result

[1339] Output: Reward added to user account

[1340] Specific operation: The server calculates the user's reward based on the evaluation results and credits the reward to the user's account.

[1341] Step 9:

[1342] The server continuously trains the generative AI model with new data it collects, which improves the model's accuracy.

[1343] Input: New power usage data, feedback data

[1344] Output: An updated generative AI model

[1345] What it does: The server retrains the generative AI model with newly collected data to improve the model's performance.

[1346] (Application example 1)

[1347] 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."

[1348] This invention relates to a system that makes appropriate energy-saving suggestions based on the store's power usage, and aims to solve the problem that conventional energy-saving methods are abstract and do not provide specific guidelines for action. In addition, by establishing an evaluation and reward system based on user feedback, the system encourages users to continue energy-saving behavior.

[1349] 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.

[1350] In this invention, the server includes means for collecting attribute information and power usage data from users via their terminals, means for preprocessing the collected attribute information and power usage data, means for generating optimal power-saving methods using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving methods, means for collecting and evaluating feedback from users, means for rewarding users based on the evaluation, and means for providing optimal power-saving methods in real time based on the store's power usage status and power usage data. This makes it possible to provide specific and feasible power-saving suggestions to stores in real time, effectively encouraging users to take energy-saving actions.

[1351] A "terminal" is an electronic device, such as a smartphone, tablet, or PC, that allows a user to input and receive information.

[1352] "Attribute information" refers to information about an individual or household, such as the user's family structure, type of residence, and types of home appliances owned.

[1353] "Electricity usage data" refers to information about electricity consumption collected from smart meters and IoT devices.

[1354] "Preprocessing" refers to operations that process collected data, such as imputing missing values, scaling, and encoding categorical variables.

[1355] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to analyze a user's electricity usage patterns and attribute information to generate optimal energy-saving methods.

[1356] "Power saving methods" are specific suggestions or courses of action that users can take to reduce their electricity consumption.

[1357] "Notification" refers to sending the generated power saving method to the user's device in the form of a push notification or message.

[1358] "Feedback" refers to the sending back to the server of actual behavioral data and opinions after the user follows the suggestions.

[1359] "Evaluation" refers to analyzing the effectiveness of the energy-saving measures implemented based on feedback collected from users.

[1360] "Rewards" are incentives such as in-app currency or physical prizes provided to users.

[1361] "Real-time" means that analysis and recommendations are made immediately after data is collected, with results communicated to users almost instantly.

[1362] A "store" is a business office or facility for selling goods or providing services.

[1363] "Power usage data" is detailed data on power consumption in a store by hour.

[1364] "Power saving suggestions" are specific advice for reducing power consumption provided to users based on the analysis of collected data and the generated AI model.

[1365] This invention relates to a system that makes energy-saving suggestions based on the electricity usage status of a store. A user launches an eco-electricity management app using a device such as a smartphone or tablet, and inputs attribute information about the store (e.g., store size, business format, and types of electrical equipment used) into the app. In addition, the store's electricity usage data is periodically sent to a server from smart meters and IoT devices.

[1366] The server receives the attribute information and energy usage data collected via the device. The server then preprocesses this data, which includes imputing missing values, scaling, and encoding categorical variables. The preprocessed data is then input into the generative AI model.

[1367] The generative AI model analyzes the user's power usage patterns and attribute information to generate optimal power-saving methods. This generative AI model uses machine learning frameworks such as TensorFlow and PyTorch. The generated power-saving methods are provided to the user as specific, actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can review the suggestions and take specific actions.

[1368] Additionally, the server collects user feedback and evaluates the effectiveness of the implemented energy-saving measures. Based on this evaluation, users are rewarded with in-app currency, physical prizes, etc. The generative AI model is continuously trained with new data to improve its accuracy.

[1369] Specific examples

[1370] Example 1: A store in a shopping mall

[1371] User: A store owner in a shopping mall who uses a lot of air conditioning, lighting, and electronics.

[1372] Data collected by the server: Store electricity usage graph, business hours, and information on home appliances being used.

[1373] The generative AI model analyzes this data and generates a suggestion such as, "By raising the air conditioner temperature by 2 degrees after closing, you can save 2,000 yen per month on electricity."

[1374] The server will send a push notification of this proposal to the manager's smartphone.

[1375] The manager follows the suggestions, changes the air conditioning settings and checks the effect.

[1376] Prompt Sentence Examples

[1377] "Generate optimal energy-saving methods based on store power consumption data."

[1378] "Analyze this data and provide specific energy-saving suggestions: e.g., adjust the air conditioner temperature setting after closing time."

[1379] This allows stores to receive specific and actionable energy-saving suggestions in real time, effectively encouraging users to take energy-saving actions.

[1380] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1381] Step 1:

[1382] Data collection

[1383] Users launch the eco-electricity management app on their smartphones, tablets, or other devices and enter their store's attribute information (e.g., store size, business format, and types of electrical equipment used). In addition, the store's electricity usage data is periodically sent to the server from smart meters and IoT devices.

[1384] Input: User attribute information, electricity usage data

[1385] Output: User attribute information and power usage data stored on the server

[1386] Step 2:

[1387] Data Preprocessing

[1388] The server preprocesses the collected attribute information and electricity usage data, including imputing missing values, scaling, and encoding categorical variables.

[1389] Input: Raw user demographic information and electricity usage data

[1390] Output: Preprocessed user attribute information and electricity usage data

[1391] Specific behaviors: missing value imputation, data normalization, categorical variable encoding

[1392] Step 3:

[1393] Input to generative AI models

[1394] The server inputs the preprocessed data into a generative AI model, which is built using a machine learning framework (e.g., TensorFlow or PyTorch).

[1395] Input: Preprocessed user demographic information and electricity usage data

[1396] Output: Analysis results from the generative AI model

[1397] Specific operations: Data analysis, pattern recognition, and generation of power saving methods

[1398] Step 4:

[1399] Generate specific energy saving methods

[1400] The generative AI model analyzes the user's energy usage patterns and attribute information to generate optimal energy-saving methods, which are then sent to the server as specific, actionable suggestions.

[1401] Input: Preprocessed data

[1402] Output: Specific power saving methods

[1403] Specific operations: Generate power saving methods and confirm the proposed contents

[1404] Step 5:

[1405] notification

[1406] The server sends the generated power saving methods to the user's device as a push notification, allowing the user to review the suggestions and take specific actions.

[1407] Input: Specific energy saving methods

[1408] Output: Push notification sent to user device

[1409] Specific behavior: Creating and sending a push notification

[1410] Step 6:

[1411] Gathering and evaluating feedback

[1412] The server collects feedback from users and evaluates the effectiveness of the implemented power saving measures.

[1413] Input: User feedback

[1414] Output: Evaluation result

[1415] Specific actions: Analyzing feedback and evaluating effectiveness

[1416] Step 7:

[1417] Rewarding

[1418] Based on their ratings, users are rewarded with in-app currency, physical prizes, and other rewards. The generative AI model is continually trained with new data to improve its accuracy.

[1419] Input: Evaluation result

[1420] Output: Reward, updated generative AI model

[1421] Specific operations: Calculating and awarding rewards, training and updating generative AI models

[1422] 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.

[1423] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the electricity usage situation in a home.

[1424] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[1425] The device sends the input attribute information and emotion data to a server, which receives this information and stores it in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day.

[1426] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model.

[1427] The generative AI model analyzes the user's power usage patterns, attribute information, and emotional data to generate optimal power-saving methods for each user. The generated power-saving methods are provided to the user as specific and actionable suggestions. The server sends these power-saving methods to the user's device as push notifications. The user can then review the suggestions and take specific actions.

[1428] Furthermore, the server collects feedback from users and not only evaluates the effectiveness of the implemented power-saving measures, but also evaluates the emotional aspects of the feedback using an emotion engine. This evaluation is a comprehensive evaluation that includes the degree of power consumption reduction and the user's emotional response. Based on this evaluation, users are given rewards such as in-app currency and real prizes.

[1429] The generative AI model is also continually trained with new data to improve its accuracy, ensuring advice is always based on the most up-to-date information and personalized energy-saving suggestions that take into account the user's emotional state.

[1430] Specific examples

[1431] Example 1: For a user living alone

[1432] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[1433] Data collected by the server: This includes the fact that the user is away from home between 7am and 6pm, how often the air conditioner is used, peak hours of power usage, and emotional data (e.g., stress levels, mood states).

[1434] The generative AI model analyzes this data and generates energy-saving suggestions, such as "Raising the air conditioner temperature setting by 1 degree in the morning will save you 5,000 yen in electricity bills per year." At the same time, the emotion engine takes into account the user's stress level and adjusts the suggestions to be made during times when stress is lower.

[1435] The server will push this proposal to the user's device.

[1436] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect of the suggestions.

[1437] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1438] Example 2: Family users

[1439] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[1440] Data collected by the server: Includes the fact that the user's family consumes the most electricity in the evening, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[1441] The generative AI model analyzes this data and generates energy-saving suggestions such as, "Use LED lighting, which consumes less energy, after dinner. This will save you about 3,000 yen a year." The emotion engine takes into account the emotional state of the entire family and makes suggestions at the most acceptable times.

[1442] The server will push this proposal to the user's device.

[1443] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[1444] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1445] This example allows users to receive personalized energy-saving suggestions that take their emotional state into account without asking any direct questions, and implement them in a simple process. Continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[1446] The processing flow will be explained below.

[1447] Step 1:

[1448] Users launch the Eco Electricity app via a device such as a smartphone, tablet, or PC, and enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and emotional data (e.g., current mood, stress level) as initial settings.

[1449] Step 2:

[1450] The device sends the input attribute information and emotion data to the server, which receives the attribute information and emotion data and stores them in a database.

[1451] Step 3:

[1452] The server periodically collects electricity usage data from smart meters and IoT devices, including information on household electricity consumption and usage patterns by time of day.

[1453] Step 4:

[1454] The server preprocesses the collected attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[1455] Step 5:

[1456] The server inputs the preprocessed data into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate individually optimized energy-saving methods.

[1457] Step 6:

[1458] The server sends the generated power-saving methods to the device as push notifications. The emotion engine adjusts the timing and content of the suggestions based on the user's emotional state.

[1459] Step 7:

[1460] The user can check the push notification via their device and take specific actions to save energy, such as changing the temperature setting of the air conditioner or doing laundry at a specific time.

[1461] Step 8:

[1462] The server collects user feedback along with emotional data, and users can provide feedback such as their feelings and perceived stress levels through the app.

[1463] Step 9:

[1464] The server analyzes the collected feedback and power usage data to evaluate the effectiveness of the implemented energy-saving measures, based on a comprehensive evaluation that includes the degree of reduction in power consumption and the user's emotional response.

[1465] Step 10:

[1466] The server calculates a success fee based on the evaluation and credits the user's account with the reward, which can be in the form of in-app currency or physical prizes.

[1467] Step 11:

[1468] The server continuously collects new data to train and update the generative AI model and emotion engine, improving the model's accuracy and providing the latest energy-saving suggestions.

[1469] Example 2

[1470] 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."

[1471] In modern homes, reducing power consumption is an important issue for environmental protection and energy cost reduction. However, it is difficult for users to understand their own power usage patterns and find optimal ways to save power. In addition, there is a demand for energy-saving suggestions that take emotional factors into account, but until now, no system has existed that can achieve this.

[1472] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for collecting emotion data, means for preprocessing the collected attribute information, power usage data, and emotion data, means for generating an optimal power-saving method using a generative AI model with the preprocessed data, means for notifying the user's terminal of the generated power-saving method, means for collecting and evaluating feedback from the user, means for rewarding the user based on the evaluation, and means for retraining the generative AI model. This enables highly accurate power-saving suggestions that take into account the user's individual power usage pattern and emotional state.

[1473] "Terminal" refers to a device used by a user to input information or receive notifications, and specifically includes smartphones, tablets, and personal computers.

[1474] "Attribute information" refers to information about the user's lifestyle and environment, such as the user's family structure, type of residence, and types of home appliances owned.

[1475] "Electricity usage data" refers to information such as household electricity consumption and usage patterns by time of day obtained through smart meters and IoT devices.

[1476] "Emotional data" refers to information about a user's emotional state, such as their stress level or mood, and is obtained through the app's camera, microphone, or text input.

[1477] "Preprocessing" refers to the process of converting collected data into a format that is easier to analyze, and specifically includes imputing missing data, scaling numerical data, and encoding categorical variables.

[1478] "Generative AI model" refers to an artificial intelligence model used to analyze collected data and generate optimal energy-saving methods for each user.

[1479] "Power saving method" refers to a specific and feasible method for reducing power consumption that is provided based on a user's power usage pattern.

[1480] "Notification" refers to the act of notifying the user's device of the power saving method generated by the server, and specifically includes push notifications.

[1481] "Feedback" refers to the act of a user providing information such as the results of implementing a proposed energy-saving method and their impressions.

[1482] "Evaluation" refers to the act of analyzing the effectiveness of implemented energy-saving measures and users' emotional reactions based on feedback collected from users.

[1483] "Rewards" refers to incentives such as in-app currency or real prizes given to users based on the evaluation results.

[1484] "Retraining" refers to the act of retraining a generative AI model using newly collected data in order to improve its accuracy.

[1485] The present invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation in a home. Specifically, the system is implemented in the following manner.

[1486] System configuration

[1487] First, users launch the Eco Electric app on their smartphone, tablet, PC, or other device and enter their attribute information (e.g., family composition, type of residence, and types of home appliances owned) as the initial setting. Users can also provide emotional data through the app's camera, microphone, or text input.

[1488] The device sends the input attribute information and emotion data to a server. The server receives this information and stores it in a database, such as MySQL or MongoDB. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes household electricity consumption and usage patterns by time of day.

[1489] The server preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. Python libraries (e.g., Pandas, Scikit-learn) are used for preprocessing.

[1490] The preprocessed data is input into a generative AI model, which analyzes the user's energy usage patterns, attribute information, and emotional data to generate optimal energy-saving methods for each user. This analysis is performed using deep learning frameworks (e.g., TensorFlow, PyTorch).

[1491] The generated power-saving methods are provided to the user as specific and actionable suggestions, and the server sends these power-saving methods to the user's device as push notifications using a notification service such as Firebase Cloud Messaging (FCM).

[1492] Users can review the suggestions and take specific actions. They also provide feedback within the app, such as the effectiveness of the suggestions and their impressions. The server receives this feedback and evaluates it. The evaluation includes analyzing the collected emotional data with an emotion engine.

[1493] Based on the feedback, the server can reward the user, which can include in-app currency or physical prizes.

[1494] The generative AI model is also continually trained with new data to improve its accuracy, ensuring that advice is always based on the most up-to-date information and that personalized energy-saving suggestions take into account the user's emotional state.

[1495] Specific examples

[1496] Example 1: For a user living alone

[1497] User: A company employee in his 20s who lives alone in an apartment. He uses a refrigerator, air conditioner, washing machine, and microwave.

[1498] Data collected by the server: Attribute information such as being away from home between 7am and 6pm, frequency of air conditioning use, peak hours of electricity usage, and emotional data (e.g., stress level, mood state).

[1499] Based on this data, the generative AI model suggests, "Raising the air conditioner temperature setting by 1 degree in the morning will save 5,000 yen in electricity bills per year." The emotion engine takes into account the user's stress level and makes suggestions for times when stress is low.

[1500] The server sends a push notification of this proposal to the user's device.

[1501] The user follows the suggestions, changes the air conditioner's temperature setting, and checks the effect.

[1502] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1503] Example 2: Family users

[1504] User: A family of four (couple and two children) living in a detached house. They frequently use a refrigerator, air conditioner, television, and lighting fixtures.

[1505] Data collected by the server: Attribute information such as which hours of the day a family uses the most electricity, regular laundry and cooking schedules, and emotional data (e.g., family members' emotional state, stress levels).

[1506] Based on this data, the generative AI model suggests, "Using LED lighting after dinner, which consumes less energy, can save approximately 3,000 yen per year." The model makes this suggestion at the most receptive timing, taking into account the emotional state of the entire family.

[1507] The server sends a push notification of this proposal to the user's device.

[1508] The user follows the suggestion and uses the LED lighting after dinner to see the effect.

[1509] The server evaluates the power consumption and emotion data and awards a reward to the user.

[1510] This allows users to receive individually optimized energy-saving suggestions that take into account their emotional state without asking any direct questions, and implement them in a simple procedure. In addition, continuous feedback and rewards motivate users to take sustainable energy-saving actions.

[1511] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1512] Step 1:

[1513] Users launch the Eco Electricity app using a device such as a smartphone, tablet, or PC. On the initial setup screen, users enter attribute information such as family composition, type of residence, and the types of appliances used. Users can also provide emotional data using the app's camera, microphone, or text input. Inputs include attribute information and emotional data, and the output is data that the device sends to the server.

[1514] As a specific operation, after the user has finished inputting, he or she presses the "send" button.

[1515] Step 2:

[1516] The terminal transmits the attribute information and emotion data entered by the user to the server via the Internet. The input data includes the user's attribute information and emotion data, and the output data is delivered to the server.

[1517] Specifically, the device uses Wi-Fi or mobile data communication to send data to the server's API as a POST request.

[1518] Step 3:

[1519] The server receives the attribute information and emotion data and stores them in a database, such as MySQL or MongoDB. The input is the received data, and the output is the attribute information and emotion data stored in the database.

[1520] Specifically, the server receives the data in JSON format and inserts it into the appropriate table or collection.

[1521] Step 4:

[1522] The server periodically collects household electricity usage data from smart meters and IoT devices, including household electricity consumption and usage patterns by time of day. The input is electricity usage data from the smart meters, and the output is electricity usage data accumulated by the server.

[1523] Specifically, the server uses an API to send a data acquisition request to the smart meter every 30 minutes.

[1524] Step 5:

[1525] The server preprocesses the collected attribute information, emotion data, and power usage data. Preprocessing includes imputing missing data, scaling numerical data, encoding categorical variables, etc. The input is the various collected and stored data, and the output is the preprocessed data.

[1526] Specifically, it uses Python's Pandas and Scikit-learn libraries to cleanse and transform data.

[1527] Step 6:

[1528] The preprocessed data is input into a generative AI model, which uses this data to generate optimal power-saving methods for each user. The input is the preprocessed data, and the output is the optimal power-saving method.

[1529] Specifically, it runs deep learning models using TensorFlow and PyTorch to generate user-specific power-saving suggestions.

[1530] Step 7:

[1531] The generated power saving method is sent from the server to the user's device as a push notification. The input is the generated power saving method, and the output is a notification displayed on the user's device.

[1532] Specifically, it sends a message using a notification service such as Firebase Cloud Messaging (FCM).

[1533] Step 8:

[1534] The user checks the received power-saving suggestions and takes specific actions according to the suggestions. The input is the power-saving suggestions displayed on the terminal, and the output is the actual power-saving actions.

[1535] Specific actions include following suggestions such as raising the air conditioner's set temperature by 1 degree or switching to LED lighting.

[1536] Step 9:

[1537] The server collects feedback from users and evaluates the effectiveness of the implemented power-saving measures. The evaluation also analyzes emotional feedback using an emotion engine. The input is user feedback data, and the output is the evaluation result.

[1538] Specifically, the server collects opinions and feedback through a feedback form and runs a Python script to analyze them.

[1539] Step 10:

[1540] The server retrains the generative AI model to improve its accuracy, updating it with newly collected data, with the new data as input and the retrained model as output.

[1541] Specifically, it periodically inputs new data into the model in batches and runs a script to retrain it.

[1542] (Application example 2)

[1543] 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."

[1544] Optimizing energy consumption is an urgent issue in modern homes and brick-and-mortar stores, but existing energy-saving suggestion systems have problems with low suggestion acceptance and implementation rates because they do not fully consider the user's emotional state or individual attribute information. Furthermore, there are insufficient means to properly evaluate user feedback and improve the accuracy of generative AI models through continuous training.

[1545] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting attribute information and power usage data from a user via a terminal, means for preprocessing the collected attribute information and power usage data, means for generating an optimal power-saving method using a generative AI model based on the preprocessed data, means for notifying the user of the generated power-saving method, means for collecting and preprocessing user emotion data, means for analyzing the emotion data to optimize the timing of the notification of the suggestion, means for collecting and evaluating feedback from the user, and means for rewarding the user based on the evaluation. This enables individually optimized power-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, by training and updating the generative AI model based on continuous feedback, the system always provides the latest and most accurate suggestions.

[1546] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[1547] "Attribute information" refers to information such as the user's family composition, type of residence, and types of home appliances owned.

[1548] "Electricity usage data" refers to data on electricity consumption within homes and stores and usage patterns by time of day, collected from smart meters and IoT devices.

[1549] "Preprocessing" is the process of preparing collected data by completing missing data, scaling numerical data, encoding categorical variables, etc.

[1550] A "generative AI model" is an artificial intelligence model that analyzes data, finds complex patterns and relationships, and generates optimal energy-saving methods.

[1551] "Power saving methods" refers to specific techniques and proposals for reducing power consumption.

[1552] "Feedback" is data obtained from users regarding the effectiveness of implemented energy saving suggestions and their emotional reactions.

[1553] "Rewards" are incentives such as in-app currency or physical prizes that are given to users after they put the suggested energy-saving methods into practice and their effectiveness is confirmed.

[1554] "Emotional data" refers to data that indicates the user's emotional state, such as stress level or mood.

[1555] The "Emotion Engine" is an artificial intelligence system that analyzes collected emotional data and optimizes the timing of notification suggestions.

[1556] This invention relates to a system that uses a terminal, a server, a generative AI model, and an emotion engine to make appropriate energy-saving suggestions according to the power usage situation of a home or a brick-and-mortar store. Detailed embodiments of this system will be described below.

[1557] First, the user launches the Eco Electricity app on a device such as a smartphone, tablet, or PC. During initial setup, attribute information (e.g., family composition, residence type, and types of appliances owned) and electricity usage data are collected from the user via the device. The user also provides emotional data via the app's camera, microphone, and text input.

[1558] The device sends this information to a server, which stores the received attribute information and emotion data in a database. At the same time, the server periodically collects electricity usage data from smart meters and IoT devices. This data includes electricity consumption in homes and stores and usage patterns by time of day.

[1559] The server then preprocesses the collected attribute information, emotion data, and energy usage data. This preprocessing includes imputing missing data, scaling numerical data, and encoding categorical variables. The preprocessed data is then input into a generative AI model to generate optimal energy-saving methods based on the user's energy usage patterns, attribute information, and emotion data.

[1560] The generated power-saving methods are notified to the device as specific and actionable suggestions. These suggestions are notified at appropriate times by the emotion engine, taking into account the user's emotional state. The server then sends these power-saving methods to the user's device as push notifications, allowing the user to confirm the suggestions and take specific actions.

[1561] The server also collects user feedback and evaluates the effectiveness of the app, based on a comprehensive evaluation that includes the degree of energy consumption reduction and the user's emotional response. Based on this evaluation, users are rewarded with in-app currency or real prizes.

[1562] Additionally, the generative AI model is continually trained with new data to improve its accuracy, ensuring that it always delivers the most up-to-date and accurate recommendations.

[1563] As a concrete example, let us consider the case of a coffee shop.

[1564] For example, if the user is a coffee shop manager, the server collects business hours, peak power usage, and staff emotional data (e.g., stress levels during busy hours). The generative AI model generates suggestions such as, "By reducing the store's lighting by half between 10:00 and 11:00 a.m., when there are fewer customers, you can save 2,000 yen per month on electricity." The emotion engine takes into account the emotional state of the staff and notifies them at times when stress is low. The server sends a push notification of this suggestion to the manager's smartphone, who then consults with the staff and adjusts the lighting. The server then evaluates the change in power usage and confirms the power-saving effect. The manager is rewarded with in-app currency as a success reward.

[1565] An example of a prompt would be, "Consider power usage data and emotion data and generate the optimal energy-saving method for a coffee shop. For example, reduce the lights by half between 10:00 and 11:00 AM." By inputting this prompt into the generative AI model, the corresponding energy-saving suggestion will be generated.

[1566] As described above, this system enables individually optimized energy-saving suggestions that take into account the user's emotional state and attribute information. Furthermore, continuous feedback and model training enable the system to always provide the latest and most accurate suggestions.

[1567] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1568] Step 1:

[1569] Users launch the Eco Electric app on their smartphone, tablet, PC, or other device. During the initial setup, users enter attribute information (e.g., family composition, type of residence, types of home appliances owned) and also provide emotional data (e.g., stress level, mood state).

[1570] Input: attribute information, emotion data

[1571] Output: Attribute information and emotion data are saved on the device.

[1572] Step 2:

[1573] The device sends the collected attribute information and emotion data to the server. It also periodically collects electricity usage data from smart meters and IoT devices within the home or physical store and sends it to the server.

[1574] Input: Attribute information, emotion data, power usage data

[1575] Output: Attribute information, emotion data, and power usage data are stored on the server.

[1576] Step 3:

[1577] The server preprocesses the received attribute information, emotion data, and energy usage data, including imputing missing data, scaling numerical data, and encoding categorical variables.

[1578] Input: Attribute information, emotion data, power usage data

[1579] Output: Preprocessed data

[1580] Step 4:

[1581] The server inputs the preprocessed data into a generative AI model, which generates optimal energy-saving methods based on the user's power usage patterns, attribute information, and emotional data.

[1582] Input: Preprocessed data

[1583] Output: Best way to save power

[1584] Step 5:

[1585] The server sends the generated power-saving methods to the user's device as push notifications, with the emotion engine providing the notifications at appropriate times, taking into account the user's emotional state.

[1586] Input: Optimal power saving method, emotional data

[1587] Output: Push notification of power saving suggestions

[1588] Step 6:

[1589] Users can check the energy-saving suggestions sent to their device and take specific actions, such as adjusting lighting or changing air conditioning settings.

[1590] Input: Push notification of power saving suggestions

[1591] Output: Energy saving actions taken

[1592] Step 7:

[1593] The server collects feedback from users and evaluates the effectiveness of the implemented energy-saving measures, including the degree of reduction in power consumption and the user's emotional response.

[1594] Input: Feedback data

[1595] Output: Evaluation result

[1596] Step 8:

[1597] The server rewards the user (e.g., in-app currency, real prizes) based on the evaluation results.

[1598] Input: Evaluation result

[1599] Output: Reward granted

[1600] Step 9:

[1601] The server uses the preprocessed data and feedback data to train and update the generative AI model, and this continuous training improves the accuracy of the generative AI model.

[1602] Input: Preprocessed data, feedback data

[1603] Output: An updated generative AI model

[1604] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1605] 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.

[1606] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1607] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1608] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1609] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1610] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1611] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1612] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1613] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1614] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1615] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1616] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1617] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1618] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1619] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1620] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1621] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1622] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1623] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1624] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1625] The following is further disclosed regarding the above embodiment.

[1626] (Claim 1)

[1627] A means for collecting attribute information and electricity usage data from users via a terminal;

[1628] means for preprocessing the collected attribute information and electricity usage data;

[1629] A means for generating an optimal power saving method using a generative AI model using preprocessed data;

[1630] a means for notifying a user's device of the generated power saving method;

[1631] a means of collecting and evaluating user feedback;

[1632] a means for rewarding users based on their ratings;

[1633] A system including:

[1634] (Claim 2)

[1635] The system of claim 1, wherein the generative AI model analyzes a user's power usage patterns and attribute information to provide individually optimized power saving suggestions.

[1636] (Claim 3)

[1637] 10. The system of claim 1, further comprising means for training and updating the generative AI model using the preprocessed data.

[1638] "Example 1"

[1639] (Claim 1)

[1640] A means for collecting attribute information and electricity usage data from users via a terminal;

[1641] means for preprocessing the collected attribute information and electricity usage data;

[1642] A means for generating an optimal power saving method using a generative AI model using preprocessed data;

[1643] a means for notifying a user's device of the generated power saving method;

[1644] a means of collecting and evaluating user feedback;

[1645] a means for rewarding users based on their ratings;

[1646] A means to continuously train and update the generative AI model; and

[1647] A system including:

[1648] (Claim 2)

[1649] The system of claim 1, wherein the generative AI model analyzes a user's power usage patterns and attribute information to provide individually optimized power saving suggestions.

[1650] (Claim 3)

[1651] The system of claim 1, wherein power saving method suggestions using the generative AI model are notified to the user's terminal as executable actions.

[1652] "Application Example 1"

[1653] (Claim 1)

[1654] A means for collecting attribute information and electricity usage data from users via a terminal;

[1655] means for preprocessing the collected attribute information and electricity usage data;

[1656] A means for generating an optimal power saving method using a generative AI model using preprocessed data;

[1657] a means for notifying a user's device of the generated power saving method;

[1658] a means of collecting and evaluating user feedback;

[1659] a means for rewarding users based on their ratings;

[1660] A means to provide optimal energy-saving methods in real time based on the store's power usage status and power usage data,

[1661] A system including:

[1662] (Claim 2)

[1663] The system of claim 1, wherein the generative AI model analyzes a user's power usage patterns and attribute information to provide individually optimized power saving suggestions.

[1664] (Claim 3)

[1665] 10. The system of claim 1, further comprising means for training and updating the generative AI model using the preprocessed data.

[1666] "Example 2: Combining Emotion Engines"

[1667] (Claim 1)

[1668] means for collecting attribute information and power usage data from users via terminals;

[1669] a means for collecting emotion data;

[1670] A means for preprocessing the collected attribute information, power usage data, and emotion data;

[1671] A means for generating an optimal power saving method using a generative AI model using preprocessed data;

[1672] means for notifying a user terminal of the generated power saving method;

[1673] a means for collecting and evaluating user feedback;

[1674] means for rewarding users based on their ratings;

[1675] A means to retrain the generative AI model; and

[1676] A system including:

[1677] (Claim 2)

[1678] The system of claim 1, wherein the generative AI model analyzes a user's power usage patterns, attribute information, and emotional data to provide individually optimized power saving suggestions.

[1679] (Claim 3)

[1680] 10. The system of claim 1, further comprising means for training and updating the generative AI model using the preprocessed data.

[1681] "Application example 2 when combining emotion engines"

[1682] (Claim 1)

[1683] A means for collecting attribute information and electricity usage data from users via a terminal;

[1684] means for preprocessing the collected attribute information and electricity usage data;

[1685] A means for generating an optimal power saving method using a generative AI model using preprocessed data;

[1686] a means for notifying a user's device of the generated power saving method;

[1687] a means for collecting and preprocessing user emotion data;

[1688] A means for analyzing emotional data to optimize the timing of notification of suggestions;

[1689] a means of collecting and evaluating user feedback;

[1690] a means for rewarding users based on their ratings;

[1691] A system including:

[1692] (Claim 2)

[1693] 2. The system of claim 1, wherein the generative AI model analyzes a user's power usage patterns, attribute information, and emotional data to provide individually optimized power saving suggestions.

[1694] (Claim 3)

[1695] 10. The system of claim 1, further comprising means for training and updating the generative AI model using the preprocessed data and the feedback data. [Explanation of symbols]

[1696] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting attribute information and electricity usage data from users via a terminal; means for preprocessing the collected attribute information and electricity usage data; A means for generating an optimal power saving method using a generative AI model using preprocessed data; a means for notifying a user's device of the generated power saving method; a means of collecting and evaluating user feedback; a means for rewarding users based on their ratings; A system including:

2. The system of claim 1, wherein the generative AI model analyzes a user's power usage patterns and attribute information to provide individually optimized power saving suggestions.

3. 10. The system of claim 1, further comprising means for training and updating the generative AI model using the preprocessed data.

Images