system

Abstract

Provide a system. [Solution] means for receiving historical power usage information and condition parameters from a user; a means for referencing a database of a plurality of electric power companies and their service menus based on the received information; A means for analyzing the information and database using a machine learning algorithm to identify the optimal power company and service menu for the user; means for presenting the identified electric power company and its service menu to a user; a means for recording the user's selection and using it to improve the accuracy of future analyses; A system including:

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] In today's deregulated electricity market, it is extremely complicated for users to select the optimal power company and its service menu. Finding the optimal plan while considering a wide range of factors, such as the user's past electricity usage data, family composition, and lifestyle patterns, requires a significant amount of time and effort. It is also not easy to compare different plans offered by numerous power companies. Therefore, there is a need for a system that can effectively analyze these complex factors and present the optimal power company and plan to the user. [Means for solving the problem]

[0005] The present invention collects past electricity usage information and condition parameters from a user and, based on that information, references a database of power companies and their service menus. A system is provided that uses a machine learning algorithm to analyze this information and identify the power company and service menu that are optimal for the user. First, the user inputs information about their past electricity consumption data, the power company and plan they are using, and their lifestyle patterns via their terminal. Next, the terminal transmits that information to a server, which retrieves related information from the database. A machine learning algorithm is used to perform analysis and identify the power company and plan that are optimal for the user. Finally, the identified plan is presented to the user, and the user's selection information is recorded and used to improve the accuracy of future analysis. In this way, the user can effectively select the optimal power company and plan.

[0006] A "user" is an individual or household who uses this system to select the most suitable power company and service menu.

[0007] "Past power usage information" is data such as the amount of power consumed by the user in the past and the time period.

[0008] "Condition parameters" are various factors that should be taken into consideration in order to select the optimal power plan, such as the user's household configuration, lifestyle patterns, and types of electrical appliances used.

[0009] A "database" is an information source that stores detailed information about multiple electric power companies and their service menus.

[0010] A "machine learning algorithm" is a computer program that learns patterns from large amounts of data and makes predictions and classifications.

[0011] "Analysis" is a data processing process that uses the collected data to determine the optimal power company and service menu.

[0012] An "electric power company" is a business that supplies electricity to homes.

[0013] A "service menu" is a plan that includes various rate plans and contract terms offered by an electric power company.

[0014] "API" stands for Application Program Interface, a standardized means of exchanging data between systems.

[0015] "Feedback data" is data, such as user selection results, that is used to improve the accuracy of future analyses. [Brief explanation of the drawings]

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

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

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

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

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The present invention is a system that helps electricity consumers select the most suitable electric power company and the service menu they offer. This system is realized through a series of processes, including data collection from users, data analysis on the server side, and presentation of the optimal plan. How the user, terminal, and server implement this system is described in detail below.

[0038] User operations

[0039] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[0040] Electricity usage over the past 12 months

[0041] Your current electricity provider and plan name

[0042] Family composition (e.g., 2 adults, 2 children)

[0043] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0044] When the user enters this information, the terminal checks the data format and required fields to verify that it has been entered correctly.

[0045] Terminal handling

[0046] The device then compiles the verified information and sends it to the server, typically via an API call to ensure security and data integrity.

[0047] Server Processing

[0048] The server receives the user data sent from the device and stores it in a database. The server then retrieves detailed information about the electricity company and its plans from the database, including each plan's rate structure (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0049] The server uses machine learning algorithms to analyze the user's past electricity usage information and condition parameters. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption pattern.

[0050] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then generated as a proposal.

[0051] Presentation of proposed results

[0052] The server then sends the generated proposal results to the device, which include a price estimate for each plan and the reasons for the recommendation (e.g., cost savings, which plan is best suited to your usage pattern, etc.).

[0053] The device displays the information received from the server to the user. The user can then check the details of the proposed power company and plan on the device screen. For example, the user can view the specific plan details, fee simulation, and advantages and disadvantages of "Power Company A's Home Plan B" and "Power Company B's Eco Plan C."

[0054] User Choice and Feedback

[0055] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data to improve the accuracy of the AI ​​model in the future.

[0056] As described above, the present invention is a system that efficiently provides the most suitable electric power company and service menu to an electric power consumer through cooperation between a user, a terminal, and a server.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user enters information

[0060] Users access a device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.).

[0061] Step 2:

[0062] The terminal validates the input data

[0063] The terminal checks the format and mandatory fields of the data entered by the user, and performs input validation to ensure the data is entered correctly.

[0064] Step 3:

[0065] The device sends the data to the server

[0066] Once the verification is complete, the device sends the information to the server, which then makes an API call to securely send the data to the server.

[0067] Step 4:

[0068] The server receives the data

[0069] The server receives the user data sent from the terminal, and the received data is first stored in a database.

[0070] Step 5:

[0071] The server retrieves the relevant information from the database

[0072] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0073] Step 6:

[0074] The server performs the analysis using the AI ​​model

[0075] The server analyzes the aforementioned user data and the acquired plan information using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern.

[0076] Step 7:

[0077] The server generates the analysis results

[0078] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan, thereby generating a list of the most suitable power companies and plans for the user.

[0079] Step 8:

[0080] The server sends the proposal results to the device.

[0081] The server then sends the generated recommendation results to the terminal, which include a price estimate and the reason for the recommendation.

[0082] Step 9:

[0083] The terminal receives and displays the results

[0084] The terminal visually displays the proposal results received from the server to the user, who can then check the detailed information of each plan.

[0085] Step 10:

[0086] The user selects a plan

[0087] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[0088] Step 11:

[0089] The device sends the selection information to the server

[0090] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[0091] Step 12:

[0092] The server records the selection information

[0093] The server stores the received selection results in a database, which is used as feedback data to train the AI ​​model to improve the accuracy of future analysis.

[0094] Example 1

[0095] 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."

[0096] For electricity consumers to select the optimal plan from the wide variety of electricity supplier plans, it takes a huge amount of time and effort to collect detailed information about each plan and perform comparative analysis. Advanced analysis is also required to predict the optimal plan based on electricity usage patterns, but average consumers lack the skills and tools to perform such analysis. Therefore, it is necessary to provide a system that allows consumers to easily select the electricity supplier and rate plan that is best for them.

[0097] 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.

[0098] In this invention, the server includes means for receiving past electricity usage information and condition parameters from a user, means for referencing a database of multiple electricity suppliers and their rate plans, and means for analyzing the information and database using a machine learning algorithm to identify an electricity supplier and rate plan that are optimal for the user, thereby enabling consumers to select an electricity supplier and rate plan that are optimal for them without complex information gathering and analysis.

[0099] "User" refers to an individual or legal entity that is an electricity consumer or uses the system.

[0100] "Electricity usage information" refers to data related to a user's electricity usage, such as electricity consumption over the past 12 months.

[0101] "Condition parameters" refer to factors that affect power usage, such as the user's household configuration and lifestyle patterns.

[0102] "Electricity supplier" means a company or organization that supplies electricity to consumers.

[0103] "Price plan" refers to the content of the electricity supply contract and fee structure provided by the electricity supplier.

[0104] A "database" refers to a collection of systematically stored information such as electricity supplier plan information and user information.

[0105] A "machine learning algorithm" refers to a program or method that learns from large amounts of data and makes predictions and classifications.

[0106] "Analysis" refers to the process of working with data, extracting information, and drawing conclusions.

[0107] "Simulation" refers to a technology that reproduces actual electricity usage conditions on a computer and makes predictions by testing different scenarios.

[0108] "Optimal plan" refers to the electricity supplier's rate plan that best suits the user's electricity usage pattern and conditions.

[0109] "Proposal result" refers to information about a plan recommended to a user, generated by the server through analysis and simulation.

[0110] "Feedback" refers to the process of reusing data to improve future analysis accuracy based on user-selected plan information.

[0111] "Security" refers to the measures and procedures used to protect the confidentiality, integrity, and availability of information.

[0112] The present invention is a system that helps electricity consumers select the most suitable electricity supplier and the rate plan they offer. This system is realized by collecting data from users, verifying the data on their terminals, analyzing the data on the server side, and presenting the most suitable plan.

[0113] First, the user accesses the system using a device (such as a smartphone or PC). The system's initial screen displays a form for entering information about electricity usage over the past 12 months, the current electricity supplier and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, which electrical appliances are frequently used, etc.). After completing the information, the user clicks the "Submit" button.

[0114] The device checks the format and required fields of the data entered by the user to verify that it has been entered correctly. Once verified, the data is sent to the server using an API while maintaining security. The data is encrypted before being sent, ensuring the confidentiality of the information.

[0115] The server receives the user data sent from the device and stores it in a database. The server then retrieves information about the electricity supplier and its rate plans from the database. This information includes the rate structure of each plan (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0116] The server uses machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests) to analyze the user's electricity usage information and condition parameters. This predicts the electricity supplier and rate plan that best suits the user's consumption pattern. The server then runs multiple simulations to evaluate the cost performance of each plan. The analysis results are then used to generate a proposal.

[0117] The server sends the proposal results to the device, which then displays them to the user. The proposal includes a price estimate, the reason for the recommendation, and detailed information about each plan (e.g., "Electricity Company A's Home Plan B," "Electricity Company B's Eco Plan C," etc.). The user can review this information on the screen and select the plan they deem most suitable.

[0118] Once the user selects a plan, the device sends the selection back to the server. The server stores the received selection in a database and uses it as feedback data to improve the accuracy of future analysis. This allows the system to self-learn and provide more accurate suggestions to the next user.

[0119] For example, if a user inputs their electricity usage data from the past 12 months and their current contract plan, and the system analyzes it and displays that "Electricity Company A's Home Plan B" is the best option, the user can check the details of that plan and select it. This result is saved in the system as feedback data.

[0120] An example of a prompt sentence is "Analyze the user's electricity usage data from the past 12 months and their current contracted plan, and suggest the most suitable electricity supplier and plan."

[0121] As described above, this system efficiently provides the most suitable power supplier and rate plan to power consumers through collaboration between users, terminals, and servers.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] Users access the system using devices such as smartphones or PCs. On the initial screen, users enter their electricity usage information for the past 12 months, their current electricity supplier and plan name, household composition, and lifestyle patterns.

[0125] Input: User's electricity usage information for the past 12 months, current contract information, household composition, and lifestyle patterns

[0126] Output: The input data

[0127] Specific behavior: The user enters information into each field and clicks the "Submit" button.

[0128] Step 2:

[0129] The terminal checks the format and required fields of the entered data to verify that the data has been entered correctly.

[0130] Input: Data entered by the user

[0131] Output: Validated data

[0132] Specific operation: The terminal checks the validity of input data using regular expressions and validation rules within the program.

[0133] Step 3:

[0134] The device then uses the API to send the verified data to the server, where it is encrypted before being sent.

[0135] Input: Validated data

[0136] Output: Data sent to the server

[0137] What it does: Securely transmits data using HTTP requests.

[0138] Step 4:

[0139] The server receives the data sent from the device and stores it in a database, using the user ID as a key.

[0140] Input: Request for validated data

[0141] Output: User data stored in the database

[0142] Specific operation: Data is saved to the database using the SQL INSERT command.

[0143] Step 5:

[0144] The server retrieves the electricity supplier's rate plans from a database, including rate structures, special offers, and contract terms.

[0145] Input: Database query

[0146] Output: Electricity supplier rate plan information

[0147] What it does: Uses an SQL query to retrieve the required pricing plan information.

[0148] Step 6:

[0149] The server uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests) to perform analysis based on the user's power usage information and condition parameters.

[0150] Input: User data and electricity supplier rate plan information

[0151] Output: Prediction of optimal electricity supplier and tariff plan

[0152] What it does: It uses machine learning algorithms to analyze data and predict the optimal plan.

[0153] Step 7:

[0154] The server runs multiple simulations, evaluates the cost performance of each plan, and generates a proposal result.

[0155] Input: Optimal pricing plan prediction results

[0156] Output: Proposal results

[0157] Specific actions: Use a simulation program to perform detailed cost comparisons.

[0158] Step 8:

[0159] The server then sends the generated proposal results to the device, using an API to ensure data integrity and confidentiality.

[0160] Input: Suggestion results

[0161] Output: Data sent to the terminal

[0162] Specific behavior: Sends data in the form of an HTTP response.

[0163] Step 9:

[0164] The terminal displays the received proposal results to the user, who then checks the details of the proposed plan (such as the price estimate and the reason for the recommendation).

[0165] Input: Proposal results received from the server

[0166] Output: Information displayed to the user

[0167] Specific operation: Display data on the screen using HTML and JavaScript (registered trademark).

[0168] Step 10:

[0169] The user selects the most suitable plan from the proposed plans and clicks the selection button.

[0170] Input: User's choice

[0171] Output: Selected plan information

[0172] Specific behavior: The user clicks the "Select" button on the screen.

[0173] Step 11:

[0174] The device sends the user's selection to the server, which also sends the data via an API.

[0175] Input: User selection

[0176] Output: Data sent to the server

[0177] What it does: Sends the selection data using an HTTP request.

[0178] Step 12:

[0179] The server stores the received selections in a database and uses them as feedback data to improve the accuracy of future analyses.

[0180] Input: User selection

[0181] Output: Feedback data stored in a database

[0182] Specific operation: Executes an INSERT or UPDATE command to the database.

[0183] (Application example 1)

[0184] 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."

[0185] In modern industrial manufacturing facilities, efficient energy management contributes significantly to reducing production costs and environmental impact. However, the energy consumption patterns of factory robots and equipment are complex, and advanced analysis is required to select the optimal energy plan. Conventional methods lack a system that efficiently solves these issues, resulting in wasted energy costs. The present invention aims to solve these energy management problems and improve factory operational efficiency.

[0186] 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.

[0187] In this invention, the server includes: means for receiving past energy usage information and condition parameters from a user; means for referencing a database of multiple energy suppliers and their service menus; means for analyzing the information and database using a machine learning algorithm to identify the energy supplier and service menu that are optimal for the user; means for presenting the identified energy supplier and service menu to the user; means for recording information selected by the user and using it to improve the accuracy of future analyses; means for a factory robot to collect energy consumption data in real time and transmit it to a cloud server; means for the cloud server to analyze the energy consumption data and recommend the optimal energy supplier and service menu; and means for displaying the recommendation results to a factory manager, thereby enabling efficient and optimized energy management throughout the factory.

[0188] "User" refers to a factory manager or factory operator who provides energy consumption information and condition parameters and receives a proposal for an optimal energy plan.

[0189] "Energy usage information" refers to information about energy usage within a factory, such as past energy consumption data and current consumption status.

[0190] "Condition parameters" are factors that affect energy consumption, including information on work style and equipment used.

[0191] "Energy supplier" refers to a company or organization that supplies energy such as electricity or gas.

[0192] "Service menu" refers to the various plans and contract terms offered by energy suppliers.

[0193] "Database" refers to a collection of information that stores an energy supplier's service menu, rate structure, contract terms, etc.

[0194] A "machine learning algorithm" refers to a mathematical technique that analyzes patterns based on past data to make predictions and optimal choices.

[0195] A "cloud server" is a remote server that can be accessed via the Internet and is a computer system used to store and analyze data.

[0196] "Energy consumption data" refers to data on energy usage generated in real time by factory robots and equipment.

[0197] "Recommendation" refers to the act of presenting the optimal energy supplier and service menu based on the analysis results.

[0198] A "factory robot" is a device used to perform automated tasks within a factory, and has the ability to monitor energy consumption in real time and collect data.

[0199] "Factory manager" refers to the person in charge of factory operations and energy management.

[0200] This invention is a system that uses factory robots to collect energy consumption data in real time, analyzes it on a cloud server, and recommends the optimal energy supplier and service menu. This system is realized through collaboration between users, terminals, and the cloud server.

[0201] First, factory robots collect energy consumption data in real time. This data includes past and current energy usage information, factory operation patterns, and information on equipment in use. The robots periodically send this data to a cloud server. Data transmission is generally done using an API to ensure security and data integrity.

[0202] The cloud server stores the received data in a database. It then references a database of multiple energy suppliers and their service menus to match the energy consumption data. This matching process uses machine learning algorithms. Specifically, analysis is performed using algorithms such as k-nearest neighbors, decision trees, and random forests. This identifies the energy supplier and service menu that best suits the energy consumption pattern.

[0203] The analysis results are generated as recommendations after a simulation is run to compare the cost performance of each plan. The cloud server then sends the generated recommendations to the factory robots and management terminal. The management terminal (PC, smartphone, etc.) then presents this information to the factory manager. On the screen, the factory manager can view detailed information about each energy supplier and service menu, a rate simulation, and the reasons for the recommendation.

[0204] As a concrete example, a certain factory consumes 1,500 kWh of energy per month. Robots in this factory collect data in real time and send it to a cloud server. The server analyzes past energy usage information and current consumption status, and recommends an optimal energy plan. The recommended results are sent to a management terminal, allowing factory managers to implement efficient energy management.

[0205] An example of a prompt is, "Please enter your current energy consumption data (consumption over the past 12 months, current consumption, work style, and information on the devices you use). We will recommend the optimal energy supplier and plan." By entering your energy consumption data according to this prompt, the optimal energy plan will be recommended.

[0206] This system will improve the efficiency of energy management throughout the factory and make it possible to select the most suitable energy supplier and service menu.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] Factory robots collect energy consumption data in real time. The collected data includes past energy usage information, current consumption status, operation patterns within the factory, and information on equipment being used. This data is temporarily stored in local memory. The input is sensor data from the factory robots, and the output is formatted energy consumption data.

[0210] Step 2:

[0211] The energy consumption data collected by the factory robot is sent to a cloud server using an API call, with the SSL / TLS protocol used to ensure security and data integrity. The input is the formatted energy consumption data, and the output is a message that the data was successfully uploaded to the cloud server.

[0212] Step 3:

[0213] The server stores the received energy consumption data in a database. The database contains information on past energy usage, factory operation patterns, and information on equipment used. The input is the energy consumption data received by the cloud server, and the output is a message that the data was successfully saved in the database.

[0214] Step 4:

[0215] The server accesses a database of multiple energy suppliers and their service menus, thereby collecting information on all available energy plans. The input is energy consumption data, and the output is information on the service menu.

[0216] Step 5:

[0217] The server analyzes the energy consumption data and service menu using machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests), thereby identifying the optimal energy supplier and service menu for the user. The input is the user's energy consumption data and service menu information, and the output is the recommendation of the optimal energy plan.

[0218] Step 6:

[0219] The server generates a recommendation and sends it to the factory management terminal. This includes the recommended energy plan, its reasons, and a price simulation. The input is the recommendation, and the output is a message to the factory management terminal indicating that the information was successfully sent.

[0220] Step 7:

[0221] The factory management terminal receives the recommendation results from the server and presents them to the user. On the screen, the user can view detailed information about each energy supplier and service menu, a price simulation, and the reasons for the recommendation. The input is the recommendation results received from the server, and the output is a confirmation message from the user.

[0222] 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.

[0223] The present invention is a system that can incorporate the user's emotional state into its analysis in addition to various condition parameters such as the user's past electricity usage information, household configuration, and lifestyle patterns. This system is implemented through a series of processes: collecting data from the user, analyzing the data on the server side, presenting an optimal plan, and analyzing and reflecting emotions using an emotion engine. Below, we will explain in detail how the user, terminal, server, and emotion engine implement this system.

[0224] User operations

[0225] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[0226] Electricity usage over the past 12 months

[0227] Your current electricity provider and plan name

[0228] Family composition (e.g., 2 adults, 2 children)

[0229] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0230] Furthermore, the emotion engine recognizes the user's current emotional state by analyzing the user's facial expressions and voice using the device's camera and microphone. For example, facial recognition technology can detect smiling or angry expressions, and voice analysis technology can analyze the tone and speed of speech.

[0231] Terminal handling

[0232] The device verifies the past power usage information and condition parameters entered by the user. At the same time, this data, including the emotion data acquired by the emotion engine, is sent to the server. At this time, an API call is made to ensure the data is sent securely.

[0233] Server Processing

[0234] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity company and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[0235] The server uses machine learning algorithms to analyze the user's past electricity usage information, condition parameters, and emotional data. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption patterns and emotional state.

[0236] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then used to generate a proposal, which is then provided to the user as a customized proposal that takes into account emotional data.

[0237] Presentation of proposed results

[0238] The server then sends the generated recommendation results to the device, which include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on the user's emotional state.

[0239] The device displays the information received from the server to the user. The user can check detailed information about each plan along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[0240] User Choice and Feedback

[0241] The user selects the plan they think is best from the proposed plans. The device then sends the user's selection results to the server, which stores the received selection results in a database and uses them as feedback data for future AI model accuracy improvements and emotion engine training.

[0242] As described above, this invention is a system that efficiently provides electricity consumers with the most suitable electric power company and service menu through collaboration between users, terminals, servers, and an emotion engine. Utilizing the emotion engine makes it possible to provide proposals that are even more customized to meet the user's needs.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user enters information

[0246] Users access their device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.). Users also use the device's camera and microphone to provide facial expressions and voice recordings to the system.

[0247] Step 2:

[0248] The terminal validates the input data

[0249] The device checks the format and required fields of the data entered by the user. It also validates the input values ​​to ensure that the data is entered correctly. At the same time, the emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state.

[0250] Step 3:

[0251] The device sends the data to the server

[0252] Once verified, the information and emotion data are sent from the device to the server, where the device makes an API call to securely transmit the data to the server.

[0253] Step 4:

[0254] The server receives the data

[0255] The server receives the user data and emotion data sent from the terminal, and the received data is first stored in a database.

[0256] Step 5:

[0257] The server retrieves the relevant information from the database

[0258] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0259] Step 6:

[0260] The server performs the analysis using the AI ​​model

[0261] The server analyzes the aforementioned user data, the acquired plan information, and emotional data using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern and emotional state.

[0262] Step 7:

[0263] The server generates the analysis results

[0264] The server simulates multiple scenarios based on the analysis results, compares the cost performance of each plan, and generates a list of the most suitable power companies and plans for the user as a customized proposal that also reflects emotional data.

[0265] Step 8:

[0266] The server sends the proposal results to the device.

[0267] The server then sends the generated recommendation results to the device, which include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state.

[0268] Step 9:

[0269] The terminal receives and displays the results

[0270] The device visually displays the results of the proposals received from the server to the user. The user can view detailed information about each plan, along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[0271] Step 10:

[0272] The user selects a plan

[0273] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[0274] Step 11:

[0275] The device sends the selection information to the server

[0276] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[0277] Step 12:

[0278] The server records the selection information

[0279] The server stores the received selections in a database, which is used as feedback data to improve future analysis and train the emotion engine.

[0280] Example 2

[0281] 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."

[0282] Conventional systems for recommending power companies and service menus only consider the user's past electricity usage information and condition parameters, and have the problem of being unable to provide customized proposals that reflect the user's emotional state. This makes it difficult to provide optimal service plans that match the user's emotions and lifestyle.

[0283] 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 receiving past power usage information and condition parameters from the user, means for analyzing the user's facial expressions and voice to recognize the user's emotional state, means for referencing a database of multiple power companies and their service menus based on the received information and emotional state data, means for analyzing the information, emotional data, and database using a machine learning algorithm to identify the power company and service menu that are optimal for the user, means for presenting the identified power company and service menu to the user, means for generating and presenting comments and advice based on the user's emotional state, and means for recording information selected by the user and using it to improve future analysis accuracy. This makes it possible to suggest the optimal power company and service menu that takes the user's emotional state into consideration.

[0284] "User" refers to an individual or household who uses the system to receive an electricity plan proposal.

[0285] "Past electricity usage information" refers to data regarding the amount of electricity a user has consumed in the past, including detailed usage history over a specific period of time (e.g., the past 12 months).

[0286] "Condition parameters" refer to information related to the user's household structure and lifestyle patterns, and include, for example, the number of family members, the amount of time spent at home, and frequently used electrical appliances.

[0287] "Means for recognizing an emotional state by analyzing facial expressions and voice" refers to technology that captures a user's facial expressions with a camera, records their voice with a microphone, and analyzes them to recognize the user's current emotional state.

[0288] "Means for referencing a database" refers to a technology for accessing a database that stores information about multiple electric power companies and their service menus, and obtaining the necessary data.

[0289] "Machine learning algorithms" refer to algorithms that use statistical methods and computational models to learn patterns from data and make predictions or classifications for future data. Examples include k-nearest neighbors, decision trees, and random forests.

[0290] "Means for identifying" refers to technology that uses machine learning algorithms to select the electricity company and service menu that best suits the user's conditions and emotional state.

[0291] The "means for presenting" refers to a technique for displaying the identified power company and service menu to the user, and includes, for example, a function for displaying information on the screen of a terminal.

[0292] "Means for generating and presenting comments and advice" refers to a technology for generating customized comments and advice based on the recognized emotional state of the user and displaying them to the user.

[0293] "Means for recording and using to improve the accuracy of future analysis" refers to technology that stores the plan selected by the user and its results in a database, and uses this data to improve the accuracy of the machine learning model and the performance of the entire system.

[0294] This invention is a system that proposes the most suitable power company and service menu by analyzing the user's emotional state in addition to their past electricity usage information, household configuration, and lifestyle patterns. This system is realized through the cooperation of the user, terminal, server, and emotion engine.

[0295] User operations

[0296] Users access the system using a smartphone or PC at home. The initial screen displays a form for users to enter their electricity usage over the past 12 months, the name of their current electricity provider and plan, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, and frequently used electrical appliances).

[0297] Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes their current emotional state. Specifically, facial recognition and voice analysis technologies are used to detect smiling and angry expressions, as well as voice tone and speed.

[0298] Terminal handling

[0299] The device verifies the user-entered historical power usage information and condition parameters, and transmits them along with the emotion data acquired by the emotion engine to the server, using an API call and encryption technology such as HTTPS to ensure secure transmission of the data.

[0300] Server Processing

[0301] The server receives the user data and emotion data sent from the device and stores them in a database. After storing them, it retrieves detailed information about the electricity company and its plan (e.g., basic charge, metered charge, time-of-use charge, special offer information, contract terms, etc.) from the database.

[0302] The server then uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests, etc.) to analyze the user's past electricity usage information, condition parameters, and emotional data, and predicts the optimal electricity provider and plan for the user's consumption pattern and emotional state.

[0303] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan. Based on the analysis and simulation results, the server generates proposals and adds customized comments and advice that take into account emotional data.

[0304] Presentation of proposed results

[0305] The server then sends the generated proposal results to the device. The proposal results include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on emotional data. For example, a user who is feeling stressed may be recommended an energy-saving plan that helps them relax.

[0306] User Choice and Feedback

[0307] The user selects the plan they think is best from the presented options. The device sends the selection results to the server, which stores them in a database. This feedback data is used to improve the accuracy of analysis and train the emotion engine in the future.

[0308] Examples of specific examples and prompts

[0309] Specific examples

[0310] User A accesses the system and enters the following information:

[0311] Electricity usage for the past 12 months: 600kWh / month

[0312] Current plan: X Electric Company Y Plan (pay-as-you-go)

[0313] Family composition: 2 adults, 1 child

[0314] Lifestyle: Both spouses work, at home after 6pm on weekdays, main appliances are an air conditioner and a refrigerator

[0315] Facial expression and voice analysis results: fatigue, slow voice

[0316] Based on this information, the system suggests a plan from Power Company Z, which has low off-peak rates, as the optimal plan, and provides customized advice such as, "Since you use a lot of electricity at night, a plan with low off-peak rates would be best. Also, make sure to use eco mode when you're tired."

[0317] Prompt Sentence Examples

[0318] "Please enter the user's electricity usage over the past 12 months, their current electricity contract plan, household composition and lifestyle patterns. The system will also estimate their emotional state from facial expressions and voice recordings made by the device's camera and microphone, and suggest the optimal electricity plan."

[0319] As described above, the system of the present invention can efficiently provide an optimal power plan based on the user's power usage pattern and emotional state.

[0320] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0321] Step 1:

[0322] User Data Entry

[0323] Users access the system using a smartphone or PC. They input their electricity usage over the past 12 months, their current electricity provider and plan name, household composition, and lifestyle patterns. The input data is temporarily stored in the device's local storage.

[0324] Input: electricity usage for the past 12 months, current electricity company and plan name, household composition, lifestyle patterns

[0325] Output: User data stored in the device's local storage

[0326] Step 2:

[0327] Acquiring emotion data

[0328] The device's camera and microphone are used to collect the user's facial expressions and voice data. The collected data is analyzed in real time by an emotion engine within the device. Facial recognition and voice analysis technologies are used to identify emotional states such as smile, anger, voice tone, and speed.

[0329] Input: Facial expression and voice data via camera and microphone

[0330] Output: Parsed emotional state data

[0331] Step 3:

[0332] Validating and submitting data

[0333] The device verifies the power usage information and condition parameters entered by the user. It checks the format and range to ensure the data is in the correct format. At the same time, it also verifies the emotion data and sends it to the server via an API. The data is transmitted securely using encryption technologies such as HTTPS.

[0334] Input: User data, emotional state data

[0335] Output: Validated data sent to the server

[0336] Step 4:

[0337] Receiving and storing data

[0338] The server receives the user data and emotional state data sent from the device and stores them in a database. Once stored, the server checks the data to ensure its consistency and completeness.

[0339] Input: User data and emotional state data sent from the device

[0340] Output: User data and emotional state data stored in a database

[0341] Step 5:

[0342] Obtaining electricity plan information

[0343] The server retrieves information about currently available energy plans (e.g., rate structures, special offers, contract terms, etc.) from a database, which may also include retrieving data from external APIs.

[0344] Input: User data and emotional state data

[0345] Output: Obtained electricity plan information

[0346] Step 6:

[0347] Analysis using machine learning algorithms

[0348] The server inputs user data, emotional state data, and the acquired power plan information and analyzes them using machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests). As a result of the analysis, the optimal power plan for the user is identified.

[0349] Input: User data, emotional state data, power plan information

[0350] Output: Optimal power plan information

[0351] Step 7:

[0352] Scenario simulation

[0353] The server simulates multiple scenarios based on the analysis results and evaluates the cost performance of each plan, thereby determining the optimal plan.

[0354] Input: Analysis results (optimal power plan information)

[0355] Output: Simulation results and evaluation data

[0356] Step 8:

[0357] Generate and send proposal results

[0358] The server generates suggestions based on the simulation results, adds comments and advice based on the emotional state data, and sends the suggestions to the device via API.

[0359] Input: Simulation results and evaluation data

[0360] Output: Suggestion results and customized advice sent to your device

[0361] Step 9:

[0362] Displaying the proposed results

[0363] The device displays the proposal results received from the server to the user, including price estimates, detailed plan information, and comments and advice based on emotion data.

[0364] Input: Suggested results and customized advice sent from the server

[0365] Output: Suggestion results displayed in the user interface

[0366] Step 10:

[0367] User Choice and Feedback

[0368] The user selects the plan they think is best from the presented options. The selection results are sent to the server via the device and stored in a database. The feedback data will be used to improve the accuracy of analysis and train the emotion engine.

[0369] Input: User selection

[0370] Output: Feedback data stored in a database

[0371] This series of processing steps enables the system to efficiently propose an optimal power plan to the user.

[0372] (Application example 2)

[0373] 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."

[0374] The main function of conventional energy plan proposal systems was to provide optimal plans based on parameters such as the user's past energy usage information, household configuration, and lifestyle patterns. However, these systems did not take into account the user's emotional state, which limited the ability to improve the user experience and customize proposals. In particular, in physical stores, the inability to make proposals based on the customer's emotions was a major problem.

[0375] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0376] means for receiving historical power usage information and condition parameters from a user;

[0377] a means for referencing a database of a plurality of power supply companies and service plans of each power supply company based on the received information;

[0378] means for analyzing the information and database using machine learning algorithms to identify the most suitable electricity supplier and service plan for the user;

[0379] means for presenting the identified electricity supplier and service plan to a user;

[0380] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[0381] means for recognizing a user's current emotional state and customizing a recommended service plan based on the emotional state;

[0382] This makes it possible to propose an optimal power plan according to the user's emotional state.

[0383] "Past electricity usage information" refers to data on the electricity used by a user over a certain period of time (e.g., the past 12 months).

[0384] "Condition parameters" refer to information indicating factors that affect power consumption, such as a user's lifestyle patterns and household configuration.

[0385] "Electricity supplier" means a company or entity that supplies electricity to users.

[0386] "Service plan" refers to the various contract menus and rate plans offered by electricity suppliers.

[0387] "Database" refers to a system that systematically stores information about electricity suppliers and service plans.

[0388] "Machine learning algorithms" refer to computational techniques used to analyze data and recognize patterns.

[0389] "Emotional state" refers to the user's current state of mind, such as joy, sadness, anger, etc., and is recognized from facial expressions and voice.

[0390] "Camera" refers to an image capturing device for recognizing a user's facial expressions.

[0391] "Microphone" refers to a voice capture device for capturing a user's voice and analyzing their emotional state.

[0392] "Real-time" refers to processing and analysis occurring immediately, without delay.

[0393] "Receiving power usage information" refers to the system receiving data regarding power usage provided by a user.

[0394] "Plan customization" refers to the process of adapting the service plan provided based on the user's individual requirements and emotional state.

[0395] "Proposal presentation" refers to the system displaying or notifying the user of the optimal power plan based on the analysis results.

[0396] The present invention is a system for proposing an optimal power plan to a user by utilizing power usage information and emotional state. This system is composed of the following components:

[0397] User operations

[0398] Users access the system using devices such as smart glasses, smartphones, or PCs. On the initial screen, users enter the following information:

[0399] Electricity usage over the past 12 months

[0400] Your current electricity provider and plan name

[0401] Family composition (e.g., 2 adults, 2 children)

[0402] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0403] Furthermore, the smart glasses' camera and microphone are used to analyze the user's facial expressions and voice, and the emotion engine recognizes the user's current emotional state.

[0404] Terminal handling

[0405] The device verifies the entered power usage information and condition parameters. At the same time, it sends this data, including the emotion data acquired by the emotion engine, to the server. At this time, an API call is made and the data is securely transmitted.

[0406] Server Processing

[0407] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity supplier and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[0408] Using machine learning algorithms (k-nearest neighbors, decision trees, random forests, etc.), the server analyzes the user's electricity usage information, condition parameters, and emotional data. The optimal electricity provider and plan are predicted based on the user's consumption patterns and emotional state.

[0409] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The results of this analysis are then generated as a customized proposal, which is provided to the user in a format that takes into account emotional data.

[0410] Presentation of proposed results

[0411] The server then sends the generated proposal to the device. The proposal includes a price estimate, reasons for the recommendation (e.g., cost savings, plan suitable for usage patterns, etc.), and customized comments and advice based on the user's emotional state. For example, a user experiencing high stress may be recommended an energy-saving plan that helps them relax.

[0412] User Choice and Feedback

[0413] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data for future AI model accuracy improvements and emotion engine training.

[0414] Specific examples

[0415] When a customer visits a physical store, a sales associate wearing smart glasses can analyze the customer's facial expressions and voice to recognize their "confused" emotional state in real time. Based on this, the sales associate can provide a friendly explanation and recommend the optimal energy plan. This improves the user experience and enables suggestions tailored to individual needs.

[0416] Prompt Sentence Examples

[0417] Use the following prompts to generate code for an application that improves customer support in brick-and-mortar stores.

[0418] Prompt statement:

[0419] Generate an application program that uses smart glasses to analyze a customer's emotional state and suggest appropriate products and services. Specific technologies used include TENSORFLOW (registered trademark), Flask, and OpenCV. Analyze emotions from the customer's facial expressions, receive the results on the server, and provide customized suggestions in real time.

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

[0421] Program processing steps

[0422] Step 1:

[0423] Users access the system using smart glasses or a smartphone and input condition parameters such as past power usage information, household composition, and lifestyle patterns.Facial expression and voice data are also acquired through the smart glasses' camera and microphone.This allows the system to collect "power usage information," "condition parameters," "facial expression data," and "voice data" as input from the user.

[0424] Step 2:

[0425] The device transmits the information input by the user and the acquired emotion data to the server. The transmitted data includes power usage information, condition parameters, facial expression data, and voice data. This data is securely transferred to the server using an API.

[0426] Step 3:

[0427] The server stores the received data in a database for analysis. The database contains detailed information about the electricity supplier and each plan (such as rate structure, benefit information, and contract terms). The input is "user data (electricity usage information, condition parameters, facial expression data, and voice data)," and the output is "a dataset for analysis."

[0428] Step 4:

[0429] The server processes the analysis dataset using a machine learning algorithm. This analyzes the user's electricity consumption patterns and emotional state, and based on this, predicts the optimal electricity supplier and plan. Algorithms used include k-nearest neighbors, decision trees, and random forests. The input is the "analysis dataset," and the output is the "prediction of the optimal plan."

[0430] Step 5:

[0431] The server simulates multiple scenarios based on the predicted optimal plan and compares the cost performance of each plan. This generates a customized proposal that also takes emotional data into account. The input is the "predicted optimal plan" and the output is the "customized proposal."

[0432] Step 6:

[0433] The server sends the generated recommendation results to the device. The recommendation results include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state. The input is the "customized recommendation results," and the output is the "data sent to the device."

[0434] Step 7:

[0435] The terminal displays the proposal results received from the server to the user. The user can select the plan that they think is best from the proposed plans. The user's selection results are sent from the terminal to the server, which then stores them in a database. The inputs are the "proposal results" and the "user's selection results," and the output is the "database storage of the selection results."

[0436] Step 8:

[0437] The server uses the received selection results as feedback data for improving analysis accuracy and for learning the emotion engine. The input is the "selection result" and the output is "updated feedback data."

[0438] 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.

[0439] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0440] 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.

[0441] [Second embodiment]

[0442] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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."

[0454] The present invention is a system that helps electricity consumers select the most suitable electric power company and the service menu they offer. This system is realized through a series of processes, including data collection from users, data analysis on the server side, and presentation of the optimal plan. How the user, terminal, and server implement this system is described in detail below.

[0455] User operations

[0456] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[0457] Electricity usage over the past 12 months

[0458] Your current electricity provider and plan name

[0459] Family composition (e.g., 2 adults, 2 children)

[0460] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0461] When the user enters this information, the terminal checks the data format and required fields to verify that it has been entered correctly.

[0462] Terminal handling

[0463] The device then compiles the verified information and sends it to the server, typically via an API call to ensure security and data integrity.

[0464] Server Processing

[0465] The server receives the user data sent from the device and stores it in a database. The server then retrieves detailed information about the electricity company and its plans from the database, including each plan's rate structure (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0466] The server uses machine learning algorithms to analyze the user's past electricity usage information and condition parameters. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption pattern.

[0467] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then generated as a proposal.

[0468] Presentation of proposed results

[0469] The server then sends the generated proposal results to the device, which include a price estimate for each plan and the reasons for the recommendation (e.g., cost savings, which plan is best suited to your usage pattern, etc.).

[0470] The device displays the information received from the server to the user. The user can then check the details of the proposed power company and plan on the device screen. For example, the user can view the specific plan details, fee simulation, and advantages and disadvantages of "Power Company A's Home Plan B" and "Power Company B's Eco Plan C."

[0471] User Choice and Feedback

[0472] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data to improve the accuracy of the AI ​​model in the future.

[0473] As described above, the present invention is a system that efficiently provides the most suitable electric power company and service menu to an electric power consumer through cooperation between a user, a terminal, and a server.

[0474] The processing flow will be explained below.

[0475] Step 1:

[0476] The user enters information

[0477] Users access a device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.).

[0478] Step 2:

[0479] The terminal validates the input data

[0480] The terminal checks the format and mandatory fields of the data entered by the user, and performs input validation to ensure the data is entered correctly.

[0481] Step 3:

[0482] The device sends the data to the server

[0483] Once the verification is complete, the device sends the information to the server, which then makes an API call to securely send the data to the server.

[0484] Step 4:

[0485] The server receives the data

[0486] The server receives the user data sent from the terminal, and the received data is first stored in a database.

[0487] Step 5:

[0488] The server retrieves the relevant information from the database

[0489] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0490] Step 6:

[0491] The server performs the analysis using the AI ​​model

[0492] The server analyzes the aforementioned user data and the acquired plan information using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern.

[0493] Step 7:

[0494] The server generates the analysis results

[0495] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan, thereby generating a list of the most suitable power companies and plans for the user.

[0496] Step 8:

[0497] The server sends the proposal results to the device.

[0498] The server then sends the generated recommendation results to the terminal, which include a price estimate and the reason for the recommendation.

[0499] Step 9:

[0500] The terminal receives and displays the results

[0501] The terminal visually displays the proposal results received from the server to the user, who can then check the detailed information of each plan.

[0502] Step 10:

[0503] The user selects a plan

[0504] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[0505] Step 11:

[0506] The device sends the selection information to the server

[0507] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[0508] Step 12:

[0509] The server records the selection information

[0510] The server stores the received selection results in a database, which is used as feedback data to train the AI ​​model to improve the accuracy of future analysis.

[0511] Example 1

[0512] 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."

[0513] For electricity consumers to select the optimal plan from the wide variety of electricity supplier plans, it takes a huge amount of time and effort to collect detailed information about each plan and perform comparative analysis. Advanced analysis is also required to predict the optimal plan based on electricity usage patterns, but average consumers lack the skills and tools to perform such analysis. Therefore, it is necessary to provide a system that allows consumers to easily select the electricity supplier and rate plan that is best for them.

[0514] 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.

[0515] In this invention, the server includes means for receiving past electricity usage information and condition parameters from a user, means for referencing a database of multiple electricity suppliers and their rate plans, and means for analyzing the information and database using a machine learning algorithm to identify an electricity supplier and rate plan that are optimal for the user, thereby enabling consumers to select an electricity supplier and rate plan that are optimal for them without complex information gathering and analysis.

[0516] "User" refers to an individual or legal entity that is an electricity consumer or uses the system.

[0517] "Electricity usage information" refers to data related to a user's electricity usage, such as electricity consumption over the past 12 months.

[0518] "Condition parameters" refer to factors that affect power usage, such as the user's household configuration and lifestyle patterns.

[0519] "Electricity supplier" means a company or organization that supplies electricity to consumers.

[0520] "Price plan" refers to the content of the electricity supply contract and fee structure provided by the electricity supplier.

[0521] A "database" refers to a collection of systematically stored information such as electricity supplier plan information and user information.

[0522] A "machine learning algorithm" refers to a program or method that learns from large amounts of data and makes predictions and classifications.

[0523] "Analysis" refers to the process of working with data, extracting information, and drawing conclusions.

[0524] "Simulation" refers to a technology that reproduces actual electricity usage conditions on a computer and makes predictions by testing different scenarios.

[0525] "Optimal plan" refers to the electricity supplier's rate plan that best suits the user's electricity usage pattern and conditions.

[0526] "Proposal result" refers to information about a plan recommended to a user, generated by the server through analysis and simulation.

[0527] "Feedback" refers to the process of reusing data to improve future analysis accuracy based on user-selected plan information.

[0528] "Security" refers to the measures and procedures used to protect the confidentiality, integrity, and availability of information.

[0529] The present invention is a system that helps electricity consumers select the most suitable electricity supplier and the rate plan they offer. This system is realized by collecting data from users, verifying the data on their terminals, analyzing the data on the server side, and presenting the most suitable plan.

[0530] First, the user accesses the system using a device (such as a smartphone or PC). The system's initial screen displays a form for entering information about electricity usage over the past 12 months, the current electricity supplier and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, which electrical appliances are frequently used, etc.). After completing the information, the user clicks the "Submit" button.

[0531] The device checks the format and required fields of the data entered by the user to verify that it has been entered correctly. Once verified, the data is sent to the server using an API while maintaining security. The data is encrypted before being sent, ensuring the confidentiality of the information.

[0532] The server receives the user data sent from the device and stores it in a database. The server then retrieves information about the electricity supplier and its rate plans from the database. This information includes the rate structure of each plan (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0533] The server uses machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests) to analyze the user's electricity usage information and condition parameters. This predicts the electricity supplier and rate plan that best suits the user's consumption pattern. The server then runs multiple simulations to evaluate the cost performance of each plan. The analysis results are then used to generate a proposal.

[0534] The server sends the proposal results to the device, which then displays them to the user. The proposal includes a price estimate, the reason for the recommendation, and detailed information about each plan (e.g., "Electricity Company A's Home Plan B," "Electricity Company B's Eco Plan C," etc.). The user can review this information on the screen and select the plan they deem most suitable.

[0535] Once the user selects a plan, the device sends the selection back to the server. The server stores the received selection in a database and uses it as feedback data to improve the accuracy of future analysis. This allows the system to self-learn and provide more accurate suggestions to the next user.

[0536] For example, if a user inputs their electricity usage data from the past 12 months and their current contract plan, and the system analyzes it and displays that "Electricity Company A's Home Plan B" is the best option, the user can check the details of that plan and select it. This result is saved in the system as feedback data.

[0537] An example of a prompt sentence is "Analyze the user's electricity usage data from the past 12 months and their current contracted plan, and suggest the most suitable electricity supplier and plan."

[0538] As described above, this system efficiently provides the most suitable power supplier and rate plan to power consumers through collaboration between users, terminals, and servers.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] Users access the system using devices such as smartphones or PCs. On the initial screen, users enter their electricity usage information for the past 12 months, their current electricity supplier and plan name, household composition, and lifestyle patterns.

[0542] Input: User's electricity usage information for the past 12 months, current contract information, household composition, and lifestyle patterns

[0543] Output: The input data

[0544] Specific behavior: The user enters information into each field and clicks the "Submit" button.

[0545] Step 2:

[0546] The terminal checks the format and required fields of the entered data to verify that the data has been entered correctly.

[0547] Input: Data entered by the user

[0548] Output: Validated data

[0549] Specific operation: The terminal checks the validity of input data using regular expressions and validation rules within the program.

[0550] Step 3:

[0551] The device then uses the API to send the verified data to the server, where it is encrypted before being sent.

[0552] Input: Validated data

[0553] Output: Data sent to the server

[0554] What it does: Securely transmits data using HTTP requests.

[0555] Step 4:

[0556] The server receives the data sent from the device and stores it in a database, using the user ID as a key.

[0557] Input: Request for validated data

[0558] Output: User data stored in the database

[0559] Specific operation: Data is saved to the database using the SQL INSERT command.

[0560] Step 5:

[0561] The server retrieves the electricity supplier's rate plans from a database, including rate structures, special offers, and contract terms.

[0562] Input: Database query

[0563] Output: Electricity supplier rate plan information

[0564] What it does: Uses an SQL query to retrieve the required pricing plan information.

[0565] Step 6:

[0566] The server uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests) to perform analysis based on the user's power usage information and condition parameters.

[0567] Input: User data and electricity supplier rate plan information

[0568] Output: Prediction of optimal electricity supplier and tariff plan

[0569] What it does: It uses machine learning algorithms to analyze data and predict the optimal plan.

[0570] Step 7:

[0571] The server runs multiple simulations, evaluates the cost performance of each plan, and generates a proposal result.

[0572] Input: Optimal pricing plan prediction results

[0573] Output: Proposal results

[0574] Specific actions: Use a simulation program to perform detailed cost comparisons.

[0575] Step 8:

[0576] The server then sends the generated proposal results to the device, using an API to ensure data integrity and confidentiality.

[0577] Input: Suggestion results

[0578] Output: Data sent to the terminal

[0579] Specific behavior: Sends data in the form of an HTTP response.

[0580] Step 9:

[0581] The terminal displays the received proposal results to the user, who then checks the details of the proposed plan (such as the price estimate and the reason for the recommendation).

[0582] Input: Proposal results received from the server

[0583] Output: Information displayed to the user

[0584] Specific behavior: Display data on the screen using HTML and JavaScript.

[0585] Step 10:

[0586] The user selects the most suitable plan from the proposed plans and clicks the selection button.

[0587] Input: User's choice

[0588] Output: Selected plan information

[0589] Specific behavior: The user clicks the "Select" button on the screen.

[0590] Step 11:

[0591] The device sends the user's selection to the server, which also sends the data via an API.

[0592] Input: User selection

[0593] Output: Data sent to the server

[0594] What it does: Sends the selection data using an HTTP request.

[0595] Step 12:

[0596] The server stores the received selections in a database and uses them as feedback data to improve the accuracy of future analyses.

[0597] Input: User selection

[0598] Output: Feedback data stored in a database

[0599] Specific operation: Executes an INSERT or UPDATE command to the database.

[0600] (Application example 1)

[0601] 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."

[0602] In modern industrial manufacturing facilities, efficient energy management contributes significantly to reducing production costs and environmental impact. However, the energy consumption patterns of factory robots and equipment are complex, and advanced analysis is required to select the optimal energy plan. Conventional methods lack a system that efficiently solves these issues, resulting in wasted energy costs. The present invention aims to solve these energy management problems and improve factory operational efficiency.

[0603] 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.

[0604] In this invention, the server includes: means for receiving past energy usage information and condition parameters from a user; means for referencing a database of multiple energy suppliers and their service menus; means for analyzing the information and database using a machine learning algorithm to identify the energy supplier and service menu that are optimal for the user; means for presenting the identified energy supplier and service menu to the user; means for recording information selected by the user and using it to improve the accuracy of future analyses; means for a factory robot to collect energy consumption data in real time and transmit it to a cloud server; means for the cloud server to analyze the energy consumption data and recommend the optimal energy supplier and service menu; and means for displaying the recommendation results to a factory manager, thereby enabling efficient and optimized energy management throughout the factory.

[0605] "User" refers to a factory manager or factory operator who provides energy consumption information and condition parameters and receives a proposal for an optimal energy plan.

[0606] "Energy usage information" refers to information about energy usage within a factory, such as past energy consumption data and current consumption status.

[0607] "Condition parameters" are factors that affect energy consumption, including information on work style and equipment used.

[0608] "Energy supplier" refers to a company or organization that supplies energy such as electricity or gas.

[0609] "Service menu" refers to the various plans and contract terms offered by energy suppliers.

[0610] "Database" refers to a collection of information that stores an energy supplier's service menu, rate structure, contract terms, etc.

[0611] A "machine learning algorithm" refers to a mathematical technique that analyzes patterns based on past data to make predictions and optimal choices.

[0612] A "cloud server" is a remote server that can be accessed via the Internet and is a computer system used to store and analyze data.

[0613] "Energy consumption data" refers to data on energy usage generated in real time by factory robots and equipment.

[0614] "Recommendation" refers to the act of presenting the optimal energy supplier and service menu based on the analysis results.

[0615] A "factory robot" is a device used to perform automated tasks within a factory, and has the ability to monitor energy consumption in real time and collect data.

[0616] "Factory manager" refers to the person in charge of factory operations and energy management.

[0617] This invention is a system that uses factory robots to collect energy consumption data in real time, analyzes it on a cloud server, and recommends the optimal energy supplier and service menu. This system is realized through collaboration between users, terminals, and the cloud server.

[0618] First, factory robots collect energy consumption data in real time. This data includes past and current energy usage information, factory operation patterns, and information on equipment in use. The robots periodically send this data to a cloud server. Data transmission is generally done using an API to ensure security and data integrity.

[0619] The cloud server stores the received data in a database. It then references a database of multiple energy suppliers and their service menus to match the energy consumption data. This matching process uses machine learning algorithms. Specifically, analysis is performed using algorithms such as k-nearest neighbors, decision trees, and random forests. This identifies the energy supplier and service menu that best suits the energy consumption pattern.

[0620] The analysis results are generated as recommendations after a simulation is run to compare the cost performance of each plan. The cloud server then sends the generated recommendations to the factory robots and management terminal. The management terminal (PC, smartphone, etc.) then presents this information to the factory manager. On the screen, the factory manager can view detailed information about each energy supplier and service menu, a rate simulation, and the reasons for the recommendation.

[0621] As a concrete example, a certain factory consumes 1,500 kWh of energy per month. Robots in this factory collect data in real time and send it to a cloud server. The server analyzes past energy usage information and current consumption status, and recommends an optimal energy plan. The recommended results are sent to a management terminal, allowing factory managers to implement efficient energy management.

[0622] An example of a prompt is, "Please enter your current energy consumption data (consumption over the past 12 months, current consumption, work style, and information on the devices you use). We will recommend the optimal energy supplier and plan." By entering your energy consumption data according to this prompt, the optimal energy plan will be recommended.

[0623] This system will improve the efficiency of energy management throughout the factory and make it possible to select the most suitable energy supplier and service menu.

[0624] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0625] Step 1:

[0626] Factory robots collect energy consumption data in real time. The collected data includes past energy usage information, current consumption status, operation patterns within the factory, and information on equipment being used. This data is temporarily stored in local memory. The input is sensor data from the factory robots, and the output is formatted energy consumption data.

[0627] Step 2:

[0628] The energy consumption data collected by the factory robot is sent to a cloud server using an API call, with the SSL / TLS protocol used to ensure security and data integrity. The input is the formatted energy consumption data, and the output is a message that the data was successfully uploaded to the cloud server.

[0629] Step 3:

[0630] The server stores the received energy consumption data in a database. The database contains information on past energy usage, factory operation patterns, and information on equipment used. The input is the energy consumption data received by the cloud server, and the output is a message that the data was successfully saved in the database.

[0631] Step 4:

[0632] The server accesses a database of multiple energy suppliers and their service menus, thereby collecting information on all available energy plans. The input is energy consumption data, and the output is information on the service menu.

[0633] Step 5:

[0634] The server analyzes the energy consumption data and service menu using machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests), thereby identifying the optimal energy supplier and service menu for the user. The input is the user's energy consumption data and service menu information, and the output is the recommendation of the optimal energy plan.

[0635] Step 6:

[0636] The server generates a recommendation and sends it to the factory management terminal. This includes the recommended energy plan, its reasons, and a price simulation. The input is the recommendation, and the output is a message to the factory management terminal indicating that the information was successfully sent.

[0637] Step 7:

[0638] The factory management terminal receives the recommendation results from the server and presents them to the user. On the screen, the user can view detailed information about each energy supplier and service menu, a price simulation, and the reasons for the recommendation. The input is the recommendation results received from the server, and the output is a confirmation message from the user.

[0639] 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.

[0640] The present invention is a system that can incorporate the user's emotional state into its analysis in addition to various condition parameters such as the user's past electricity usage information, household configuration, and lifestyle patterns. This system is implemented through a series of processes: collecting data from the user, analyzing the data on the server side, presenting an optimal plan, and analyzing and reflecting emotions using an emotion engine. Below, we will explain in detail how the user, terminal, server, and emotion engine implement this system.

[0641] User operations

[0642] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[0643] Electricity usage over the past 12 months

[0644] Your current electricity provider and plan name

[0645] Family composition (e.g., 2 adults, 2 children)

[0646] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0647] Furthermore, the emotion engine recognizes the user's current emotional state by analyzing the user's facial expressions and voice using the device's camera and microphone. For example, facial recognition technology can detect smiling or angry expressions, and voice analysis technology can analyze the tone and speed of speech.

[0648] Terminal handling

[0649] The device verifies the past power usage information and condition parameters entered by the user. At the same time, this data, including the emotion data acquired by the emotion engine, is sent to the server. At this time, an API call is made to ensure the data is sent securely.

[0650] Server Processing

[0651] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity company and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[0652] The server uses machine learning algorithms to analyze the user's past electricity usage information, condition parameters, and emotional data. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption patterns and emotional state.

[0653] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then used to generate a proposal, which is then provided to the user as a customized proposal that takes into account emotional data.

[0654] Presentation of proposed results

[0655] The server then sends the generated recommendation results to the device, which include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on the user's emotional state.

[0656] The device displays the information received from the server to the user. The user can check detailed information about each plan along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[0657] User Choice and Feedback

[0658] The user selects the plan they think is best from the proposed plans. The device then sends the user's selection results to the server, which stores the received selection results in a database and uses them as feedback data for future AI model accuracy improvements and emotion engine training.

[0659] As described above, this invention is a system that efficiently provides electricity consumers with the most suitable electric power company and service menu through collaboration between users, terminals, servers, and an emotion engine. Utilizing the emotion engine makes it possible to provide proposals that are even more customized to meet the user's needs.

[0660] The processing flow will be explained below.

[0661] Step 1:

[0662] The user enters information

[0663] Users access their device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.). Users also use the device's camera and microphone to provide facial expressions and voice recordings to the system.

[0664] Step 2:

[0665] The terminal validates the input data

[0666] The device checks the format and required fields of the data entered by the user. It also validates the input values ​​to ensure that the data is entered correctly. At the same time, the emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state.

[0667] Step 3:

[0668] The device sends the data to the server

[0669] Once verified, the information and emotion data are sent from the device to the server, where the device makes an API call to securely transmit the data to the server.

[0670] Step 4:

[0671] The server receives the data

[0672] The server receives the user data and emotion data sent from the terminal, and the received data is first stored in a database.

[0673] Step 5:

[0674] The server retrieves the relevant information from the database

[0675] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0676] Step 6:

[0677] The server performs the analysis using the AI ​​model

[0678] The server analyzes the aforementioned user data, the acquired plan information, and emotional data using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern and emotional state.

[0679] Step 7:

[0680] The server generates the analysis results

[0681] The server simulates multiple scenarios based on the analysis results, compares the cost performance of each plan, and generates a list of the most suitable power companies and plans for the user as a customized proposal that also reflects emotional data.

[0682] Step 8:

[0683] The server sends the proposal results to the device.

[0684] The server then sends the generated recommendation results to the device, which include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state.

[0685] Step 9:

[0686] The terminal receives and displays the results

[0687] The device visually displays the results of the proposals received from the server to the user. The user can view detailed information about each plan, along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[0688] Step 10:

[0689] The user selects a plan

[0690] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[0691] Step 11:

[0692] The device sends the selection information to the server

[0693] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[0694] Step 12:

[0695] The server records the selection information

[0696] The server stores the received selections in a database, which is used as feedback data to improve future analysis and train the emotion engine.

[0697] Example 2

[0698] 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."

[0699] Conventional systems for recommending power companies and service menus only consider the user's past electricity usage information and condition parameters, and have the problem of being unable to provide customized proposals that reflect the user's emotional state. This makes it difficult to provide optimal service plans that match the user's emotions and lifestyle.

[0700] 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 receiving past power usage information and condition parameters from the user, means for analyzing the user's facial expressions and voice to recognize the user's emotional state, means for referencing a database of multiple power companies and their service menus based on the received information and emotional state data, means for analyzing the information, emotional data, and database using a machine learning algorithm to identify the power company and service menu that are optimal for the user, means for presenting the identified power company and service menu to the user, means for generating and presenting comments and advice based on the user's emotional state, and means for recording information selected by the user and using it to improve future analysis accuracy. This makes it possible to suggest the optimal power company and service menu that takes the user's emotional state into consideration.

[0701] "User" refers to an individual or household who uses the system to receive an electricity plan proposal.

[0702] "Past electricity usage information" refers to data regarding the amount of electricity a user has consumed in the past, including detailed usage history over a specific period of time (e.g., the past 12 months).

[0703] "Condition parameters" refer to information related to the user's household structure and lifestyle patterns, and include, for example, the number of family members, the amount of time spent at home, and frequently used electrical appliances.

[0704] "Means for recognizing an emotional state by analyzing facial expressions and voice" refers to technology that captures a user's facial expressions with a camera, records their voice with a microphone, and analyzes them to recognize the user's current emotional state.

[0705] "Means for referencing a database" refers to a technology for accessing a database that stores information about multiple electric power companies and their service menus, and obtaining the necessary data.

[0706] "Machine learning algorithms" refer to algorithms that use statistical methods and computational models to learn patterns from data and make predictions or classifications for future data. Examples include k-nearest neighbors, decision trees, and random forests.

[0707] "Means for identifying" refers to technology that uses machine learning algorithms to select the electricity company and service menu that best suits the user's conditions and emotional state.

[0708] The "means for presenting" refers to a technique for displaying the identified power company and service menu to the user, and includes, for example, a function for displaying information on the screen of a terminal.

[0709] "Means for generating and presenting comments and advice" refers to a technology for generating customized comments and advice based on the recognized emotional state of the user and displaying them to the user.

[0710] "Means for recording and using to improve the accuracy of future analysis" refers to technology that stores the plan selected by the user and its results in a database, and uses this data to improve the accuracy of the machine learning model and the performance of the entire system.

[0711] This invention is a system that proposes the most suitable power company and service menu by analyzing the user's emotional state in addition to their past electricity usage information, household configuration, and lifestyle patterns. This system is realized through the cooperation of the user, terminal, server, and emotion engine.

[0712] User operations

[0713] Users access the system using a smartphone or PC at home. The initial screen displays a form for users to enter their electricity usage over the past 12 months, the name of their current electricity provider and plan, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, and frequently used electrical appliances).

[0714] Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes their current emotional state. Specifically, facial recognition and voice analysis technologies are used to detect smiling and angry expressions, as well as voice tone and speed.

[0715] Terminal handling

[0716] The device verifies the user-entered historical power usage information and condition parameters, and transmits them along with the emotion data acquired by the emotion engine to the server, using an API call and encryption technology such as HTTPS to ensure secure transmission of the data.

[0717] Server Processing

[0718] The server receives the user data and emotion data sent from the device and stores them in a database. After storing them, it retrieves detailed information about the electricity company and its plan (e.g., basic charge, metered charge, time-of-use charge, special offer information, contract terms, etc.) from the database.

[0719] The server then uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests, etc.) to analyze the user's past electricity usage information, condition parameters, and emotional data, and predicts the optimal electricity provider and plan for the user's consumption pattern and emotional state.

[0720] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan. Based on the analysis and simulation results, the server generates proposals and adds customized comments and advice that take into account emotional data.

[0721] Presentation of proposed results

[0722] The server then sends the generated proposal results to the device. The proposal results include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on emotional data. For example, a user who is feeling stressed may be recommended an energy-saving plan that helps them relax.

[0723] User Choice and Feedback

[0724] The user selects the plan they think is best from the presented options. The device sends the selection results to the server, which stores them in a database. This feedback data is used to improve the accuracy of analysis and train the emotion engine in the future.

[0725] Examples of specific examples and prompts

[0726] Specific examples

[0727] User A accesses the system and enters the following information:

[0728] Electricity usage for the past 12 months: 600kWh / month

[0729] Current plan: X Electric Company Y Plan (pay-as-you-go)

[0730] Family composition: 2 adults, 1 child

[0731] Lifestyle: Both spouses work, at home after 6pm on weekdays, main appliances are an air conditioner and a refrigerator

[0732] Facial expression and voice analysis results: fatigue, slow voice

[0733] Based on this information, the system suggests a plan from Power Company Z, which has low off-peak rates, as the optimal plan, and provides customized advice such as, "Since you use a lot of electricity at night, a plan with low off-peak rates would be best. Also, make sure to use eco mode when you're tired."

[0734] Prompt Sentence Examples

[0735] "Please enter the user's electricity usage over the past 12 months, their current electricity contract plan, household composition and lifestyle patterns. The system will also estimate their emotional state from facial expressions and voice recordings made by the device's camera and microphone, and suggest the optimal electricity plan."

[0736] As described above, the system of the present invention can efficiently provide an optimal power plan based on the user's power usage pattern and emotional state.

[0737] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0738] Step 1:

[0739] User Data Entry

[0740] Users access the system using a smartphone or PC. They input their electricity usage over the past 12 months, their current electricity provider and plan name, household composition, and lifestyle patterns. The input data is temporarily stored in the device's local storage.

[0741] Input: electricity usage for the past 12 months, current electricity company and plan name, household composition, lifestyle patterns

[0742] Output: User data stored in the device's local storage

[0743] Step 2:

[0744] Acquiring emotion data

[0745] The device's camera and microphone are used to collect the user's facial expressions and voice data. The collected data is analyzed in real time by an emotion engine within the device. Facial recognition and voice analysis technologies are used to identify emotional states such as smile, anger, voice tone, and speed.

[0746] Input: Facial expression and voice data via camera and microphone

[0747] Output: Parsed emotional state data

[0748] Step 3:

[0749] Validating and submitting data

[0750] The device verifies the power usage information and condition parameters entered by the user. It checks the format and range to ensure the data is in the correct format. At the same time, it also verifies the emotion data and sends it to the server via an API. The data is transmitted securely using encryption technologies such as HTTPS.

[0751] Input: User data, emotional state data

[0752] Output: Validated data sent to the server

[0753] Step 4:

[0754] Receiving and storing data

[0755] The server receives the user data and emotional state data sent from the device and stores them in a database. Once stored, the server checks the data to ensure its consistency and completeness.

[0756] Input: User data and emotional state data sent from the device

[0757] Output: User data and emotional state data stored in a database

[0758] Step 5:

[0759] Obtaining electricity plan information

[0760] The server retrieves information about currently available energy plans (e.g., rate structures, special offers, contract terms, etc.) from a database, which may also include retrieving data from external APIs.

[0761] Input: User data and emotional state data

[0762] Output: Obtained electricity plan information

[0763] Step 6:

[0764] Analysis using machine learning algorithms

[0765] The server inputs user data, emotional state data, and the acquired power plan information and analyzes them using machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests). As a result of the analysis, the optimal power plan for the user is identified.

[0766] Input: User data, emotional state data, power plan information

[0767] Output: Optimal power plan information

[0768] Step 7:

[0769] Scenario simulation

[0770] The server simulates multiple scenarios based on the analysis results and evaluates the cost performance of each plan, thereby determining the optimal plan.

[0771] Input: Analysis results (optimal power plan information)

[0772] Output: Simulation results and evaluation data

[0773] Step 8:

[0774] Generate and send proposal results

[0775] The server generates suggestions based on the simulation results, adds comments and advice based on the emotional state data, and sends the suggestions to the device via API.

[0776] Input: Simulation results and evaluation data

[0777] Output: Suggestion results and customized advice sent to your device

[0778] Step 9:

[0779] Displaying the proposed results

[0780] The device displays the proposal results received from the server to the user, including price estimates, detailed plan information, and comments and advice based on emotion data.

[0781] Input: Suggested results and customized advice sent from the server

[0782] Output: Suggestion results displayed in the user interface

[0783] Step 10:

[0784] User Choice and Feedback

[0785] The user selects the plan they think is best from the presented options. The selection results are sent to the server via the device and stored in a database. The feedback data will be used to improve the accuracy of analysis and train the emotion engine.

[0786] Input: User selection

[0787] Output: Feedback data stored in a database

[0788] This series of processing steps enables the system to efficiently propose an optimal power plan to the user.

[0789] (Application example 2)

[0790] 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."

[0791] The main function of conventional energy plan proposal systems was to provide optimal plans based on parameters such as the user's past energy usage information, household configuration, and lifestyle patterns. However, these systems did not take into account the user's emotional state, which limited the ability to improve the user experience and customize proposals. In particular, in physical stores, the inability to make proposals based on the customer's emotions was a major problem.

[0792] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0793] means for receiving historical power usage information and condition parameters from a user;

[0794] a means for referencing a database of a plurality of power supply companies and service plans of each power supply company based on the received information;

[0795] means for analyzing the information and database using machine learning algorithms to identify the most suitable electricity supplier and service plan for the user;

[0796] means for presenting the identified electricity supplier and service plan to a user;

[0797] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[0798] means for recognizing a user's current emotional state and customizing a recommended service plan based on the emotional state;

[0799] This makes it possible to propose an optimal power plan according to the user's emotional state.

[0800] "Past electricity usage information" refers to data on the electricity used by a user over a certain period of time (e.g., the past 12 months).

[0801] "Condition parameters" refer to information indicating factors that affect power consumption, such as a user's lifestyle patterns and household configuration.

[0802] "Electricity supplier" means a company or entity that supplies electricity to users.

[0803] "Service plan" refers to the various contract menus and rate plans offered by electricity suppliers.

[0804] "Database" refers to a system that systematically stores information about electricity suppliers and service plans.

[0805] "Machine learning algorithms" refer to computational techniques used to analyze data and recognize patterns.

[0806] "Emotional state" refers to the user's current state of mind, such as joy, sadness, anger, etc., and is recognized from facial expressions and voice.

[0807] "Camera" refers to an image capturing device for recognizing a user's facial expressions.

[0808] "Microphone" refers to a voice capture device for capturing a user's voice and analyzing their emotional state.

[0809] "Real-time" refers to processing and analysis occurring immediately, without delay.

[0810] "Receiving power usage information" refers to the system receiving data regarding power usage provided by a user.

[0811] "Plan customization" refers to the process of adapting the service plan provided based on the user's individual requirements and emotional state.

[0812] "Proposal presentation" refers to the system displaying or notifying the user of the optimal power plan based on the analysis results.

[0813] The present invention is a system for proposing an optimal power plan to a user by utilizing power usage information and emotional state. This system is composed of the following components:

[0814] User operations

[0815] Users access the system using devices such as smart glasses, smartphones, or PCs. On the initial screen, users enter the following information:

[0816] Electricity usage over the past 12 months

[0817] Your current electricity provider and plan name

[0818] Family composition (e.g., 2 adults, 2 children)

[0819] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0820] Furthermore, the smart glasses' camera and microphone are used to analyze the user's facial expressions and voice, and the emotion engine recognizes the user's current emotional state.

[0821] Terminal handling

[0822] The device verifies the entered power usage information and condition parameters. At the same time, it sends this data, including the emotion data acquired by the emotion engine, to the server. At this time, an API call is made and the data is securely transmitted.

[0823] Server Processing

[0824] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity supplier and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[0825] Using machine learning algorithms (k-nearest neighbors, decision trees, random forests, etc.), the server analyzes the user's electricity usage information, condition parameters, and emotional data. The optimal electricity provider and plan are predicted based on the user's consumption patterns and emotional state.

[0826] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The results of this analysis are then generated as a customized proposal, which is provided to the user in a format that takes into account emotional data.

[0827] Presentation of proposed results

[0828] The server then sends the generated proposal to the device. The proposal includes a price estimate, reasons for the recommendation (e.g., cost savings, plan suitable for usage patterns, etc.), and customized comments and advice based on the user's emotional state. For example, a user experiencing high stress may be recommended an energy-saving plan that helps them relax.

[0829] User Choice and Feedback

[0830] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data for future AI model accuracy improvements and emotion engine training.

[0831] Specific examples

[0832] When a customer visits a physical store, a sales associate wearing smart glasses can analyze the customer's facial expressions and voice to recognize their "confused" emotional state in real time. Based on this, the sales associate can provide a friendly explanation and recommend the optimal energy plan. This improves the user experience and enables suggestions tailored to individual needs.

[0833] Prompt Sentence Examples

[0834] Use the following prompts to generate code for an application that improves customer support in brick-and-mortar stores.

[0835] Prompt statement:

[0836] Your goal is to generate an application program that uses smart glasses to analyze a customer's emotional state and suggest appropriate products and services. Specific technologies used include TensorFlow, Flask, and OpenCV. Analyze emotions from the customer's facial expressions, receive the results on the server, and provide customized suggestions in real time.

[0837] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0838] Program processing steps

[0839] Step 1:

[0840] Users access the system using smart glasses or a smartphone and input condition parameters such as past power usage information, household composition, and lifestyle patterns.Facial expression and voice data are also acquired through the smart glasses' camera and microphone.This allows the system to collect "power usage information," "condition parameters," "facial expression data," and "voice data" as input from the user.

[0841] Step 2:

[0842] The device transmits the information input by the user and the acquired emotion data to the server. The transmitted data includes power usage information, condition parameters, facial expression data, and voice data. This data is securely transferred to the server using an API.

[0843] Step 3:

[0844] The server stores the received data in a database for analysis. The database contains detailed information about the electricity supplier and each plan (such as rate structure, benefit information, and contract terms). The input is "user data (electricity usage information, condition parameters, facial expression data, and voice data)," and the output is "a dataset for analysis."

[0845] Step 4:

[0846] The server processes the analysis dataset using a machine learning algorithm. This analyzes the user's electricity consumption patterns and emotional state, and based on this, predicts the optimal electricity supplier and plan. Algorithms used include k-nearest neighbors, decision trees, and random forests. The input is the "analysis dataset," and the output is the "prediction of the optimal plan."

[0847] Step 5:

[0848] The server simulates multiple scenarios based on the predicted optimal plan and compares the cost performance of each plan. This generates a customized proposal that also takes emotional data into account. The input is the "predicted optimal plan" and the output is the "customized proposal."

[0849] Step 6:

[0850] The server sends the generated recommendation results to the device. The recommendation results include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state. The input is the "customized recommendation results," and the output is the "data sent to the device."

[0851] Step 7:

[0852] The terminal displays the proposal results received from the server to the user. The user can select the plan that they think is best from the proposed plans. The user's selection results are sent from the terminal to the server, which then stores them in a database. The inputs are the "proposal results" and the "user's selection results," and the output is the "database storage of the selection results."

[0853] Step 8:

[0854] The server uses the received selection results as feedback data for improving analysis accuracy and for learning the emotion engine. The input is the "selection result" and the output is "updated feedback data."

[0855] 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.

[0856] 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.

[0857] 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.

[0858] [Third embodiment]

[0859] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0860] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0861] 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).

[0862] 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.

[0863] 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.

[0864] 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).

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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."

[0871] The present invention is a system that helps electricity consumers select the most suitable electric power company and the service menu they offer. This system is realized through a series of processes, including data collection from users, data analysis on the server side, and presentation of the optimal plan. How the user, terminal, and server implement this system is described in detail below.

[0872] User operations

[0873] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[0874] Electricity usage over the past 12 months

[0875] Your current electricity provider and plan name

[0876] Family composition (e.g., 2 adults, 2 children)

[0877] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[0878] When the user enters this information, the terminal checks the data format and required fields to verify that it has been entered correctly.

[0879] Terminal handling

[0880] The device then compiles the verified information and sends it to the server, typically via an API call to ensure security and data integrity.

[0881] Server Processing

[0882] The server receives the user data sent from the device and stores it in a database. The server then retrieves detailed information about the electricity company and its plans from the database, including each plan's rate structure (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0883] The server uses machine learning algorithms to analyze the user's past electricity usage information and condition parameters. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption pattern.

[0884] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then generated as a proposal.

[0885] Presentation of proposed results

[0886] The server then sends the generated proposal results to the device, which include a price estimate for each plan and the reasons for the recommendation (e.g., cost savings, which plan is best suited to your usage pattern, etc.).

[0887] The device displays the information received from the server to the user. The user can then check the details of the proposed power company and plan on the device screen. For example, the user can view the specific plan details, fee simulation, and advantages and disadvantages of "Power Company A's Home Plan B" and "Power Company B's Eco Plan C."

[0888] User Choice and Feedback

[0889] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data to improve the accuracy of the AI ​​model in the future.

[0890] As described above, the present invention is a system that efficiently provides the most suitable electric power company and service menu to an electric power consumer through cooperation between a user, a terminal, and a server.

[0891] The processing flow will be explained below.

[0892] Step 1:

[0893] The user enters information

[0894] Users access a device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.).

[0895] Step 2:

[0896] The terminal validates the input data

[0897] The terminal checks the format and mandatory fields of the data entered by the user, and performs input validation to ensure the data is entered correctly.

[0898] Step 3:

[0899] The device sends the data to the server

[0900] Once the verification is complete, the device sends the information to the server, which then makes an API call to securely send the data to the server.

[0901] Step 4:

[0902] The server receives the data

[0903] The server receives the user data sent from the terminal, and the received data is first stored in a database.

[0904] Step 5:

[0905] The server retrieves the relevant information from the database

[0906] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0907] Step 6:

[0908] The server performs the analysis using the AI ​​model

[0909] The server analyzes the aforementioned user data and the acquired plan information using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern.

[0910] Step 7:

[0911] The server generates the analysis results

[0912] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan, thereby generating a list of the most suitable power companies and plans for the user.

[0913] Step 8:

[0914] The server sends the proposal results to the device.

[0915] The server then sends the generated recommendation results to the terminal, which include a price estimate and the reason for the recommendation.

[0916] Step 9:

[0917] The terminal receives and displays the results

[0918] The terminal visually displays the proposal results received from the server to the user, who can then check the detailed information of each plan.

[0919] Step 10:

[0920] The user selects a plan

[0921] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[0922] Step 11:

[0923] The device sends the selection information to the server

[0924] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[0925] Step 12:

[0926] The server records the selection information

[0927] The server stores the received selection results in a database, which is used as feedback data to train the AI ​​model to improve the accuracy of future analysis.

[0928] Example 1

[0929] 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."

[0930] For electricity consumers to select the optimal plan from the wide variety of electricity supplier plans, it takes a huge amount of time and effort to collect detailed information about each plan and perform comparative analysis. Advanced analysis is also required to predict the optimal plan based on electricity usage patterns, but average consumers lack the skills and tools to perform such analysis. Therefore, it is necessary to provide a system that allows consumers to easily select the electricity supplier and rate plan that is best for them.

[0931] 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.

[0932] In this invention, the server includes means for receiving past electricity usage information and condition parameters from a user, means for referencing a database of multiple electricity suppliers and their rate plans, and means for analyzing the information and database using a machine learning algorithm to identify an electricity supplier and rate plan that are optimal for the user, thereby enabling consumers to select an electricity supplier and rate plan that are optimal for them without complex information gathering and analysis.

[0933] "User" refers to an individual or legal entity that is an electricity consumer or uses the system.

[0934] "Electricity usage information" refers to data related to a user's electricity usage, such as electricity consumption over the past 12 months.

[0935] "Condition parameters" refer to factors that affect power usage, such as the user's household configuration and lifestyle patterns.

[0936] "Electricity supplier" means a company or organization that supplies electricity to consumers.

[0937] "Price plan" refers to the content of the electricity supply contract and fee structure provided by the electricity supplier.

[0938] A "database" refers to a collection of systematically stored information such as electricity supplier plan information and user information.

[0939] A "machine learning algorithm" refers to a program or method that learns from large amounts of data and makes predictions and classifications.

[0940] "Analysis" refers to the process of working with data, extracting information, and drawing conclusions.

[0941] "Simulation" refers to a technology that reproduces actual electricity usage conditions on a computer and makes predictions by testing different scenarios.

[0942] "Optimal plan" refers to the electricity supplier's rate plan that best suits the user's electricity usage pattern and conditions.

[0943] "Proposal result" refers to information about a plan recommended to a user, generated by the server through analysis and simulation.

[0944] "Feedback" refers to the process of reusing data to improve future analysis accuracy based on user-selected plan information.

[0945] "Security" refers to the measures and procedures used to protect the confidentiality, integrity, and availability of information.

[0946] The present invention is a system that helps electricity consumers select the most suitable electricity supplier and the rate plan they offer. This system is realized by collecting data from users, verifying the data on their terminals, analyzing the data on the server side, and presenting the most suitable plan.

[0947] First, the user accesses the system using a device (such as a smartphone or PC). The system's initial screen displays a form for entering information about electricity usage over the past 12 months, the current electricity supplier and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, which electrical appliances are frequently used, etc.). After completing the information, the user clicks the "Submit" button.

[0948] The device checks the format and required fields of the data entered by the user to verify that it has been entered correctly. Once verified, the data is sent to the server using an API while maintaining security. The data is encrypted before being sent, ensuring the confidentiality of the information.

[0949] The server receives the user data sent from the device and stores it in a database. The server then retrieves information about the electricity supplier and its rate plans from the database. This information includes the rate structure of each plan (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[0950] The server uses machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests) to analyze the user's electricity usage information and condition parameters. This predicts the electricity supplier and rate plan that best suits the user's consumption pattern. The server then runs multiple simulations to evaluate the cost performance of each plan. The analysis results are then used to generate a proposal.

[0951] The server sends the proposal results to the device, which then displays them to the user. The proposal includes a price estimate, the reason for the recommendation, and detailed information about each plan (e.g., "Electricity Company A's Home Plan B," "Electricity Company B's Eco Plan C," etc.). The user can review this information on the screen and select the plan they deem most suitable.

[0952] Once the user selects a plan, the device sends the selection back to the server. The server stores the received selection in a database and uses it as feedback data to improve the accuracy of future analysis. This allows the system to self-learn and provide more accurate suggestions to the next user.

[0953] For example, if a user inputs their electricity usage data from the past 12 months and their current contract plan, and the system analyzes it and displays that "Electricity Company A's Home Plan B" is the best option, the user can check the details of that plan and select it. This result is saved in the system as feedback data.

[0954] An example of a prompt sentence is "Analyze the user's electricity usage data from the past 12 months and their current contracted plan, and suggest the most suitable electricity supplier and plan."

[0955] As described above, this system efficiently provides the most suitable power supplier and rate plan to power consumers through collaboration between users, terminals, and servers.

[0956] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0957] Step 1:

[0958] Users access the system using devices such as smartphones or PCs. On the initial screen, users enter their electricity usage information for the past 12 months, their current electricity supplier and plan name, household composition, and lifestyle patterns.

[0959] Input: User's electricity usage information for the past 12 months, current contract information, household composition, and lifestyle patterns

[0960] Output: The input data

[0961] Specific behavior: The user enters information into each field and clicks the "Submit" button.

[0962] Step 2:

[0963] The terminal checks the format and required fields of the entered data to verify that the data has been entered correctly.

[0964] Input: Data entered by the user

[0965] Output: Validated data

[0966] Specific operation: The terminal checks the validity of input data using regular expressions and validation rules within the program.

[0967] Step 3:

[0968] The device then uses the API to send the verified data to the server, where it is encrypted before being sent.

[0969] Input: Validated data

[0970] Output: Data sent to the server

[0971] What it does: Securely transmits data using HTTP requests.

[0972] Step 4:

[0973] The server receives the data sent from the device and stores it in a database, using the user ID as a key.

[0974] Input: Request for validated data

[0975] Output: User data stored in the database

[0976] Specific operation: Data is saved to the database using the SQL INSERT command.

[0977] Step 5:

[0978] The server retrieves the electricity supplier's rate plans from a database, including rate structures, special offers, and contract terms.

[0979] Input: Database query

[0980] Output: Electricity supplier rate plan information

[0981] What it does: Uses an SQL query to retrieve the required pricing plan information.

[0982] Step 6:

[0983] The server uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests) to perform analysis based on the user's power usage information and condition parameters.

[0984] Input: User data and electricity supplier rate plan information

[0985] Output: Prediction of optimal electricity supplier and tariff plan

[0986] What it does: It uses machine learning algorithms to analyze data and predict the optimal plan.

[0987] Step 7:

[0988] The server runs multiple simulations, evaluates the cost performance of each plan, and generates a proposal result.

[0989] Input: Optimal pricing plan prediction results

[0990] Output: Proposal results

[0991] Specific actions: Use a simulation program to perform detailed cost comparisons.

[0992] Step 8:

[0993] The server then sends the generated proposal results to the device, using an API to ensure data integrity and confidentiality.

[0994] Input: Suggestion results

[0995] Output: Data sent to the terminal

[0996] Specific behavior: Sends data in the form of an HTTP response.

[0997] Step 9:

[0998] The terminal displays the received proposal results to the user, who then checks the details of the proposed plan (such as the price estimate and the reason for the recommendation).

[0999] Input: Proposal results received from the server

[1000] Output: Information displayed to the user

[1001] Specific behavior: Display data on the screen using HTML and JavaScript.

[1002] Step 10:

[1003] The user selects the most suitable plan from the proposed plans and clicks the selection button.

[1004] Input: User's choice

[1005] Output: Selected plan information

[1006] Specific behavior: The user clicks the "Select" button on the screen.

[1007] Step 11:

[1008] The device sends the user's selection to the server, which also sends the data via an API.

[1009] Input: User selection

[1010] Output: Data sent to the server

[1011] What it does: Sends the selection data using an HTTP request.

[1012] Step 12:

[1013] The server stores the received selections in a database and uses them as feedback data to improve the accuracy of future analyses.

[1014] Input: User selection

[1015] Output: Feedback data stored in a database

[1016] Specific operation: Executes an INSERT or UPDATE command to the database.

[1017] (Application example 1)

[1018] 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."

[1019] In modern industrial manufacturing facilities, efficient energy management contributes significantly to reducing production costs and environmental impact. However, the energy consumption patterns of factory robots and equipment are complex, and advanced analysis is required to select the optimal energy plan. Conventional methods lack a system that efficiently solves these issues, resulting in wasted energy costs. The present invention aims to solve these energy management problems and improve factory operational efficiency.

[1020] 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.

[1021] In this invention, the server includes: means for receiving past energy usage information and condition parameters from a user; means for referencing a database of multiple energy suppliers and their service menus; means for analyzing the information and database using a machine learning algorithm to identify the energy supplier and service menu that are optimal for the user; means for presenting the identified energy supplier and service menu to the user; means for recording information selected by the user and using it to improve the accuracy of future analyses; means for a factory robot to collect energy consumption data in real time and transmit it to a cloud server; means for the cloud server to analyze the energy consumption data and recommend the optimal energy supplier and service menu; and means for displaying the recommendation results to a factory manager, thereby enabling efficient and optimized energy management throughout the factory.

[1022] "User" refers to a factory manager or factory operator who provides energy consumption information and condition parameters and receives a proposal for an optimal energy plan.

[1023] "Energy usage information" refers to information about energy usage within a factory, such as past energy consumption data and current consumption status.

[1024] "Condition parameters" are factors that affect energy consumption, including information on work style and equipment used.

[1025] "Energy supplier" refers to a company or organization that supplies energy such as electricity or gas.

[1026] "Service menu" refers to the various plans and contract terms offered by energy suppliers.

[1027] "Database" refers to a collection of information that stores an energy supplier's service menu, rate structure, contract terms, etc.

[1028] A "machine learning algorithm" refers to a mathematical technique that analyzes patterns based on past data to make predictions and optimal choices.

[1029] A "cloud server" is a remote server that can be accessed via the Internet and is a computer system used to store and analyze data.

[1030] "Energy consumption data" refers to data on energy usage generated in real time by factory robots and equipment.

[1031] "Recommendation" refers to the act of presenting the optimal energy supplier and service menu based on the analysis results.

[1032] A "factory robot" is a device used to perform automated tasks within a factory, and has the ability to monitor energy consumption in real time and collect data.

[1033] "Factory manager" refers to the person in charge of factory operations and energy management.

[1034] This invention is a system that uses factory robots to collect energy consumption data in real time, analyzes it on a cloud server, and recommends the optimal energy supplier and service menu. This system is realized through collaboration between users, terminals, and the cloud server.

[1035] First, factory robots collect energy consumption data in real time. This data includes past and current energy usage information, factory operation patterns, and information on equipment in use. The robots periodically send this data to a cloud server. Data transmission is generally done using an API to ensure security and data integrity.

[1036] The cloud server stores the received data in a database. It then references a database of multiple energy suppliers and their service menus to match the energy consumption data. This matching process uses machine learning algorithms. Specifically, analysis is performed using algorithms such as k-nearest neighbors, decision trees, and random forests. This identifies the energy supplier and service menu that best suits the energy consumption pattern.

[1037] The analysis results are generated as recommendations after a simulation is run to compare the cost performance of each plan. The cloud server then sends the generated recommendations to the factory robots and management terminal. The management terminal (PC, smartphone, etc.) then presents this information to the factory manager. On the screen, the factory manager can view detailed information about each energy supplier and service menu, a rate simulation, and the reasons for the recommendation.

[1038] As a concrete example, a certain factory consumes 1,500 kWh of energy per month. Robots in this factory collect data in real time and send it to a cloud server. The server analyzes past energy usage information and current consumption status, and recommends an optimal energy plan. The recommended results are sent to a management terminal, allowing factory managers to implement efficient energy management.

[1039] An example of a prompt is, "Please enter your current energy consumption data (consumption over the past 12 months, current consumption, work style, and information on the devices you use). We will recommend the optimal energy supplier and plan." By entering your energy consumption data according to this prompt, the optimal energy plan will be recommended.

[1040] This system will improve the efficiency of energy management throughout the factory and make it possible to select the most suitable energy supplier and service menu.

[1041] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1042] Step 1:

[1043] Factory robots collect energy consumption data in real time. The collected data includes past energy usage information, current consumption status, operation patterns within the factory, and information on equipment being used. This data is temporarily stored in local memory. The input is sensor data from the factory robots, and the output is formatted energy consumption data.

[1044] Step 2:

[1045] The energy consumption data collected by the factory robot is sent to a cloud server using an API call, with the SSL / TLS protocol used to ensure security and data integrity. The input is the formatted energy consumption data, and the output is a message that the data was successfully uploaded to the cloud server.

[1046] Step 3:

[1047] The server stores the received energy consumption data in a database. The database contains information on past energy usage, factory operation patterns, and information on equipment used. The input is the energy consumption data received by the cloud server, and the output is a message that the data was successfully saved in the database.

[1048] Step 4:

[1049] The server accesses a database of multiple energy suppliers and their service menus, thereby collecting information on all available energy plans. The input is energy consumption data, and the output is information on the service menu.

[1050] Step 5:

[1051] The server analyzes the energy consumption data and service menu using machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests), thereby identifying the optimal energy supplier and service menu for the user. The input is the user's energy consumption data and service menu information, and the output is the recommendation of the optimal energy plan.

[1052] Step 6:

[1053] The server generates a recommendation and sends it to the factory management terminal. This includes the recommended energy plan, its reasons, and a price simulation. The input is the recommendation, and the output is a message to the factory management terminal indicating that the information was successfully sent.

[1054] Step 7:

[1055] The factory management terminal receives the recommendation results from the server and presents them to the user. On the screen, the user can view detailed information about each energy supplier and service menu, a price simulation, and the reasons for the recommendation. The input is the recommendation results received from the server, and the output is a confirmation message from the user.

[1056] 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.

[1057] The present invention is a system that can incorporate the user's emotional state into its analysis in addition to various condition parameters such as the user's past electricity usage information, household configuration, and lifestyle patterns. This system is implemented through a series of processes: collecting data from the user, analyzing the data on the server side, presenting an optimal plan, and analyzing and reflecting emotions using an emotion engine. Below, we will explain in detail how the user, terminal, server, and emotion engine implement this system.

[1058] User operations

[1059] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[1060] Electricity usage over the past 12 months

[1061] Your current electricity provider and plan name

[1062] Family composition (e.g., 2 adults, 2 children)

[1063] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[1064] Furthermore, the emotion engine recognizes the user's current emotional state by analyzing the user's facial expressions and voice using the device's camera and microphone. For example, facial recognition technology can detect smiling or angry expressions, and voice analysis technology can analyze the tone and speed of speech.

[1065] Terminal handling

[1066] The device verifies the past power usage information and condition parameters entered by the user. At the same time, this data, including the emotion data acquired by the emotion engine, is sent to the server. At this time, an API call is made to ensure the data is sent securely.

[1067] Server Processing

[1068] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity company and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[1069] The server uses machine learning algorithms to analyze the user's past electricity usage information, condition parameters, and emotional data. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption patterns and emotional state.

[1070] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then used to generate a proposal, which is then provided to the user as a customized proposal that takes into account emotional data.

[1071] Presentation of proposed results

[1072] The server then sends the generated recommendation results to the device, which include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on the user's emotional state.

[1073] The device displays the information received from the server to the user. The user can check detailed information about each plan along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[1074] User Choice and Feedback

[1075] The user selects the plan they think is best from the proposed plans. The device then sends the user's selection results to the server, which stores the received selection results in a database and uses them as feedback data for future AI model accuracy improvements and emotion engine training.

[1076] As described above, this invention is a system that efficiently provides electricity consumers with the most suitable electric power company and service menu through collaboration between users, terminals, servers, and an emotion engine. Utilizing the emotion engine makes it possible to provide proposals that are even more customized to meet the user's needs.

[1077] The processing flow will be explained below.

[1078] Step 1:

[1079] The user enters information

[1080] Users access their device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.). Users also use the device's camera and microphone to provide facial expressions and voice recordings to the system.

[1081] Step 2:

[1082] The terminal validates the input data

[1083] The device checks the format and required fields of the data entered by the user. It also validates the input values ​​to ensure that the data is entered correctly. At the same time, the emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state.

[1084] Step 3:

[1085] The device sends the data to the server

[1086] Once verified, the information and emotion data are sent from the device to the server, where the device makes an API call to securely transmit the data to the server.

[1087] Step 4:

[1088] The server receives the data

[1089] The server receives the user data and emotion data sent from the terminal, and the received data is first stored in a database.

[1090] Step 5:

[1091] The server retrieves the relevant information from the database

[1092] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[1093] Step 6:

[1094] The server performs the analysis using the AI ​​model

[1095] The server analyzes the aforementioned user data, the acquired plan information, and emotional data using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern and emotional state.

[1096] Step 7:

[1097] The server generates the analysis results

[1098] The server simulates multiple scenarios based on the analysis results, compares the cost performance of each plan, and generates a list of the most suitable power companies and plans for the user as a customized proposal that also reflects emotional data.

[1099] Step 8:

[1100] The server sends the proposal results to the device.

[1101] The server then sends the generated recommendation results to the device, which include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state.

[1102] Step 9:

[1103] The terminal receives and displays the results

[1104] The device visually displays the results of the proposals received from the server to the user. The user can view detailed information about each plan, along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[1105] Step 10:

[1106] The user selects a plan

[1107] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[1108] Step 11:

[1109] The device sends the selection information to the server

[1110] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[1111] Step 12:

[1112] The server records the selection information

[1113] The server stores the received selections in a database, which is used as feedback data to improve future analysis and train the emotion engine.

[1114] Example 2

[1115] 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."

[1116] Conventional systems for recommending power companies and service menus only consider the user's past electricity usage information and condition parameters, and have the problem of being unable to provide customized proposals that reflect the user's emotional state. This makes it difficult to provide optimal service plans that match the user's emotions and lifestyle.

[1117] 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 receiving past power usage information and condition parameters from the user, means for analyzing the user's facial expressions and voice to recognize the user's emotional state, means for referencing a database of multiple power companies and their service menus based on the received information and emotional state data, means for analyzing the information, emotional data, and database using a machine learning algorithm to identify the power company and service menu that are optimal for the user, means for presenting the identified power company and service menu to the user, means for generating and presenting comments and advice based on the user's emotional state, and means for recording information selected by the user and using it to improve future analysis accuracy. This makes it possible to suggest the optimal power company and service menu that takes the user's emotional state into consideration.

[1118] "User" refers to an individual or household who uses the system to receive an electricity plan proposal.

[1119] "Past electricity usage information" refers to data regarding the amount of electricity a user has consumed in the past, including detailed usage history over a specific period of time (e.g., the past 12 months).

[1120] "Condition parameters" refer to information related to the user's household structure and lifestyle patterns, and include, for example, the number of family members, the amount of time spent at home, and frequently used electrical appliances.

[1121] "Means for recognizing an emotional state by analyzing facial expressions and voice" refers to technology that captures a user's facial expressions with a camera, records their voice with a microphone, and analyzes them to recognize the user's current emotional state.

[1122] "Means for referencing a database" refers to a technology for accessing a database that stores information about multiple electric power companies and their service menus, and obtaining the necessary data.

[1123] "Machine learning algorithms" refer to algorithms that use statistical methods and computational models to learn patterns from data and make predictions or classifications for future data. Examples include k-nearest neighbors, decision trees, and random forests.

[1124] "Means for identifying" refers to technology that uses machine learning algorithms to select the electricity company and service menu that best suits the user's conditions and emotional state.

[1125] The "means for presenting" refers to a technique for displaying the identified power company and service menu to the user, and includes, for example, a function for displaying information on the screen of a terminal.

[1126] "Means for generating and presenting comments and advice" refers to a technology for generating customized comments and advice based on the recognized emotional state of the user and displaying them to the user.

[1127] "Means for recording and using to improve the accuracy of future analysis" refers to technology that stores the plan selected by the user and its results in a database, and uses this data to improve the accuracy of the machine learning model and the performance of the entire system.

[1128] This invention is a system that proposes the most suitable power company and service menu by analyzing the user's emotional state in addition to their past electricity usage information, household configuration, and lifestyle patterns. This system is realized through the cooperation of the user, terminal, server, and emotion engine.

[1129] User operations

[1130] Users access the system using a smartphone or PC at home. The initial screen displays a form for users to enter their electricity usage over the past 12 months, the name of their current electricity provider and plan, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, and frequently used electrical appliances).

[1131] Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes their current emotional state. Specifically, facial recognition and voice analysis technologies are used to detect smiling and angry expressions, as well as voice tone and speed.

[1132] Terminal handling

[1133] The device verifies the user-entered historical power usage information and condition parameters, and transmits them along with the emotion data acquired by the emotion engine to the server, using an API call and encryption technology such as HTTPS to ensure secure transmission of the data.

[1134] Server Processing

[1135] The server receives the user data and emotion data sent from the device and stores them in a database. After storing them, it retrieves detailed information about the electricity company and its plan (e.g., basic charge, metered charge, time-of-use charge, special offer information, contract terms, etc.) from the database.

[1136] The server then uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests, etc.) to analyze the user's past electricity usage information, condition parameters, and emotional data, and predicts the optimal electricity provider and plan for the user's consumption pattern and emotional state.

[1137] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan. Based on the analysis and simulation results, the server generates proposals and adds customized comments and advice that take into account emotional data.

[1138] Presentation of proposed results

[1139] The server then sends the generated proposal results to the device. The proposal results include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on emotional data. For example, a user who is feeling stressed may be recommended an energy-saving plan that helps them relax.

[1140] User Choice and Feedback

[1141] The user selects the plan they think is best from the presented options. The device sends the selection results to the server, which stores them in a database. This feedback data is used to improve the accuracy of analysis and train the emotion engine in the future.

[1142] Examples of specific examples and prompts

[1143] Specific examples

[1144] User A accesses the system and enters the following information:

[1145] Electricity usage for the past 12 months: 600kWh / month

[1146] Current plan: X Electric Company Y Plan (pay-as-you-go)

[1147] Family composition: 2 adults, 1 child

[1148] Lifestyle: Both spouses work, at home after 6pm on weekdays, main appliances are an air conditioner and a refrigerator

[1149] Facial expression and voice analysis results: fatigue, slow voice

[1150] Based on this information, the system suggests a plan from Power Company Z, which has low off-peak rates, as the optimal plan, and provides customized advice such as, "Since you use a lot of electricity at night, a plan with low off-peak rates would be best. Also, make sure to use eco mode when you're tired."

[1151] Prompt Sentence Examples

[1152] "Please enter the user's electricity usage over the past 12 months, their current electricity contract plan, household composition and lifestyle patterns. The system will also estimate their emotional state from facial expressions and voice recordings made by the device's camera and microphone, and suggest the optimal electricity plan."

[1153] As described above, the system of the present invention can efficiently provide an optimal power plan based on the user's power usage pattern and emotional state.

[1154] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1155] Step 1:

[1156] User Data Entry

[1157] Users access the system using a smartphone or PC. They input their electricity usage over the past 12 months, their current electricity provider and plan name, household composition, and lifestyle patterns. The input data is temporarily stored in the device's local storage.

[1158] Input: electricity usage for the past 12 months, current electricity company and plan name, household composition, lifestyle patterns

[1159] Output: User data stored in the device's local storage

[1160] Step 2:

[1161] Acquiring emotion data

[1162] The device's camera and microphone are used to collect the user's facial expressions and voice data. The collected data is analyzed in real time by an emotion engine within the device. Facial recognition and voice analysis technologies are used to identify emotional states such as smile, anger, voice tone, and speed.

[1163] Input: Facial expression and voice data via camera and microphone

[1164] Output: Parsed emotional state data

[1165] Step 3:

[1166] Validating and submitting data

[1167] The device verifies the power usage information and condition parameters entered by the user. It checks the format and range to ensure the data is in the correct format. At the same time, it also verifies the emotion data and sends it to the server via an API. The data is transmitted securely using encryption technologies such as HTTPS.

[1168] Input: User data, emotional state data

[1169] Output: Validated data sent to the server

[1170] Step 4:

[1171] Receiving and storing data

[1172] The server receives the user data and emotional state data sent from the device and stores them in a database. Once stored, the server checks the data to ensure its consistency and completeness.

[1173] Input: User data and emotional state data sent from the device

[1174] Output: User data and emotional state data stored in a database

[1175] Step 5:

[1176] Obtaining electricity plan information

[1177] The server retrieves information about currently available energy plans (e.g., rate structures, special offers, contract terms, etc.) from a database, which may also include retrieving data from external APIs.

[1178] Input: User data and emotional state data

[1179] Output: Obtained electricity plan information

[1180] Step 6:

[1181] Analysis using machine learning algorithms

[1182] The server inputs user data, emotional state data, and the acquired power plan information and analyzes them using machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests). As a result of the analysis, the optimal power plan for the user is identified.

[1183] Input: User data, emotional state data, power plan information

[1184] Output: Optimal power plan information

[1185] Step 7:

[1186] Scenario simulation

[1187] The server simulates multiple scenarios based on the analysis results and evaluates the cost performance of each plan, thereby determining the optimal plan.

[1188] Input: Analysis results (optimal power plan information)

[1189] Output: Simulation results and evaluation data

[1190] Step 8:

[1191] Generate and send proposal results

[1192] The server generates suggestions based on the simulation results, adds comments and advice based on the emotional state data, and sends the suggestions to the device via API.

[1193] Input: Simulation results and evaluation data

[1194] Output: Suggestion results and customized advice sent to your device

[1195] Step 9:

[1196] Displaying the proposed results

[1197] The device displays the proposal results received from the server to the user, including price estimates, detailed plan information, and comments and advice based on emotion data.

[1198] Input: Suggested results and customized advice sent from the server

[1199] Output: Suggestion results displayed in the user interface

[1200] Step 10:

[1201] User Choice and Feedback

[1202] The user selects the plan they think is best from the presented options. The selection results are sent to the server via the device and stored in a database. The feedback data will be used to improve the accuracy of analysis and train the emotion engine.

[1203] Input: User selection

[1204] Output: Feedback data stored in a database

[1205] This series of processing steps enables the system to efficiently propose an optimal power plan to the user.

[1206] (Application example 2)

[1207] 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."

[1208] The main function of conventional energy plan proposal systems was to provide optimal plans based on parameters such as the user's past energy usage information, household configuration, and lifestyle patterns. However, these systems did not take into account the user's emotional state, which limited the ability to improve the user experience and customize proposals. In particular, in physical stores, the inability to make proposals based on the customer's emotions was a major problem.

[1209] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1210] means for receiving historical power usage information and condition parameters from a user;

[1211] a means for referencing a database of a plurality of power supply companies and service plans of each power supply company based on the received information;

[1212] means for analyzing the information and database using machine learning algorithms to identify the most suitable electricity supplier and service plan for the user;

[1213] means for presenting the identified electricity supplier and service plan to a user;

[1214] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1215] means for recognizing a user's current emotional state and customizing a recommended service plan based on the emotional state;

[1216] This makes it possible to propose an optimal power plan according to the user's emotional state.

[1217] "Past electricity usage information" refers to data on the electricity used by a user over a certain period of time (e.g., the past 12 months).

[1218] "Condition parameters" refer to information indicating factors that affect power consumption, such as a user's lifestyle patterns and household configuration.

[1219] "Electricity supplier" means a company or entity that supplies electricity to users.

[1220] "Service plan" refers to the various contract menus and rate plans offered by electricity suppliers.

[1221] "Database" refers to a system that systematically stores information about electricity suppliers and service plans.

[1222] "Machine learning algorithms" refer to computational techniques used to analyze data and recognize patterns.

[1223] "Emotional state" refers to the user's current state of mind, such as joy, sadness, anger, etc., and is recognized from facial expressions and voice.

[1224] "Camera" refers to an image capturing device for recognizing a user's facial expressions.

[1225] "Microphone" refers to a voice capture device for capturing a user's voice and analyzing their emotional state.

[1226] "Real-time" refers to processing and analysis occurring immediately, without delay.

[1227] "Receiving power usage information" refers to the system receiving data regarding power usage provided by a user.

[1228] "Plan customization" refers to the process of adapting the service plan provided based on the user's individual requirements and emotional state.

[1229] "Proposal presentation" refers to the system displaying or notifying the user of the optimal power plan based on the analysis results.

[1230] The present invention is a system for proposing an optimal power plan to a user by utilizing power usage information and emotional state. This system is composed of the following components:

[1231] User operations

[1232] Users access the system using devices such as smart glasses, smartphones, or PCs. On the initial screen, users enter the following information:

[1233] Electricity usage over the past 12 months

[1234] Your current electricity provider and plan name

[1235] Family composition (e.g., 2 adults, 2 children)

[1236] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[1237] Furthermore, the smart glasses' camera and microphone are used to analyze the user's facial expressions and voice, and the emotion engine recognizes the user's current emotional state.

[1238] Terminal handling

[1239] The device verifies the entered power usage information and condition parameters. At the same time, it sends this data, including the emotion data acquired by the emotion engine, to the server. At this time, an API call is made and the data is securely transmitted.

[1240] Server Processing

[1241] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity supplier and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[1242] Using machine learning algorithms (k-nearest neighbors, decision trees, random forests, etc.), the server analyzes the user's electricity usage information, condition parameters, and emotional data. The optimal electricity provider and plan are predicted based on the user's consumption patterns and emotional state.

[1243] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The results of this analysis are then generated as a customized proposal, which is provided to the user in a format that takes into account emotional data.

[1244] Presentation of proposed results

[1245] The server then sends the generated proposal to the device. The proposal includes a price estimate, reasons for the recommendation (e.g., cost savings, plan suitable for usage patterns, etc.), and customized comments and advice based on the user's emotional state. For example, a user experiencing high stress may be recommended an energy-saving plan that helps them relax.

[1246] User Choice and Feedback

[1247] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data for future AI model accuracy improvements and emotion engine training.

[1248] Specific examples

[1249] When a customer visits a physical store, a sales associate wearing smart glasses can analyze the customer's facial expressions and voice to recognize their "confused" emotional state in real time. Based on this, the sales associate can provide a friendly explanation and recommend the optimal energy plan. This improves the user experience and enables suggestions tailored to individual needs.

[1250] Prompt Sentence Examples

[1251] Use the following prompts to generate code for an application that improves customer support in brick-and-mortar stores.

[1252] Prompt statement:

[1253] Your goal is to generate an application program that uses smart glasses to analyze a customer's emotional state and suggest appropriate products and services. Specific technologies used include TensorFlow, Flask, and OpenCV. Analyze emotions from the customer's facial expressions, receive the results on the server, and provide customized suggestions in real time.

[1254] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1255] Program processing steps

[1256] Step 1:

[1257] Users access the system using smart glasses or a smartphone and input condition parameters such as past power usage information, household composition, and lifestyle patterns.Facial expression and voice data are also acquired through the smart glasses' camera and microphone.This allows the system to collect "power usage information," "condition parameters," "facial expression data," and "voice data" as input from the user.

[1258] Step 2:

[1259] The device transmits the information input by the user and the acquired emotion data to the server. The transmitted data includes power usage information, condition parameters, facial expression data, and voice data. This data is securely transferred to the server using an API.

[1260] Step 3:

[1261] The server stores the received data in a database for analysis. The database contains detailed information about the electricity supplier and each plan (such as rate structure, benefit information, and contract terms). The input is "user data (electricity usage information, condition parameters, facial expression data, and voice data)," and the output is "a dataset for analysis."

[1262] Step 4:

[1263] The server processes the analysis dataset using a machine learning algorithm. This analyzes the user's electricity consumption patterns and emotional state, and based on this, predicts the optimal electricity supplier and plan. Algorithms used include k-nearest neighbors, decision trees, and random forests. The input is the "analysis dataset," and the output is the "prediction of the optimal plan."

[1264] Step 5:

[1265] The server simulates multiple scenarios based on the predicted optimal plan and compares the cost performance of each plan. This generates a customized proposal that also takes emotional data into account. The input is the "predicted optimal plan" and the output is the "customized proposal."

[1266] Step 6:

[1267] The server sends the generated recommendation results to the device. The recommendation results include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state. The input is the "customized recommendation results," and the output is the "data sent to the device."

[1268] Step 7:

[1269] The terminal displays the proposal results received from the server to the user. The user can select the plan that they think is best from the proposed plans. The user's selection results are sent from the terminal to the server, which then stores them in a database. The inputs are the "proposal results" and the "user's selection results," and the output is the "database storage of the selection results."

[1270] Step 8:

[1271] The server uses the received selection results as feedback data for improving analysis accuracy and for learning the emotion engine. The input is the "selection result" and the output is "updated feedback data."

[1272] 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.

[1273] 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.

[1274] 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.

[1275] [Fourth embodiment]

[1276] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1277] 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.

[1278] 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).

[1279] 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.

[1280] 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.

[1281] 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).

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] 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."

[1289] The present invention is a system that helps electricity consumers select the most suitable electric power company and the service menu they offer. This system is realized through a series of processes, including data collection from users, data analysis on the server side, and presentation of the optimal plan. How the user, terminal, and server implement this system is described in detail below.

[1290] User operations

[1291] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[1292] Electricity usage over the past 12 months

[1293] Your current electricity provider and plan name

[1294] Family composition (e.g., 2 adults, 2 children)

[1295] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[1296] When the user enters this information, the terminal checks the data format and required fields to verify that it has been entered correctly.

[1297] Terminal handling

[1298] The device then compiles the verified information and sends it to the server, typically via an API call to ensure security and data integrity.

[1299] Server Processing

[1300] The server receives the user data sent from the device and stores it in a database. The server then retrieves detailed information about the electricity company and its plans from the database, including each plan's rate structure (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[1301] The server uses machine learning algorithms to analyze the user's past electricity usage information and condition parameters. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption pattern.

[1302] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then generated as a proposal.

[1303] Presentation of proposed results

[1304] The server then sends the generated proposal results to the device, which include a price estimate for each plan and the reasons for the recommendation (e.g., cost savings, which plan is best suited to your usage pattern, etc.).

[1305] The device displays the information received from the server to the user. The user can then check the details of the proposed power company and plan on the device screen. For example, the user can view the specific plan details, fee simulation, and advantages and disadvantages of "Power Company A's Home Plan B" and "Power Company B's Eco Plan C."

[1306] User Choice and Feedback

[1307] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data to improve the accuracy of the AI ​​model in the future.

[1308] As described above, the present invention is a system that efficiently provides the most suitable electric power company and service menu to an electric power consumer through cooperation between a user, a terminal, and a server.

[1309] The processing flow will be explained below.

[1310] Step 1:

[1311] The user enters information

[1312] Users access a device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.).

[1313] Step 2:

[1314] The terminal validates the input data

[1315] The terminal checks the format and mandatory fields of the data entered by the user, and performs input validation to ensure the data is entered correctly.

[1316] Step 3:

[1317] The device sends the data to the server

[1318] Once the verification is complete, the device sends the information to the server, which then makes an API call to securely send the data to the server.

[1319] Step 4:

[1320] The server receives the data

[1321] The server receives the user data sent from the terminal, and the received data is first stored in a database.

[1322] Step 5:

[1323] The server retrieves the relevant information from the database

[1324] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[1325] Step 6:

[1326] The server performs the analysis using the AI ​​model

[1327] The server analyzes the aforementioned user data and the acquired plan information using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern.

[1328] Step 7:

[1329] The server generates the analysis results

[1330] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan, thereby generating a list of the most suitable power companies and plans for the user.

[1331] Step 8:

[1332] The server sends the proposal results to the device.

[1333] The server then sends the generated recommendation results to the terminal, which include a price estimate and the reason for the recommendation.

[1334] Step 9:

[1335] The terminal receives and displays the results

[1336] The terminal visually displays the proposal results received from the server to the user, who can then check the detailed information of each plan.

[1337] Step 10:

[1338] The user selects a plan

[1339] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[1340] Step 11:

[1341] The device sends the selection information to the server

[1342] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[1343] Step 12:

[1344] The server records the selection information

[1345] The server stores the received selection results in a database, which is used as feedback data to train the AI ​​model to improve the accuracy of future analysis.

[1346] Example 1

[1347] 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."

[1348] For electricity consumers to select the optimal plan from the wide variety of electricity supplier plans, it takes a huge amount of time and effort to collect detailed information about each plan and perform comparative analysis. Advanced analysis is also required to predict the optimal plan based on electricity usage patterns, but average consumers lack the skills and tools to perform such analysis. Therefore, it is necessary to provide a system that allows consumers to easily select the electricity supplier and rate plan that is best for them.

[1349] 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.

[1350] In this invention, the server includes means for receiving past electricity usage information and condition parameters from a user, means for referencing a database of multiple electricity suppliers and their rate plans, and means for analyzing the information and database using a machine learning algorithm to identify an electricity supplier and rate plan that are optimal for the user, thereby enabling consumers to select an electricity supplier and rate plan that are optimal for them without complex information gathering and analysis.

[1351] "User" refers to an individual or legal entity that is an electricity consumer or uses the system.

[1352] "Electricity usage information" refers to data related to a user's electricity usage, such as electricity consumption over the past 12 months.

[1353] "Condition parameters" refer to factors that affect power usage, such as the user's household configuration and lifestyle patterns.

[1354] "Electricity supplier" means a company or organization that supplies electricity to consumers.

[1355] "Price plan" refers to the content of the electricity supply contract and fee structure provided by the electricity supplier.

[1356] A "database" refers to a collection of systematically stored information such as electricity supplier plan information and user information.

[1357] A "machine learning algorithm" refers to a program or method that learns from large amounts of data and makes predictions and classifications.

[1358] "Analysis" refers to the process of working with data, extracting information, and drawing conclusions.

[1359] "Simulation" refers to a technology that reproduces actual electricity usage conditions on a computer and makes predictions by testing different scenarios.

[1360] "Optimal plan" refers to the electricity supplier's rate plan that best suits the user's electricity usage pattern and conditions.

[1361] "Proposal result" refers to information about a plan recommended to a user, generated by the server through analysis and simulation.

[1362] "Feedback" refers to the process of reusing data to improve future analysis accuracy based on user-selected plan information.

[1363] "Security" refers to the measures and procedures used to protect the confidentiality, integrity, and availability of information.

[1364] The present invention is a system that helps electricity consumers select the most suitable electricity supplier and the rate plan they offer. This system is realized by collecting data from users, verifying the data on their terminals, analyzing the data on the server side, and presenting the most suitable plan.

[1365] First, the user accesses the system using a device (such as a smartphone or PC). The system's initial screen displays a form for entering information about electricity usage over the past 12 months, the current electricity supplier and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, which electrical appliances are frequently used, etc.). After completing the information, the user clicks the "Submit" button.

[1366] The device checks the format and required fields of the data entered by the user to verify that it has been entered correctly. Once verified, the data is sent to the server using an API while maintaining security. The data is encrypted before being sent, ensuring the confidentiality of the information.

[1367] The server receives the user data sent from the device and stores it in a database. The server then retrieves information about the electricity supplier and its rate plans from the database. This information includes the rate structure of each plan (basic rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[1368] The server uses machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests) to analyze the user's electricity usage information and condition parameters. This predicts the electricity supplier and rate plan that best suits the user's consumption pattern. The server then runs multiple simulations to evaluate the cost performance of each plan. The analysis results are then used to generate a proposal.

[1369] The server sends the proposal results to the device, which then displays them to the user. The proposal includes a price estimate, the reason for the recommendation, and detailed information about each plan (e.g., "Electricity Company A's Home Plan B," "Electricity Company B's Eco Plan C," etc.). The user can review this information on the screen and select the plan they deem most suitable.

[1370] Once the user selects a plan, the device sends the selection back to the server. The server stores the received selection in a database and uses it as feedback data to improve the accuracy of future analysis. This allows the system to self-learn and provide more accurate suggestions to the next user.

[1371] For example, if a user inputs their electricity usage data from the past 12 months and their current contract plan, and the system analyzes it and displays that "Electricity Company A's Home Plan B" is the best option, the user can check the details of that plan and select it. This result is saved in the system as feedback data.

[1372] An example of a prompt sentence is "Analyze the user's electricity usage data from the past 12 months and their current contracted plan, and suggest the most suitable electricity supplier and plan."

[1373] As described above, this system efficiently provides the most suitable power supplier and rate plan to power consumers through collaboration between users, terminals, and servers.

[1374] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1375] Step 1:

[1376] Users access the system using devices such as smartphones or PCs. On the initial screen, users enter their electricity usage information for the past 12 months, their current electricity supplier and plan name, household composition, and lifestyle patterns.

[1377] Input: User's electricity usage information for the past 12 months, current contract information, household composition, and lifestyle patterns

[1378] Output: The input data

[1379] Specific behavior: The user enters information into each field and clicks the "Submit" button.

[1380] Step 2:

[1381] The terminal checks the format and required fields of the entered data to verify that the data has been entered correctly.

[1382] Input: Data entered by the user

[1383] Output: Validated data

[1384] Specific operation: The terminal checks the validity of input data using regular expressions and validation rules within the program.

[1385] Step 3:

[1386] The device then uses the API to send the verified data to the server, where it is encrypted before being sent.

[1387] Input: Validated data

[1388] Output: Data sent to the server

[1389] What it does: Securely transmits data using HTTP requests.

[1390] Step 4:

[1391] The server receives the data sent from the device and stores it in a database, using the user ID as a key.

[1392] Input: Request for validated data

[1393] Output: User data stored in the database

[1394] Specific operation: Data is saved to the database using the SQL INSERT command.

[1395] Step 5:

[1396] The server retrieves the electricity supplier's rate plans from a database, including rate structures, special offers, and contract terms.

[1397] Input: Database query

[1398] Output: Electricity supplier rate plan information

[1399] What it does: Uses an SQL query to retrieve the required pricing plan information.

[1400] Step 6:

[1401] The server uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests) to perform analysis based on the user's power usage information and condition parameters.

[1402] Input: User data and electricity supplier rate plan information

[1403] Output: Prediction of optimal electricity supplier and tariff plan

[1404] What it does: It uses machine learning algorithms to analyze data and predict the optimal plan.

[1405] Step 7:

[1406] The server runs multiple simulations, evaluates the cost performance of each plan, and generates a proposal result.

[1407] Input: Optimal pricing plan prediction results

[1408] Output: Proposal results

[1409] Specific actions: Use a simulation program to perform detailed cost comparisons.

[1410] Step 8:

[1411] The server then sends the generated proposal results to the device, using an API to ensure data integrity and confidentiality.

[1412] Input: Suggestion results

[1413] Output: Data sent to the terminal

[1414] Specific behavior: Sends data in the form of an HTTP response.

[1415] Step 9:

[1416] The terminal displays the received proposal results to the user, who then checks the details of the proposed plan (such as the price estimate and the reason for the recommendation).

[1417] Input: Proposal results received from the server

[1418] Output: Information displayed to the user

[1419] Specific behavior: Display data on the screen using HTML and JavaScript.

[1420] Step 10:

[1421] The user selects the most suitable plan from the proposed plans and clicks the selection button.

[1422] Input: User's choice

[1423] Output: Selected plan information

[1424] Specific behavior: The user clicks the "Select" button on the screen.

[1425] Step 11:

[1426] The device sends the user's selection to the server, which also sends the data via an API.

[1427] Input: User selection

[1428] Output: Data sent to the server

[1429] What it does: Sends the selection data using an HTTP request.

[1430] Step 12:

[1431] The server stores the received selections in a database and uses them as feedback data to improve the accuracy of future analyses.

[1432] Input: User selection

[1433] Output: Feedback data stored in a database

[1434] Specific operation: Executes an INSERT or UPDATE command to the database.

[1435] (Application example 1)

[1436] 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."

[1437] In modern industrial manufacturing facilities, efficient energy management contributes significantly to reducing production costs and environmental impact. However, the energy consumption patterns of factory robots and equipment are complex, and advanced analysis is required to select the optimal energy plan. Conventional methods lack a system that efficiently solves these issues, resulting in wasted energy costs. The present invention aims to solve these energy management problems and improve factory operational efficiency.

[1438] 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.

[1439] In this invention, the server includes: means for receiving past energy usage information and condition parameters from a user; means for referencing a database of multiple energy suppliers and their service menus; means for analyzing the information and database using a machine learning algorithm to identify the energy supplier and service menu that are optimal for the user; means for presenting the identified energy supplier and service menu to the user; means for recording information selected by the user and using it to improve the accuracy of future analyses; means for a factory robot to collect energy consumption data in real time and transmit it to a cloud server; means for the cloud server to analyze the energy consumption data and recommend the optimal energy supplier and service menu; and means for displaying the recommendation results to a factory manager, thereby enabling efficient and optimized energy management throughout the factory.

[1440] "User" refers to a factory manager or factory operator who provides energy consumption information and condition parameters and receives a proposal for an optimal energy plan.

[1441] "Energy usage information" refers to information about energy usage within a factory, such as past energy consumption data and current consumption status.

[1442] "Condition parameters" are factors that affect energy consumption, including information on work style and equipment used.

[1443] "Energy supplier" refers to a company or organization that supplies energy such as electricity or gas.

[1444] "Service menu" refers to the various plans and contract terms offered by energy suppliers.

[1445] "Database" refers to a collection of information that stores an energy supplier's service menu, rate structure, contract terms, etc.

[1446] A "machine learning algorithm" refers to a mathematical technique that analyzes patterns based on past data to make predictions and optimal choices.

[1447] A "cloud server" is a remote server that can be accessed via the Internet and is a computer system used to store and analyze data.

[1448] "Energy consumption data" refers to data on energy usage generated in real time by factory robots and equipment.

[1449] "Recommendation" refers to the act of presenting the optimal energy supplier and service menu based on the analysis results.

[1450] A "factory robot" is a device used to perform automated tasks within a factory, and has the ability to monitor energy consumption in real time and collect data.

[1451] "Factory manager" refers to the person in charge of factory operations and energy management.

[1452] This invention is a system that uses factory robots to collect energy consumption data in real time, analyzes it on a cloud server, and recommends the optimal energy supplier and service menu. This system is realized through collaboration between users, terminals, and the cloud server.

[1453] First, factory robots collect energy consumption data in real time. This data includes past and current energy usage information, factory operation patterns, and information on equipment in use. The robots periodically send this data to a cloud server. Data transmission is generally done using an API to ensure security and data integrity.

[1454] The cloud server stores the received data in a database. It then references a database of multiple energy suppliers and their service menus to match the energy consumption data. This matching process uses machine learning algorithms. Specifically, analysis is performed using algorithms such as k-nearest neighbors, decision trees, and random forests. This identifies the energy supplier and service menu that best suits the energy consumption pattern.

[1455] The analysis results are generated as recommendations after a simulation is run to compare the cost performance of each plan. The cloud server then sends the generated recommendations to the factory robots and management terminal. The management terminal (PC, smartphone, etc.) then presents this information to the factory manager. On the screen, the factory manager can view detailed information about each energy supplier and service menu, a rate simulation, and the reasons for the recommendation.

[1456] As a concrete example, a certain factory consumes 1,500 kWh of energy per month. Robots in this factory collect data in real time and send it to a cloud server. The server analyzes past energy usage information and current consumption status, and recommends an optimal energy plan. The recommended results are sent to a management terminal, allowing factory managers to implement efficient energy management.

[1457] An example of a prompt is, "Please enter your current energy consumption data (consumption over the past 12 months, current consumption, work style, and information on the devices you use). We will recommend the optimal energy supplier and plan." By entering your energy consumption data according to this prompt, the optimal energy plan will be recommended.

[1458] This system will improve the efficiency of energy management throughout the factory and make it possible to select the most suitable energy supplier and service menu.

[1459] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1460] Step 1:

[1461] Factory robots collect energy consumption data in real time. The collected data includes past energy usage information, current consumption status, operation patterns within the factory, and information on equipment being used. This data is temporarily stored in local memory. The input is sensor data from the factory robots, and the output is formatted energy consumption data.

[1462] Step 2:

[1463] The energy consumption data collected by the factory robot is sent to a cloud server using an API call, with the SSL / TLS protocol used to ensure security and data integrity. The input is the formatted energy consumption data, and the output is a message that the data was successfully uploaded to the cloud server.

[1464] Step 3:

[1465] The server stores the received energy consumption data in a database. The database contains information on past energy usage, factory operation patterns, and information on equipment used. The input is the energy consumption data received by the cloud server, and the output is a message that the data was successfully saved in the database.

[1466] Step 4:

[1467] The server accesses a database of multiple energy suppliers and their service menus, thereby collecting information on all available energy plans. The input is energy consumption data, and the output is information on the service menu.

[1468] Step 5:

[1469] The server analyzes the energy consumption data and service menu using machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests), thereby identifying the optimal energy supplier and service menu for the user. The input is the user's energy consumption data and service menu information, and the output is the recommendation of the optimal energy plan.

[1470] Step 6:

[1471] The server generates a recommendation and sends it to the factory management terminal. This includes the recommended energy plan, its reasons, and a price simulation. The input is the recommendation, and the output is a message to the factory management terminal indicating that the information was successfully sent.

[1472] Step 7:

[1473] The factory management terminal receives the recommendation results from the server and presents them to the user. On the screen, the user can view detailed information about each energy supplier and service menu, a price simulation, and the reasons for the recommendation. The input is the recommendation results received from the server, and the output is a confirmation message from the user.

[1474] 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.

[1475] The present invention is a system that can incorporate the user's emotional state into its analysis in addition to various condition parameters such as the user's past electricity usage information, household configuration, and lifestyle patterns. This system is implemented through a series of processes: collecting data from the user, analyzing the data on the server side, presenting an optimal plan, and analyzing and reflecting emotions using an emotion engine. Below, we will explain in detail how the user, terminal, server, and emotion engine implement this system.

[1476] User operations

[1477] First, the user accesses the system using a device (smartphone or PC). The initial screen of the system displays a form for the user to enter the following information:

[1478] Electricity usage over the past 12 months

[1479] Your current electricity provider and plan name

[1480] Family composition (e.g., 2 adults, 2 children)

[1481] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[1482] Furthermore, the emotion engine recognizes the user's current emotional state by analyzing the user's facial expressions and voice using the device's camera and microphone. For example, facial recognition technology can detect smiling or angry expressions, and voice analysis technology can analyze the tone and speed of speech.

[1483] Terminal handling

[1484] The device verifies the past power usage information and condition parameters entered by the user. At the same time, this data, including the emotion data acquired by the emotion engine, is sent to the server. At this time, an API call is made to ensure the data is sent securely.

[1485] Server Processing

[1486] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity company and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[1487] The server uses machine learning algorithms to analyze the user's past electricity usage information, condition parameters, and emotional data. Specific algorithms used include k-nearest neighbors, decision trees, and random forests. This allows the server to predict the optimal electricity provider and plan for the user's consumption patterns and emotional state.

[1488] The server simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The analysis results are then used to generate a proposal, which is then provided to the user as a customized proposal that takes into account emotional data.

[1489] Presentation of proposed results

[1490] The server then sends the generated recommendation results to the device, which include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on the user's emotional state.

[1491] The device displays the information received from the server to the user. The user can check detailed information about each plan along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[1492] User Choice and Feedback

[1493] The user selects the plan they think is best from the proposed plans. The device then sends the user's selection results to the server, which stores the received selection results in a database and uses them as feedback data for future AI model accuracy improvements and emotion engine training.

[1494] As described above, this invention is a system that efficiently provides electricity consumers with the most suitable electric power company and service menu through collaboration between users, terminals, servers, and an emotion engine. Utilizing the emotion engine makes it possible to provide proposals that are even more customized to meet the user's needs.

[1495] The processing flow will be explained below.

[1496] Step 1:

[1497] The user enters information

[1498] Users access their device (smartphone or PC) and enter the following information into the system's input form: electricity usage over the past 12 months, current electricity provider and plan name, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.). Users also use the device's camera and microphone to provide facial expressions and voice recordings to the system.

[1499] Step 2:

[1500] The terminal validates the input data

[1501] The device checks the format and required fields of the data entered by the user. It also validates the input values ​​to ensure that the data is entered correctly. At the same time, the emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state.

[1502] Step 3:

[1503] The device sends the data to the server

[1504] Once verified, the information and emotion data are sent from the device to the server, where the device makes an API call to securely transmit the data to the server.

[1505] Step 4:

[1506] The server receives the data

[1507] The server receives the user data and emotion data sent from the terminal, and the received data is first stored in a database.

[1508] Step 5:

[1509] The server retrieves the relevant information from the database

[1510] The server retrieves detailed information about the electricity provider and its plans from a database, including each plan's pricing structure (base rate, metered rate, time-of-use rate, etc.), special offers, and contract terms.

[1511] Step 6:

[1512] The server performs the analysis using the AI ​​model

[1513] The server analyzes the aforementioned user data, the acquired plan information, and emotional data using machine learning algorithms, including k-nearest neighbors, decision trees, and random forests, to predict the optimal energy provider and plan for the user's consumption pattern and emotional state.

[1514] Step 7:

[1515] The server generates the analysis results

[1516] The server simulates multiple scenarios based on the analysis results, compares the cost performance of each plan, and generates a list of the most suitable power companies and plans for the user as a customized proposal that also reflects emotional data.

[1517] Step 8:

[1518] The server sends the proposal results to the device.

[1519] The server then sends the generated recommendation results to the device, which include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state.

[1520] Step 9:

[1521] The terminal receives and displays the results

[1522] The device visually displays the results of the proposals received from the server to the user. The user can view detailed information about each plan, along with suggestions and comments based on emotional data. For example, a user experiencing high stress may be recommended a relaxing energy-saving plan.

[1523] Step 10:

[1524] The user selects a plan

[1525] The user selects the plan that he or she thinks is best suited to him or her from the proposed plans.

[1526] Step 11:

[1527] The device sends the selection information to the server

[1528] The user's selection is sent to the server by the device, which then makes another API call to securely transmit the selection to the server.

[1529] Step 12:

[1530] The server records the selection information

[1531] The server stores the received selections in a database, which is used as feedback data to improve future analysis and train the emotion engine.

[1532] Example 2

[1533] 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."

[1534] Conventional systems for recommending power companies and service menus only consider the user's past electricity usage information and condition parameters, and have the problem of being unable to provide customized proposals that reflect the user's emotional state. This makes it difficult to provide optimal service plans that match the user's emotions and lifestyle.

[1535] 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 receiving past power usage information and condition parameters from the user, means for analyzing the user's facial expressions and voice to recognize the user's emotional state, means for referencing a database of multiple power companies and their service menus based on the received information and emotional state data, means for analyzing the information, emotional data, and database using a machine learning algorithm to identify the power company and service menu that are optimal for the user, means for presenting the identified power company and service menu to the user, means for generating and presenting comments and advice based on the user's emotional state, and means for recording information selected by the user and using it to improve future analysis accuracy. This makes it possible to suggest the optimal power company and service menu that takes the user's emotional state into consideration.

[1536] "User" refers to an individual or household who uses the system to receive an electricity plan proposal.

[1537] "Past electricity usage information" refers to data regarding the amount of electricity a user has consumed in the past, including detailed usage history over a specific period of time (e.g., the past 12 months).

[1538] "Condition parameters" refer to information related to the user's household structure and lifestyle patterns, and include, for example, the number of family members, the amount of time spent at home, and frequently used electrical appliances.

[1539] "Means for recognizing an emotional state by analyzing facial expressions and voice" refers to technology that captures a user's facial expressions with a camera, records their voice with a microphone, and analyzes them to recognize the user's current emotional state.

[1540] "Means for referencing a database" refers to a technology for accessing a database that stores information about multiple electric power companies and their service menus, and obtaining the necessary data.

[1541] "Machine learning algorithms" refer to algorithms that use statistical methods and computational models to learn patterns from data and make predictions or classifications for future data. Examples include k-nearest neighbors, decision trees, and random forests.

[1542] "Means for identifying" refers to technology that uses machine learning algorithms to select the electricity company and service menu that best suits the user's conditions and emotional state.

[1543] The "means for presenting" refers to a technique for displaying the identified power company and service menu to the user, and includes, for example, a function for displaying information on the screen of a terminal.

[1544] "Means for generating and presenting comments and advice" refers to a technology for generating customized comments and advice based on the recognized emotional state of the user and displaying them to the user.

[1545] "Means for recording and using to improve the accuracy of future analysis" refers to technology that stores the plan selected by the user and its results in a database, and uses this data to improve the accuracy of the machine learning model and the performance of the entire system.

[1546] This invention is a system that proposes the most suitable power company and service menu by analyzing the user's emotional state in addition to their past electricity usage information, household configuration, and lifestyle patterns. This system is realized through the cooperation of the user, terminal, server, and emotion engine.

[1547] User operations

[1548] Users access the system using a smartphone or PC at home. The initial screen displays a form for users to enter their electricity usage over the past 12 months, the name of their current electricity provider and plan, household composition (e.g., two adults, two children), and lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, and frequently used electrical appliances).

[1549] Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine analyzes their current emotional state. Specifically, facial recognition and voice analysis technologies are used to detect smiling and angry expressions, as well as voice tone and speed.

[1550] Terminal handling

[1551] The device verifies the user-entered historical power usage information and condition parameters, and transmits them along with the emotion data acquired by the emotion engine to the server, using an API call and encryption technology such as HTTPS to ensure secure transmission of the data.

[1552] Server Processing

[1553] The server receives the user data and emotion data sent from the device and stores them in a database. After storing them, it retrieves detailed information about the electricity company and its plan (e.g., basic charge, metered charge, time-of-use charge, special offer information, contract terms, etc.) from the database.

[1554] The server then uses machine learning algorithms (e.g., k-nearest neighbors, decision trees, random forests, etc.) to analyze the user's past electricity usage information, condition parameters, and emotional data, and predicts the electricity provider and plan that best suits the user's consumption pattern and emotional state.

[1555] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan. Based on the analysis and simulation results, the server generates proposals and adds customized comments and advice that take into account emotional data.

[1556] Presentation of proposed results

[1557] The server then sends the generated proposal results to the device. The proposal results include a price estimate, reasons for the recommendation (e.g., cost savings, a plan that suits your usage pattern, etc.), and customized comments and advice based on emotional data. For example, a user who is feeling stressed may be recommended an energy-saving plan that helps them relax.

[1558] User Choice and Feedback

[1559] The user selects the plan they think is best from the presented options. The device sends the selection results to the server, which stores them in a database. This feedback data is used to improve the accuracy of analysis and train the emotion engine in the future.

[1560] Examples of specific examples and prompts

[1561] Specific examples

[1562] User A accesses the system and enters the following information:

[1563] Electricity usage for the past 12 months: 600kWh / month

[1564] Current plan: X Electric Company Y Plan (pay-as-you-go)

[1565] Family composition: 2 adults, 1 child

[1566] Lifestyle: Both spouses work, at home after 6pm on weekdays, main appliances are an air conditioner and a refrigerator

[1567] Facial expression and voice analysis results: fatigue, slow voice

[1568] Based on this information, the system suggests a plan from Power Company Z, which has low off-peak rates, as the optimal plan, and provides customized advice such as, "Since you use a lot of electricity at night, a plan with low off-peak rates would be best. Also, make sure to use eco mode when you're tired."

[1569] Prompt Sentence Examples

[1570] "Please enter the user's electricity usage over the past 12 months, their current electricity contract plan, household composition and lifestyle patterns. The system will also estimate their emotional state from facial expressions and voice recordings made by the device's camera and microphone, and suggest the optimal electricity plan."

[1571] As described above, the system of the present invention can efficiently provide an optimal power plan based on the user's power usage pattern and emotional state.

[1572] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1573] Step 1:

[1574] User Data Entry

[1575] Users access the system using a smartphone or PC. They input their electricity usage over the past 12 months, their current electricity provider and plan name, household composition, and lifestyle patterns. The input data is temporarily stored in the device's local storage.

[1576] Input: electricity usage for the past 12 months, current electricity company and plan name, household composition, lifestyle patterns

[1577] Output: User data stored in the device's local storage

[1578] Step 2:

[1579] Acquiring emotion data

[1580] The device's camera and microphone are used to collect the user's facial expressions and voice data. The collected data is analyzed in real time by an emotion engine within the device. Facial recognition and voice analysis technologies are used to identify emotional states such as smile, anger, voice tone, and speed.

[1581] Input: Facial expression and voice data via camera and microphone

[1582] Output: Parsed emotional state data

[1583] Step 3:

[1584] Validating and submitting data

[1585] The device verifies the power usage information and condition parameters entered by the user. It checks the format and range to ensure the data is in the correct format. At the same time, it also verifies the emotion data and sends it to the server via an API. The data is transmitted securely using encryption technologies such as HTTPS.

[1586] Input: User data, emotional state data

[1587] Output: Validated data sent to the server

[1588] Step 4:

[1589] Receiving and storing data

[1590] The server receives the user data and emotional state data sent from the device and stores them in a database. Once stored, the server checks the data to ensure its consistency and completeness.

[1591] Input: User data and emotional state data sent from the device

[1592] Output: User data and emotional state data stored in a database

[1593] Step 5:

[1594] Obtaining electricity plan information

[1595] The server retrieves information about currently available energy plans (e.g., rate structures, special offers, contract terms, etc.) from a database, which may also include retrieving data from external APIs.

[1596] Input: User data and emotional state data

[1597] Output: Obtained electricity plan information

[1598] Step 6:

[1599] Analysis using machine learning algorithms

[1600] The server inputs user data, emotional state data, and the acquired power plan information and analyzes them using machine learning algorithms (such as k-nearest neighbors, decision trees, and random forests). As a result of the analysis, the optimal power plan for the user is identified.

[1601] Input: User data, emotional state data, power plan information

[1602] Output: Optimal power plan information

[1603] Step 7:

[1604] Scenario simulation

[1605] The server simulates multiple scenarios based on the analysis results and evaluates the cost performance of each plan, thereby determining the optimal plan.

[1606] Input: Analysis results (optimal power plan information)

[1607] Output: Simulation results and evaluation data

[1608] Step 8:

[1609] Generate and send proposal results

[1610] The server generates suggestions based on the simulation results, adds comments and advice based on the emotional state data, and sends the suggestions to the device via API.

[1611] Input: Simulation results and evaluation data

[1612] Output: Suggestion results and customized advice sent to your device

[1613] Step 9:

[1614] Displaying the proposed results

[1615] The device displays the proposal results received from the server to the user, including price estimates, detailed plan information, and comments and advice based on emotion data.

[1616] Input: Suggested results and customized advice sent from the server

[1617] Output: Suggestion results displayed in the user interface

[1618] Step 10:

[1619] User Choice and Feedback

[1620] The user selects the plan they think is best from the presented options. The selection results are sent to the server via the device and stored in a database. The feedback data will be used to improve the accuracy of analysis and train the emotion engine.

[1621] Input: User selection

[1622] Output: Feedback data stored in a database

[1623] This series of processing steps enables the system to efficiently propose an optimal power plan to the user.

[1624] (Application example 2)

[1625] 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."

[1626] The main function of conventional energy plan proposal systems was to provide optimal plans based on parameters such as the user's past energy usage information, household configuration, and lifestyle patterns. However, these systems did not take into account the user's emotional state, which limited the ability to improve the user experience and customize proposals. In particular, in physical stores, the inability to make proposals based on the customer's emotions was a major problem.

[1627] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1628] means for receiving historical power usage information and condition parameters from a user;

[1629] a means for referencing a database of a plurality of power supply companies and service plans of each power supply company based on the received information;

[1630] means for analyzing the information and database using machine learning algorithms to identify the most suitable electricity supplier and service plan for the user;

[1631] means for presenting the identified electricity supplier and service plan to a user;

[1632] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1633] means for recognizing a user's current emotional state and customizing a recommended service plan based on the emotional state;

[1634] This makes it possible to propose an optimal power plan according to the user's emotional state.

[1635] "Past electricity usage information" refers to data on the electricity used by a user over a certain period of time (e.g., the past 12 months).

[1636] "Condition parameters" refer to information indicating factors that affect power consumption, such as a user's lifestyle patterns and household configuration.

[1637] "Electricity supplier" means a company or entity that supplies electricity to users.

[1638] "Service plan" refers to the various contract menus and rate plans offered by electricity suppliers.

[1639] "Database" refers to a system that systematically stores information about electricity suppliers and service plans.

[1640] "Machine learning algorithms" refer to computational techniques used to analyze data and recognize patterns.

[1641] "Emotional state" refers to the user's current state of mind, such as joy, sadness, anger, etc., and is recognized from facial expressions and voice.

[1642] "Camera" refers to an image capturing device for recognizing a user's facial expressions.

[1643] "Microphone" refers to a voice capture device for capturing a user's voice and analyzing their emotional state.

[1644] "Real-time" refers to processing and analysis occurring immediately, without delay.

[1645] "Receiving power usage information" refers to the system receiving data regarding power usage provided by a user.

[1646] "Plan customization" refers to the process of adapting the service plan provided based on the user's individual requirements and emotional state.

[1647] "Proposal presentation" refers to the system displaying or notifying the user of the optimal power plan based on the analysis results.

[1648] The present invention is a system for proposing an optimal power plan to a user by utilizing power usage information and emotional state. This system is composed of the following components:

[1649] User operations

[1650] Users access the system using devices such as smart glasses, smartphones, or PCs. On the initial screen, users enter the following information:

[1651] Electricity usage over the past 12 months

[1652] Your current electricity provider and plan name

[1653] Family composition (e.g., 2 adults, 2 children)

[1654] Lifestyle patterns (e.g., whether both spouses work, how much time they spend at home, frequently used electrical appliances, etc.)

[1655] Furthermore, the smart glasses' camera and microphone are used to analyze the user's facial expressions and voice, and the emotion engine recognizes the user's current emotional state.

[1656] Terminal handling

[1657] The device verifies the entered power usage information and condition parameters. At the same time, it sends this data, including the emotion data acquired by the emotion engine, to the server. At this time, an API call is made and the data is securely transmitted.

[1658] Server Processing

[1659] The server receives the user data and emotion data sent from the device and stores them in a database. Next, the server retrieves detailed information about the electricity supplier and its plans from the database, including each plan's fee structure (basic fee, metered fee, time-of-use fee, etc.), special offers, and contract terms.

[1660] Using machine learning algorithms (k-nearest neighbors, decision trees, random forests, etc.), the server analyzes the user's electricity usage information, condition parameters, and emotional data. The optimal electricity provider and plan are predicted based on the user's consumption patterns and emotional state.

[1661] The server then simulates multiple scenarios based on the analysis results and compares the cost performance of each plan.The results of this analysis are then generated as a customized proposal, which is provided to the user in a format that takes into account emotional data.

[1662] Presentation of proposed results

[1663] The server then sends the generated proposal to the device. The proposal includes a price estimate, reasons for the recommendation (e.g., cost savings, plan suitable for usage patterns, etc.), and customized comments and advice based on the user's emotional state. For example, a user experiencing high stress may be recommended an energy-saving plan that helps them relax.

[1664] User Choice and Feedback

[1665] The user selects the plan they think is best from the proposed options. The device then sends the user's selection to the server, which stores the received selection in a database and uses it as feedback data for future AI model accuracy improvements and emotion engine training.

[1666] Specific examples

[1667] When a customer visits a physical store, a sales associate wearing smart glasses can analyze the customer's facial expressions and voice to recognize their "confused" emotional state in real time. Based on this, the sales associate can provide a friendly explanation and recommend the optimal energy plan. This improves the user experience and enables suggestions tailored to individual needs.

[1668] Prompt Sentence Examples

[1669] Use the following prompts to generate code for an application that improves customer support in brick-and-mortar stores.

[1670] Prompt statement:

[1671] Your goal is to generate an application program that uses smart glasses to analyze a customer's emotional state and suggest appropriate products and services. Specific technologies used include TensorFlow, Flask, and OpenCV. Analyze emotions from the customer's facial expressions, receive the results on the server, and provide customized suggestions in real time.

[1672] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1673] Program processing steps

[1674] Step 1:

[1675] Users access the system using smart glasses or a smartphone and input condition parameters such as past power usage information, household composition, and lifestyle patterns.Facial expression and voice data are also acquired through the smart glasses' camera and microphone.This allows the system to collect "power usage information," "condition parameters," "facial expression data," and "voice data" as input from the user.

[1676] Step 2:

[1677] The device transmits the information input by the user and the acquired emotion data to the server. The transmitted data includes power usage information, condition parameters, facial expression data, and voice data. This data is securely transferred to the server using an API.

[1678] Step 3:

[1679] The server stores the received data in a database for analysis. The database contains detailed information about the electricity supplier and each plan (such as rate structure, benefit information, and contract terms). The input is "user data (electricity usage information, condition parameters, facial expression data, and voice data)," and the output is "a dataset for analysis."

[1680] Step 4:

[1681] The server processes the analysis dataset using a machine learning algorithm. This analyzes the user's electricity consumption patterns and emotional state, and based on this, predicts the optimal electricity supplier and plan. Algorithms used include k-nearest neighbors, decision trees, and random forests. The input is the "analysis dataset," and the output is the "prediction of the optimal plan."

[1682] Step 5:

[1683] The server simulates multiple scenarios based on the predicted optimal plan and compares the cost performance of each plan. This generates a customized proposal that also takes emotional data into account. The input is the "predicted optimal plan" and the output is the "customized proposal."

[1684] Step 6:

[1685] The server sends the generated recommendation results to the device. The recommendation results include a price estimate, the reason for the recommendation, and customized comments and advice based on the user's emotional state. The input is the "customized recommendation results," and the output is the "data sent to the device."

[1686] Step 7:

[1687] The terminal displays the proposal results received from the server to the user. The user can select the plan that they think is best from the proposed plans. The user's selection results are sent from the terminal to the server, which then stores them in a database. The inputs are the "proposal results" and the "user's selection results," and the output is the "database storage of the selection results."

[1688] Step 8:

[1689] The server uses the received selection results as feedback data for improving analysis accuracy and for learning the emotion engine. The input is the "selection result" and the output is "updated feedback data."

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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).

[1697] 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.

[1698] 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."

[1699] 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.

[1700] 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).

[1701] 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.

[1702] 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.

[1703] 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.

[1704] 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.

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] The following is further disclosed regarding the above embodiment.

[1712] (Claim 1)

[1713] means for receiving historical power usage information and condition parameters from a user;

[1714] a means for referencing a database of a plurality of electric power companies and their service menus based on the received information;

[1715] A means for analyzing the information and database using a machine learning algorithm to identify the optimal power company and service menu for the user;

[1716] means for presenting the identified electric power company and its service menu to a user;

[1717] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1718] A system including:

[1719] (Claim 2)

[1720] 2. The system of claim 1, wherein the machine learning algorithm used to analyze a user's power consumption pattern is a k-nearest neighbor algorithm, a decision tree, or a random forest.

[1721] (Claim 3)

[1722] 2. The system according to claim 1, wherein the power company and service menu presented to the user includes a rate estimate and a reason for the recommendation.

[1723] "Example 1"

[1724] (Claim 1)

[1725] means for receiving historical power usage information and condition parameters from a user;

[1726] means for referencing a database of a plurality of power suppliers and rate plans of each power supplier based on the received information;

[1727] means for analyzing said information and database using machine learning algorithms to identify the most suitable electricity supplier and rate plan for the user;

[1728] means for presenting the identified electricity supplier and rate plan to a user;

[1729] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1730] A means for verifying user data at the device and transmitting it securely to a server;

[1731] A means for comprehensively analyzing user data and information from electricity suppliers on a server and evaluating the cost performance of plans using simulations;

[1732] A system including:

[1733] (Claim 2)

[1734] 2. The system of claim 1, wherein the machine learning algorithm used to analyze a user's power consumption pattern is a k-nearest neighbor algorithm, a decision tree, or a random forest.

[1735] (Claim 3)

[1736] 10. The system of claim 1, wherein the electricity supplier and rate plan presented to the user includes a rate quote and a reason for the recommendation.

[1737] "Application Example 1"

[1738] (Claim 1)

[1739] means for receiving historical energy usage information and condition parameters from a user;

[1740] A means for referencing a database of a plurality of energy suppliers and service menus of each energy supplier based on the received information;

[1741] A means for analyzing the information and database using a machine learning algorithm to identify the most suitable energy supplier and service menu for the user;

[1742] means for presenting the identified energy supplier and a service menu to a user;

[1743] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1744] A means for the factory robot to collect energy consumption data in real time and transmit it to a cloud server;

[1745] A cloud server analyzes the energy consumption data and recommends an optimal energy supplier and service menu;

[1746] means for displaying the recommendation results to a factory manager;

[1747] A system including:

[1748] (Claim 2)

[1749] The system of claim 1, wherein the machine learning algorithm used to analyze the user's energy consumption pattern is k-nearest neighbor, decision tree, or random forest.

[1750] (Claim 3)

[1751] 2. The system of claim 1, wherein the energy supplier and service menu presented to the user includes a price estimate and reasons for the recommendation.

[1752] "Example 2: Combining Emotion Engines"

[1753] (Claim 1)

[1754] means for receiving historical power usage information and condition parameters from a user;

[1755] means for analyzing the facial expression and voice of the user to recognize the emotional state of the user;

[1756] a means for referencing a database of a plurality of electric power companies and their service menus based on the received information and emotional state data;

[1757] A means for analyzing the information, emotion data, and database using a machine learning algorithm to identify the optimal power company and service menu for the user;

[1758] means for presenting the identified electric power company and its service menu to a user;

[1759] means for generating and presenting comments and advice based on the user's emotional state;

[1760] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1761] A system including:

[1762] (Claim 2)

[1763] 2. The system of claim 1, wherein the machine learning algorithm used to analyze a user's power consumption pattern is a k-nearest neighbor algorithm, a decision tree, or a random forest.

[1764] (Claim 3)

[1765] 2. The system according to claim 1, wherein the power company and service menu presented to the user includes a rate estimate and a reason for the recommendation.

[1766] "Application example 2 when combining emotion engines"

[1767] (Claim 1)

[1768] means for receiving historical power usage information and condition parameters from a user;

[1769] a means for referencing a database of a plurality of power supply companies and service plans of each power supply company based on the received information;

[1770] means for analyzing the information and database using machine learning algorithms to identify the most suitable electricity supplier and service plan for the user;

[1771] means for presenting the identified electricity supplier and service plan to a user;

[1772] a means for recording the user's selection and using it to improve the accuracy of future analyses;

[1773] means for recognizing a user's current emotional state and customizing a recommended service plan based on the emotional state;

[1774] A system including:

[1775] (Claim 2)

[1776] 2. The system of claim 1, wherein the machine learning algorithm used to analyze a user's power consumption pattern is a k-nearest neighbor algorithm, a decision tree, or a random forest.

[1777] (Claim 3)

[1778] 10. The system of claim 1, wherein the electricity supplier and service plan presented to the user includes a rate quote and reasons for the recommendation.

[1779] (Claim 4)

[1780] 10. The system of claim 1, further comprising means for performing emotion analysis using a camera and a microphone to analyze the user's facial expressions and voice. [Explanation of symbols]

[1781] 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. means for receiving historical power usage information and condition parameters from a user; A means for referencing a database of a plurality of electric power companies and their service menus based on the received information; A means for analyzing the information and database using a machine learning algorithm to identify the optimal power company and service menu for the user; means for presenting the identified electric power company and its service menu to a user; a means for recording the user's selection and using it to improve the accuracy of future analyses; A system including:

2. The system of claim 1 , wherein the machine learning algorithm used to analyze the user's power consumption pattern is a k-nearest neighbor algorithm, a decision tree, or a random forest.

3. The system according to claim 1 , wherein the power company and service menu presented to the user includes a price estimate and a recommendation reason.

Images