Information processing system

Abstract

The invention provides an information processing system. The information processing system comprises a means for collecting energy consumption data and CO2 emission data in real time through an IoT terminal; a means for storing and preprocessing the received data in the cloud server; a means for analyzing the preprocessed data by generative artificial intelligence and generating a renewable energy investment scheme; means for generating and presenting an investment plan report to a user.

Description

Technical Field

[0001] The technology disclosed herein relates to an information processing system. Background Technology

[0002] Japanese Patent Application Publication No. 2022-180282 discloses a method for controlling a role-based chatbot executed by at least one processor. The method includes the following steps: receiving a user's speech; adding the user's speech to a prompt word, the prompt word containing instruction statements associated with an explanation of the chatbot's role; encoding the prompt word; and inputting the encoded prompt word into a language model to generate a chatbot response to the user's speech.

[0003] Existing enterprises face challenges in managing energy consumption and CO2 emissions, including insufficient real-time data, low data accuracy, and a lack of scientifically sound tools to support renewable energy investment decisions. Specifically, enterprises struggle to effectively integrate energy and emissions data, detect anomalies, and perform automated analysis, thus hindering the achievement of energy efficiency improvement and CO2 reduction targets. Furthermore, the lack of quantitative analysis and return forecasting based on actual data when selecting renewable energy investments leads to somewhat arbitrary investment decisions and hinders the continuous optimization of energy management. Summary of the Invention

[0004] This invention provides an integrated system that includes real-time collection of enterprise energy consumption and CO2 emission data via IoT terminals, storage and preprocessing of the data on a cloud server, in-depth analysis of the preprocessed data using generative artificial intelligence to automatically generate renewable energy investment plans, and presentation of the investment plans to users in the form of reports. The system can also perform data consistency verification and outlier correction, continuously monitor and provide feedback on the actual operating performance of the renewable energy system, and improve data accuracy and decision-making scientificity through process automation and intelligent analysis methods, thereby effectively improving energy utilization efficiency and promoting the achievement of CO2 emission reduction targets.

[0005] "IoT terminal" refers to a smart device that can collect energy consumption data and CO2 emission data in real time through various sensors and send the data to a server.

[0006] "Energy consumption data" refers to quantitative information reflecting the electricity, gas, and other energy sources consumed by an enterprise during its production or operation.

[0007] "CO2 emission data" refers to numerical information about the carbon dioxide generated and released into the environment by enterprises during energy consumption or production processes.

[0008] "Cloud server" refers to a server system with network connectivity that can remotely receive, store, process, and analyze data from terminals.

[0009] "Data storage" refers to the operation of saving collected or received data in a database or storage medium for subsequent processing and analysis.

[0010] "Data preprocessing" refers to the process of cleaning, formatting, detecting anomalies, and completing raw data before data analysis to ensure data quality.

[0011] "Generative artificial intelligence" refers to an intelligent analysis system that uses deep learning algorithms to analyze input data and automatically generate conclusions or suggestions.

[0012] "Renewable Energy Investment Plan" refers to recommendations made by enterprises based on energy data and analysis results, suggesting the adoption of certain renewable energy equipment or systems and providing specific investment plans and return forecasts.

[0013] An "investment plan report" refers to an information carrier that compiles investment plans analyzed and recommended by generative artificial intelligence into documents or visual reports for users to review and make decisions.

[0014] "User" refers to enterprise managers or relevant responsible persons who use this system to view energy analysis results and investment recommendations, and make decisions based on system information.

[0015] "Data consistency verification" refers to the inspection and verification process that checks and verifies whether there are duplicates, errors, or omissions in the data during the collection, transmission, and storage process.

[0016] "Outlier correction" refers to adjusting or replacing data using appropriate methods when extreme or unreasonable values ​​are found, in order to ensure data accuracy.

[0017] "Renewable energy system" refers to a device or equipment that uses renewable resources such as solar energy, wind energy, and biomass energy for energy production, conversion, and utilization.

[0018] "Operational performance monitoring" refers to the process of continuously collecting and analyzing various operating parameters of a renewable energy system during actual use.

[0019] "Feedback" refers to the behavior of the system notifying users of performance improvement suggestions, maintenance tips, or optimization measures based on the analysis results. Attached Figure Description

[0020] Figure 1 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the first embodiment.

[0021] Figure 2This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0022] Figure 3 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the second embodiment.

[0023] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0024] Figure 5 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the third embodiment.

[0025] Figure 6 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and head-mounted terminal according to the third embodiment.

[0026] Figure 7 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the fourth embodiment.

[0027] Figure 8 This is a conceptual diagram illustrating an example of the main functions of the data processing device and robot according to the fourth embodiment.

[0028] Figure 9 This represents an emotion map that maps multiple emotions.

[0029] Figure 10 This represents an emotion map that maps multiple emotions.

[0030] Figure 11 This is a sequence diagram illustrating the processing flow of the data processing system of the first embodiment.

[0031] Figure 12 This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 1.

[0032] Figure 13 This is a sequence diagram illustrating the processing flow of the data processing system of the second embodiment.

[0033] Figure 14 This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 2. Detailed Implementation

[0034] Hereinafter, an example of an implementation of the system according to the present disclosure will be described with reference to the accompanying drawings.

[0035] First, let me explain the terminology used in the following instructions.

[0036] In the following embodiments, the processor (hereinafter referred to as "processor") with reference numerals may be a single computing device or a combination of multiple computing devices. Furthermore, the processor may be a single computing device or a combination of multiple computing devices. Examples of computing devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0037] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory that temporarily stores information and is used as working memory by the processor.

[0038] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices that store various programs and parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes.

[0039] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface that includes a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. As an example of a communication specification applicable to the communication I / F, wireless communication specifications such as 5G (5th Generation Mobile Communication System), Wi-Fi (wireless fidelity) (registered trademark), or Bluetooth (registered trademark) can be listed.

[0040] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects to express more than three items, the same interpretation as "A and / or B" applies.

[0041] First Implementation Method

[0042] Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0043] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. A server can be cited as an example of the data processing device 12.

[0044] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0045] The smart device 14 includes a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiving device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0046] The receiving device 38 includes a touchscreen 38A and a microphone 38B, and receives user input. The touchscreen 38A receives user input via touch by detecting contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input via sound by detecting the user's voice. The control unit 46A in the processor 46 sends data representing the user input received by the touchscreen 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data representing the user input.

[0047] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting data in a form perceptible to the user 20 (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0048] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0049] Figure 2 The diagram shows an example of the main functions of the data processing device 12 and the smart device 14.

[0050] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0051] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0052] In the smart device 14, the processor 46 performs the acceptance output processing. The memory 50 stores the acceptance output program 60. The acceptance output program 60 is used in conjunction with the data processing system 10 and the specific processing program 56. The processor 46 reads the acceptance output program 60 from the memory 50 and executes the read acceptance output program 60 on the RAM 48. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48. Furthermore, the smart device 14 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48.

[0053] Alternatively, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-held terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing of the data processing system 10 of the first embodiment will be described.

[0054] Example 1

[0055] The flow of a specific process in Example 1 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. Furthermore, the data processing device 12 is referred to as the "server," and the smart device 14 is referred to as the "terminal."

[0056] Existing enterprises generally face challenges in managing energy consumption and greenhouse gas emissions, including untimely data collection, low data quality, and an inability to make optimal renewable energy investment decisions based on real-time data. Furthermore, relying on manual analysis of large amounts of complex energy consumption and CO2 emission data makes it difficult to promptly output optimal investment plans, resulting in limited improvements in energy efficiency and carbon reduction. The lack of automated systems based on real-time data and intelligent analysis creates technological bottlenecks for enterprises in developing renewable energy investment plans and conducting subsequent operational monitoring and feedback.

[0057] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 1 is achieved by the following means.

[0058] In this invention, the server includes an information processing module for real-time on-site acquisition of energy resource usage and greenhouse gas emission-related observations via information acquisition devices; a data processing module for storing and preprocessing the observation data on a big data platform; an intelligent analysis module for automatically invoking a generative artificial intelligence model based on the preprocessed observations and prompts to perform time-series analysis, trend identification, and generation of optimal renewable energy investment solutions; a report generation and display module for generating structured reports based on the analysis results and displaying them to users via web pages or terminals; and a prompt generation module for automatically generating AI model prompts. This enables efficient, real-time acquisition and quality improvement of enterprise energy and emission data. Through intelligent algorithms, it automatically analyzes and outputs optimal renewable energy investment solutions, assisting enterprises in making accurate decisions. Simultaneously, it allows for subsequent monitoring and feedback of equipment operating efficiency, significantly improving energy utilization efficiency and carbon emission reduction effects.

[0059] "Information acquisition device" refers to sensing hardware equipment used to detect and acquire energy usage status and greenhouse gas emission values ​​in real time on site, including but not limited to electricity meters, gas flow meters, CO2 sensors, etc.

[0060] "Energy resource use related observations" refers to data obtained by information collection devices that reflect the amount of energy consumed, such as electricity, gas, and heat.

[0061] "Greenhouse gas emission-related observations" refer to data obtained by information collection devices, used to characterize the total emissions of greenhouse gases such as CO2 per unit time and per unit area.

[0062] "Information processing device" refers to a data processing component that receives, performs preliminary processing, and locally caches collected data. It can be a computing unit with communication and data integration functions.

[0063] A "big data processing platform" refers to an information infrastructure with large-capacity storage and high-speed computing capabilities, used to store, organize, and further process various types of observation data.

[0064] "Data quality improvement preprocessing" refers to the process of processing raw observation data through algorithms such as consistency verification, outlier detection, and missing value completion to ensure data accuracy and reliability.

[0065] "Generative artificial intelligence processing device" refers to an artificial intelligence computing unit that can automatically analyze and judge input data and generate investment optimization plans through methods such as deep learning.

[0066] "Prompt statements" refer to the text input content that guides generative artificial intelligence models to perform reasoning and generate for specific tasks. They usually contain key information such as the target and data background.

[0067] "Report output device" refers to the output unit responsible for outputting analysis results and investment plans in the form of structured reports (such as PDF, web pages, etc.) and providing access to users through terminals or networks.

[0068] The “data consistency and correction device” refers to a functional module that automatically performs consistency checks on input data and uses statistical methods to correct outliers and missing data.

[0069] "Operational efficiency monitoring" refers to the periodic collection and analysis of the actual performance indicators of deployed renewable energy utilization equipment to evaluate its operation and production capacity.

[0070] "Feedback device" refers to a system component that promptly transmits the results of operational efficiency monitoring back to the user in the form of data, reports, etc.

[0071] This invention provides a comprehensive energy data analysis and decision support system based on the collaborative operation of an information acquisition device, a server, a generative artificial intelligence model, and a user terminal. This system can achieve real-time data collection of energy and greenhouse gas emissions, intelligent data processing, automatic solution generation, and visualized result output. The following detailed description of the implementation of this invention, including hardware and software structure, specific operating steps, and application examples, provides further elaboration.

[0072] First, terminals (such as smart meters, gas flow meters, and CO2 sensors) are deployed at energy-consuming sites such as factory buildings and office areas. These data collection devices can continuously and in real-time obtain raw data such as electricity consumption, gas consumption, and CO2 emissions. The terminals embed microprocessors and IoT communication units (such as IoT modules supporting MQTT and HTTP protocols), which can automatically perform preliminary data encapsulation and storage, and securely upload the data to the server at set intervals.

[0073] After receiving data, the server (such as a general-purpose high-performance cloud server) uses a big data processing platform (such as a relational database management system and a distributed storage system) to store the data, and completes the data preprocessing through the data processing module (which can be a data cleaning script implemented in Python or a database built-in consistency verification tool), including consistency verification, outlier detection and correction, and missing data completion.

[0074] Subsequently, the server, through an integrated generative artificial intelligence model (such as a deployed OpenAI GPT-4 or equivalent model), invokes the data analysis and investment recommendation module. The server automatically constructs prompts based on the company's current energy and emissions situation and sends them to the generative artificial intelligence model interface. This enables time-series analysis of energy consumption and emissions trends, structural pattern mining, and the generation of optimal renewable energy investment plans based on the latest renewable energy market information. The model can output decision-making information including recommended equipment types, initial investment, payback period, expected energy efficiency improvements, and CO2 emission reduction benefits.

[0075] The server then automatically organizes the analysis results through the report generation module, integrating the solution content and statistical charts into a structured report. The report can be output as a PDF file or displayed in real time on a WebDashboard based on web technologies (such as React). Users (such as enterprise energy managers) can log in to the system platform via desktop computers, mobile devices, and other terminals to view, download, and share the report at any time, providing a strong basis for the scientific formulation of investment and energy conservation and emission reduction plans.

[0076] For example, after deploying this system, manufacturing company A automatically collects electricity consumption, gas consumption, and CO2 emission data from various energy-consuming points in the workshop every minute, sending them directly to the server via the MQTT protocol. Upon receiving the data, the server performs quality improvement and consistency maintenance, and periodically calls a generative artificial intelligence model for analysis according to business requirements. The analysis output might include an investment plan such as, "It is recommended to introduce a 300 kW solar power system in the eastern area, which is expected to reduce annual energy consumption by 5%, with a payback period of 6 years and an annual CO2 emission reduction of 80 tons." The report is automatically pushed to users via the Web Dashboard, facilitating management decisions based on actual needs.

[0077] Here are some examples of prompts for generative artificial intelligence models:

[0078] "Based on Company X's energy consumption and CO2 emission data, please generate the optimal renewable energy investment plan. Given that the average monthly electricity consumption is 100,000 kWh, gas consumption is 20,000 cubic meters, and annual CO2 emissions are 2,400 tons, please refer to the latest renewable energy industry trends."

[0079] In summary, this system, through IoT information collection devices, server-side big data and artificial intelligence algorithms, automated reporting modules, and a user-friendly interface, has achieved an innovative digital solution for energy and carbon management, effectively improving energy efficiency and promoting the green and low-carbon transformation of enterprises.

[0080] use Figure 11 The processing procedure is explained.

[0081] Step 1:

[0082] The terminal collects real-time raw data on a company's electricity consumption, gas usage, and CO2 emissions through information acquisition devices such as smart meters, gas flow meters, and CO2 sensors. The input is the values ​​collected by various sensors, and the output is a packaged raw data packet. The terminal locally caches the data collected every minute and periodically checks the data integrity.

[0083] Step 2:

[0084] The terminal uploads cached raw energy and CO2 data to the server via the communication module using MQTT or HTTP protocols. The input is locally cached data packets, and the output is a data stream sent to the server over the network. The terminal checks network connectivity at set time intervals, sending data in batches when a connection is available, and automatically retrying if a transmission fails.

[0085] Step 3:

[0086] The server receives data sent from the terminal, parses the data packets through an API interface, and stores the data in a big data processing platform (such as a relational database). The input is the received data stream, and the output is the formatted data saved in the database. The server performs operations such as JSON parsing and data format validation to ensure successful data storage and records the reception status in the logs.

[0087] Step 4:

[0088] The server performs data quality improvement and preprocessing on the raw data stored in the database, including consistency checks, outlier correction, and missing data completion. The input is the raw records in the database, and the output is the preprocessed, high-quality data. The server uses SQL scripts or automated data cleaning tools to detect errors and outliers, and performs statistical corrections and data completion.

[0089] Step 5:

[0090] Based on preprocessed energy and CO2 data, the server automatically generates prompts for a generative AI model. It then uses the data and prompts as input to call upon the generative AI model (such as GPT-4) for data analysis. The input consists of high-quality energy and emissions data and the constructed prompts; the output is AI-generated investment recommendations and analysis results. The server is responsible for dynamically constructing the prompts (e.g., "Please generate the optimal renewable energy investment plan based on the company's historical energy consumption and CO2 emission data") and uploading the data to the AI ​​interface.

[0091] Step 6:

[0092] The server post-processes the suggestions output by the generative AI model, automatically extracting the optimal renewable energy investment plan, including details such as suggested equipment type, investment amount, payback period, and expected carbon emission reduction. The input is the analysis text returned by the AI, and the output is structured investment plan data. The server uses a semantic extraction algorithm to break down the suggestions into actionable structured fields.

[0093] Step 7:

[0094] Based on the structured investment plan, the server automatically generates a visual report (such as a PDF document or a web dashboard) through the report generation module, and pushes or displays it to the user. The input is structured investment plan data, and the output is a visual report file that users can view and download. The server calls a chart generation tool to draw trend curves and comparison charts, and displays the report content through a web front-end component.

[0095] Step 8:

[0096] Users access the system via web dashboards or mobile devices to view the latest investment reports pushed by the server. Input is a visual report file, and output is user-readable report content and decision-making basis. Users can view detailed recommendations, download reports, or share relevant data with other decision-makers within the system interface to aid in decision-making.

[0097] Application Example 1

[0098] The process flow corresponding to the specific processing in Use Case 1 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. Furthermore, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0099] Existing energy management systems, in large-scale industrial and infrastructure scenarios, suffer from several shortcomings in data collection and analysis of energy consumption and carbon dioxide emissions. These include insufficient real-time performance, inadequate handling of data anomalies, a disconnect between information presentation and actual user experience, and insufficient support for subsequent green energy investment decisions. Consequently, achieving a harmonious balance between energy efficiency optimization and environmental friendliness remains challenging. Furthermore, current technologies lack the ability to recognize and integrate user emotional states, resulting in limited targeted intelligent recommendations and low decision-making reliability. Therefore, providing a system capable of real-time collection of various physical quantity data and continuously optimizing energy investment and management processes through intelligent data processing, natural language generation model analysis, user emotion recognition, and personalized information display has become a pressing technical challenge.

[0100] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is achieved by the following means.

[0101] In this invention, the server includes an information acquisition module, a data storage and preprocessing module, a natural language generation model analysis module, a user status recognition and adaptive information display module, and an energy management and feedback module. This enables real-time acquisition and automated transmission of various physical quantity data, ensuring data consistency and accuracy; improves the reliability of subsequent analysis by performing format verification, tagging, and anomaly correction on raw data; utilizes generative artificial intelligence models to perform deep semantic mining on the data, automatically outputting optimized energy utilization and investment recommendations; intelligently identifies user psychological states by combining user information and biometrics, and dynamically adjusts the information display method to improve information acceptability and decision-making efficiency; and supports continuous monitoring and effect tracking after investment implementation, forming a complete closed-loop intelligent energy management system.

[0102] "Information acquisition device" refers to hardware or software equipment used to acquire data on various physical quantities, including electricity, gas, temperature, and carbon dioxide emissions, from the physical environment in real time and to perform preliminary processing or packaging.

[0103] "Physical quantity data" refers to digital information that reflects actual measured parameters such as energy consumption, emissions, temperature, and pressure in the monitored environment.

[0104] "Data communication network" refers to wired or wireless communication infrastructure used to enable long-distance data transmission between various information devices, including the Internet, local area network, 4G / 5G, etc.

[0105] "Information processing device" refers to a computer, server, or equivalent software system that stores, converts, tags, preprocesses, and performs subsequent intelligent analysis on data received from the acquisition device.

[0106] "Data storage" refers to the process or apparatus of storing received raw or processed data into a database, file, or other electronically readable medium for later retrieval.

[0107] "Data tag" refers to an additional field in the data record structure used to identify metadata such as the object being collected, its location, time, and type.

[0108] "Data preprocessing" refers to the process of cleaning, format verification, missing data completion, and outlier correction of collected data to improve data quality.

[0109] "Format verification" refers to the process of checking whether data conforms to predetermined rules in terms of structure and content.

[0110] "Data correction" refers to the processing actions of supplementing, replacing, or correcting detected abnormal, missing, or noisy data.

[0111] "Outlier correction" refers to the process of automatically adjusting or replacing data points that are far from the normal range or have abnormal statistical distributions in order to improve the overall accuracy of the data.

[0112] "Natural language generation model" refers to an artificial intelligence algorithm or software system based on machine learning and deep learning technologies that can understand input structured data and automatically output natural language text content.

[0113] "Information analysis" refers to the process of using specific algorithms and models to calculate and process continuous or batch data, and to uncover trends, patterns, and correlations to support decision-making.

[0114] "Energy utilization optimization recommendations" refer to suggested solutions for improving energy efficiency and reducing emissions, based on collected and analyzed data, combined with industry standards and predictive models.

[0115] "Evaluation data" refers to a collection of documents or data that archives, categorizes, and presents the recommendations in detail based on methods, indicators, and expected results.

[0116] "Display device" refers to hardware or software equipment that can visually output data, reports, charts, and alarms to user terminals, including displays, head-mounted displays, etc.

[0117] "Real-time alarm notification" refers to the function of automatically sending prompts or warning messages to users when relevant monitoring data is abnormal or reaches the warning threshold.

[0118] "User information data" refers to digital data that reflects a user's identity, role, permissions, historical behavior, and other personal or organizational attributes.

[0119] "Bioinformatics data" refers to physiological or behavioral data derived from users, including facial expressions, voice characteristics, heart rate, body temperature, and other data.

[0120] "Psychological state inference" refers to the process of using intelligent models to identify and classify a user's current preferences, interests, emotions, concentration, and other internal psychological activities.

[0121] "Automatic adjustment of information display content" refers to the operation of dynamically configuring the content, display method, and interaction method pushed by the system based on the user's status and preferences.

[0122] The "user interface" refers to the software and hardware interface through which users interact with the system, display information, and input commands, including consoles, web pages, and mobile applications.

[0123] "Input instructions" refer to the operational information entered by the user through the user interface, including commands, data, voice, gestures, etc.

[0124] "Emotional feature output response" refers to the system's function of automatically adjusting feedback content, text, interface style, etc., to provide personalized output based on the user's emotions and feedback.

[0125] "Energy efficiency change tracking" refers to the real-time collection, recording, and trend analysis of key indicators such as energy consumption and emissions after the implementation of measures.

[0126] "Environmental load change tracking" refers to the continuous monitoring and analysis of environmental impacts, including emissions of greenhouse gases such as carbon dioxide.

[0127] "Feedback device" refers to the software and hardware module that returns the tracking and analysis results or suggestions to the user through display, reporting, push, or other means.

[0128] The embodiments of the present invention are described below.

[0129] This invention relates to an energy management system based on intelligent data processing and a generative artificial intelligence model. The system mainly includes a terminal (information acquisition device), a server (information processing and analysis device), and a terminal (display device / user interface) providing information display and interaction for users. The following details the various components, optional configurations, hardware and software tools used, data processing methods, and specific application examples of this invention to ensure its feasibility and scalability.

[0130] First, the terminal is deployed within factories, buildings, or other facilities, integrating various physical quantity sensors (such as electricity metering devices, gas meters, CO2 gas detectors, etc.). It can utilize an STM32 series embedded controller and supports data communication protocols such as ZigBee, LoRa, Ethernet, and WIFI. The terminal periodically (e.g., every minute) collects data on various energy consumption and emissions, adds device identifiers and timestamps, and then packages and transmits the raw or pre-processed data to a cloud server via a data communication network (such as 4G / 5G, Ethernet, etc.).

[0131] The recommended server-side architecture includes high-performance general-purpose computers, cloud servers, and edge computing gateways, capable of running Linux operating systems and databases (such as MySQL and MongoDB), data processing software (such as a Python environment combined with libraries like Pandas, NumPy, and Scikit-learn), and natural language generation model APIs (such as GPT-4 and Wenxin Yiyan). The server performs validation, formatting, tagging, missing value correction, and outlier detection on the data sent from the terminal. After data processing, the server constructs prompts to input the structured data into a generative artificial intelligence model, enabling automated information analysis, energy management trend prediction, and optimal solution recommendations.

[0132] For example, the server can generate the following prompt statement and submit it to the AI ​​model for energy utilization optimization and investment advice production:

[0133] "Please analyze the energy consumption and CO2 emission trends of the following factory zones, and based on current global renewable energy technologies and rates of return, develop an optimal green energy investment plan for the factory, including recommended equipment types, estimated investment, energy saving and emission reduction benefits."

[0134] or

[0135] "Based on the real-time energy consumption and CO2 emissions data of Factory A in various regions over the past month, please analyze the current energy consumption trend and generate the optimal renewable energy investment portfolio plan in combination with industry best practices. You need to provide equipment recommendations, energy saving and emission reduction forecasts, initial investment and expected return time."

[0136] Based on the natural language results returned by the AI ​​model and combined with the economic analysis module in the database, the server automatically generates a detailed report document that includes investment equipment recommendations, energy consumption reduction, CO2 emission reduction effects, equipment model selection, estimated investment capital, and investment payback period. This report can be presented in various formats such as PDF, HTML, and interactive dashboards; the server also supports visualization functions such as real-time chart displays, trend forecasts, and regional comparisons.

[0137] In addition, the system is equipped with a user status recognition and adaptive display module. The display device collects user facial expressions, voice, and other biometric signals through cameras, microphones, etc., and the server calls sentiment analysis APIs (such as Azure Sentiment Cognition and Baidu Sentiment Cloud) to analyze user emotions. Based on this, the server intelligently adjusts report descriptions, emphasizes key information, and enhances the interactive experience. If it detects that the user has doubts about investment risks, it automatically supplements the report with economic case analysis or chart explanations to improve user understanding and satisfaction.

[0138] Users can log in via head-mounted displays (such as smart glasses), PC interfaces, mobile apps, or other terminals to intuitively view real-time energy consumption data, view automated feedback reports, perform multi-modal interactions such as voice, text, or gestures, confirm and export reports, and provide feedback on the results.

[0139] For example, if a user discovers an abnormally high level of CO2 emissions from a production workshop on the energy management platform, the system automatically pushes analysis and control suggestions. Alternatively, a user can request a voice command to "display a comparison of the energy-saving and economic benefits of solar energy investments over the past three years." The system automatically invokes AI output and adjusts the display interface to ultimately assist the user in making decisions and developing implementation plans.

[0140] This system enables real-time, precise management of energy consumption and environmental impact. By fully integrating generative artificial intelligence models and an emotion engine, it intelligently and personally delivers the best investment advice and management strategies, greatly improving decision-making efficiency, energy conservation and carbon reduction, and user experience.

[0141] use Figure 12 The processing procedure is explained.

[0142] Step 1:

[0143] The terminal, through integrated energy consumption sensors and gas detection modules, collects real-time data on physical quantities such as electricity consumption, gas usage, and CO2 emissions in various areas of a factory or building. The input is the raw data collected by each sensor. The terminal packages the collected data, adds a device ID, timestamp, and partition tag, and automatically sends it to the server via wired or wireless communication networks (such as Wi-Fi, 4G, and Ethernet) as output.

[0144] Step 2:

[0145] The server receives data packets from the terminal, with the input being raw energy consumption and emissions data uploaded by the terminal. The server first stores the data, simultaneously performing format validation and data tag parsing to check the validity of values ​​and the completeness of fields. The server then outputs structured raw data records to the database, recording the data reception time and status.

[0146] Step 3:

[0147] The server performs batch preprocessing on the raw data in the database, with the input being stored structured energy consumption and emissions data. The server uses data processing software (such as Python's Pandas library) to check for outliers and missing values, automatically performing data repair, such as filling out outliers with pre- and post-means, and adding correction information to the data. The output is a cleaned and labeled dataset.

[0148] Step 4:

[0149] Based on the cleaned data, the server constructs generative AI model prompts tailored to specific business scenarios. The input consists of processed energy consumption, CO2 time-series data, and partition information. The server calls generative AI model APIs (such as GPT-4 and Wenxin Yiyan), uploading the prompts along with the data for analysis. Based on the input data and prompts, the server outputs energy utilization trend analysis and investment optimization suggestions in natural language text format.

[0150] Step 5:

[0151] The server analyzes and interprets the output and suggestions from the generative artificial intelligence model, with AI-generated text content and auxiliary data as input. The server integrates relevant data and automatically generates an evaluation report, including recommended equipment types, investment amounts, energy-saving and emission-reduction effects, and investment payback period. The output is a complete investment analysis report, which can be generated in various formats such as PDF or HTML.

[0152] Step 6:

[0153] The server pushes the generated reports and related real-time data to the user through a user-end display device (such as a head-mounted display, PC, or mobile app). The input consists of the generated analysis reports and trend charts; the output is a visual display in the user interface, including data charts, zoning maps, and alert notifications.

[0154] Step 7:

[0155] Users view reports and analyze data through display devices, and interact via interface selection, voice, or text input commands. Input includes user commands, feedback, and biometric signals (such as facial expressions and voice); user output includes feedback data, decision-making actions, or further information requests.

[0156] Step 8:

[0157] The server collects user feedback and biometric information, with input including user operation records, feedback statements, and facial expression analysis results. The server then calls the sentiment analysis module to determine the user's emotional state and automatically adjusts the information display and recommended content based on the analysis results. The output is a report and interactive interface that better match the user's emotions and needs.

[0158] Step 9:

[0159] After the user actually adopts the investment recommendations and implements the modifications, the server continues to periodically receive new energy consumption and emission data collected by the terminals. The input is the monitoring data after implementation; the server processes the data and compares the changes in energy efficiency and environmental load before and after implementation, generating trend analysis and optimization feedback. The output is the post-evaluation results and new optimization suggestions, forming a data-driven continuous improvement cycle.

[0160] Alternatively, an emotion engine for inferring user emotions can be combined. That is, the specific processing unit 290 can also use the emotion-specific model 59 to infer user emotions and perform specific processing using user emotions.

[0161] Example 2

[0162] The flow of a specific process in Example 2 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 as the "terminal."

[0163] Existing enterprises generally lack efficient, automated, and intelligent processing methods for real-time data collection of energy consumption and greenhouse gas emissions, data integrity verification, outlier correction, and renewable energy investment decisions based on actual operations and user feedback. Systems typically struggle to achieve real-time integration and high-precision analysis of multi-source data, and cannot dynamically optimize investment recommendation reports based on actual user needs and psychological responses. This makes it difficult for enterprises to obtain scientific, personalized, and feasible solutions to support their decisions in promoting energy structure optimization, cost savings, and carbon emission reduction.

[0164] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 2 is achieved by the following means.

[0165] In this invention, the server includes a data acquisition module for time-series collection of energy use data and greenhouse gas emission data of the monitored object; a data preprocessing module for storage and preprocessing, including data shaping, tagging, missing value completion, and outlier correction; a decision generation module for automatically generating energy consumption trend analysis and renewable energy investment recommendations based on a generative artificial intelligence model; a sentiment analysis and content adaptation module for collecting and analyzing user sentiment data and optimizing content accordingly; and a result display module for outputting personalized reports through a display device. Furthermore, it may include functions for consistency verification of collected data and automatic outlier correction, as well as self-learning and optimization of investment recommendations. This enables intelligent processing of multi-source data, personalized adjustment of decision content, and scientific, automated, and efficient information utilization for enterprises in energy conservation, emission reduction, and investment decisions.

[0166] "Information acquisition device" refers to a hardware terminal or equipment that can collect energy consumption data and greenhouse gas emission data of the monitored object in real time or periodically.

[0167] "Energy usage data" refers to digital information that reflects the quantity, time, and type of energy (such as electricity, heat, gas, etc.) consumed by the monitored object within a specific period.

[0168] "Greenhouse gas emission data" refers to the measurement data and related time information of greenhouse gases such as carbon dioxide and methane emitted by the monitored object per unit time.

[0169] "Electronic information storage device" refers to data storage hardware or system based on disks, solid-state storage or cloud services for long-term or short-term storage of structured or unstructured data.

[0170] The "data preprocessing module" refers to the data processing unit that performs operations such as shaping, labeling, missing value completion, outlier detection and correction on the collected raw data in order to optimize subsequent analysis.

[0171] "Generative artificial intelligence models" refer to software systems or algorithmic models that are based on artificial intelligence and machine learning technologies and can take data as input and output analytical conclusions or automatically generate text, solutions, reports, and other content.

[0172] "Energy consumption trend analysis" refers to the statistical analysis and modeling of energy usage data collected over a period of time, revealing the regularity of energy consumption changes by identifying periodic and sudden patterns.

[0173] The "Investment Recommendation Generation Module" is a system component that automatically generates renewable energy investment plans based on data analysis and optimization calculations and outputs documents to users.

[0174] "User physiological response information" refers to physiological signal data reflecting a user's psychological state, such as changes in facial expressions and tone of voice, generated by sensing devices like cameras and microphones.

[0175] "Input records" refer to interactive data related to a user's responses, such as text, selections, and evaluations entered through a human-computer interface.

[0176] The “Sentiment Analysis and Content Adaptation Module” refers to a software unit that analyzes user physiological response information or emotional data obtained from input records and makes real-time personalized adjustments to the system's output content.

[0177] "Information display device" refers to an electronic display terminal used to display various types of content such as reports, suggestions, and charts to users, including but not limited to computer screens and smart mobile devices.

[0178] "Data consistency verification" refers to the technical process of checking collected data to ensure that its time sequence, numerical range, field integrity, etc., meet the set standards.

[0179] "Outlier detection and correction" refers to the technical measures of marking values ​​in data that are outside the expected range or have logical errors, and then using algorithms to replace, correct, or interpolate them.

[0180] The "self-learning optimization module" refers to a processing unit that can continuously optimize model parameters or investment recommendations based on historical system data, user feedback, and new inputs.

[0181] This invention relates to an energy management and renewable energy investment recommendation system based on the fusion of generative artificial intelligence models and multi-source data acquisition. The following provides a detailed description of embodiments of this invention, in conjunction with specific hardware and software.

[0182] This system mainly includes an information acquisition device, a server (information processing device), user terminals, and related software components. The information acquisition device can be an intelligent terminal installed in industrial or commercial locations, such as an embedded microcontroller (e.g., Raspberry Pi, ESP32), equipped with a power meter, gas flow meter, carbon dioxide concentration sensor, etc. The terminal is responsible for collecting on-site energy consumption data and greenhouse gas emission data in real time or at regular intervals, and pushing the data in encrypted format to a server on the public network via standard communication protocols such as MQTT.

[0183] The server hardware can be mainstream cloud server equipment or a local high-performance computer, running an environment such as Amazon EC2 or Linux servers. The server side includes the following main modules:

[0184] 1. Data Receiving and Storage Module. The server uses a database such as Amazon RDS as an electronic information storage device, and receives data packets from the terminal in real time through a data interface, storing them in a structured table in the database.

[0185] 2. Data Preprocessing Module. The server uses Python and software such as Pandas to perform data shaping, labeling, data integrity checks, missing data completion, and outlier detection and correction. For outlier or missing data segments, the server can automatically complete them using methods such as linear interpolation and generate additional label information for each data segment.

[0186] 3. Decision Recommendation Generation Module. The server integrates generative artificial intelligence models, such as GPT-like models deployed locally or accessed via API. The AI ​​model receives pre-processed data and automatically generates renewable energy investment plans (such as optimal combinations of solar, wind, and energy storage technologies) based on energy consumption trends and the latest publicly available market data (such as photovoltaic module prices and government subsidy policies), and outputs investment recommendation documents in natural language.

[0187] 4. Sentiment Analysis and Content Adaptation Module. The server, in conjunction with user terminals (such as PCs or mobile devices equipped with cameras and microphones), uses sentiment recognition algorithms (such as machine learning-based facial expression analysis and voice emotion recognition APIs) to analyze users' physiological reactions and input content while browsing investment advice. Based on different emotional responses from users, the system can adjust the content and style of the investment advice document in real time, for example, by providing more detailed explanations and frequently asked questions for parts that confuse users.

[0188] 5. Results Display Module. Customized investment advice reports generated by the server are securely pushed to user terminals via electronic information display devices such as web dashboards, mobile apps, and emails, enabling users to access diverse information such as decision reports, energy consumption trend curves, energy-saving and carbon reduction simulations, and investment return analyses in a user-friendly and intuitive manner.

[0189] The system allows users to provide real-time feedback on questions, changes in requirements, and other information through dashboards or interfaces. The server uses generative artificial intelligence models to reanalyze user feedback and newly collected data, enabling investment recommendations to self-learn and be continuously updated.

[0190] For example, a factory deploys terminals in workshops A, B, and C, uploading real-time electricity and CO2 data every 5 minutes. The server detects abnormally high energy consumption in area A during a certain time on Friday, automatically corrects the issue, and then sends it to a generative AI model. Based on energy consumption and market technology trends over the past month, the AI ​​generates an investment plan suggesting a 300 kW photovoltaic system, with a total investment of 2.6 million yuan and an estimated payback period of 4 years. When the user views the report on the web interface, the system notices the user's confused facial expression and automatically inserts more detailed technical explanations and case comparison charts in the plan's description section.

[0191] To facilitate operation and human-computer interaction, generative AI models support the following types of prompt input. For example:

[0192] Based on your company's energy consumption and emissions data for the past six months, as well as current renewable energy market policies, please generate a detailed investment recommendation for photovoltaics and energy storage, and estimate the energy saving and carbon reduction effects.

[0193] By combining user sentiment data when reading investment proposals, the report content is automatically adjusted, and the parts that users focus on are presented in charts and detailed explanations are added.

[0194] This system has efficient, intelligent, and personalized decision support capabilities, and is suitable for various enterprise users who need to improve energy management and achieve green transformation.

[0195] use Figure 13 The processing procedure is explained.

[0196] Step 1:

[0197] The terminal uses built-in hardware such as a power meter, gas flow meter, and carbon dioxide sensor to collect real-time energy consumption and greenhouse gas emission data from various areas of the factory. The input is the raw data from each sensor, and the output is a structured data packet containing timestamps, area identifiers, energy consumption values, and emission values. The terminal uses the MQTT protocol to periodically and encryptedly push the packaged data to a designated address on the server.

[0198] Step 2:

[0199] The server starts a data receiving program, listening on the MQTT port to continuously receive data packets from terminals. The input is structured data packets sent by the terminals; the server parses and formats the data, including verifying the terminal ID, time, and data integrity. The output is the formatted raw data rows, stored in a cloud database (such as Amazon RDS). While storing the data, the server generates a receiving log and monitors for data loss or anomalies.

[0200] Step 3:

[0201] The server periodically calls the data preprocessing module to process the raw data stored in the database in batches. The input consists of data records from a given period in the database. The server uses data analysis tools such as Pandas to perform missing data completion (e.g., linear interpolation based on adjacent records), outlier identification (e.g., energy consumption values ​​exceeding reasonable limits), data integration, and labeling. The output is a corrected and structured dataset, with labels including the correction method and the location of outliers appended to the data.

[0202] Step 4:

[0203] The server inputs preprocessed data into a generative artificial intelligence model (such as a locally deployed GPT model). The input consists of corrected energy consumption and emissions data. The server automatically generates targeted prompts, such as "Analyze the factory's energy consumption changes over the past 30 days and provide optimal investment recommendations based on current market parameters." The AI ​​model automatically identifies energy consumption trends and peak cycles based on historical data patterns, external market data, and policy parameters, and generates detailed renewable energy investment recommendations. The output is a structured investment recommendation report, including details such as equipment selection, expected energy-saving benefits, and cost recovery period.

[0204] Step 5:

[0205] The server combines physiological reaction data uploaded by the user's terminal (such as facial expressions captured by the camera and voice tone collected by the microphone while the user views the report) and page operation records, and calls the emotion recognition and analysis module. The input consists of real-time images, audio, and behavioral logs of the user during report reading. After analysis using the emotion recognition API, the server outputs the user's emotion tags (such as surprise, confusion, and agreement) and their correspondence with the page content, and binds this data to the relevant paragraphs of the report.

[0206] Step 6:

[0207] The server personalizes investment advice reports based on the analysis results of a generative artificial intelligence model and user sentiment tags. The input consists of the original AI-generated investment report text and real-time sentiment tags. The server supplements key sections with detailed explanations, adds FAQs, and inserts case comparisons based on user feedback. The output is a final, personalized investment advice report with adaptive content and structure. The report is pushed to users via a web dashboard or mobile device, allowing users to view, export, or provide feedback in real time.

[0208] Step 7:

[0209] After viewing the customized investment advice report, users can submit questions, suggestions, or supplementary requests through the feedback portal on the page. Input includes the user's text, selections, and additional explanations. After collecting the feedback, the server re-analyzes it using a generative artificial intelligence model and sentiment analysis system. Based on the feedback, the server automatically adjusts the investment plan and regenerates an optimized report. The output is a further optimized and supplemented investment advice plan, enabling the system's self-learning and continuous improvement capabilities.

[0210] Application Example 2

[0211] The process flow corresponding to the specific processing in Use Case 2 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. In addition, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0212] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is achieved by the following means.

[0213] In this invention, the server includes an information processing device, a generative artificial intelligence model, and a status recognition device. This enables the automatic collection, complete verification, and anomaly correction of energy consumption and emission information. The generative artificial intelligence model intelligently analyzes and generates renewable energy investment recommendations. Furthermore, it dynamically optimizes the content and presentation of these recommendations by incorporating user sentiment recognition results. Finally, it continuously improves the effectiveness of the solutions through post-implementation performance monitoring and feedback, achieving efficient and intelligent enterprise energy management and carbon emission control.

[0214] "Collection device" refers to hardware or integrated system used to acquire and record consumption and emission information, such as terminal equipment equipped with sensors.

[0215] "Consumption information" refers to various types of data related to energy use, including but not limited to real-time consumption data of energy sources such as electricity and gas.

[0216] "Emissions information" refers to data related to emissions of carbon dioxide or other greenhouse gases, including actual emissions generated during processes at facilities such as factories and businesses.

[0217] "Information processing device" refers to a software or hardware system that receives, stores, preprocesses, and analyzes information acquired by an acquisition device.

[0218] "Integrity verification" refers to checking the consistency and accuracy of the collected information to ensure that there are no omissions or anomalies in the data.

[0219] "Outlier correction" refers to the automatic correction or replacement of abnormal or erroneous data that appears in the collected information during the data processing process.

[0220] "Generative artificial intelligence models" refer to technical models that automatically generate analysis results and suggestive information based on input data through artificial intelligence algorithms such as deep learning.

[0221] "Analysis" refers to a series of automated processing steps that extract features, recognize patterns, and determine trends from preprocessed information.

[0222] "Recommendation information" refers to the recommendations generated based on the analysis results, which are specific implementation plans for renewable energy investments, etc.

[0223] "State recognition device" refers to a system used to collect user state data and infer the user's emotional state through algorithms, including functions such as image recognition, speech recognition and text analysis.

[0224] "User emotional state" refers to the type of subjective emotion a user is inferred by the system through multimodal data analysis of the user's facial expressions, voice, text feedback, etc., such as positive, neutral, negative, etc.

[0225] "Optimization" refers to the process of adjusting the content and expression of suggested information according to specific goals in order to meet user needs and improve the effectiveness of the solution.

[0226] "Document information" refers to the final recommendations and related content recorded and presented in the form of text, charts, etc.

[0227] "Performance monitoring" refers to the operation of real-time detection and evaluation of the effects of the recommendations during the implementation process after they have been adopted.

[0228] "Feedback information" refers to data or suggestions based on performance monitoring results, used for further adjustments or optimizations.

[0229] To facilitate the implementation of this invention, the following detailed description of the implementation methods is provided in conjunction with the technical solution of this system.

[0230] This invention relates to an intelligent energy consumption and emission management system based on information processing technology and a generative artificial intelligence model. The system mainly includes components such as a data acquisition device, an information processing device, a generative artificial intelligence model, a status recognition device, and a user terminal. These components interact with each other via a communication network (such as Wi-Fi or Ethernet). The specific functions of each hardware and software component in the system, as well as their data processing and calculation methods, are described below.

[0231] The terminal (data acquisition device) typically exists in the form of a robot or intelligent terminal integrating energy consumption sensors and CO2 sensors. It is responsible for collecting real-time data on various emissions, such as electricity consumption, gas consumption, and carbon dioxide, in industrial environments. The terminal uses a Wi-Fi module to package the collected data and periodically sends it to a server-side information processing device. Specific hardware includes various industrial-grade energy consumption sensors, carbon dioxide sensors, and Wi-Fi communication modules.

[0232] The server (information processing device) receives data transmitted from the terminal and stores it in a database (such as a relational database management system). It then initiates a data preprocessing program to verify the integrity of the received energy consumption and emission information and correct outliers. The server uses a data cleaning module written in programming languages ​​such as Python to automatically identify missing or abnormal data and make corresponding corrections. The preprocessed data serves as input for subsequent analysis.

[0233] The server invokes generative artificial intelligence models (such as neural network models implemented based on TensorFlow or PyTorch) to analyze historical and real-time data. This model can detect energy consumption and emission patterns in different time periods and regions, predict future trends, and automatically generate renewable energy investment recommendations based on existing data, including investment type, budget, payback period, energy efficiency changes, and emission reduction expectations.

[0234] During report generation and user interaction, the server also invokes a state recognition device (such as an emotion recognition subsystem based on OpenCV and the Emotion API) to collect and analyze users' facial expressions, voice comments, and text feedback while browsing investment advice reports. The analysis automatically determines the user's emotional state (e.g., positive, neutral, negative), and this determination directly impacts the optimization of subsequent investment advice report content. For example, if the user's emotion is determined to be positive, the report uses more optimistic and encouraging language; if it is determined to be negative, the report emphasizes risk prevention and mitigation measures.

[0235] Users can access the system's web interface via terminal devices (such as computers, tablets, or mobile phones) to view customized energy consumption and investment reports. Users can provide feedback, suggestions, or secondary evaluations on the page. All user feedback is synchronized to the server, which can further refine the generative AI model and report content based on user feedback, enabling the system to self-learn and continuously optimize.

[0236] For example, in one implementation at a manufacturing plant, the terminal automatically collects data on workshop electricity consumption, natural gas consumption, and CO2 emissions every five minutes and sends it to a server in real time via Wi-Fi. The server uses a generative artificial intelligence model to analyze the data and generate investment plans. It also combines this data with data such as the user manager's facial expressions and voice responses while viewing the investment report, using a state recognition device to determine their emotional inclination. Ultimately, the user receives a renewable energy investment recommendation report optimized based on their emotional state and can participate in subsequent feedback and interaction.

[0237] Here are some examples of prompts for generative artificial intelligence models:

[0238] Please analyze the emotional state of users while viewing investment advice reports. Based on the data entered below, categorize user sentiment as "positive," "neutral," or "negative":

[0239] Emoticon image file: user_expression.png

[0240] Audio file: user_voice.wav

[0241] Text transcript: "This investment offer is very attractive, and I would like to learn more about it."

[0242] This system integrates multiple sensors, data processing, artificial intelligence analysis, and multimodal user feedback optimization mechanisms. It is suitable for various application scenarios with high standards for energy management and carbon emission control. It can accurately, intelligently, and efficiently generate optimal energy investment recommendations for enterprise users and dynamically adapt to user needs.

[0243] use Figure 14 The processing procedure is explained.

[0244] Step 1:

[0245] The terminal uses built-in energy consumption and CO2 sensors to collect real-time energy consumption and carbon dioxide emission data for each area of ​​the factory.

[0246] The input consists of raw sensing signals of various energy consumption and emissions, and the output consists of formatted data packets (such as energy consumption and emissions values ​​with timestamps).

[0247] The specific actions include calling the sensors to read energy consumption and CO2 data, formatting the data, and temporarily storing it in the local cache.

[0248] Step 2:

[0249] The terminal uses a Wi-Fi module to package the collected energy consumption and emission data and send it to the server's information processing device via the network.

[0250] The input is the formatted data packet obtained in step 1, and the output is the data record sent to the server.

[0251] Specific actions include establishing a network connection with the server, data encryption, data uploading, and handling abnormal retransmissions.

[0252] Step 3:

[0253] The server receives data sent by the terminal, stores it in the database, and performs data integrity checks and outlier corrections.

[0254] The input is energy consumption and emissions data uploaded by the terminal, and the output is a preprocessed dataset.

[0255] Specific data processing includes format checking, missing value completion, outlier replacement (such as replacing outlier peaks with historical averages), data labeling, and saving the results to the database.

[0256] Step 4:

[0257] The server calls a generative artificial intelligence model (such as a deep learning model implemented in TensorFlow or PyTorch) to perform time series analysis and feature extraction on the preprocessed dataset and generate renewable energy investment recommendations.

[0258] The input is preprocessed energy consumption and emission data, and the output is an investment plan containing suggested information (such as investment type, budget, payback period, expected results, etc.).

[0259] Specific data processing includes model loading, feature vector extraction, pattern recognition, and suggestion generation.

[0260] Step 5:

[0261] When users view investment reports on their devices, the system automatically captures facial expressions, voice data, and text feedback from users via camera and microphone, and uploads them to the server.

[0262] The input consists of emoticons, audio files, and text input from the user during the report browsing process, and the output is the corresponding multimodal sentiment data.

[0263] Specific actions include the front-end calling the camera to capture still images, recording user voice, collecting real-time comments in text boxes, and automatically uploading relevant files to the server.

[0264] Step 6:

[0265] The server calls a state recognition device (such as OpenCV or Emotion API) to perform sentiment analysis on the user's facial expressions, voice, and text data to determine the user's current emotional state.

[0266] The input is the user's sentiment data (images, audio, text), and the output is the categorized sentiment labels (such as positive, neutral, negative).

[0267] The specific processing includes image recognition, speech emotion modeling, text semantic analysis, multimodal emotion fusion, and emotion tag output.

[0268] Step 7:

[0269] The server uses investment recommendations generated by a generative artificial intelligence model and user sentiment analysis results to personalize and optimize the content and presentation of investment reports, which are then pushed to user terminals as the final report document.

[0270] The input consists of AI-generated suggestions and sentiment analysis output, and the output is an optimized personalized investment report.

[0271] Specific actions include adjusting the report's language style and prioritizing key content based on emotional state, and finally generating and pushing the document to the user's dashboard.

[0272] Step 8:

[0273] Users can read the optimized investment report through the terminal interface and provide feedback, annotations, or selections.

[0274] The input is the investment report pushed by the system, and the output is the user's feedback information.

[0275] Specific actions include users browsing reports online, filling in suggestions, clicking "agree," or asking questions. Feedback is automatically recorded and uploaded to the server for subsequent optimization.

[0276] The specific processing unit 290 sends 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 sound representing user input regarding the result of the specific processing. The control unit 46A sends the sound data representing 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 sound data.

[0277] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0278] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0279] For example, the collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart device 14 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0280] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart device 14.

[0281] Second Implementation Method

[0282] Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0283] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. A server can be cited as an example of the data processing device 12.

[0284] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0285] 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, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and communication I / F 44 are also connected to the bus 52.

[0286] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0287] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to capture images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0288] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0289] Figure 4 This illustrates an example of the main functions of the data processing device 12 and the smart glasses 214. For example... Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0290] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0291] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0292] In the smart glasses 214, the processor 46 performs reception and output processing. The memory 50 stores the reception and output program 60. The processor 46 reads the reception and output program 60 from the memory 50 and executes the read reception and output program 60 on the RAM 48. The reception and output processing is implemented by the processor 46 operating as a control unit 46A according to the reception and output program 60 executed on the RAM 48. Furthermore, the smart glasses 214 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290.

[0293] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart glasses 214. 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".

[0294] Example 1

[0295] The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0296] Application Example 1

[0297] The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0298] Example 2

[0299] The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0300] Application Example 2

[0301] The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0302] The specific processing unit 290 sends the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A outputs the result of the specific processing to the speaker 240. The microphone 238 acquires sound input representing the user's input regarding the result of the specific processing. The control unit 46A sends the sound data representing the user's 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 sound data.

[0303] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0304] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0305] For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart glasses 214 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0306] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart glasses 214.

[0307] Third Implementation Method

[0308] Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0309] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. A server can be cited as an example of the data processing device 12.

[0310] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0311] The head-mounted 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, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, display 343, and communication I / F 44 are also connected to the bus 52.

[0312] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0313] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to capture images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0314] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0315] Figure 6 This illustrates an example of the main functions of the data processing device 12 and the head-mounted terminal 314. For example... Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0316] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0317] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0318] In the head-mounted terminal 314, the processor 46 performs the acceptance / output processing. The memory 50 stores the acceptance / output program 60. The processor 46 reads the acceptance / output program 60 from the memory 50 and executes the read acceptance / output program 60 on the RAM 48. The acceptance / output processing is implemented by the processor 46 operating as a control unit 46A according to the acceptance / output program 60 executed on the RAM 48.

[0319] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the head-mounted terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the head-mounted terminal 314 will be referred to as the "terminal".

[0320] Example 1

[0321] The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0322] Application Example 1

[0323] The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0324] Example 2

[0325] The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0326] Application Example 2

[0327] The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0328] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted terminal 314, the control unit 46A outputs the result of the specific processing to the speaker 240 and the display 343. The microphone 238 acquires sound input representing the result of the specific processing. The control unit 46A sends the sound data representing 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 sound data.

[0329] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 includes prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0330] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0331] For example, the collection unit is implemented by the control unit 46A of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the head-mounted terminal 314 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 to analyze the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 to generate a menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12 to provide the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0332] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the head-mounted terminal 314.

[0333] Fourth Implementation Method

[0334] Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0335] like Figure 7 As shown, the data processing system 410 includes a data processing device 12 and a robot 414. A server can be cited as an example of the data processing device 12.

[0336] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0337] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, controlled object 443, and communication I / F 44 are also connected to the bus 52.

[0338] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0339] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to photograph the area around robot 414 (e.g., the field of view defined by a perspective equivalent to the field of vision of an average healthy person).

[0340] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0341] The controlled object 443 includes a display device, LEDs (light-emitting diodes) for the eyes, and motors for driving the arms, hands, and feet. The posture or movement of the robot 414 is controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0342] Figure 8 This illustrates an example of the main functions of the data processing device 12 and the robot 414. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0343] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0344] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0345] In robot 414, the processor 46 performs the acceptance and output processing. The memory 50 stores the acceptance and output program 60. The processor 46 reads the acceptance and output program 60 from the memory 50 and executes the read acceptance and output program 60 on RAM 48. The acceptance and output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance and output program 60 executed on RAM 48.

[0346] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal".

[0347] Example 1

[0348] The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0349] Application Example 1

[0350] The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0351] Example 2

[0352] The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0353] Application Example 2

[0354] The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0355] The specific processing unit 290 sends the result of the specific processing to the robot 414. In the robot 414, the control unit 46A outputs the result of the specific processing to the speaker 240 and the controlled object 443. The microphone 238 acquires sound input representing the result of the specific processing. The control unit 46A sends the sound data representing 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 sound data.

[0356] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0357] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0358] For example, the collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the robot 414 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the robot 414 and the control object 443 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0359] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the robot 414.

[0360] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine a user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine a user's emotion based on an emotion graph that serves as a specific mapping (see [reference]). Figure 9 The system determines the user's emotions. Furthermore, the emotion-specific model 59 can similarly determine the robot's emotions, and the specific processing unit 290 performs specific processing based on the robot's emotions.

[0361] Figure 9 This is a diagram representing an emotion map 400 that maps multiple emotions. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotion is. On the outer side of the concentric circles, emotions representing states or behaviors arising from mood are arranged. Emotions are concepts that include feelings and mental states. Emotions generated by reactions occurring in the brain are arranged roughly to the left of the concentric circles. Emotions derived from situational judgments are arranged roughly to the right of the concentric circles. Emotions generated by reactions occurring in the brain and derived from situational judgments are arranged roughly above and below the concentric circles. Furthermore, "pleasant" emotions are arranged above the concentric circles, and "unpleasant" emotions are arranged below them. Thus, in the emotion map 400, multiple emotions are mapped based on the structure that generates emotions, and emotions that are likely to occur simultaneously are mapped close to each other.

[0362] These emotions are distributed at the three o'clock position of the emotion map 400, typically fluctuating between peace and anxiety. In the right half of the emotion map 400, situational awareness dominates over internal sensation, thus resulting in an impression of calm.

[0363] The inner side of the emotion map 400 represents the inner state, while the outer side represents behavior. Therefore, the further outward you are from the emotion map 400, the more visible the emotion becomes (manifested in behavior).

[0364] Here, human emotions are based on various balances such as posture and blood sugar levels. When these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotions in robots, cars, motorcycles, etc., can also be created in the following way: based on various balances such as posture and remaining battery power, when these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a Brain Physiological Signal Analysis System for Voice Emotion Recognition and Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the sensory-dominated region, called "response," are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the situational cognition-dominated region, called "situation," are arranged.

[0365] In the emotion map, two types of emotions that promote learning are defined. One is a negative emotion on the situational side, in the middle or peripheral region of "repentance" or "reflection." This occurs when the robot experiences negative emotions such as "I don't want to experience this feeling again" or "I don't want to be blamed again." The other is a positive emotion on the response side, near the "desire" region. This occurs when there are positive feelings such as "wanting more" or "wanting to know more."

[0366] The emotion-specific model 59 inputs user input into a pre-trained neural network to obtain emotion values ​​representing each emotion shown in the emotion map 400, thereby determining the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network... Figure 10 As shown in the sentiment graph 900, it was trained in a way that sentiments that are configured close to each other have similar values. Figure 10 The text shows examples of emotions such as "peace of mind", "stability", and "reassurance" that have similar emotion values.

[0367] The above description focuses on the functions of the data processing device 12, but the system of this disclosure is not necessarily installed on a server. The system of this disclosure can also be installed as a general information processing system. This disclosure can also be installed, for example, as a software program running on a personal computer, an application running on a smartphone, etc. The method of this disclosure can also be provided to users in the form of SaaS (Software as a Service).

[0368] In the above embodiments, an example of a specific process being performed by a single computer 22 is given. However, the technology disclosed herein is not limited to this, and the specific process can also be distributed among multiple computers, including computer 22. For example, the data generation model 58 can be located on an external device of the data processing apparatus 12, where data is generated based on the input data.

[0369] In the above embodiments, examples of storing a specific processing program 56 in the memory 32 have been described, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also 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 into the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0370] Alternatively, a specific processing program 56 may be pre-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 according to the requirements of the data processing device 12.

[0371] In addition, it is not necessary to store all the specific processing program 56 in the storage device such as the server connected to the data processing device 12 via the network 54 or in the memory 32; a portion of the specific processing program 56 may be stored in advance.

[0372] As hardware resources for performing specific processes, various processors, as shown below, can be used. For example, a CPU can be listed as a processor, which functions as a general-purpose processor that performs specific processes by executing software, i.e., a program. Furthermore, processors can be listed as special-purpose circuits such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application-Specific Integrated Circuits), which are processors with circuitry specifically designed to perform specific processes. Each processor has built-in or connected memory, and each processor executes specific processes using that memory.

[0373] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resources for performing a specific process can be a single processor.

[0374] As an example of a single processor, there are two approaches: First, a processor is composed of a combination of one or more CPUs and software, which functions as a hardware resource to perform a specific process; second, as represented by a SoC (System-on-a-chip), a processor is used to implement the functionality of the entire system, which includes multiple hardware resources for performing a specific process, using a single IC (Integrated Circuit) chip. In this way, the specific process is implemented by using one or more of the aforementioned processors as hardware resources.

[0375] Furthermore, the hardware architecture of these various processors, more specifically, can utilize circuits that combine semiconductor elements and other circuit components. Moreover, the specific process described above is just one example. Therefore, without departing from the main point, unnecessary steps can certainly be deleted, new steps added, or the processing order changed.

[0376] The descriptions and illustrations above are detailed explanations of a portion of the technology disclosed herein, and are merely one example of the technology disclosed herein. For example, the above descriptions of the structure, function, effect, and results are just one example of the structure, function, effect, and results of a portion of the technology disclosed herein. Therefore, without departing from the spirit of the technology disclosed herein, unnecessary parts may be deleted, new elements added, or replacements may be made to the descriptions and illustrations above. Furthermore, to avoid confusion and facilitate understanding of a portion of the technology disclosed herein, explanations of common technical knowledge that do not require special explanation under the premise of being able to implement the technology disclosed herein have been omitted from the descriptions and illustrations above.

[0377] All documents, patent applications and technical specifications set forth in this specification are incorporated herein by reference to the same extent that each document, patent application and technical specification is specifically and individually described therein and referenced by reference.

[0378] In addition, the following notes are provided in response to the above explanation.

[0379] Example 1

[0380] (Note 1)

[0381] An information processing system includes: an information processing device for real-time on-site acquisition of energy resource usage-related observations and greenhouse gas emission-related observations via an information acquisition device; a data processing device for storing the received observations and performing data quality improvement preprocessing in a big data processing platform; an analysis device for performing time-series analysis and trend extraction on the preprocessed observations using a generative artificial intelligence processing device, and automatically generating an optimal design scheme for renewable energy investment; a report output device for outputting the generated optimal design scheme in a structured format to a recording medium and displaying it to a user via a web browsing device or information terminal; and a prompt generation device for automatically generating and providing prompting information to the generative artificial intelligence processing device.

[0382] (Note 2)

[0383] The information processing system according to Note 1 further includes a data consistency and correction device for performing consistency checks on observations and correcting outliers using a statistical correction algorithm.

[0384] (Note 3)

[0385] The information processing system according to Appendix 1 also includes a performance monitoring and feedback device for monitoring the operational efficiency of renewable energy utilization equipment after its introduction and feeding back the results to the user.

[0386] Application Example 1

[0387] (Note 1)

[0388] An information processing system includes: a device for acquiring multiple physical quantity data in real time via an information acquisition device and transmitting them via a data communication network; a device for storing, formatting, tagging, and preprocessing the received data in the information processing device; a device for performing format verification, data correction, and outlier correction during data preprocessing; a device for analyzing the preprocessed data using a natural language generation model and generating energy utilization optimization suggestions; a device for analyzing the generated suggestions and classifying them according to methods to generate assessment data including indicators, effect predictions, and equipment lists; a device for visually displaying the assessment data and related data and providing real-time alarm notifications via a display device; a device for acquiring user information data and biometric data to infer the user's psychological state and automatically adjusting the information display content based on the inference results; a device for inputting commands through a user interface and outputting responses based on emotional characteristics; and a device for continuously collecting new data after the implementation of measures and tracking, analyzing, and providing feedback on changes in energy efficiency and environmental load.

[0389] (Note 2)

[0390] The information processing system according to Appendix 1 is characterized in that it can verify the time series consistency of the data structure and automatically perform anomaly detection and correction processing of the physical quantity data.

[0391] (Note 3)

[0392] The information processing system according to Appendix 1 is characterized in that it can provide optimized information visualization and interactive response based on the user's input behavior, biosignals and input content through a psychological state judgment model and display adjustment algorithm.

[0393] Example 2

[0394] (Note 1)

[0395] An information processing system includes: a data acquisition module for time-series acquisition of energy use data and greenhouse gas emission data of monitored objects through an information acquisition device; a data preprocessing module for storing the acquired data in an electronic information storage device and performing data shaping, labeling, data missing completion, and outlier detection and correction on the data; an investment recommendation generation module for performing energy consumption trend analysis on the preprocessed data based on a built-in generative artificial intelligence model, automatically generating renewable energy investment plans by combining market data and optimization calculations, and generating electronic documents for output; a sentiment analysis and content adaptation module for collecting and analyzing users' physiological reaction information or input records to obtain emotional data, and controlling the generative artificial intelligence model or personalizing the content displayed in the electronic documents accordingly; and a result display module for outputting investment recommendations and personalized content optimized based on users' emotions to users through an information display device.

[0396] (Note 2)

[0397] The information processing system according to Appendix 1 also includes a data verification and correction module for performing data consistency verification and automatically correcting abnormal detection values.

[0398] (Note 3)

[0399] The information processing system according to Note 1 also includes a self-learning optimization module for continuously acquiring post-implementation operational data and updating and optimizing investment advice documents or control parameters based on analysis results and user feedback.

[0400] Application Example 2

[0401] (Note 1)

[0402] An information processing system includes: a data acquisition device for acquiring consumption and emission information; an information processing device for receiving the information acquired by the data acquisition device and performing preprocessing on the information, including storage, integrity verification, and outlier correction; the information processing device is further configured to analyze the preprocessed information using a generative artificial intelligence model and generate suggested information; a state recognition device for acquiring user state information and inferring the user's emotional state; and the information processing device is further configured to optimize the content and display method of the suggested information based on the user's emotional state, and generate the optimized suggested information as document information and display it on the user's terminal device.

[0403] (Note 2)

[0404] According to the information processing system described in Appendix 1, the information processing device performs integrity verification and outlier correction on the consumption information and emission information.

[0405] (Note 3)

[0406] According to the information processing system described in Appendix 1, the information processing device further includes post-implementation performance monitoring based on the suggested information and processing for providing feedback information.

Claims

1. An information processing system, characterized in that, include: A means of collecting energy consumption data and CO2 emission data in real time via IoT terminals; A means of storing and preprocessing received data in a cloud server; A means of analyzing preprocessed data using generative artificial intelligence to generate renewable energy investment plans; A means of generating investment plan reports and presenting them to users.

2. The information processing system according to claim 1, characterized in that, It also includes methods for consistency verification and outlier correction of energy consumption data and CO2 emission data.

3. The information processing system according to claim 1, characterized in that, It also includes means for continuously monitoring the operational performance of renewable energy systems and providing feedback after their deployment.

Images