System

Abstract

A system is provided.SOLUTION: A system comprising: means for developing metrics based on generated data; means for automatically measuring activity performance based on the metrics; means for storing the measurements in a database; means for generating an outcome report from the stored data; and means for displaying the generated outcome report.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While initiatives related to the SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) are costly for small and medium-sized enterprises, they also present challenges in terms of the difficulty of achieving clear results. In particular, formulating evaluation indicators and measuring activity performance is time-consuming and laborious, making it difficult to carry out these measures efficiently. This means that companies are unable to immediately confirm the effectiveness of their initiatives, potentially delaying action toward realizing a sustainable society. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. First, a means for formulating evaluation indicators based on generated data is provided. This means analyzes data entered by a user using an LLM (large-scale language model) and automatically generates appropriate evaluation indicators. Furthermore, a means for automatically measuring activity performance based on the evaluation indicators is provided, enabling accurate evaluation of corporate efforts based on daily activity data. These measurement results are stored in a database, and progress reports are generated periodically. The generated progress reports are displayed so that users can easily check them. Furthermore, a means for rating corporate efforts based on the generated activity performance measurement results and displaying the results is provided, allowing SMEs to easily understand their position and compare them with other companies. This provides a system that enables even SMEs to efficiently advance SDGs and ESG efforts.

[0006] "Generated data" refers to information related to SDGs and ESG entered by users, and is data used to formulate evaluation indicators.

[0007] "Evaluation indicators" are specific standards and measures for evaluating a company's efforts based on SDGs and ESG criteria.

[0008] "Operational performance" refers to the tangible results and achievements that a company achieves as a result of its efforts related to the Sustainable Development Goals and environmental, social and governance issues.

[0009] "Automatic measurement" refers to the process of using AI models and algorithms to analyze data entered by users and automatically evaluate activity performance based on evaluation indicators.

[0010] A "database" is a digital storage device or system for organizing and storing data such as measurement results.

[0011] A "results report" is a document or digital file generated based on collected data and its evaluation results, which shows the results of a company's efforts.

[0012] A "rating instrument" is a process of ranking companies on specific criteria based on the results of an evaluation of the company's activity performance.

[0013] The "display means" refers to a display or interface that visually presents information such as performance reports and rating results to the user.

[0014] "LLM (Large-scale Language Model)" is a language processing model trained on extremely large amounts of text data, and is a technology for understanding and generating natural language. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific modes for carrying out the invention are described below.

[0037] System configuration

[0038] The system consists of the following main components:

[0039] 1. User Device

[0040] 2. Central Server

[0041] 3. Database

[0042] 4. Results report generation module

[0043] 5. Display and display interface

[0044] Specific examples of program processing

[0045] Initial Data Entry

[0046] As an initial setting, users input data related to the SDGs and ESG into the device, such as energy consumption, recycling rate, and exhaust gas volume.

[0047] The terminal transmits the entered data to a central server.

[0048] Establishment of evaluation indicators

[0049] The server passes the received initial data to the LLM (Large Scale Language Model).

[0050] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0051] Uploading daily activity data

[0052] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0053] The devices transmit these daily activity data to a central server.

[0054] Measuring activity performance

[0055] The server passes the received daily activity data to the AI ​​model.

[0056] The server uses an AI model to analyze this data based on evaluation indicators and automatically measure activity performance, generating evaluation results such as "successfully reduced energy consumption by 10%."

[0057] Generate and view performance reports

[0058] At the end of the month, the server collects and organizes all collected data and its evaluation results.

[0059] Based on the collected data, the server generates a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[0060] The server provides the generated performance report in a format that can be viewed by the user, and the report is displayed on a display, which the user can download as needed.

[0061] SDGs / ESG Ratings

[0062] The server uses the latest evaluation data to perform calculations to rank companies' efforts toward SDGs and ESG.

[0063] The server rates companies on a six-point scale from A to F. The ratings are then presented to the user in a web interface for review.

[0064] Users can use the device to check their own rating and compare it with other small and medium-sized businesses.

[0065] Specific examples

[0066] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs the energy consumption and recycling rate as initial data into a terminal and sends the data to a server.

[0067] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[0068] 3. The user uploads daily energy consumption data from the device to the server.

[0069] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[0070] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[0071] 6. The server then uses this data to assign an SDG rating, giving it an A rank, and displays the result to the user.

[0072] As described above, this system provides a mechanism for SMEs to efficiently evaluate their SDG and ESG initiatives and confirm their results. This makes it easier for companies to understand the effects of their efforts and promotes actions toward realizing a sustainable society.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] Users input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, and gas emissions) into the terminal as initial data.

[0076] Step 2:

[0077] The terminal transmits the entered initial data to the central server.

[0078] Step 3:

[0079] The server passes the received initial data to the LLM (Large Scale Language Model).

[0080] Step 4:

[0081] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0082] Step 5:

[0083] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[0084] Step 6:

[0085] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0086] Step 7:

[0087] The device sends daily activity data to a server.

[0088] Step 8:

[0089] The server passes the received daily activity data to the AI ​​model.

[0090] Step 9:

[0091] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[0092] Step 10:

[0093] The server stores the evaluation results in a database and notifies the user of the information.

[0094] Step 11:

[0095] At the end of the month, the server collects and organizes all the data collected so far and its evaluation results.

[0096] Step 12:

[0097] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[0098] Step 13:

[0099] The server provides the performance report in a user-viewable format to the web interface.

[0100] Step 14:

[0101] Users can check the results report on their device and download it if necessary.

[0102] Step 15:

[0103] The server performs calculations based on the latest evaluation data to rank companies' efforts toward SDGs and ESG.

[0104] Step 16:

[0105] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[0106] Step 17:

[0107] Users can use the device to check their own ratings and compare them with other companies.

[0108] This will enable companies to efficiently evaluate and confirm the effectiveness of their SDGs and ESG initiatives.

[0109] Example 1

[0110] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0111] With conventional systems, it has been extremely difficult for small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare their results. In particular, there has been a demand for a system that automates the entire process of collecting, analyzing, evaluating, and reporting activity data, making it easy to use. In addition, there has been a lack of means to rate a company's efforts, making it difficult to compare them with other companies. The objective of this invention is to solve these problems.

[0112] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0113] In this invention, the server includes means for receiving and storing initial data entered by a user, means for converting the initial data into an analysis format, means for passing the data converted into the analysis format to a large-scale language model (LLM), means for generating evaluation indicators from the data analyzed by the LLM and saving them in a database, means for a user to input daily activity data and send it to the server, means for converting the sent daily activity data into an analysis format, means for passing the data converted into the analysis format to an AI model and automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, and means for generating monthly performance reports from the saved data and displaying them to the user via a web interface. This enables efficient evaluation of a company's efforts, checking its results in real time, and comparing it with other companies.

[0114] A "user" is an individual or company employee who uses the system to enter or view data.

[0115] "Initial data" refers to data related to the SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance), such as energy consumption, recycling rates, and exhaust gas emissions.

[0116] A "large-scale language model (LLM)" is an AI algorithm for analyzing natural language data and generating more advanced information.

[0117] "Evaluation indicators" are specific indicators such as energy efficiency and recycling rates that are generated based on SDGs and ESG standards.

[0118] "Daily activity data" refers to data such as energy consumption data and recycling activity records that are input by the user in relation to their daily activities.

[0119] An "AI model" is an artificial intelligence algorithm that analyzes collected data and evaluates activity performance.

[0120] "Operational performance" refers to the achievements and results that are automatically measured based on a company's daily activities, and includes, for example, the rate of reduction in energy consumption.

[0121] "Measurement results" are specific evaluation results of activity performance analyzed by the AI ​​model.

[0122] A "database" is an electronic storage device for storing received data, analysis results, generated evaluation indexes, and the like.

[0123] The "Results Report" is a report generated based on the saved data that shows the results of a company's SDGs and ESG initiatives.

[0124] A "web interface" is an online operating screen that allows users to view performance reports and rating results.

[0125] The "rating" involves evaluating and ranking a company's SDGs and ESG initiatives on a six-point scale from A to F based on the latest evaluation data.

[0126] Embodiments of the invention

[0127] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific embodiments for carrying out the invention are described below.

[0128] System configuration

[0129] The system consists of the following main components:

[0130] 1. User Device

[0131] 2. Central Server

[0132] 3. Database

[0133] 4. Results report generation module

[0134] 5. Display and display interface

[0135] User terminal

[0136] The user terminal is a device that users use to input their initial data and daily activity data. This can be a PC, tablet, smartphone, etc. The user enters the data through a dedicated input screen and sends it to the central server.

[0137] Central Server

[0138] The central server is the main computing unit that processes and stores the data it receives. The server uses the following software and hardware:

[0139] LLM (Large Scale Language Model): Used to analyze natural language data and generate evaluation metrics.

[0140] AI model: Using frameworks such as TensorFlow, it analyzes daily activity data and automatically measures activity performance.

[0141] Database: Received data, analysis results, evaluation indicators, rating results, etc. are stored using PostgreSQL or similar.

[0142] Database

[0143] The database is a storage unit for securely storing and managing all data received on a central server, including initial data, daily data, analysis results, evaluation indicators, performance reports, and rating results.

[0144] Results report generation module

[0145] The performance report generation module is a software component that aggregates monthly data and generates reports that show the results of the company's efforts. It generates performance reports in plain text and PDF format.

[0146] Displays and display interfaces

[0147] The display and viewing interface is the interface that users use to view the generated performance reports and rating results. This is provided through a web browser, allowing users to easily compare their own efforts and the results of their efforts with those of other companies.

[0148] Specific examples

[0149] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rate as initial data into a user terminal and transmits the data to a central server.

[0150] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[0151] 3. Users upload their daily energy consumption data from their devices to a central server.

[0152] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[0153] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[0154] 6. The server then uses this data to rate the company on SDGs, assigning it an A rank and displaying the results to the user.

[0155] Prompt Sentence Examples

[0156] "This system efficiently evaluates the SDGs and ESG efforts of small and medium-sized enterprises, and allows them to report and compare their results. Specifically, users input data such as energy consumption and recycling rates, and the server uses LLM and AI models to generate evaluation indicators and measure activity performance. At the end of the month, an outcome report is generated and the company's efforts are ranked based on the results."

[0157] In this way, the present invention provides a concrete method for small and medium-sized enterprises to efficiently evaluate their SDGs and ESG initiatives and confirm and compare their results, thereby supporting the sustainable development of companies.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1:

[0160] The user inputs the initial data into the user terminal.

[0161] Input data such as energy consumption, recycling rate, and exhaust gas volume is entered through an input form.

[0162] The device converts this input data into packets and sends them over secure communications to a central server, which then receives the data.

[0163] Step 2:

[0164] The server converts the received initial data into a format for analysis.

[0165] As input, it receives data sent from the terminal.

[0166] The server runs a program to convert this data into JSON format, and the output is JSON data that can be parsed.

[0167] Step 3:

[0168] The server passes the converted data to a large-scale language model (LLM).

[0169] As input, it uses the converted JSON data for parsing.

[0170] The server requests analysis by sending data to the API endpoint of LLM, and receives the analysis results from LLM as output.

[0171] Step 4:

[0172] The server generates evaluation metrics from the data analyzed by LLM and stores them in a database.

[0173] As input, evaluation indicators are generated based on the analysis results obtained from the LLM.

[0174] The server executes the evaluation metric generation algorithm and stores the evaluation results in a PostgreSQL database. As an output, the evaluation metrics are stored in the database.

[0175] Step 5:

[0176] The user inputs and transmits daily activity data into the user terminal.

[0177] Inputs include daily energy consumption data and records of recycling activities.

[0178] The device converts daily data into packets and sends them to a central server, which then receives the data.

[0179] Step 6:

[0180] A server converts the received daily activity data into a format for analysis.

[0181] As input, it uses daily data received from the terminal.

[0182] The server runs a program that converts the daily data into CSV format, and generates CSV data as output for analysis.

[0183] Step 7:

[0184] The server passes the converted daily data to an AI model, which automatically measures activity performance based on evaluation indicators.

[0185] As input, it uses the CSV data that has been transformed for analysis.

[0186] The server inputs the data into the AI ​​model for analysis and evaluation, and generates an evaluation result of activity performance as the output.

[0187] Step 8:

[0188] The server stores the measurement results in a database.

[0189] As input, it uses the activity performance evaluation results generated by the AI ​​model.

[0190] The server stores the evaluation results in a PostgreSQL database. As an output, the measurement results are stored in the database.

[0191] Step 9:

[0192] At the end of the month, the server generates a performance report based on the accumulated data.

[0193] As input, the query retrieves all data in the database.

[0194] The server runs the outcome report generation algorithm to generate an outcome report in plain text or PDF format. As an output, an outcome report is generated.

[0195] Step 10:

[0196] The server displays the generated performance report to the user via a web interface.

[0197] Use the generated outcome report as input.

[0198] The server generates HTML pages for the web interface and serves them to the user, allowing the user to view the report as output.

[0199] Step 11:

[0200] The user can view the generated results report through a web interface and download it if necessary.

[0201] As an input, you log in through the web interface and view the performance report.

[0202] The terminal executes the download command and saves the results report in PDF format. As an output, the report is saved on the user's terminal.

[0203] Step 12:

[0204] The server will rate companies' efforts toward SDGs and ESG based on the latest evaluation data.

[0205] It uses the most recent evaluation data in the database as input.

[0206] The server runs a rating algorithm and rates the company's efforts on a six-point scale (A to F). The rating is generated as an output.

[0207] Step 13:

[0208] The server provides the rating results in a web interface that can be viewed by the user.

[0209] As input, the rating results are used.

[0210] The server generates a page for a web interface that allows users to view the rating results, and as an output, the rating results are displayed on a web page.

[0211] Step 14:

[0212] Users use a web interface to view their own ratings and compare them with other small businesses.

[0213] As an input, log in to the web interface.

[0214] The terminal displays the rating results and accesses a comparison page with other companies. As an output, users can compare their own evaluation results with those of other companies.

[0215] In this way, the system can efficiently evaluate the SDGs and ESG initiatives of small and medium-sized enterprises, check their results in real time, and compare them with other companies.

[0216] (Application example 1)

[0217] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0218] Current systems for efficiently and accurately evaluating and reporting on SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) initiatives for small and medium-sized enterprises require manual data entry and analysis, which is time-consuming and costly. Furthermore, the inability to collect and analyze data in real time makes it difficult to make quick decisions. Furthermore, because evaluation results and reports are generated manually, the data lacks reliability and consistency, making comparisons and analysis difficult.

[0219] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0220] In this invention, the server includes means for formulating evaluation indicators based on generated data, means for automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for the robot to collect environmental data and operational data, means for transmitting the collected data to a cloud server, and means for converting the analysis results into an evaluation report on the cloud server. This enables small and medium-sized enterprises to automatically collect and analyze data on SDGs and ESG activities in real time and efficiently generate and display evaluation reports.

[0221] "Generated data" refers to various data related to the SDGs and ESG initiatives of small and medium-sized enterprises, including energy consumption, recycling rates, and emissions.

[0222] "Evaluation indicators" are specific measurement standards set based on SDGs and ESG criteria, and include energy efficiency and carbon emission reduction.

[0223] "Activity Performance" evaluates a company's daily performance in relation to SDGs and ESG initiatives.

[0224] "Measurement results" are the results of a company's activity performance calculated based on evaluation indicators.

[0225] A "database" is a system for storing data such as measurement results.

[0226] The "Results Report" is a report generated based on the saved data, detailing the results of a company's SDGs and ESG initiatives.

[0227] "Display means" refers to a device or interface for presenting the generated result report in a format that can be viewed by the user.

[0228] A "robot" is an automated device that operates within a factory and collects environmental and operational data.

[0229] "Environmental data" refers to data related to the environment, such as energy consumption and exhaust gas emissions at factories.

[0230] "Operational data" refers to data related to production activities and the operating status of equipment within a factory.

[0231] A "cloud server" is a remote server that provides data and services over the Internet.

[0232] An "evaluation report" is a report generated based on data analyzed on a cloud server that details the results of a company's SDGs and ESG initiatives.

[0233] "Real-time" refers to a state in which data collection, analysis, and display are carried out immediately without delay.

[0234] System configuration

[0235] The system of the present invention comprises the following main components:

[0236] 1. User Device

[0237] 2. Robot

[0238] 3. Cloud Server

[0239] 4. Database

[0240] 5. Results report generation module

[0241] 6. Display and display interface

[0242] Program processing

[0243] Data collection and transmission

[0244] Robots operating in factories collect environmental and operational data in real time. The robots are equipped with sensors such as energy consumption meters and exhaust gas sensors, and acquire data from these sensors. The acquired data is then sent to a cloud server via a network module.

[0245] Data analysis and generation of evaluation indicators

[0246] The cloud server passes the received data to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. These evaluation indicators are stored in a database.

[0247] Measuring activity performance

[0248] The server passes daily activity data to the AI ​​model, which analyzes it based on evaluation indicators. This generates a measurement result for activity performance. For example, a measurement result such as "successfully reduced energy consumption by 10%" is generated. These measurement results are stored in a database.

[0249] Generate and view performance reports

[0250] The cloud server organizes all collected data and evaluation results and generates a performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts." The generated performance report is provided in a format that can be viewed by users. It can be monitored in real time via user terminals, displays, and mobile devices.

[0251] Specific examples

[0252] 1. The user initializes the system and inputs initial data such as energy consumption and recycling rate.

[0253] 2. The robot collects environmental and operational data within the factory and sends it to a cloud server.

[0254] 3. The server passes the received data to the LLM, which generates evaluation metrics from the analyzed data.

[0255] 4. The server uses an AI model to analyze daily activity data and measure activity performance.

[0256] 5. The server generates a performance report and displays it on the user's terminal or display.

[0257] Prompt Sentence Examples

[0258] "Based on the energy consumption and recycling data for the following factory, please evaluate it based on the SDGs indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[0259] Specific hardware and software names to be used

[0260] Robot: Automated equipment for collecting environmental and operational data

[0261] Sensors: Energy consumption meter, exhaust gas sensor

[0262] Network module: for data transmission

[0263] Cloud server: A server for running LLM and AI models (e.g., AWS, Google Cloud)

[0264] LLM: Large-scale language model (e.g., OpenAI GPT-4)

[0265] Database: A system for storing measurement results and evaluation indicators (e.g., MySQL, PostgreSQL)

[0266] Displays and mobile devices: devices that display the generated outcome reports

[0267] In this way, the system can efficiently evaluate and report on SMEs' SDGs and ESG activities and promote improvements.

[0268] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0269] Step 1:

[0270] Entering initial data

[0271] The user inputs initial data such as energy consumption and recycling rate into the user terminal. The terminal then sends the initial data entered by the user to the cloud server. The input initial data is stored on the server and used to develop evaluation indicators.

[0272] Step 2:

[0273] Robotic data collection

[0274] Robots collect environmental and operational data within the factory using energy consumption meters, exhaust gas sensors, etc. The robots then send the collected data to a cloud server via a network. Input: Environmental and operational data. Output: Data stored on the cloud server.

[0275] Step 3:

[0276] Data analysis and evaluation index generation

[0277] The cloud server passes the data received from the robot to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. Input: Environmental data and operational data stored on the cloud server. Output: Evaluation indicators.

[0278] Step 4:

[0279] Measuring activity performance

[0280] The server uses an AI model to automatically measure activity performance based on evaluation indicators. It analyzes daily activity data and measures specific results (e.g., successful 10% reduction in energy consumption). Input: Evaluation indicators and daily activity data. Output: Measurement results.

[0281] Step 5:

[0282] Saving measurement results

[0283] The server stores the measurement results in a database. Input: Measurement results. Output: Measurement results stored in the database.

[0284] Step 6:

[0285] Generate a performance report

[0286] The server generates a performance report based on the stored measurement results. The report includes the current month's energy consumption, reduction rate, and recycling effort results. Input: Measurement results stored in the database. Output: Performance report.

[0287] Step 7:

[0288] View the results report

[0289] The server provides the generated results report in a format that can be viewed by the user. It can be monitored in real time through the user's terminal, display, or mobile terminal. Input: Results report. Output: Results report displayed on the user's terminal or display.

[0290] Step 8:

[0291] Generate prompt statement

[0292] The server generates prompts for data analysis of the factory's SDG / ESG efforts. Example: "Based on the energy consumption data and recycling data of the following factory, please evaluate it based on SDG indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[0293] Input: Target data. Output: Generated prompt sentence.

[0294] Through the above processing steps, this system can efficiently evaluate the SDGs and ESG activities of small and medium-sized enterprises, and confirm and improve their results in real time.

[0295] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0296] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in the areas of SDGs (Sustainable Development Goals) and ESG (Environment, Social and Governance), and also recognizes and utilizes user emotions to more effectively understand, report and improve the results of those efforts.

[0297] System configuration

[0298] The system consists of the following main components:

[0299] 1. User Device

[0300] 2. Central Server

[0301] 3. Database

[0302] 4. Results report generation module

[0303] 5. Display and display interface

[0304] 6. Emotion Engine

[0305] Specific examples of program processing

[0306] Initial Data Entry

[0307] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[0308] The terminal transmits the entered data to a central server.

[0309] Establishment of evaluation indicators

[0310] The server passes the received initial data to the LLM (Large Scale Language Model).

[0311] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0312] Uploading daily activity data

[0313] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0314] The device transmits this daily activity data to a server.

[0315] Measuring activity performance

[0316] The server passes the received daily activity data to the AI ​​model.

[0317] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[0318] Recognizing and Using Emotional Data

[0319] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[0320] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[0321] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion, thereby providing a more accurate evaluation.

[0322] Generate and view performance reports

[0323] At the end of the month, the server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[0324] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[0325] The server provides the generated performance report in a user-viewable format to the web interface.

[0326] Users can use their devices to check the results reports and download them if necessary.

[0327] SDGs / ESG Ratings

[0328] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[0329] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[0330] Users can use the device to check their own ratings and compare them with other companies.

[0331] Specific examples

[0332] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rates as initial data into a terminal and sends the data to a server.

[0333] 2. The server analyzes this data using LLM to generate evaluation indicators such as "energy efficiency" and "recycling rate."

[0334] 3. The user uploads daily energy consumption data from the device to the server.

[0335] 4. The server uses an AI model to analyze the daily data and obtains the evaluation result: "This month's energy consumption has been successfully reduced by 10%."

[0336] 5. The emotion engine recognizes the emotion data when the user inputs the day's work report by voice and sends the data to the server.

[0337] 6. The server converts the emotion data into evaluation metrics, integrates them with performance evaluations, and generates an outcome report.

[0338] 7. The server provides the user with a report summarizing the generated results and emotion data.

[0339] 8. The server then performs an SDGs rating based on the data, assigns an A rank, and displays the rating results to the user.

[0340] In this way, by incorporating user sentiment data into the evaluation of SDGs and ESG initiatives, the system provides a more comprehensive and appropriate evaluation, efficiently supporting the sustainable initiatives of small and medium-sized enterprises.

[0341] The processing flow will be explained below.

[0342] Step 1:

[0343] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[0344] Step 2:

[0345] The terminal transmits the entered initial data to the central server.

[0346] Step 3:

[0347] The server passes the received initial data to the LLM (Large Scale Language Model).

[0348] Step 4:

[0349] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0350] Step 5:

[0351] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[0352] Step 6:

[0353] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0354] Step 7:

[0355] The device sends daily activity data to a server.

[0356] Step 8:

[0357] The server passes the received daily activity data to the AI ​​model.

[0358] Step 9:

[0359] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[0360] Step 10:

[0361] The server stores the evaluation results in a database and notifies the user of the information.

[0362] Step 11:

[0363] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[0364] Step 12:

[0365] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[0366] Step 13:

[0367] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion.

[0368] Step 14:

[0369] The server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[0370] Step 15:

[0371] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[0372] Step 16:

[0373] The server provides the generated performance report in a user-viewable format to the web interface.

[0374] Step 17:

[0375] Users can use their devices to check the results reports and download them if necessary.

[0376] Step 18:

[0377] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[0378] Step 19:

[0379] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[0380] Step 20:

[0381] Users can use the device to check their own ratings and compare them with other companies.

[0382] Example 2

[0383] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0384] Conventional systems lack the means to efficiently evaluate and report on initiatives related to the Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG), and in particular lack the means to reflect user sentiment in the evaluation. As a result, it is difficult to accurately grasp the performance of activities and the effectiveness of initiatives, and more effective evaluation and improvement methods are needed.

[0385] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0386] In this invention, the server includes means for inputting initial data into a user terminal, means for transmitting the input initial data to a central server, means for formulating evaluation indexes based on the generated data, and means for automatically measuring activity performance based on the evaluation indexes. This enables the collection of initial data, the formulation of evaluation indexes, and the measurement of activity performance. The server also includes means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for recognizing emotional data and converting it into an evaluation index, and means for integrating the emotional data to adjust the evaluation of activity performance. This enables a more accurate and comprehensive evaluation that reflects the user's emotional data in the evaluation.

[0387] "Initial data" refers to basic data that allows users to input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.).

[0388] A "user terminal" is a computing device used by a user to enter data and view performance reports.

[0389] A "central server" is a computing system that receives, analyzes, and evaluates data transmitted from user terminals.

[0390] "Generated data" refers to data that is newly generated based on collected information and analysis results.

[0391] "Evaluation indicators" are specific indicators (e.g., "energy efficiency" or "carbon emission reduction") used to evaluate a company's performance based on the SDGs and ESG standards.

[0392] "Activity Performance" is the outcome of a company's efforts, calculated based on daily data entered by the user.

[0393] "Measurement results" are evaluation data of activity performance analyzed using AI models and evaluation indicators.

[0394] A "database" is a data storage system for storing and managing measurement results, initial data, and generated data.

[0395] The "Results Report" is a detailed report on SDGs and ESG generated based on data collected by a central server.

[0396] "Emotion data" refers to data related to emotions recognized from the user's voice, text, facial expressions, etc.

[0397] The "emotion engine" is a component that analyzes the user's voice, text, facial expressions, etc. to generate and recognize emotional data.

[0398] "Rating" is the process of evaluating a company's efforts toward the SDGs and ESG and assigning it a rank (for example, from A to F).

[0399] A "web interface" is a user interface that allows users to view performance reports, rating results, etc. via the Internet.

[0400] MODE FOR CARRYING OUT THE INVENTION

[0401] The present invention is a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and more effectively grasp, report, and improve the results of their efforts by recognizing and utilizing user emotions. Specific embodiments of this system are described below.

[0402] System configuration

[0403] The system consists of the following main components:

[0404] 1. User Device

[0405] 2. Central Server

[0406] 3. Database

[0407] 4. Results report generation module

[0408] 5. Display and display interface

[0409] 6. Emotion Engine

[0410] Hardware and Software

[0411] User terminal: Uses a computing device such as a PC or smartphone.

[0412] Central server: A high-performance cloud server is used to process and store data, and is particularly responsible for sending and receiving data using APIs.

[0413] Database: An SQL database is used to store and manage evaluation data and initial data.

[0414] Results report generation module: Implemented using a program using Python or JavaScript.

[0415] Display and Presentation Interface: Build a web-based interface using HTML, CSS, and JavaScript.

[0416] Emotion Engine: Uses Python to parse emotion data using natural language processing (NLP) libraries and facial recognition algorithms.

[0417] Data processing and calculation

[0418] Entering and saving initial data

[0419] The user inputs the energy consumption, recycling rate, and exhaust gas volume into the terminal. For example, the user can provide specific figures such as "energy consumption: 1000 kWh" and "recycling rate: 80%."

[0420] The device sends the entered data in JSON format to a central server.

[0421] Generating evaluation metrics

[0422] The server passes the received initial data to the LLM and generates evaluation indicators (e.g., "energy efficiency" or "carbon emission reduction").

[0423] The generated metrics are stored in an SQL database.

[0424] Measuring and storing activity performance

[0425] The user inputs daily activity data (for example, daily energy consumption, "Energy consumption: 950 kWh") from the terminal and transmits it to the server.

[0426] The server uses an AI model to analyze the data and generate a result, such as "energy consumption successfully reduced by 10%."

[0427] The measurement results are stored in a database.

[0428] Recognizing and Using Emotional Data

[0429] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions, and generates positive and negative scores using, for example, text analysis and facial recognition technology.

[0430] The server converts the emotion data into evaluation metrics and integrates them into the evaluation of activity performance.

[0431] Generate and view performance reports

[0432] At the end of the month, the server aggregates all the data and generates a performance report with items such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[0433] The results report is provided to the user via a web interface and can be saved, for example in PDF format, via a "download" button.

[0434] SDGs / ESG Ratings

[0435] The server integrates the latest evaluation data and sentiment data to rank companies' SDGs and ESG initiatives, and stores the ranking results in a database.

[0436] Users can use the terminal to check their own rating information and compare it with other companies.

[0437] Examples of specific examples and prompts

[0438] As a concrete example, the sequence of events from when a user inputs initial data to when the server generates evaluation metrics is as follows:

[0439] When a user enters data such as "energy consumption: 1000 kWh" and "recycling rate: 80%" into a terminal and sends the data to the server, the server requests analysis from LLM, generates evaluation indicators such as "energy efficiency" and "carbon emission reduction," and stores them in a database.

[0440] Example prompt sentence:

[0441] "Generate metrics to assess a company's sustainability based on the following SDGs: energy consumption, recycling rate, carbon emissions."

[0442] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0443] Step 1: Enter and submit initial data

[0444] The user inputs initial data (energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal. For example, the energy consumption is "1000 kWh" and the recycling rate is "80%."

[0445] The device converts the entered data into JSON format and sends it to the central server via an HTTP POST request.

[0446] Input: Energy consumption, recycling rate, exhaust gas volume (specific numerical data)

[0447] Output: JSON formatted data sent

[0448] Step 2: Analyze initial data and generate evaluation metrics

[0449] The server passes the received initial data to an LLM (large-scale language model) for analysis.

[0450] Based on the analysis results returned by the LLM, the server generates evaluation indicators based on SDGs and ESG, such as "energy efficiency" and "carbon emission reduction."

[0451] The server stores the generated evaluation indexes in a database.

[0452] Input: Initial data sent to the server in JSON format

[0453] Output: Evaluation metrics stored in a database

[0454] Step 3: Enter and submit your daily activity data

[0455] The user inputs daily activity data (e.g., daily energy consumption, recycling activity records) into the terminal. For example, data such as "energy consumption: 950 kWh" is input.

[0456] The device converts this daily activity data into JSON format and sends it to a central server via an HTTP POST request.

[0457] Input: Daily energy consumption, recycling activity records (specific numerical data)

[0458] Output: Daily data sent in JSON format

[0459] Step 4: Analyze and evaluate activity data

[0460] The server passes the received daily activity data to the AI ​​model for analysis.

[0461] The server uses an AI model to analyze activity data based on evaluation metrics.

[0462] As a result of the analysis, the server generates a specific evaluation, such as "successfully reduced energy consumption by 10%."

[0463] The measurement results are stored in a database.

[0464] Input: Daily activity data in JSON format sent to the server

[0465] Output: Evaluation results stored in a database

[0466] Step 5: Recognize and analyze emotion data

[0467] The emotion engine recognizes emotion data from the user's voice, text, facial expressions, etc. For example, inputs include voice recordings, text input, and camera images.

[0468] The emotion engine analyzes the recognized emotion data and converts it into an appropriate evaluation index, for example, generating a positive or negative score.

[0469] The emotion engine sends the analysis results to a central server.

[0470] Input: User voice, text, and facial expression data

[0471] Output: Analyzed emotion data (evaluation index)

[0472] Step 6: Integrating emotion and activity data

[0473] The server integrates the emotion data with daily activity data and adjusts the evaluation of activity performance based on the user's emotion using a weighting algorithm.

[0474] The server stores the integrated evaluation results in a database.

[0475] Input: Emotion data, daily activity data

[0476] Output: Adjusted evaluation results stored in a database

[0477] Step 7: Generate and view the results report

[0478] At the end of the month, the server aggregates and analyzes all the data collected so far and generates a detailed performance report, with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[0479] The server converts the generated results report into a format that can be displayed in the web interface. A template engine is used to generate the HTML report.

[0480] Users can use their devices to view the results report through a web interface and download it in PDF format if desired.

[0481] Input: All data collected so far

[0482] Output: Generated outcome report

[0483] Step 8: SDG / ESG Rating

[0484] The server will rank companies on their SDGs and ESG initiatives based on the latest evaluation and sentiment data, using a six-point scale from A to F.

[0485] The server stores the rating results in a database and notifies the user via an API.

[0486] Users can use the terminal to check their own ratings and compare them with other companies.

[0487] Input: Latest evaluation data, emotion data

[0488] Output: Rating results stored in the database and information communicated to the user

[0489] (Application example 2)

[0490] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0491] When small and medium-sized enterprises evaluate their Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG) initiatives, traditional systems typically evaluate only environmental data. However, this can result in an inaccurate assessment of a company's overall performance. In particular, evaluations that ignore the impact of employee emotions and motivation on performance are incomplete and difficult to reflect actual results. Furthermore, the lack of real-time data collection and evaluation makes it difficult to take timely action.

[0492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0493] In this invention, the server includes means for formulating evaluation indexes based on generated data, means for automatically measuring activity performance based on the evaluation indexes, means for saving the measurement results in a database, means for generating a performance report from the saved data, means for displaying the generated performance report, means for collecting environmental data in real time, means for recognizing and analyzing emotional data, means for adjusting activity performance by integrating the environmental data and the emotional data, and means for including the emotional data in the performance report. This enables companies to perform comprehensive and accurate activity performance evaluations in real time that take into account not only environmental data but also employee emotional data.

[0494] "Generated Data" refers to the set of data obtained by the system from its initial setup and daily activities.

[0495] "Evaluation index" refers to a criterion for evaluating activity performance that is analyzed based on generated data.

[0496] "Activity performance" refers to the implementation status and results of a company's sustainable initiatives.

[0497] A "database" is an information management system for storing generated data, measurement results, evaluation indicators, etc.

[0498] A "results report" is a report generated by organizing and analyzing the saved data and its evaluation results.

[0499] The "display means" refers to an interface for providing the generated performance report, rating results, etc. to the user.

[0500] "Environmental data" refers to information related to the environment, such as energy consumption, recycling rates, and the amount of pollutants in the air.

[0501] "Emotion data" refers to information about emotions obtained from the user's voice, text, facial expressions, etc.

[0502] The "means for adjusting the evaluation index" refers to a function for resetting the evaluation index based on the environmental data and the emotion data.

[0503] "Rating" refers to ranking the level of a company's efforts based on the generated activity performance measurement results.

[0504] An "LLM (Large-Scale Language Model)" is a model that uses natural language processing technology to analyze large amounts of data and extract knowledge and information.

[0505] This invention is a system that efficiently evaluates the Sustainable Development Goals (SDGs) and Environmental, Social and Governance (ESG) initiatives of small and medium-sized enterprises, and recognizes and utilizes user sentiment. The system consists of the following main components:

[0506] System configuration

[0507] User terminal: A device used by factory managers and employees to input data and interact with the system. This can be a smartphone, tablet, or PC.

[0508] Central Server: This is the main computer system that analyzes, evaluates, ranks, and generates reports. It requires a high-performance processor and a large amount of memory.

[0509] Database: A data management system for permanently storing generated data, evaluation indicators, activity performance data, etc.

[0510] Emotion engine: A software module for recognizing emotions from a user's voice, text, and facial expressions. It uses deep learning libraries such as TensorFlow and PyTorch.

[0511] Display interface: This is the interface for providing the generated performance reports and evaluation results to the user. It is displayed in a web browser or mobile application.

[0512] Program processing overview

[0513] The central server receives environmental data and emotional data sent from user devices in real time. The server formulates evaluation indicators based on this data and automatically measures and evaluates activity performance based on the generated evaluation indicators. The evaluation results are stored in a database, and at the end of the month, a performance report is generated and displayed to the user. Emotional data is used to adjust the evaluation of activity performance.

[0514] Specific example explanation

[0515] For example, a factory manager can input their daily energy consumption data into the system via their smartphone, and the data will be sent to a central server. The server will then use an emotion engine to recognize the emotion "satisfied" from the manager's voice report. It will then integrate environmental and emotion data to adjust activity performance. This allows the system to provide a more comprehensive and accurate evaluation, and at the end of the month, a performance report will be generated, including "energy efficiency this month" and "employee satisfaction."

[0516] Prompt Sentence Examples

[0517] "Analyze the voice data, recognize the user's emotions, and output the following: emotions such as 'satisfied', 'dissatisfied', 'fatigued', etc."

[0518] User says: "My energy consumption is below my goal today."

[0519] Expected Output: Emotion: Satisfied

[0520] As described above, this invention is a system that efficiently evaluates, reports, and improves SDGs and ESG initiatives by integrating environmental data and emotional data to evaluate activity performance.

[0521] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0522] Step 1:

[0523] The user inputs environmental data such as energy consumption and recycling rate into the terminal as initial data. The input data is sent from the user terminal to the central server. At this time, the input data is sent to the server in text format.

[0524] Step 2:

[0525] The central server analyzes the received initial data and formulates evaluation indicators using a large-scale language model (LLM). Specifically, the generated data is passed to the LLM, and specific evaluation indicators such as "energy efficiency" and "recycling rate" are generated based on the results of analyzing the environmental data. The server stores these evaluation indicators in a database.

[0526] Step 3:

[0527] Users input their daily activity data (e.g., daily energy consumption data and recycling activity records) into their terminals, which are then transmitted to a central server.

[0528] Step 4:

[0529] The central server passes the received daily activity data to the AI ​​model, which then automatically measures activity performance based on the evaluation index. Specifically, the activity data is compared with the evaluation index and a specific evaluation result, such as "successfully reduced energy consumption by 10%," is generated. This result is stored in a database.

[0530] Step 5:

[0531] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions. When a user reports work to the system by voice using a smartphone or tablet, the voice data is input into the emotion engine. The emotion engine analyzes the voice data and recognizes emotions such as "satisfaction" or "fatigue." The resulting emotional data is sent to the server.

[0532] Step 6:

[0533] The central server integrates the emotion data and activity data to adjust the evaluation of activity performance. Specifically, it resets the evaluation indicators based on the emotion data and recalculates the evaluation results. This evaluation adjustment enables more accurate evaluation. This data is also stored in the database.

[0534] Step 7:

[0535] At the end of the month, the central server compiles all the collected data, evaluation results, and emotional data to generate a performance report. The report includes information such as this month's energy consumption and reduction rate, the results of recycling efforts, and employee emotional data. This performance report is presented to users in a format they can view through the display interface.

[0536] Step 8:

[0537] Finally, the central server will rate the company's SDGs and ESG initiatives based on the latest evaluation data and sentiment data. The results of this rating are rated on a six-point scale from A to F and displayed for users to check on their devices. Users can also compare their performance with other companies.

[0538] This will enable the system to efficiently support the sustainability efforts of small and medium-sized enterprises and provide more comprehensive and accurate assessments.

[0539] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0540] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0541] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0542] [Second embodiment]

[0543] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0544] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0545] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0546] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0547] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0548] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0549] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0550] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0551] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0552] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0553] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0554] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0555] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific modes for carrying out the invention are described below.

[0556] System configuration

[0557] The system consists of the following main components:

[0558] 1. User Device

[0559] 2. Central Server

[0560] 3. Database

[0561] 4. Results report generation module

[0562] 5. Display and display interface

[0563] Specific examples of program processing

[0564] Initial Data Entry

[0565] As an initial setting, users input data related to the SDGs and ESG into the device, such as energy consumption, recycling rate, and exhaust gas volume.

[0566] The terminal transmits the entered data to a central server.

[0567] Establishment of evaluation indicators

[0568] The server passes the received initial data to the LLM (Large Scale Language Model).

[0569] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0570] Uploading daily activity data

[0571] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0572] The devices transmit these daily activity data to a central server.

[0573] Measuring activity performance

[0574] The server passes the received daily activity data to the AI ​​model.

[0575] The server uses an AI model to analyze this data based on evaluation indicators and automatically measure activity performance, generating evaluation results such as "successfully reduced energy consumption by 10%."

[0576] Generate and view performance reports

[0577] At the end of the month, the server collects and organizes all collected data and its evaluation results.

[0578] Based on the collected data, the server generates a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[0579] The server provides the generated performance report in a format that can be viewed by the user, and the report is displayed on a display, which the user can download as needed.

[0580] SDGs / ESG Ratings

[0581] The server uses the latest evaluation data to perform calculations to rank companies' efforts toward SDGs and ESG.

[0582] The server rates companies on a six-point scale from A to F. The ratings are then presented to the user in a web interface for review.

[0583] Users can use the device to check their own rating and compare it with other small and medium-sized businesses.

[0584] Specific examples

[0585] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs the energy consumption and recycling rate as initial data into a terminal and sends the data to a server.

[0586] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[0587] 3. The user uploads daily energy consumption data from the device to the server.

[0588] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[0589] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[0590] 6. The server then uses this data to assign an SDG rating, giving it an A rank, and displays the result to the user.

[0591] As described above, this system provides a mechanism for SMEs to efficiently evaluate their SDG and ESG initiatives and confirm their results. This makes it easier for companies to understand the effects of their efforts and promotes actions toward realizing a sustainable society.

[0592] The processing flow will be explained below.

[0593] Step 1:

[0594] Users input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, and gas emissions) into the terminal as initial data.

[0595] Step 2:

[0596] The terminal transmits the entered initial data to the central server.

[0597] Step 3:

[0598] The server passes the received initial data to the LLM (Large Scale Language Model).

[0599] Step 4:

[0600] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0601] Step 5:

[0602] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[0603] Step 6:

[0604] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0605] Step 7:

[0606] The device sends daily activity data to a server.

[0607] Step 8:

[0608] The server passes the received daily activity data to the AI ​​model.

[0609] Step 9:

[0610] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[0611] Step 10:

[0612] The server stores the evaluation results in a database and notifies the user of the information.

[0613] Step 11:

[0614] At the end of the month, the server collects and organizes all the data collected so far and its evaluation results.

[0615] Step 12:

[0616] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[0617] Step 13:

[0618] The server provides the performance report in a user-viewable format to the web interface.

[0619] Step 14:

[0620] Users can check the results report on their device and download it if necessary.

[0621] Step 15:

[0622] The server performs calculations based on the latest evaluation data to rank companies' efforts toward SDGs and ESG.

[0623] Step 16:

[0624] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[0625] Step 17:

[0626] Users can use the device to check their own ratings and compare them with other companies.

[0627] This will enable companies to efficiently evaluate and confirm the effectiveness of their SDGs and ESG initiatives.

[0628] Example 1

[0629] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0630] With conventional systems, it has been extremely difficult for small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare their results. In particular, there has been a demand for a system that automates the entire process of collecting, analyzing, evaluating, and reporting activity data, making it easy to use. In addition, there has been a lack of means to rate a company's efforts, making it difficult to compare them with other companies. The objective of this invention is to solve these problems.

[0631] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0632] In this invention, the server includes means for receiving and storing initial data entered by a user, means for converting the initial data into an analysis format, means for passing the data converted into the analysis format to a large-scale language model (LLM), means for generating evaluation indicators from the data analyzed by the LLM and saving them in a database, means for a user to input daily activity data and send it to the server, means for converting the sent daily activity data into an analysis format, means for passing the data converted into the analysis format to an AI model and automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, and means for generating monthly performance reports from the saved data and displaying them to the user via a web interface. This enables efficient evaluation of a company's efforts, checking its results in real time, and comparing it with other companies.

[0633] A "user" is an individual or company employee who uses the system to enter or view data.

[0634] "Initial data" refers to data related to the SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance), such as energy consumption, recycling rates, and exhaust gas emissions.

[0635] A "large-scale language model (LLM)" is an AI algorithm for analyzing natural language data and generating more advanced information.

[0636] "Evaluation indicators" are specific indicators such as energy efficiency and recycling rates that are generated based on SDGs and ESG standards.

[0637] "Daily activity data" refers to data such as energy consumption data and recycling activity records that are input by the user in relation to their daily activities.

[0638] An "AI model" is an artificial intelligence algorithm that analyzes collected data and evaluates activity performance.

[0639] "Operational performance" refers to the achievements and results that are automatically measured based on a company's daily activities, and includes, for example, the rate of reduction in energy consumption.

[0640] "Measurement results" are specific evaluation results of activity performance analyzed by the AI ​​model.

[0641] A "database" is an electronic storage device for storing received data, analysis results, generated evaluation indexes, and the like.

[0642] The "Results Report" is a report generated based on the saved data that shows the results of a company's SDGs and ESG initiatives.

[0643] A "web interface" is an online operating screen that allows users to view performance reports and rating results.

[0644] The "rating" involves evaluating and ranking a company's SDGs and ESG initiatives on a six-point scale from A to F based on the latest evaluation data.

[0645] Embodiments of the invention

[0646] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific embodiments for carrying out the invention are described below.

[0647] System configuration

[0648] The system consists of the following main components:

[0649] 1. User Device

[0650] 2. Central Server

[0651] 3. Database

[0652] 4. Results report generation module

[0653] 5. Display and display interface

[0654] User terminal

[0655] The user terminal is a device that users use to input their initial data and daily activity data. This can be a PC, tablet, smartphone, etc. The user enters the data through a dedicated input screen and sends it to the central server.

[0656] Central Server

[0657] The central server is the main computing unit that processes and stores the data it receives. The server uses the following software and hardware:

[0658] LLM (Large Scale Language Model): Used to analyze natural language data and generate evaluation metrics.

[0659] AI model: Using frameworks such as TensorFlow, it analyzes daily activity data and automatically measures activity performance.

[0660] Database: Received data, analysis results, evaluation indicators, rating results, etc. are stored using PostgreSQL or similar.

[0661] Database

[0662] The database is a storage unit for securely storing and managing all data received on a central server, including initial data, daily data, analysis results, evaluation indicators, performance reports, and rating results.

[0663] Results report generation module

[0664] The performance report generation module is a software component that aggregates monthly data and generates reports that show the results of the company's efforts. It generates performance reports in plain text and PDF format.

[0665] Displays and display interfaces

[0666] The display and viewing interface is the interface that users use to view the generated performance reports and rating results. This is provided through a web browser, allowing users to easily compare their own efforts and the results of their efforts with those of other companies.

[0667] Specific examples

[0668] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rate as initial data into a user terminal and transmits the data to a central server.

[0669] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[0670] 3. Users upload their daily energy consumption data from their devices to a central server.

[0671] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[0672] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[0673] 6. The server then uses this data to rate the company on SDGs, assigning it an A rank and displaying the results to the user.

[0674] Prompt Sentence Examples

[0675] "This system efficiently evaluates the SDGs and ESG efforts of small and medium-sized enterprises, and allows them to report and compare their results. Specifically, users input data such as energy consumption and recycling rates, and the server uses LLM and AI models to generate evaluation indicators and measure activity performance. At the end of the month, an outcome report is generated and the company's efforts are ranked based on the results."

[0676] In this way, the present invention provides a concrete method for small and medium-sized enterprises to efficiently evaluate their SDGs and ESG initiatives and confirm and compare their results, thereby supporting the sustainable development of companies.

[0677] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0678] Step 1:

[0679] The user inputs the initial data into the user terminal.

[0680] Input data such as energy consumption, recycling rate, and exhaust gas volume is entered through an input form.

[0681] The device converts this input data into packets and sends them over secure communications to a central server, which then receives the data.

[0682] Step 2:

[0683] The server converts the received initial data into a format for analysis.

[0684] As input, it receives data sent from the terminal.

[0685] The server runs a program to convert this data into JSON format, and the output is JSON data that can be parsed.

[0686] Step 3:

[0687] The server passes the converted data to a large-scale language model (LLM).

[0688] As input, it uses the converted JSON data for parsing.

[0689] The server requests analysis by sending data to the API endpoint of LLM, and receives the analysis results from LLM as output.

[0690] Step 4:

[0691] The server generates evaluation metrics from the data analyzed by LLM and stores them in a database.

[0692] As input, evaluation indicators are generated based on the analysis results obtained from the LLM.

[0693] The server executes the evaluation metric generation algorithm and stores the evaluation results in a PostgreSQL database. As an output, the evaluation metrics are stored in the database.

[0694] Step 5:

[0695] The user inputs and transmits daily activity data into the user terminal.

[0696] Inputs include daily energy consumption data and records of recycling activities.

[0697] The device converts daily data into packets and sends them to a central server, which then receives the data.

[0698] Step 6:

[0699] A server converts the received daily activity data into a format for analysis.

[0700] As input, it uses daily data received from the terminal.

[0701] The server runs a program that converts the daily data into CSV format, and generates CSV data as output for analysis.

[0702] Step 7:

[0703] The server passes the converted daily data to an AI model, which automatically measures activity performance based on evaluation indicators.

[0704] As input, it uses the CSV data that has been transformed for analysis.

[0705] The server inputs the data into the AI ​​model for analysis and evaluation, and generates an evaluation result of activity performance as the output.

[0706] Step 8:

[0707] The server stores the measurement results in a database.

[0708] As input, it uses the activity performance evaluation results generated by the AI ​​model.

[0709] The server stores the evaluation results in a PostgreSQL database. As an output, the measurement results are stored in the database.

[0710] Step 9:

[0711] At the end of the month, the server generates a performance report based on the accumulated data.

[0712] As input, the query retrieves all data in the database.

[0713] The server runs the outcome report generation algorithm to generate an outcome report in plain text or PDF format. As an output, an outcome report is generated.

[0714] Step 10:

[0715] The server displays the generated performance report to the user via a web interface.

[0716] Use the generated outcome report as input.

[0717] The server generates HTML pages for the web interface and serves them to the user, allowing the user to view the report as output.

[0718] Step 11:

[0719] The user can view the generated results report through a web interface and download it if necessary.

[0720] As an input, you log in through the web interface and view the performance report.

[0721] The terminal executes the download command and saves the results report in PDF format. As an output, the report is saved on the user's terminal.

[0722] Step 12:

[0723] The server will rate companies' efforts toward SDGs and ESG based on the latest evaluation data.

[0724] It uses the most recent evaluation data in the database as input.

[0725] The server runs a rating algorithm and rates the company's efforts on a six-point scale (A to F). The rating is generated as an output.

[0726] Step 13:

[0727] The server provides the rating results in a web interface that can be viewed by the user.

[0728] As input, the rating results are used.

[0729] The server generates a page for a web interface that allows users to view the rating results, and as an output, the rating results are displayed on a web page.

[0730] Step 14:

[0731] Users use a web interface to view their own ratings and compare them with other small businesses.

[0732] As an input, log in to the web interface.

[0733] The terminal displays the rating results and accesses a comparison page with other companies. As an output, users can compare their own evaluation results with those of other companies.

[0734] In this way, the system can efficiently evaluate the SDGs and ESG initiatives of small and medium-sized enterprises, check their results in real time, and compare them with other companies.

[0735] (Application example 1)

[0736] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0737] Current systems for efficiently and accurately evaluating and reporting on SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) initiatives for small and medium-sized enterprises require manual data entry and analysis, which is time-consuming and costly. Furthermore, the inability to collect and analyze data in real time makes it difficult to make quick decisions. Furthermore, because evaluation results and reports are generated manually, the data lacks reliability and consistency, making comparisons and analysis difficult.

[0738] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0739] In this invention, the server includes means for formulating evaluation indicators based on generated data, means for automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for the robot to collect environmental data and operational data, means for transmitting the collected data to a cloud server, and means for converting the analysis results into an evaluation report on the cloud server. This enables small and medium-sized enterprises to automatically collect and analyze data on SDGs and ESG activities in real time and efficiently generate and display evaluation reports.

[0740] "Generated data" refers to various data related to the SDGs and ESG initiatives of small and medium-sized enterprises, including energy consumption, recycling rates, and emissions.

[0741] "Evaluation indicators" are specific measurement standards set based on SDGs and ESG criteria, and include energy efficiency and carbon emission reduction.

[0742] "Activity Performance" evaluates a company's daily performance in relation to SDGs and ESG initiatives.

[0743] "Measurement results" are the results of a company's activity performance calculated based on evaluation indicators.

[0744] A "database" is a system for storing data such as measurement results.

[0745] The "Results Report" is a report generated based on the saved data, detailing the results of a company's SDGs and ESG initiatives.

[0746] "Display means" refers to a device or interface for presenting the generated result report in a format that can be viewed by the user.

[0747] A "robot" is an automated device that operates within a factory and collects environmental and operational data.

[0748] "Environmental data" refers to data related to the environment, such as energy consumption and exhaust gas emissions at factories.

[0749] "Operational data" refers to data related to production activities and the operating status of equipment within a factory.

[0750] A "cloud server" is a remote server that provides data and services over the Internet.

[0751] An "evaluation report" is a report generated based on data analyzed on a cloud server that details the results of a company's SDGs and ESG initiatives.

[0752] "Real-time" refers to a state in which data collection, analysis, and display are carried out immediately without delay.

[0753] System configuration

[0754] The system of the present invention comprises the following main components:

[0755] 1. User Device

[0756] 2. Robot

[0757] 3. Cloud Server

[0758] 4. Database

[0759] 5. Results report generation module

[0760] 6. Display and display interface

[0761] Program processing

[0762] Data collection and transmission

[0763] Robots operating in factories collect environmental and operational data in real time. The robots are equipped with sensors such as energy consumption meters and exhaust gas sensors, and acquire data from these sensors. The acquired data is then sent to a cloud server via a network module.

[0764] Data analysis and generation of evaluation indicators

[0765] The cloud server passes the received data to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. These evaluation indicators are stored in a database.

[0766] Measuring activity performance

[0767] The server passes daily activity data to the AI ​​model, which analyzes it based on evaluation indicators. This generates a measurement result for activity performance. For example, a measurement result such as "successfully reduced energy consumption by 10%" is generated. These measurement results are stored in a database.

[0768] Generate and view performance reports

[0769] The cloud server organizes all collected data and evaluation results and generates a performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts." The generated performance report is provided in a format that can be viewed by users. It can be monitored in real time via user terminals, displays, and mobile devices.

[0770] Specific examples

[0771] 1. The user initializes the system and inputs initial data such as energy consumption and recycling rate.

[0772] 2. The robot collects environmental and operational data within the factory and sends it to a cloud server.

[0773] 3. The server passes the received data to the LLM, which generates evaluation metrics from the analyzed data.

[0774] 4. The server uses an AI model to analyze daily activity data and measure activity performance.

[0775] 5. The server generates a performance report and displays it on the user's terminal or display.

[0776] Prompt Sentence Examples

[0777] "Based on the energy consumption and recycling data for the following factory, please evaluate it based on the SDGs indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[0778] Specific hardware and software names to be used

[0779] Robot: Automated equipment for collecting environmental and operational data

[0780] Sensors: Energy consumption meter, exhaust gas sensor

[0781] Network module: for data transmission

[0782] Cloud server: A server for running LLM and AI models (e.g., AWS, Google Cloud)

[0783] LLM: Large-scale language model (e.g., OpenAI GPT-4)

[0784] Database: A system for storing measurement results and evaluation indicators (e.g., MySQL, PostgreSQL)

[0785] Displays and mobile devices: devices that display the generated outcome reports

[0786] In this way, the system can efficiently evaluate and report on SMEs' SDGs and ESG activities and promote improvements.

[0787] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0788] Step 1:

[0789] Entering initial data

[0790] The user inputs initial data such as energy consumption and recycling rate into the user terminal. The terminal then sends the initial data entered by the user to the cloud server. The input initial data is stored on the server and used to develop evaluation indicators.

[0791] Step 2:

[0792] Robotic data collection

[0793] Robots collect environmental and operational data within the factory using energy consumption meters, exhaust gas sensors, etc. The robots then send the collected data to a cloud server via a network. Input: Environmental and operational data. Output: Data stored on the cloud server.

[0794] Step 3:

[0795] Data analysis and evaluation index generation

[0796] The cloud server passes the data received from the robot to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. Input: Environmental data and operational data stored on the cloud server. Output: Evaluation indicators.

[0797] Step 4:

[0798] Measuring activity performance

[0799] The server uses an AI model to automatically measure activity performance based on evaluation indicators. It analyzes daily activity data and measures specific results (e.g., successful 10% reduction in energy consumption). Input: Evaluation indicators and daily activity data. Output: Measurement results.

[0800] Step 5:

[0801] Saving measurement results

[0802] The server stores the measurement results in a database. Input: Measurement results. Output: Measurement results stored in the database.

[0803] Step 6:

[0804] Generate a performance report

[0805] The server generates a performance report based on the stored measurement results. The report includes the current month's energy consumption, reduction rate, and recycling effort results. Input: Measurement results stored in the database. Output: Performance report.

[0806] Step 7:

[0807] View the results report

[0808] The server provides the generated results report in a format that can be viewed by the user. It can be monitored in real time through the user's terminal, display, or mobile terminal. Input: Results report. Output: Results report displayed on the user's terminal or display.

[0809] Step 8:

[0810] Generate prompt statement

[0811] The server generates prompts for data analysis of the factory's SDG / ESG efforts. Example: "Based on the energy consumption data and recycling data of the following factory, please evaluate it based on SDG indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[0812] Input: Target data. Output: Generated prompt sentence.

[0813] Through the above processing steps, this system can efficiently evaluate the SDGs and ESG activities of small and medium-sized enterprises, and confirm and improve their results in real time.

[0814] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0815] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in the areas of SDGs (Sustainable Development Goals) and ESG (Environment, Social and Governance), and also recognizes and utilizes user emotions to more effectively understand, report and improve the results of those efforts.

[0816] System configuration

[0817] The system consists of the following main components:

[0818] 1. User Device

[0819] 2. Central Server

[0820] 3. Database

[0821] 4. Results report generation module

[0822] 5. Display and display interface

[0823] 6. Emotion Engine

[0824] Specific examples of program processing

[0825] Initial Data Entry

[0826] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[0827] The terminal transmits the entered data to a central server.

[0828] Establishment of evaluation indicators

[0829] The server passes the received initial data to the LLM (Large Scale Language Model).

[0830] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0831] Uploading daily activity data

[0832] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0833] The device transmits this daily activity data to a server.

[0834] Measuring activity performance

[0835] The server passes the received daily activity data to the AI ​​model.

[0836] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[0837] Recognizing and Using Emotional Data

[0838] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[0839] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[0840] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion, thereby providing a more accurate evaluation.

[0841] Generate and view performance reports

[0842] At the end of the month, the server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[0843] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[0844] The server provides the generated performance report in a user-viewable format to the web interface.

[0845] Users can use their devices to check the results reports and download them if necessary.

[0846] SDGs / ESG Ratings

[0847] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[0848] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[0849] Users can use the device to check their own ratings and compare them with other companies.

[0850] Specific examples

[0851] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rates as initial data into a terminal and sends the data to a server.

[0852] 2. The server analyzes this data using LLM to generate evaluation indicators such as "energy efficiency" and "recycling rate."

[0853] 3. The user uploads daily energy consumption data from the device to the server.

[0854] 4. The server uses an AI model to analyze the daily data and obtains the evaluation result: "This month's energy consumption has been successfully reduced by 10%."

[0855] 5. The emotion engine recognizes the emotion data when the user inputs the day's work report by voice and sends the data to the server.

[0856] 6. The server converts the emotion data into evaluation metrics, integrates them with performance evaluations, and generates an outcome report.

[0857] 7. The server provides the user with a report summarizing the generated results and emotion data.

[0858] 8. The server then performs an SDGs rating based on the data, assigns an A rank, and displays the rating results to the user.

[0859] In this way, by incorporating user sentiment data into the evaluation of SDGs and ESG initiatives, the system provides a more comprehensive and appropriate evaluation, efficiently supporting the sustainable initiatives of small and medium-sized enterprises.

[0860] The processing flow will be explained below.

[0861] Step 1:

[0862] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[0863] Step 2:

[0864] The terminal transmits the entered initial data to the central server.

[0865] Step 3:

[0866] The server passes the received initial data to the LLM (Large Scale Language Model).

[0867] Step 4:

[0868] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[0869] Step 5:

[0870] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[0871] Step 6:

[0872] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[0873] Step 7:

[0874] The device sends daily activity data to a server.

[0875] Step 8:

[0876] The server passes the received daily activity data to the AI ​​model.

[0877] Step 9:

[0878] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[0879] Step 10:

[0880] The server stores the evaluation results in a database and notifies the user of the information.

[0881] Step 11:

[0882] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[0883] Step 12:

[0884] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[0885] Step 13:

[0886] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion.

[0887] Step 14:

[0888] The server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[0889] Step 15:

[0890] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[0891] Step 16:

[0892] The server provides the generated performance report in a user-viewable format to the web interface.

[0893] Step 17:

[0894] Users can use their devices to check the results reports and download them if necessary.

[0895] Step 18:

[0896] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[0897] Step 19:

[0898] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[0899] Step 20:

[0900] Users can use the device to check their own ratings and compare them with other companies.

[0901] Example 2

[0902] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0903] Conventional systems lack the means to efficiently evaluate and report on initiatives related to the Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG), and in particular lack the means to reflect user sentiment in the evaluation. As a result, it is difficult to accurately grasp the performance of activities and the effectiveness of initiatives, and more effective evaluation and improvement methods are needed.

[0904] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0905] In this invention, the server includes means for inputting initial data into a user terminal, means for transmitting the input initial data to a central server, means for formulating evaluation indexes based on the generated data, and means for automatically measuring activity performance based on the evaluation indexes. This enables the collection of initial data, the formulation of evaluation indexes, and the measurement of activity performance. The server also includes means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for recognizing emotional data and converting it into an evaluation index, and means for integrating the emotional data to adjust the evaluation of activity performance. This enables a more accurate and comprehensive evaluation that reflects the user's emotional data in the evaluation.

[0906] "Initial data" refers to basic data that allows users to input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.).

[0907] A "user terminal" is a computing device used by a user to enter data and view performance reports.

[0908] A "central server" is a computing system that receives, analyzes, and evaluates data transmitted from user terminals.

[0909] "Generated data" refers to data that is newly generated based on collected information and analysis results.

[0910] "Evaluation indicators" are specific indicators (e.g., "energy efficiency" or "carbon emission reduction") used to evaluate a company's performance based on the SDGs and ESG standards.

[0911] "Activity Performance" is the outcome of a company's efforts, calculated based on daily data entered by the user.

[0912] "Measurement results" are evaluation data of activity performance analyzed using AI models and evaluation indicators.

[0913] A "database" is a data storage system for storing and managing measurement results, initial data, and generated data.

[0914] The "Results Report" is a detailed report on SDGs and ESG generated based on data collected by a central server.

[0915] "Emotion data" refers to data related to emotions recognized from the user's voice, text, facial expressions, etc.

[0916] The "emotion engine" is a component that analyzes the user's voice, text, facial expressions, etc. to generate and recognize emotional data.

[0917] "Rating" is the process of evaluating a company's efforts toward the SDGs and ESG and assigning it a rank (for example, from A to F).

[0918] A "web interface" is a user interface that allows users to view performance reports, rating results, etc. via the Internet.

[0919] MODE FOR CARRYING OUT THE INVENTION

[0920] The present invention is a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and more effectively grasp, report, and improve the results of their efforts by recognizing and utilizing user emotions. Specific embodiments of this system are described below.

[0921] System configuration

[0922] The system consists of the following main components:

[0923] 1. User Device

[0924] 2. Central Server

[0925] 3. Database

[0926] 4. Results report generation module

[0927] 5. Display and display interface

[0928] 6. Emotion Engine

[0929] Hardware and Software

[0930] User terminal: Uses a computing device such as a PC or smartphone.

[0931] Central server: A high-performance cloud server is used to process and store data, and is particularly responsible for sending and receiving data using APIs.

[0932] Database: An SQL database is used to store and manage evaluation data and initial data.

[0933] Results report generation module: Implemented using a program using Python or JavaScript.

[0934] Display and Presentation Interface: Build a web-based interface using HTML, CSS, and JavaScript.

[0935] Emotion Engine: Uses Python to parse emotion data using natural language processing (NLP) libraries and facial recognition algorithms.

[0936] Data processing and calculation

[0937] Entering and saving initial data

[0938] The user inputs the energy consumption, recycling rate, and exhaust gas volume into the terminal. For example, the user can provide specific figures such as "energy consumption: 1000 kWh" and "recycling rate: 80%."

[0939] The device sends the entered data in JSON format to a central server.

[0940] Generating evaluation metrics

[0941] The server passes the received initial data to the LLM and generates evaluation indicators (e.g., "energy efficiency" or "carbon emission reduction").

[0942] The generated metrics are stored in an SQL database.

[0943] Measuring and storing activity performance

[0944] The user inputs daily activity data (for example, daily energy consumption, "Energy consumption: 950 kWh") from the terminal and transmits it to the server.

[0945] The server uses an AI model to analyze the data and generate a result, such as "energy consumption successfully reduced by 10%."

[0946] The measurement results are stored in a database.

[0947] Recognizing and Using Emotional Data

[0948] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions, and generates positive and negative scores using, for example, text analysis and facial recognition technology.

[0949] The server converts the emotion data into evaluation metrics and integrates them into the evaluation of activity performance.

[0950] Generate and view performance reports

[0951] At the end of the month, the server aggregates all the data and generates a performance report with items such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[0952] The results report is provided to the user via a web interface and can be saved, for example in PDF format, via a "download" button.

[0953] SDGs / ESG Ratings

[0954] The server integrates the latest evaluation data and sentiment data to rank companies' SDGs and ESG initiatives, and stores the ranking results in a database.

[0955] Users can use the terminal to check their own rating information and compare it with other companies.

[0956] Examples of specific examples and prompts

[0957] As a concrete example, the sequence of events from when a user inputs initial data to when the server generates evaluation metrics is as follows:

[0958] When a user enters data such as "energy consumption: 1000 kWh" and "recycling rate: 80%" into a terminal and sends the data to the server, the server requests analysis from LLM, generates evaluation indicators such as "energy efficiency" and "carbon emission reduction," and stores them in a database.

[0959] Example prompt sentence:

[0960] "Generate metrics to assess a company's sustainability based on the following SDGs: energy consumption, recycling rate, carbon emissions."

[0961] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0962] Step 1: Enter and submit initial data

[0963] The user inputs initial data (energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal. For example, the energy consumption is "1000 kWh" and the recycling rate is "80%."

[0964] The device converts the entered data into JSON format and sends it to the central server via an HTTP POST request.

[0965] Input: Energy consumption, recycling rate, exhaust gas volume (specific numerical data)

[0966] Output: JSON formatted data sent

[0967] Step 2: Analyze initial data and generate evaluation metrics

[0968] The server passes the received initial data to an LLM (large-scale language model) for analysis.

[0969] Based on the analysis results returned by the LLM, the server generates evaluation indicators based on SDGs and ESG, such as "energy efficiency" and "carbon emission reduction."

[0970] The server stores the generated evaluation indexes in a database.

[0971] Input: Initial data sent to the server in JSON format

[0972] Output: Evaluation metrics stored in a database

[0973] Step 3: Enter and submit your daily activity data

[0974] The user inputs daily activity data (e.g., daily energy consumption, recycling activity records) into the terminal. For example, data such as "energy consumption: 950 kWh" is input.

[0975] The device converts this daily activity data into JSON format and sends it to a central server via an HTTP POST request.

[0976] Input: Daily energy consumption, recycling activity records (specific numerical data)

[0977] Output: Daily data sent in JSON format

[0978] Step 4: Analyze and evaluate activity data

[0979] The server passes the received daily activity data to the AI ​​model for analysis.

[0980] The server uses an AI model to analyze activity data based on evaluation metrics.

[0981] As a result of the analysis, the server generates a specific evaluation, such as "successfully reduced energy consumption by 10%."

[0982] The measurement results are stored in a database.

[0983] Input: Daily activity data in JSON format sent to the server

[0984] Output: Evaluation results stored in a database

[0985] Step 5: Recognize and analyze emotion data

[0986] The emotion engine recognizes emotion data from the user's voice, text, facial expressions, etc. For example, inputs include voice recordings, text input, and camera images.

[0987] The emotion engine analyzes the recognized emotion data and converts it into an appropriate evaluation index, for example, generating a positive or negative score.

[0988] The emotion engine sends the analysis results to a central server.

[0989] Input: User voice, text, and facial expression data

[0990] Output: Analyzed emotion data (evaluation index)

[0991] Step 6: Integrating emotion and activity data

[0992] The server integrates the emotion data with daily activity data and adjusts the evaluation of activity performance based on the user's emotion using a weighting algorithm.

[0993] The server stores the integrated evaluation results in a database.

[0994] Input: Emotion data, daily activity data

[0995] Output: Adjusted evaluation results stored in a database

[0996] Step 7: Generate and view the results report

[0997] At the end of the month, the server aggregates and analyzes all the data collected so far and generates a detailed performance report, with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[0998] The server converts the generated results report into a format that can be displayed in the web interface. A template engine is used to generate the HTML report.

[0999] Users can use their devices to view the results report through a web interface and download it in PDF format if desired.

[1000] Input: All data collected so far

[1001] Output: Generated outcome report

[1002] Step 8: SDG / ESG Rating

[1003] The server will rank companies on their SDGs and ESG initiatives based on the latest evaluation and sentiment data, using a six-point scale from A to F.

[1004] The server stores the rating results in a database and notifies the user via an API.

[1005] Users can use the terminal to check their own ratings and compare them with other companies.

[1006] Input: Latest evaluation data, emotion data

[1007] Output: Rating results stored in the database and information communicated to the user

[1008] (Application example 2)

[1009] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1010] When small and medium-sized enterprises evaluate their Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG) initiatives, traditional systems typically evaluate only environmental data. However, this can result in an inaccurate assessment of a company's overall performance. In particular, evaluations that ignore the impact of employee emotions and motivation on performance are incomplete and difficult to reflect actual results. Furthermore, the lack of real-time data collection and evaluation makes it difficult to take timely action.

[1011] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1012] In this invention, the server includes means for formulating evaluation indexes based on generated data, means for automatically measuring activity performance based on the evaluation indexes, means for saving the measurement results in a database, means for generating a performance report from the saved data, means for displaying the generated performance report, means for collecting environmental data in real time, means for recognizing and analyzing emotional data, means for adjusting activity performance by integrating the environmental data and the emotional data, and means for including the emotional data in the performance report. This enables companies to perform comprehensive and accurate activity performance evaluations in real time that take into account not only environmental data but also employee emotional data.

[1013] "Generated Data" refers to the set of data obtained by the system from its initial setup and daily activities.

[1014] "Evaluation index" refers to a criterion for evaluating activity performance that is analyzed based on generated data.

[1015] "Activity performance" refers to the implementation status and results of a company's sustainable initiatives.

[1016] A "database" is an information management system for storing generated data, measurement results, evaluation indicators, etc.

[1017] A "results report" is a report generated by organizing and analyzing the saved data and its evaluation results.

[1018] The "display means" refers to an interface for providing the generated performance report, rating results, etc. to the user.

[1019] "Environmental data" refers to information related to the environment, such as energy consumption, recycling rates, and the amount of pollutants in the air.

[1020] "Emotion data" refers to information about emotions obtained from the user's voice, text, facial expressions, etc.

[1021] The "means for adjusting the evaluation index" refers to a function for resetting the evaluation index based on the environmental data and the emotion data.

[1022] "Rating" refers to ranking the level of a company's efforts based on the generated activity performance measurement results.

[1023] An "LLM (Large-Scale Language Model)" is a model that uses natural language processing technology to analyze large amounts of data and extract knowledge and information.

[1024] This invention is a system that efficiently evaluates the Sustainable Development Goals (SDGs) and Environmental, Social and Governance (ESG) initiatives of small and medium-sized enterprises, and recognizes and utilizes user sentiment. The system consists of the following main components:

[1025] System configuration

[1026] User terminal: A device used by factory managers and employees to input data and interact with the system. This can be a smartphone, tablet, or PC.

[1027] Central Server: This is the main computer system that analyzes, evaluates, ranks, and generates reports. It requires a high-performance processor and a large amount of memory.

[1028] Database: A data management system for permanently storing generated data, evaluation indicators, activity performance data, etc.

[1029] Emotion engine: A software module for recognizing emotions from a user's voice, text, and facial expressions. It uses deep learning libraries such as TensorFlow and PyTorch.

[1030] Display interface: This is the interface for providing the generated performance reports and evaluation results to the user. It is displayed in a web browser or mobile application.

[1031] Program processing overview

[1032] The central server receives environmental data and emotional data sent from user devices in real time. The server formulates evaluation indicators based on this data and automatically measures and evaluates activity performance based on the generated evaluation indicators. The evaluation results are stored in a database, and at the end of the month, a performance report is generated and displayed to the user. Emotional data is used to adjust the evaluation of activity performance.

[1033] Specific example explanation

[1034] For example, a factory manager can input their daily energy consumption data into the system via their smartphone, and the data will be sent to a central server. The server will then use an emotion engine to recognize the emotion "satisfied" from the manager's voice report. It will then integrate environmental and emotion data to adjust activity performance. This allows the system to provide a more comprehensive and accurate evaluation, and at the end of the month, a performance report will be generated, including "energy efficiency this month" and "employee satisfaction."

[1035] Prompt Sentence Examples

[1036] "Analyze the voice data, recognize the user's emotions, and output the following: emotions such as 'satisfied', 'dissatisfied', 'fatigued', etc."

[1037] User says: "My energy consumption is below my goal today."

[1038] Expected Output: Emotion: Satisfied

[1039] As described above, this invention is a system that efficiently evaluates, reports, and improves SDGs and ESG initiatives by integrating environmental data and emotional data to evaluate activity performance.

[1040] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1041] Step 1:

[1042] The user inputs environmental data such as energy consumption and recycling rate into the terminal as initial data. The input data is sent from the user terminal to the central server. At this time, the input data is sent to the server in text format.

[1043] Step 2:

[1044] The central server analyzes the received initial data and formulates evaluation indicators using a large-scale language model (LLM). Specifically, the generated data is passed to the LLM, and specific evaluation indicators such as "energy efficiency" and "recycling rate" are generated based on the results of analyzing the environmental data. The server stores these evaluation indicators in a database.

[1045] Step 3:

[1046] Users input their daily activity data (e.g., daily energy consumption data and recycling activity records) into their terminals, which are then transmitted to a central server.

[1047] Step 4:

[1048] The central server passes the received daily activity data to the AI ​​model, which then automatically measures activity performance based on the evaluation index. Specifically, the activity data is compared with the evaluation index and a specific evaluation result, such as "successfully reduced energy consumption by 10%," is generated. This result is stored in a database.

[1049] Step 5:

[1050] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions. When a user reports work to the system by voice using a smartphone or tablet, the voice data is input into the emotion engine. The emotion engine analyzes the voice data and recognizes emotions such as "satisfaction" or "fatigue." The resulting emotional data is sent to the server.

[1051] Step 6:

[1052] The central server integrates the emotion data and activity data to adjust the evaluation of activity performance. Specifically, it resets the evaluation indicators based on the emotion data and recalculates the evaluation results. This evaluation adjustment enables more accurate evaluation. This data is also stored in the database.

[1053] Step 7:

[1054] At the end of the month, the central server compiles all the collected data, evaluation results, and emotional data to generate a performance report. The report includes information such as this month's energy consumption and reduction rate, the results of recycling efforts, and employee emotional data. This performance report is presented to users in a format they can view through the display interface.

[1055] Step 8:

[1056] Finally, the central server will rate the company's SDGs and ESG initiatives based on the latest evaluation data and sentiment data. The results of this rating are rated on a six-point scale from A to F and displayed for users to check on their devices. Users can also compare their performance with other companies.

[1057] This will enable the system to efficiently support the sustainability efforts of small and medium-sized enterprises and provide more comprehensive and accurate assessments.

[1058] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1059] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1060] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1061] [Third embodiment]

[1062] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1063] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1064] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1065] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1066] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1067] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1068] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1069] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1070] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1071] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1072] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1073] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1074] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific modes for carrying out the invention are described below.

[1075] System configuration

[1076] The system consists of the following main components:

[1077] 1. User Device

[1078] 2. Central Server

[1079] 3. Database

[1080] 4. Results report generation module

[1081] 5. Display and display interface

[1082] Specific examples of program processing

[1083] Initial Data Entry

[1084] As an initial setting, users input data related to the SDGs and ESG into the device, such as energy consumption, recycling rate, and exhaust gas volume.

[1085] The terminal transmits the entered data to a central server.

[1086] Establishment of evaluation indicators

[1087] The server passes the received initial data to the LLM (Large Scale Language Model).

[1088] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1089] Uploading daily activity data

[1090] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1091] The devices transmit these daily activity data to a central server.

[1092] Measuring activity performance

[1093] The server passes the received daily activity data to the AI ​​model.

[1094] The server uses an AI model to analyze this data based on evaluation indicators and automatically measure activity performance, generating evaluation results such as "successfully reduced energy consumption by 10%."

[1095] Generate and view performance reports

[1096] At the end of the month, the server collects and organizes all collected data and its evaluation results.

[1097] Based on the collected data, the server generates a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[1098] The server provides the generated performance report in a format that can be viewed by the user, and the report is displayed on a display, which the user can download as needed.

[1099] SDGs / ESG Ratings

[1100] The server uses the latest evaluation data to perform calculations to rank companies' efforts toward SDGs and ESG.

[1101] The server rates companies on a six-point scale from A to F. The ratings are then presented to the user in a web interface for review.

[1102] Users can use the device to check their own rating and compare it with other small and medium-sized businesses.

[1103] Specific examples

[1104] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs the energy consumption and recycling rate as initial data into a terminal and sends the data to a server.

[1105] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[1106] 3. The user uploads daily energy consumption data from the device to the server.

[1107] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[1108] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[1109] 6. The server then uses this data to assign an SDG rating, giving it an A rank, and displays the result to the user.

[1110] As described above, this system provides a mechanism for SMEs to efficiently evaluate their SDG and ESG initiatives and confirm their results. This makes it easier for companies to understand the effects of their efforts and promotes actions toward realizing a sustainable society.

[1111] The processing flow will be explained below.

[1112] Step 1:

[1113] Users input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, and gas emissions) into the terminal as initial data.

[1114] Step 2:

[1115] The terminal transmits the entered initial data to the central server.

[1116] Step 3:

[1117] The server passes the received initial data to the LLM (Large Scale Language Model).

[1118] Step 4:

[1119] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1120] Step 5:

[1121] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[1122] Step 6:

[1123] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1124] Step 7:

[1125] The device sends daily activity data to a server.

[1126] Step 8:

[1127] The server passes the received daily activity data to the AI ​​model.

[1128] Step 9:

[1129] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[1130] Step 10:

[1131] The server stores the evaluation results in a database and notifies the user of the information.

[1132] Step 11:

[1133] At the end of the month, the server collects and organizes all the data collected so far and its evaluation results.

[1134] Step 12:

[1135] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[1136] Step 13:

[1137] The server provides the performance report in a user-viewable format to the web interface.

[1138] Step 14:

[1139] Users can check the results report on their device and download it if necessary.

[1140] Step 15:

[1141] The server performs calculations based on the latest evaluation data to rank companies' efforts toward SDGs and ESG.

[1142] Step 16:

[1143] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[1144] Step 17:

[1145] Users can use the device to check their own ratings and compare them with other companies.

[1146] This will enable companies to efficiently evaluate and confirm the effectiveness of their SDGs and ESG initiatives.

[1147] Example 1

[1148] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1149] With conventional systems, it has been extremely difficult for small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare their results. In particular, there has been a demand for a system that automates the entire process of collecting, analyzing, evaluating, and reporting activity data, making it easy to use. In addition, there has been a lack of means to rate a company's efforts, making it difficult to compare them with other companies. The objective of this invention is to solve these problems.

[1150] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1151] In this invention, the server includes means for receiving and storing initial data entered by a user, means for converting the initial data into an analysis format, means for passing the data converted into the analysis format to a large-scale language model (LLM), means for generating evaluation indicators from the data analyzed by the LLM and saving them in a database, means for a user to input daily activity data and send it to the server, means for converting the sent daily activity data into an analysis format, means for passing the data converted into the analysis format to an AI model and automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, and means for generating monthly performance reports from the saved data and displaying them to the user via a web interface. This enables efficient evaluation of a company's efforts, checking its results in real time, and comparing it with other companies.

[1152] A "user" is an individual or company employee who uses the system to enter or view data.

[1153] "Initial data" refers to data related to the SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance), such as energy consumption, recycling rates, and exhaust gas emissions.

[1154] A "large-scale language model (LLM)" is an AI algorithm for analyzing natural language data and generating more advanced information.

[1155] "Evaluation indicators" are specific indicators such as energy efficiency and recycling rates that are generated based on SDGs and ESG standards.

[1156] "Daily activity data" refers to data such as energy consumption data and recycling activity records that are input by the user in relation to their daily activities.

[1157] An "AI model" is an artificial intelligence algorithm that analyzes collected data and evaluates activity performance.

[1158] "Operational performance" refers to the achievements and results that are automatically measured based on a company's daily activities, and includes, for example, the rate of reduction in energy consumption.

[1159] "Measurement results" are specific evaluation results of activity performance analyzed by the AI ​​model.

[1160] A "database" is an electronic storage device for storing received data, analysis results, generated evaluation indexes, and the like.

[1161] The "Results Report" is a report generated based on the saved data that shows the results of a company's SDGs and ESG initiatives.

[1162] A "web interface" is an online operating screen that allows users to view performance reports and rating results.

[1163] The "rating" involves evaluating and ranking a company's SDGs and ESG initiatives on a six-point scale from A to F based on the latest evaluation data.

[1164] Embodiments of the invention

[1165] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific embodiments for carrying out the invention are described below.

[1166] System configuration

[1167] The system consists of the following main components:

[1168] 1. User Device

[1169] 2. Central Server

[1170] 3. Database

[1171] 4. Results report generation module

[1172] 5. Display and display interface

[1173] User terminal

[1174] The user terminal is a device that users use to input their initial data and daily activity data. This can be a PC, tablet, smartphone, etc. The user enters the data through a dedicated input screen and sends it to the central server.

[1175] Central Server

[1176] The central server is the main computing unit that processes and stores the data it receives. The server uses the following software and hardware:

[1177] LLM (Large Scale Language Model): Used to analyze natural language data and generate evaluation metrics.

[1178] AI model: Using frameworks such as TensorFlow, it analyzes daily activity data and automatically measures activity performance.

[1179] Database: Received data, analysis results, evaluation indicators, rating results, etc. are stored using PostgreSQL or similar.

[1180] Database

[1181] The database is a storage unit for securely storing and managing all data received on a central server, including initial data, daily data, analysis results, evaluation indicators, performance reports, and rating results.

[1182] Results report generation module

[1183] The performance report generation module is a software component that aggregates monthly data and generates reports that show the results of the company's efforts. It generates performance reports in plain text and PDF format.

[1184] Displays and display interfaces

[1185] The display and viewing interface is the interface that users use to view the generated performance reports and rating results. This is provided through a web browser, allowing users to easily compare their own efforts and the results of their efforts with those of other companies.

[1186] Specific examples

[1187] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rate as initial data into a user terminal and transmits the data to a central server.

[1188] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[1189] 3. Users upload their daily energy consumption data from their devices to a central server.

[1190] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[1191] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[1192] 6. The server then uses this data to rate the company on SDGs, assigning it an A rank and displaying the results to the user.

[1193] Prompt Sentence Examples

[1194] "This system efficiently evaluates the SDGs and ESG efforts of small and medium-sized enterprises, and allows them to report and compare their results. Specifically, users input data such as energy consumption and recycling rates, and the server uses LLM and AI models to generate evaluation indicators and measure activity performance. At the end of the month, an outcome report is generated and the company's efforts are ranked based on the results."

[1195] In this way, the present invention provides a concrete method for small and medium-sized enterprises to efficiently evaluate their SDGs and ESG initiatives and confirm and compare their results, thereby supporting the sustainable development of companies.

[1196] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1197] Step 1:

[1198] The user inputs the initial data into the user terminal.

[1199] Input data such as energy consumption, recycling rate, and exhaust gas volume is entered through an input form.

[1200] The device converts this input data into packets and sends them over secure communications to a central server, which then receives the data.

[1201] Step 2:

[1202] The server converts the received initial data into a format for analysis.

[1203] As input, it receives data sent from the terminal.

[1204] The server runs a program to convert this data into JSON format, and the output is JSON data that can be parsed.

[1205] Step 3:

[1206] The server passes the converted data to a large-scale language model (LLM).

[1207] As input, it uses the converted JSON data for parsing.

[1208] The server requests analysis by sending data to the API endpoint of LLM, and receives the analysis results from LLM as output.

[1209] Step 4:

[1210] The server generates evaluation metrics from the data analyzed by LLM and stores them in a database.

[1211] As input, evaluation indicators are generated based on the analysis results obtained from the LLM.

[1212] The server executes the evaluation metric generation algorithm and stores the evaluation results in a PostgreSQL database. As an output, the evaluation metrics are stored in the database.

[1213] Step 5:

[1214] The user inputs and transmits daily activity data into the user terminal.

[1215] Inputs include daily energy consumption data and records of recycling activities.

[1216] The device converts daily data into packets and sends them to a central server, which then receives the data.

[1217] Step 6:

[1218] A server converts the received daily activity data into a format for analysis.

[1219] As input, it uses daily data received from the terminal.

[1220] The server runs a program that converts the daily data into CSV format, and generates CSV data as output for analysis.

[1221] Step 7:

[1222] The server passes the converted daily data to an AI model, which automatically measures activity performance based on evaluation indicators.

[1223] As input, it uses the CSV data that has been transformed for analysis.

[1224] The server inputs the data into the AI ​​model for analysis and evaluation, and generates an evaluation result of activity performance as the output.

[1225] Step 8:

[1226] The server stores the measurement results in a database.

[1227] As input, it uses the activity performance evaluation results generated by the AI ​​model.

[1228] The server stores the evaluation results in a PostgreSQL database. As an output, the measurement results are stored in the database.

[1229] Step 9:

[1230] At the end of the month, the server generates a performance report based on the accumulated data.

[1231] As input, the query retrieves all data in the database.

[1232] The server runs the outcome report generation algorithm to generate an outcome report in plain text or PDF format. As an output, an outcome report is generated.

[1233] Step 10:

[1234] The server displays the generated performance report to the user via a web interface.

[1235] Use the generated outcome report as input.

[1236] The server generates HTML pages for the web interface and serves them to the user, allowing the user to view the report as output.

[1237] Step 11:

[1238] The user can view the generated results report through a web interface and download it if necessary.

[1239] As an input, you log in through the web interface and view the performance report.

[1240] The terminal executes the download command and saves the results report in PDF format. As an output, the report is saved on the user's terminal.

[1241] Step 12:

[1242] The server will rate companies' efforts toward SDGs and ESG based on the latest evaluation data.

[1243] It uses the most recent evaluation data in the database as input.

[1244] The server runs a rating algorithm and rates the company's efforts on a six-point scale (A to F). The rating is generated as an output.

[1245] Step 13:

[1246] The server provides the rating results in a web interface that can be viewed by the user.

[1247] As input, the rating results are used.

[1248] The server generates a page for a web interface that allows users to view the rating results, and as an output, the rating results are displayed on a web page.

[1249] Step 14:

[1250] Users use a web interface to view their own ratings and compare them with other small businesses.

[1251] As an input, log in to the web interface.

[1252] The terminal displays the rating results and accesses a comparison page with other companies. As an output, users can compare their own evaluation results with those of other companies.

[1253] In this way, the system can efficiently evaluate the SDGs and ESG initiatives of small and medium-sized enterprises, check their results in real time, and compare them with other companies.

[1254] (Application example 1)

[1255] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1256] Current systems for efficiently and accurately evaluating and reporting on SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) initiatives for small and medium-sized enterprises require manual data entry and analysis, which is time-consuming and costly. Furthermore, the inability to collect and analyze data in real time makes it difficult to make quick decisions. Furthermore, because evaluation results and reports are generated manually, the data lacks reliability and consistency, making comparisons and analysis difficult.

[1257] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1258] In this invention, the server includes means for formulating evaluation indicators based on generated data, means for automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for the robot to collect environmental data and operational data, means for transmitting the collected data to a cloud server, and means for converting the analysis results into an evaluation report on the cloud server. This enables small and medium-sized enterprises to automatically collect and analyze data on SDGs and ESG activities in real time and efficiently generate and display evaluation reports.

[1259] "Generated data" refers to various data related to the SDGs and ESG initiatives of small and medium-sized enterprises, including energy consumption, recycling rates, and emissions.

[1260] "Evaluation indicators" are specific measurement standards set based on SDGs and ESG criteria, and include energy efficiency and carbon emission reduction.

[1261] "Activity Performance" evaluates a company's daily performance in relation to SDGs and ESG initiatives.

[1262] "Measurement results" are the results of a company's activity performance calculated based on evaluation indicators.

[1263] A "database" is a system for storing data such as measurement results.

[1264] The "Results Report" is a report generated based on the saved data, detailing the results of a company's SDGs and ESG initiatives.

[1265] "Display means" refers to a device or interface for presenting the generated result report in a format that can be viewed by the user.

[1266] A "robot" is an automated device that operates within a factory and collects environmental and operational data.

[1267] "Environmental data" refers to data related to the environment, such as energy consumption and exhaust gas emissions at factories.

[1268] "Operational data" refers to data related to production activities and the operating status of equipment within a factory.

[1269] A "cloud server" is a remote server that provides data and services over the Internet.

[1270] An "evaluation report" is a report generated based on data analyzed on a cloud server that details the results of a company's SDGs and ESG initiatives.

[1271] "Real-time" refers to a state in which data collection, analysis, and display are carried out immediately without delay.

[1272] System configuration

[1273] The system of the present invention comprises the following main components:

[1274] 1. User Device

[1275] 2. Robot

[1276] 3. Cloud Server

[1277] 4. Database

[1278] 5. Results report generation module

[1279] 6. Display and display interface

[1280] Program processing

[1281] Data collection and transmission

[1282] Robots operating in factories collect environmental and operational data in real time. The robots are equipped with sensors such as energy consumption meters and exhaust gas sensors, and acquire data from these sensors. The acquired data is then sent to a cloud server via a network module.

[1283] Data analysis and generation of evaluation indicators

[1284] The cloud server passes the received data to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. These evaluation indicators are stored in a database.

[1285] Measuring activity performance

[1286] The server passes daily activity data to the AI ​​model, which analyzes it based on evaluation indicators. This generates a measurement result for activity performance. For example, a measurement result such as "successfully reduced energy consumption by 10%" is generated. These measurement results are stored in a database.

[1287] Generate and view performance reports

[1288] The cloud server organizes all collected data and evaluation results and generates a performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts." The generated performance report is provided in a format that can be viewed by users. It can be monitored in real time via user terminals, displays, and mobile devices.

[1289] Specific examples

[1290] 1. The user initializes the system and inputs initial data such as energy consumption and recycling rate.

[1291] 2. The robot collects environmental and operational data within the factory and sends it to a cloud server.

[1292] 3. The server passes the received data to the LLM, which generates evaluation metrics from the analyzed data.

[1293] 4. The server uses an AI model to analyze daily activity data and measure activity performance.

[1294] 5. The server generates a performance report and displays it on the user's terminal or display.

[1295] Prompt Sentence Examples

[1296] "Based on the energy consumption and recycling data for the following factory, please evaluate it based on the SDGs indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[1297] Specific hardware and software names to be used

[1298] Robot: Automated equipment for collecting environmental and operational data

[1299] Sensors: Energy consumption meter, exhaust gas sensor

[1300] Network module: for data transmission

[1301] Cloud server: A server for running LLM and AI models (e.g., AWS, Google Cloud)

[1302] LLM: Large-scale language model (e.g., OpenAI GPT-4)

[1303] Database: A system for storing measurement results and evaluation indicators (e.g., MySQL, PostgreSQL)

[1304] Displays and mobile devices: devices that display the generated outcome reports

[1305] In this way, the system can efficiently evaluate and report on SMEs' SDGs and ESG activities and promote improvements.

[1306] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1307] Step 1:

[1308] Entering initial data

[1309] The user inputs initial data such as energy consumption and recycling rate into the user terminal. The terminal then sends the initial data entered by the user to the cloud server. The input initial data is stored on the server and used to develop evaluation indicators.

[1310] Step 2:

[1311] Robotic data collection

[1312] Robots collect environmental and operational data within the factory using energy consumption meters, exhaust gas sensors, etc. The robots then send the collected data to a cloud server via a network. Input: Environmental and operational data. Output: Data stored on the cloud server.

[1313] Step 3:

[1314] Data analysis and evaluation index generation

[1315] The cloud server passes the data received from the robot to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. Input: Environmental data and operational data stored on the cloud server. Output: Evaluation indicators.

[1316] Step 4:

[1317] Measuring activity performance

[1318] The server uses an AI model to automatically measure activity performance based on evaluation indicators. It analyzes daily activity data and measures specific results (e.g., successful 10% reduction in energy consumption). Input: Evaluation indicators and daily activity data. Output: Measurement results.

[1319] Step 5:

[1320] Saving measurement results

[1321] The server stores the measurement results in a database. Input: Measurement results. Output: Measurement results stored in the database.

[1322] Step 6:

[1323] Generate a performance report

[1324] The server generates a performance report based on the stored measurement results. The report includes the current month's energy consumption, reduction rate, and recycling effort results. Input: Measurement results stored in the database. Output: Performance report.

[1325] Step 7:

[1326] View the results report

[1327] The server provides the generated results report in a format that can be viewed by the user. It can be monitored in real time through the user's terminal, display, or mobile terminal. Input: Results report. Output: Results report displayed on the user's terminal or display.

[1328] Step 8:

[1329] Generate prompt statement

[1330] The server generates prompts for data analysis of the factory's SDG / ESG efforts. Example: "Based on the energy consumption data and recycling data of the following factory, please evaluate it based on SDG indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[1331] Input: Target data. Output: Generated prompt sentence.

[1332] Through the above processing steps, this system can efficiently evaluate the SDGs and ESG activities of small and medium-sized enterprises, and confirm and improve their results in real time.

[1333] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1334] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in the areas of SDGs (Sustainable Development Goals) and ESG (Environment, Social and Governance), and also recognizes and utilizes user emotions to more effectively understand, report and improve the results of those efforts.

[1335] System configuration

[1336] The system consists of the following main components:

[1337] 1. User Device

[1338] 2. Central Server

[1339] 3. Database

[1340] 4. Results report generation module

[1341] 5. Display and display interface

[1342] 6. Emotion Engine

[1343] Specific examples of program processing

[1344] Initial Data Entry

[1345] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[1346] The terminal transmits the entered data to a central server.

[1347] Establishment of evaluation indicators

[1348] The server passes the received initial data to the LLM (Large Scale Language Model).

[1349] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1350] Uploading daily activity data

[1351] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1352] The device transmits this daily activity data to a server.

[1353] Measuring activity performance

[1354] The server passes the received daily activity data to the AI ​​model.

[1355] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[1356] Recognizing and Using Emotional Data

[1357] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[1358] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[1359] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion, thereby providing a more accurate evaluation.

[1360] Generate and view performance reports

[1361] At the end of the month, the server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[1362] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[1363] The server provides the generated performance report in a user-viewable format to the web interface.

[1364] Users can use their devices to check the results reports and download them if necessary.

[1365] SDGs / ESG Ratings

[1366] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[1367] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[1368] Users can use the device to check their own ratings and compare them with other companies.

[1369] Specific examples

[1370] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rates as initial data into a terminal and sends the data to a server.

[1371] 2. The server analyzes this data using LLM to generate evaluation indicators such as "energy efficiency" and "recycling rate."

[1372] 3. The user uploads daily energy consumption data from the device to the server.

[1373] 4. The server uses an AI model to analyze the daily data and obtains the evaluation result: "This month's energy consumption has been successfully reduced by 10%."

[1374] 5. The emotion engine recognizes the emotion data when the user inputs the day's work report by voice and sends the data to the server.

[1375] 6. The server converts the emotion data into evaluation metrics, integrates them with performance evaluations, and generates an outcome report.

[1376] 7. The server provides the user with a report summarizing the generated results and emotion data.

[1377] 8. The server then performs an SDGs rating based on the data, assigns an A rank, and displays the rating results to the user.

[1378] In this way, by incorporating user sentiment data into the evaluation of SDGs and ESG initiatives, the system provides a more comprehensive and appropriate evaluation, efficiently supporting the sustainable initiatives of small and medium-sized enterprises.

[1379] The processing flow will be explained below.

[1380] Step 1:

[1381] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[1382] Step 2:

[1383] The terminal transmits the entered initial data to the central server.

[1384] Step 3:

[1385] The server passes the received initial data to the LLM (Large Scale Language Model).

[1386] Step 4:

[1387] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1388] Step 5:

[1389] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[1390] Step 6:

[1391] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1392] Step 7:

[1393] The device sends daily activity data to a server.

[1394] Step 8:

[1395] The server passes the received daily activity data to the AI ​​model.

[1396] Step 9:

[1397] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[1398] Step 10:

[1399] The server stores the evaluation results in a database and notifies the user of the information.

[1400] Step 11:

[1401] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[1402] Step 12:

[1403] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[1404] Step 13:

[1405] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion.

[1406] Step 14:

[1407] The server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[1408] Step 15:

[1409] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[1410] Step 16:

[1411] The server provides the generated performance report in a user-viewable format to the web interface.

[1412] Step 17:

[1413] Users can use their devices to check the results reports and download them if necessary.

[1414] Step 18:

[1415] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[1416] Step 19:

[1417] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[1418] Step 20:

[1419] Users can use the device to check their own ratings and compare them with other companies.

[1420] Example 2

[1421] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1422] Conventional systems lack the means to efficiently evaluate and report on initiatives related to the Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG), and in particular lack the means to reflect user sentiment in the evaluation. As a result, it is difficult to accurately grasp the performance of activities and the effectiveness of initiatives, and more effective evaluation and improvement methods are needed.

[1423] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1424] In this invention, the server includes means for inputting initial data into a user terminal, means for transmitting the input initial data to a central server, means for formulating evaluation indexes based on the generated data, and means for automatically measuring activity performance based on the evaluation indexes. This enables the collection of initial data, the formulation of evaluation indexes, and the measurement of activity performance. The server also includes means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for recognizing emotional data and converting it into an evaluation index, and means for integrating the emotional data to adjust the evaluation of activity performance. This enables a more accurate and comprehensive evaluation that reflects the user's emotional data in the evaluation.

[1425] "Initial data" refers to basic data that allows users to input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.).

[1426] A "user terminal" is a computing device used by a user to enter data and view performance reports.

[1427] A "central server" is a computing system that receives, analyzes, and evaluates data transmitted from user terminals.

[1428] "Generated data" refers to data that is newly generated based on collected information and analysis results.

[1429] "Evaluation indicators" are specific indicators (e.g., "energy efficiency" or "carbon emission reduction") used to evaluate a company's performance based on the SDGs and ESG standards.

[1430] "Activity Performance" is the outcome of a company's efforts, calculated based on daily data entered by the user.

[1431] "Measurement results" are evaluation data of activity performance analyzed using AI models and evaluation indicators.

[1432] A "database" is a data storage system for storing and managing measurement results, initial data, and generated data.

[1433] The "Results Report" is a detailed report on SDGs and ESG generated based on data collected by a central server.

[1434] "Emotion data" refers to data related to emotions recognized from the user's voice, text, facial expressions, etc.

[1435] The "emotion engine" is a component that analyzes the user's voice, text, facial expressions, etc. to generate and recognize emotional data.

[1436] "Rating" is the process of evaluating a company's efforts toward the SDGs and ESG and assigning it a rank (for example, from A to F).

[1437] A "web interface" is a user interface that allows users to view performance reports, rating results, etc. via the Internet.

[1438] MODE FOR CARRYING OUT THE INVENTION

[1439] The present invention is a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and more effectively grasp, report, and improve the results of their efforts by recognizing and utilizing user emotions. Specific embodiments of this system are described below.

[1440] System configuration

[1441] The system consists of the following main components:

[1442] 1. User Device

[1443] 2. Central Server

[1444] 3. Database

[1445] 4. Results report generation module

[1446] 5. Display and display interface

[1447] 6. Emotion Engine

[1448] Hardware and Software

[1449] User terminal: Uses a computing device such as a PC or smartphone.

[1450] Central server: A high-performance cloud server is used to process and store data, and is particularly responsible for sending and receiving data using APIs.

[1451] Database: An SQL database is used to store and manage evaluation data and initial data.

[1452] Results report generation module: Implemented using a program using Python or JavaScript.

[1453] Display and Presentation Interface: Build a web-based interface using HTML, CSS, and JavaScript.

[1454] Emotion Engine: Uses Python to parse emotion data using natural language processing (NLP) libraries and facial recognition algorithms.

[1455] Data processing and calculation

[1456] Entering and saving initial data

[1457] The user inputs the energy consumption, recycling rate, and exhaust gas volume into the terminal. For example, the user can provide specific figures such as "energy consumption: 1000 kWh" and "recycling rate: 80%."

[1458] The device sends the entered data in JSON format to a central server.

[1459] Generating evaluation metrics

[1460] The server passes the received initial data to the LLM and generates evaluation indicators (e.g., "energy efficiency" or "carbon emission reduction").

[1461] The generated metrics are stored in an SQL database.

[1462] Measuring and storing activity performance

[1463] The user inputs daily activity data (for example, daily energy consumption, "Energy consumption: 950 kWh") from the terminal and transmits it to the server.

[1464] The server uses an AI model to analyze the data and generate a result, such as "energy consumption successfully reduced by 10%."

[1465] The measurement results are stored in a database.

[1466] Recognizing and Using Emotional Data

[1467] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions, and generates positive and negative scores using, for example, text analysis and facial recognition technology.

[1468] The server converts the emotion data into evaluation metrics and integrates them into the evaluation of activity performance.

[1469] Generate and view performance reports

[1470] At the end of the month, the server aggregates all the data and generates a performance report with items such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[1471] The results report is provided to the user via a web interface and can be saved, for example in PDF format, via a "download" button.

[1472] SDGs / ESG Ratings

[1473] The server integrates the latest evaluation data and sentiment data to rank companies' SDGs and ESG initiatives, and stores the ranking results in a database.

[1474] Users can use the terminal to check their own rating information and compare it with other companies.

[1475] Examples of specific examples and prompts

[1476] As a concrete example, the sequence of events from when a user inputs initial data to when the server generates evaluation metrics is as follows:

[1477] When a user enters data such as "energy consumption: 1000 kWh" and "recycling rate: 80%" into a terminal and sends the data to the server, the server requests analysis from LLM, generates evaluation indicators such as "energy efficiency" and "carbon emission reduction," and stores them in a database.

[1478] Example prompt sentence:

[1479] "Generate metrics to assess a company's sustainability based on the following SDGs: energy consumption, recycling rate, carbon emissions."

[1480] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1481] Step 1: Enter and submit initial data

[1482] The user inputs initial data (energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal. For example, the energy consumption is "1000 kWh" and the recycling rate is "80%."

[1483] The device converts the entered data into JSON format and sends it to the central server via an HTTP POST request.

[1484] Input: Energy consumption, recycling rate, exhaust gas volume (specific numerical data)

[1485] Output: JSON formatted data sent

[1486] Step 2: Analyze initial data and generate evaluation metrics

[1487] The server passes the received initial data to an LLM (large-scale language model) for analysis.

[1488] Based on the analysis results returned by the LLM, the server generates evaluation indicators based on SDGs and ESG, such as "energy efficiency" and "carbon emission reduction."

[1489] The server stores the generated evaluation indexes in a database.

[1490] Input: Initial data sent to the server in JSON format

[1491] Output: Evaluation metrics stored in a database

[1492] Step 3: Enter and submit your daily activity data

[1493] The user inputs daily activity data (e.g., daily energy consumption, recycling activity records) into the terminal. For example, data such as "energy consumption: 950 kWh" is input.

[1494] The device converts this daily activity data into JSON format and sends it to a central server via an HTTP POST request.

[1495] Input: Daily energy consumption, recycling activity records (specific numerical data)

[1496] Output: Daily data sent in JSON format

[1497] Step 4: Analyze and evaluate activity data

[1498] The server passes the received daily activity data to the AI ​​model for analysis.

[1499] The server uses an AI model to analyze activity data based on evaluation metrics.

[1500] As a result of the analysis, the server generates a specific evaluation, such as "successfully reduced energy consumption by 10%."

[1501] The measurement results are stored in a database.

[1502] Input: Daily activity data in JSON format sent to the server

[1503] Output: Evaluation results stored in a database

[1504] Step 5: Recognize and analyze emotion data

[1505] The emotion engine recognizes emotion data from the user's voice, text, facial expressions, etc. For example, inputs include voice recordings, text input, and camera images.

[1506] The emotion engine analyzes the recognized emotion data and converts it into an appropriate evaluation index, for example, generating a positive or negative score.

[1507] The emotion engine sends the analysis results to a central server.

[1508] Input: User voice, text, and facial expression data

[1509] Output: Analyzed emotion data (evaluation index)

[1510] Step 6: Integrating emotion and activity data

[1511] The server integrates the emotion data with daily activity data and adjusts the evaluation of activity performance based on the user's emotion using a weighting algorithm.

[1512] The server stores the integrated evaluation results in a database.

[1513] Input: Emotion data, daily activity data

[1514] Output: Adjusted evaluation results stored in a database

[1515] Step 7: Generate and view the results report

[1516] At the end of the month, the server aggregates and analyzes all the data collected so far and generates a detailed performance report, with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[1517] The server converts the generated results report into a format that can be displayed in the web interface. A template engine is used to generate the HTML report.

[1518] Users can use their devices to view the results report through a web interface and download it in PDF format if desired.

[1519] Input: All data collected so far

[1520] Output: Generated outcome report

[1521] Step 8: SDG / ESG Rating

[1522] The server will rank companies on their SDGs and ESG initiatives based on the latest evaluation and sentiment data, using a six-point scale from A to F.

[1523] The server stores the rating results in a database and notifies the user via an API.

[1524] Users can use the terminal to check their own ratings and compare them with other companies.

[1525] Input: Latest evaluation data, emotion data

[1526] Output: Rating results stored in the database and information communicated to the user

[1527] (Application example 2)

[1528] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1529] When small and medium-sized enterprises evaluate their Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG) initiatives, traditional systems typically evaluate only environmental data. However, this can result in an inaccurate assessment of a company's overall performance. In particular, evaluations that ignore the impact of employee emotions and motivation on performance are incomplete and difficult to reflect actual results. Furthermore, the lack of real-time data collection and evaluation makes it difficult to take timely action.

[1530] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1531] In this invention, the server includes means for formulating evaluation indexes based on generated data, means for automatically measuring activity performance based on the evaluation indexes, means for saving the measurement results in a database, means for generating a performance report from the saved data, means for displaying the generated performance report, means for collecting environmental data in real time, means for recognizing and analyzing emotional data, means for adjusting activity performance by integrating the environmental data and the emotional data, and means for including the emotional data in the performance report. This enables companies to perform comprehensive and accurate activity performance evaluations in real time that take into account not only environmental data but also employee emotional data.

[1532] "Generated Data" refers to the set of data obtained by the system from its initial setup and daily activities.

[1533] "Evaluation index" refers to a criterion for evaluating activity performance that is analyzed based on generated data.

[1534] "Activity performance" refers to the implementation status and results of a company's sustainable initiatives.

[1535] A "database" is an information management system for storing generated data, measurement results, evaluation indicators, etc.

[1536] A "results report" is a report generated by organizing and analyzing the saved data and its evaluation results.

[1537] The "display means" refers to an interface for providing the generated performance report, rating results, etc. to the user.

[1538] "Environmental data" refers to information related to the environment, such as energy consumption, recycling rates, and the amount of pollutants in the air.

[1539] "Emotion data" refers to information about emotions obtained from the user's voice, text, facial expressions, etc.

[1540] The "means for adjusting the evaluation index" refers to a function for resetting the evaluation index based on the environmental data and the emotion data.

[1541] "Rating" refers to ranking the level of a company's efforts based on the generated activity performance measurement results.

[1542] An "LLM (Large-Scale Language Model)" is a model that uses natural language processing technology to analyze large amounts of data and extract knowledge and information.

[1543] This invention is a system that efficiently evaluates the Sustainable Development Goals (SDGs) and Environmental, Social and Governance (ESG) initiatives of small and medium-sized enterprises, and recognizes and utilizes user sentiment. The system consists of the following main components:

[1544] System configuration

[1545] User terminal: A device used by factory managers and employees to input data and interact with the system. This can be a smartphone, tablet, or PC.

[1546] Central Server: This is the main computer system that analyzes, evaluates, ranks, and generates reports. It requires a high-performance processor and a large amount of memory.

[1547] Database: A data management system for permanently storing generated data, evaluation indicators, activity performance data, etc.

[1548] Emotion engine: A software module for recognizing emotions from a user's voice, text, and facial expressions. It uses deep learning libraries such as TensorFlow and PyTorch.

[1549] Display interface: This is the interface for providing the generated performance reports and evaluation results to the user. It is displayed in a web browser or mobile application.

[1550] Program processing overview

[1551] The central server receives environmental data and emotional data sent from user devices in real time. The server formulates evaluation indicators based on this data and automatically measures and evaluates activity performance based on the generated evaluation indicators. The evaluation results are stored in a database, and at the end of the month, a performance report is generated and displayed to the user. Emotional data is used to adjust the evaluation of activity performance.

[1552] Specific example explanation

[1553] For example, a factory manager can input their daily energy consumption data into the system via their smartphone, and the data will be sent to a central server. The server will then use an emotion engine to recognize the emotion "satisfied" from the manager's voice report. It will then integrate environmental and emotion data to adjust activity performance. This allows the system to provide a more comprehensive and accurate evaluation, and at the end of the month, a performance report will be generated, including "energy efficiency this month" and "employee satisfaction."

[1554] Prompt Sentence Examples

[1555] "Analyze the voice data, recognize the user's emotions, and output the following: emotions such as 'satisfied', 'dissatisfied', 'fatigued', etc."

[1556] User says: "My energy consumption is below my goal today."

[1557] Expected Output: Emotion: Satisfied

[1558] As described above, this invention is a system that efficiently evaluates, reports, and improves SDGs and ESG initiatives by integrating environmental data and emotional data to evaluate activity performance.

[1559] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1560] Step 1:

[1561] The user inputs environmental data such as energy consumption and recycling rate into the terminal as initial data. The input data is sent from the user terminal to the central server. At this time, the input data is sent to the server in text format.

[1562] Step 2:

[1563] The central server analyzes the received initial data and formulates evaluation indicators using a large-scale language model (LLM). Specifically, the generated data is passed to the LLM, and specific evaluation indicators such as "energy efficiency" and "recycling rate" are generated based on the results of analyzing the environmental data. The server stores these evaluation indicators in a database.

[1564] Step 3:

[1565] Users input their daily activity data (e.g., daily energy consumption data and recycling activity records) into their terminals, which are then transmitted to a central server.

[1566] Step 4:

[1567] The central server passes the received daily activity data to the AI ​​model, which then automatically measures activity performance based on the evaluation index. Specifically, the activity data is compared with the evaluation index and a specific evaluation result, such as "successfully reduced energy consumption by 10%," is generated. This result is stored in a database.

[1568] Step 5:

[1569] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions. When a user reports work to the system by voice using a smartphone or tablet, the voice data is input into the emotion engine. The emotion engine analyzes the voice data and recognizes emotions such as "satisfaction" or "fatigue." The resulting emotional data is sent to the server.

[1570] Step 6:

[1571] The central server integrates the emotion data and activity data to adjust the evaluation of activity performance. Specifically, it resets the evaluation indicators based on the emotion data and recalculates the evaluation results. This evaluation adjustment enables more accurate evaluation. This data is also stored in the database.

[1572] Step 7:

[1573] At the end of the month, the central server compiles all the collected data, evaluation results, and emotional data to generate a performance report. The report includes information such as this month's energy consumption and reduction rate, the results of recycling efforts, and employee emotional data. This performance report is presented to users in a format they can view through the display interface.

[1574] Step 8:

[1575] Finally, the central server will rate the company's SDGs and ESG initiatives based on the latest evaluation data and sentiment data. The results of this rating are rated on a six-point scale from A to F and displayed for users to check on their devices. Users can also compare their performance with other companies.

[1576] This will enable the system to efficiently support the sustainability efforts of small and medium-sized enterprises and provide more comprehensive and accurate assessments.

[1577] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1578] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1579] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1580] [Fourth embodiment]

[1581] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1582] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1583] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1584] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1585] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1586] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1587] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1588] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1589] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1590] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1591] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1592] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1593] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1594] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific modes for carrying out the invention are described below.

[1595] System configuration

[1596] The system consists of the following main components:

[1597] 1. User Device

[1598] 2. Central Server

[1599] 3. Database

[1600] 4. Results report generation module

[1601] 5. Display and display interface

[1602] Specific examples of program processing

[1603] Initial Data Entry

[1604] As an initial setting, users input data related to the SDGs and ESG into the device, such as energy consumption, recycling rate, and exhaust gas volume.

[1605] The terminal transmits the entered data to a central server.

[1606] Establishment of evaluation indicators

[1607] The server passes the received initial data to the LLM (Large Scale Language Model).

[1608] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1609] Uploading daily activity data

[1610] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1611] The devices transmit these daily activity data to a central server.

[1612] Measuring activity performance

[1613] The server passes the received daily activity data to the AI ​​model.

[1614] The server uses an AI model to analyze this data based on evaluation indicators and automatically measure activity performance, generating evaluation results such as "successfully reduced energy consumption by 10%."

[1615] Generate and view performance reports

[1616] At the end of the month, the server collects and organizes all collected data and its evaluation results.

[1617] Based on the collected data, the server generates a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[1618] The server provides the generated performance report in a format that can be viewed by the user, and the report is displayed on a display, which the user can download as needed.

[1619] SDGs / ESG Ratings

[1620] The server uses the latest evaluation data to perform calculations to rank companies' efforts toward SDGs and ESG.

[1621] The server rates companies on a six-point scale from A to F. The ratings are then presented to the user in a web interface for review.

[1622] Users can use the device to check their own rating and compare it with other small and medium-sized businesses.

[1623] Specific examples

[1624] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs the energy consumption and recycling rate as initial data into a terminal and sends the data to a server.

[1625] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[1626] 3. The user uploads daily energy consumption data from the device to the server.

[1627] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[1628] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[1629] 6. The server then uses this data to assign an SDG rating, giving it an A rank, and displays the result to the user.

[1630] As described above, this system provides a mechanism for SMEs to efficiently evaluate their SDG and ESG initiatives and confirm their results. This makes it easier for companies to understand the effects of their efforts and promotes actions toward realizing a sustainable society.

[1631] The processing flow will be explained below.

[1632] Step 1:

[1633] Users input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, and gas emissions) into the terminal as initial data.

[1634] Step 2:

[1635] The terminal transmits the entered initial data to the central server.

[1636] Step 3:

[1637] The server passes the received initial data to the LLM (Large Scale Language Model).

[1638] Step 4:

[1639] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1640] Step 5:

[1641] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[1642] Step 6:

[1643] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1644] Step 7:

[1645] The device sends daily activity data to a server.

[1646] Step 8:

[1647] The server passes the received daily activity data to the AI ​​model.

[1648] Step 9:

[1649] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[1650] Step 10:

[1651] The server stores the evaluation results in a database and notifies the user of the information.

[1652] Step 11:

[1653] At the end of the month, the server collects and organizes all the data collected so far and its evaluation results.

[1654] Step 12:

[1655] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[1656] Step 13:

[1657] The server provides the performance report in a user-viewable format to the web interface.

[1658] Step 14:

[1659] Users can check the results report on their device and download it if necessary.

[1660] Step 15:

[1661] The server performs calculations based on the latest evaluation data to rank companies' efforts toward SDGs and ESG.

[1662] Step 16:

[1663] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[1664] Step 17:

[1665] Users can use the device to check their own ratings and compare them with other companies.

[1666] This will enable companies to efficiently evaluate and confirm the effectiveness of their SDGs and ESG initiatives.

[1667] Example 1

[1668] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1669] With conventional systems, it has been extremely difficult for small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare their results. In particular, there has been a demand for a system that automates the entire process of collecting, analyzing, evaluating, and reporting activity data, making it easy to use. In addition, there has been a lack of means to rate a company's efforts, making it difficult to compare them with other companies. The objective of this invention is to solve these problems.

[1670] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1671] In this invention, the server includes means for receiving and storing initial data entered by a user, means for converting the initial data into an analysis format, means for passing the data converted into the analysis format to a large-scale language model (LLM), means for generating evaluation indicators from the data analyzed by the LLM and saving them in a database, means for a user to input daily activity data and send it to the server, means for converting the sent daily activity data into an analysis format, means for passing the data converted into the analysis format to an AI model and automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, and means for generating monthly performance reports from the saved data and displaying them to the user via a web interface. This enables efficient evaluation of a company's efforts, checking its results in real time, and comparing it with other companies.

[1672] A "user" is an individual or company employee who uses the system to enter or view data.

[1673] "Initial data" refers to data related to the SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance), such as energy consumption, recycling rates, and exhaust gas emissions.

[1674] A "large-scale language model (LLM)" is an AI algorithm for analyzing natural language data and generating more advanced information.

[1675] "Evaluation indicators" are specific indicators such as energy efficiency and recycling rates that are generated based on SDGs and ESG standards.

[1676] "Daily activity data" refers to data such as energy consumption data and recycling activity records that are input by the user in relation to their daily activities.

[1677] An "AI model" is an artificial intelligence algorithm that analyzes collected data and evaluates activity performance.

[1678] "Operational performance" refers to the achievements and results that are automatically measured based on a company's daily activities, and includes, for example, the rate of reduction in energy consumption.

[1679] "Measurement results" are specific evaluation results of activity performance analyzed by the AI ​​model.

[1680] A "database" is an electronic storage device for storing received data, analysis results, generated evaluation indexes, and the like.

[1681] The "Results Report" is a report generated based on the saved data that shows the results of a company's SDGs and ESG initiatives.

[1682] A "web interface" is an online operating screen that allows users to view performance reports and rating results.

[1683] The "rating" involves evaluating and ranking a company's SDGs and ESG initiatives on a six-point scale from A to F based on the latest evaluation data.

[1684] Embodiments of the invention

[1685] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and report and compare the results. Specific embodiments for carrying out the invention are described below.

[1686] System configuration

[1687] The system consists of the following main components:

[1688] 1. User Device

[1689] 2. Central Server

[1690] 3. Database

[1691] 4. Results report generation module

[1692] 5. Display and display interface

[1693] User terminal

[1694] The user terminal is a device that users use to input their initial data and daily activity data. This can be a PC, tablet, smartphone, etc. The user enters the data through a dedicated input screen and sends it to the central server.

[1695] Central Server

[1696] The central server is the main computing unit that processes and stores the data it receives. The server uses the following software and hardware:

[1697] LLM (Large Scale Language Model): Used to analyze natural language data and generate evaluation metrics.

[1698] AI model: Using frameworks such as TensorFlow, it analyzes daily activity data and automatically measures activity performance.

[1699] Database: Received data, analysis results, evaluation indicators, rating results, etc. are stored using PostgreSQL or similar.

[1700] Database

[1701] The database is a storage unit for securely storing and managing all data received on a central server, including initial data, daily data, analysis results, evaluation indicators, performance reports, and rating results.

[1702] Results report generation module

[1703] The performance report generation module is a software component that aggregates monthly data and generates reports that show the results of the company's efforts. It generates performance reports in plain text and PDF format.

[1704] Displays and display interfaces

[1705] The display and viewing interface is the interface that users use to view the generated performance reports and rating results. This is provided through a web browser, allowing users to easily compare their own efforts and the results of their efforts with those of other companies.

[1706] Specific examples

[1707] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rate as initial data into a user terminal and transmits the data to a central server.

[1708] 2. The server analyzes this data using LLM, generates evaluation indicators called "energy efficiency" and "recycling rate," and stores them in a database.

[1709] 3. Users upload their daily energy consumption data from their devices to a central server.

[1710] 4. The server uses an AI model to analyze this daily data and obtains the result: "This month's energy consumption has been successfully reduced by 10%."

[1711] 5. At the end of the month, the server compiles all the data and generates a performance report called "This Month's Energy Consumption and Reduction Rate" and provides it to the user.

[1712] 6. The server then uses this data to rate the company on SDGs, assigning it an A rank and displaying the results to the user.

[1713] Prompt Sentence Examples

[1714] "This system efficiently evaluates the SDGs and ESG efforts of small and medium-sized enterprises, and allows them to report and compare their results. Specifically, users input data such as energy consumption and recycling rates, and the server uses LLM and AI models to generate evaluation indicators and measure activity performance. At the end of the month, an outcome report is generated and the company's efforts are ranked based on the results."

[1715] In this way, the present invention provides a concrete method for small and medium-sized enterprises to efficiently evaluate their SDGs and ESG initiatives and confirm and compare their results, thereby supporting the sustainable development of companies.

[1716] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1717] Step 1:

[1718] The user inputs the initial data into the user terminal.

[1719] Input data such as energy consumption, recycling rate, and exhaust gas volume is entered through an input form.

[1720] The device converts this input data into packets and sends them over secure communications to a central server, which then receives the data.

[1721] Step 2:

[1722] The server converts the received initial data into a format for analysis.

[1723] As input, it receives data sent from the terminal.

[1724] The server runs a program to convert this data into JSON format, and the output is JSON data that can be parsed.

[1725] Step 3:

[1726] The server passes the converted data to a large-scale language model (LLM).

[1727] As input, it uses the converted JSON data for parsing.

[1728] The server requests analysis by sending data to the API endpoint of LLM, and receives the analysis results from LLM as output.

[1729] Step 4:

[1730] The server generates evaluation metrics from the data analyzed by LLM and stores them in a database.

[1731] As input, evaluation indicators are generated based on the analysis results obtained from the LLM.

[1732] The server executes the evaluation metric generation algorithm and stores the evaluation results in a PostgreSQL database. As an output, the evaluation metrics are stored in the database.

[1733] Step 5:

[1734] The user inputs and transmits daily activity data into the user terminal.

[1735] Inputs include daily energy consumption data and records of recycling activities.

[1736] The device converts daily data into packets and sends them to a central server, which then receives the data.

[1737] Step 6:

[1738] A server converts the received daily activity data into a format for analysis.

[1739] As input, it uses daily data received from the terminal.

[1740] The server runs a program that converts the daily data into CSV format, and generates CSV data as output for analysis.

[1741] Step 7:

[1742] The server passes the converted daily data to an AI model, which automatically measures activity performance based on evaluation indicators.

[1743] As input, it uses the CSV data that has been transformed for analysis.

[1744] The server inputs the data into the AI ​​model for analysis and evaluation, and generates an evaluation result of activity performance as the output.

[1745] Step 8:

[1746] The server stores the measurement results in a database.

[1747] As input, it uses the activity performance evaluation results generated by the AI ​​model.

[1748] The server stores the evaluation results in a PostgreSQL database. As an output, the measurement results are stored in the database.

[1749] Step 9:

[1750] At the end of the month, the server generates a performance report based on the accumulated data.

[1751] As input, the query retrieves all data in the database.

[1752] The server runs the outcome report generation algorithm to generate an outcome report in plain text or PDF format. As an output, an outcome report is generated.

[1753] Step 10:

[1754] The server displays the generated performance report to the user via a web interface.

[1755] Use the generated outcome report as input.

[1756] The server generates HTML pages for the web interface and serves them to the user, allowing the user to view the report as output.

[1757] Step 11:

[1758] The user can view the generated results report through a web interface and download it if necessary.

[1759] As an input, you log in through the web interface and view the performance report.

[1760] The terminal executes the download command and saves the results report in PDF format. As an output, the report is saved on the user's terminal.

[1761] Step 12:

[1762] The server will rate companies' efforts toward SDGs and ESG based on the latest evaluation data.

[1763] It uses the most recent evaluation data in the database as input.

[1764] The server runs a rating algorithm and rates the company's efforts on a six-point scale (A to F). The rating is generated as an output.

[1765] Step 13:

[1766] The server provides the rating results in a web interface that can be viewed by the user.

[1767] As input, the rating results are used.

[1768] The server generates a page for a web interface that allows users to view the rating results, and as an output, the rating results are displayed on a web page.

[1769] Step 14:

[1770] Users use a web interface to view their own ratings and compare them with other small businesses.

[1771] As an input, log in to the web interface.

[1772] The terminal displays the rating results and accesses a comparison page with other companies. As an output, users can compare their own evaluation results with those of other companies.

[1773] In this way, the system can efficiently evaluate the SDGs and ESG initiatives of small and medium-sized enterprises, check their results in real time, and compare them with other companies.

[1774] (Application example 1)

[1775] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1776] Current systems for efficiently and accurately evaluating and reporting on SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) initiatives for small and medium-sized enterprises require manual data entry and analysis, which is time-consuming and costly. Furthermore, the inability to collect and analyze data in real time makes it difficult to make quick decisions. Furthermore, because evaluation results and reports are generated manually, the data lacks reliability and consistency, making comparisons and analysis difficult.

[1777] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1778] In this invention, the server includes means for formulating evaluation indicators based on generated data, means for automatically measuring activity performance based on the evaluation indicators, means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for the robot to collect environmental data and operational data, means for transmitting the collected data to a cloud server, and means for converting the analysis results into an evaluation report on the cloud server. This enables small and medium-sized enterprises to automatically collect and analyze data on SDGs and ESG activities in real time and efficiently generate and display evaluation reports.

[1779] "Generated data" refers to various data related to the SDGs and ESG initiatives of small and medium-sized enterprises, including energy consumption, recycling rates, and emissions.

[1780] "Evaluation indicators" are specific measurement standards set based on SDGs and ESG criteria, and include energy efficiency and carbon emission reduction.

[1781] "Activity Performance" evaluates a company's daily performance in relation to SDGs and ESG initiatives.

[1782] "Measurement results" are the results of a company's activity performance calculated based on evaluation indicators.

[1783] A "database" is a system for storing data such as measurement results.

[1784] The "Results Report" is a report generated based on the saved data, detailing the results of a company's SDGs and ESG initiatives.

[1785] "Display means" refers to a device or interface for presenting the generated result report in a format that can be viewed by the user.

[1786] A "robot" is an automated device that operates within a factory and collects environmental and operational data.

[1787] "Environmental data" refers to data related to the environment, such as energy consumption and exhaust gas emissions at factories.

[1788] "Operational data" refers to data related to production activities and the operating status of equipment within a factory.

[1789] A "cloud server" is a remote server that provides data and services over the Internet.

[1790] An "evaluation report" is a report generated based on data analyzed on a cloud server that details the results of a company's SDGs and ESG initiatives.

[1791] "Real-time" refers to a state in which data collection, analysis, and display are carried out immediately without delay.

[1792] System configuration

[1793] The system of the present invention comprises the following main components:

[1794] 1. User Device

[1795] 2. Robot

[1796] 3. Cloud Server

[1797] 4. Database

[1798] 5. Results report generation module

[1799] 6. Display and display interface

[1800] Program processing

[1801] Data collection and transmission

[1802] Robots operating in factories collect environmental and operational data in real time. The robots are equipped with sensors such as energy consumption meters and exhaust gas sensors, and acquire data from these sensors. The acquired data is then sent to a cloud server via a network module.

[1803] Data analysis and generation of evaluation indicators

[1804] The cloud server passes the received data to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. These evaluation indicators are stored in a database.

[1805] Measuring activity performance

[1806] The server passes daily activity data to the AI ​​model, which analyzes it based on evaluation indicators. This generates a measurement result for activity performance. For example, a measurement result such as "successfully reduced energy consumption by 10%" is generated. These measurement results are stored in a database.

[1807] Generate and view performance reports

[1808] The cloud server organizes all collected data and evaluation results and generates a performance report with sections such as "This month's energy consumption and reduction rate" and "Results of recycling efforts." The generated performance report is provided in a format that can be viewed by users. It can be monitored in real time via user terminals, displays, and mobile devices.

[1809] Specific examples

[1810] 1. The user initializes the system and inputs initial data such as energy consumption and recycling rate.

[1811] 2. The robot collects environmental and operational data within the factory and sends it to a cloud server.

[1812] 3. The server passes the received data to the LLM, which generates evaluation metrics from the analyzed data.

[1813] 4. The server uses an AI model to analyze daily activity data and measure activity performance.

[1814] 5. The server generates a performance report and displays it on the user's terminal or display.

[1815] Prompt Sentence Examples

[1816] "Based on the energy consumption and recycling data for the following factory, please evaluate it based on the SDGs indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[1817] Specific hardware and software names to be used

[1818] Robot: Automated equipment for collecting environmental and operational data

[1819] Sensors: Energy consumption meter, exhaust gas sensor

[1820] Network module: for data transmission

[1821] Cloud server: A server for running LLM and AI models (e.g., AWS, Google Cloud)

[1822] LLM: Large-scale language model (e.g., OpenAI GPT-4)

[1823] Database: A system for storing measurement results and evaluation indicators (e.g., MySQL, PostgreSQL)

[1824] Displays and mobile devices: devices that display the generated outcome reports

[1825] In this way, the system can efficiently evaluate and report on SMEs' SDGs and ESG activities and promote improvements.

[1826] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1827] Step 1:

[1828] Entering initial data

[1829] The user inputs initial data such as energy consumption and recycling rate into the user terminal. The terminal then sends the initial data entered by the user to the cloud server. The input initial data is stored on the server and used to develop evaluation indicators.

[1830] Step 2:

[1831] Robotic data collection

[1832] Robots collect environmental and operational data within the factory using energy consumption meters, exhaust gas sensors, etc. The robots then send the collected data to a cloud server via a network. Input: Environmental and operational data. Output: Data stored on the cloud server.

[1833] Step 3:

[1834] Data analysis and evaluation index generation

[1835] The cloud server passes the data received from the robot to a large-scale language model (LLM) for analysis. From the analyzed data, evaluation indicators such as energy efficiency and carbon emission reduction are generated. Input: Environmental data and operational data stored on the cloud server. Output: Evaluation indicators.

[1836] Step 4:

[1837] Measuring activity performance

[1838] The server uses an AI model to automatically measure activity performance based on evaluation indicators. It analyzes daily activity data and measures specific results (e.g., successful 10% reduction in energy consumption). Input: Evaluation indicators and daily activity data. Output: Measurement results.

[1839] Step 5:

[1840] Saving measurement results

[1841] The server stores the measurement results in a database. Input: Measurement results. Output: Measurement results stored in the database.

[1842] Step 6:

[1843] Generate a performance report

[1844] The server generates a performance report based on the stored measurement results. The report includes the current month's energy consumption, reduction rate, and recycling effort results. Input: Measurement results stored in the database. Output: Performance report.

[1845] Step 7:

[1846] View the results report

[1847] The server provides the generated results report in a format that can be viewed by the user. It can be monitored in real time through the user's terminal, display, or mobile terminal. Input: Results report. Output: Results report displayed on the user's terminal or display.

[1848] Step 8:

[1849] Generate prompt statement

[1850] The server generates prompts for data analysis of the factory's SDG / ESG efforts. Example: "Based on the energy consumption data and recycling data of the following factory, please evaluate it based on SDG indicators and propose specific improvements. Data: {energy consumption data, recycling data}"

[1851] Input: Target data. Output: Generated prompt sentence.

[1852] Through the above processing steps, this system can efficiently evaluate the SDGs and ESG activities of small and medium-sized enterprises, and confirm and improve their results in real time.

[1853] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1854] This invention provides a system that enables small and medium-sized enterprises to efficiently evaluate their efforts in the areas of SDGs (Sustainable Development Goals) and ESG (Environment, Social and Governance), and also recognizes and utilizes user emotions to more effectively understand, report and improve the results of those efforts.

[1855] System configuration

[1856] The system consists of the following main components:

[1857] 1. User Device

[1858] 2. Central Server

[1859] 3. Database

[1860] 4. Results report generation module

[1861] 5. Display and display interface

[1862] 6. Emotion Engine

[1863] Specific examples of program processing

[1864] Initial Data Entry

[1865] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[1866] The terminal transmits the entered data to a central server.

[1867] Establishment of evaluation indicators

[1868] The server passes the received initial data to the LLM (Large Scale Language Model).

[1869] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1870] Uploading daily activity data

[1871] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1872] The device transmits this daily activity data to a server.

[1873] Measuring activity performance

[1874] The server passes the received daily activity data to the AI ​​model.

[1875] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[1876] Recognizing and Using Emotional Data

[1877] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[1878] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[1879] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion, thereby providing a more accurate evaluation.

[1880] Generate and view performance reports

[1881] At the end of the month, the server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[1882] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[1883] The server provides the generated performance report in a user-viewable format to the web interface.

[1884] Users can use their devices to check the results reports and download them if necessary.

[1885] SDGs / ESG Ratings

[1886] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[1887] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[1888] Users can use the device to check their own ratings and compare them with other companies.

[1889] Specific examples

[1890] 1. A user (e.g., a person in charge at a small or medium-sized enterprise) inputs energy consumption and recycling rates as initial data into a terminal and sends the data to a server.

[1891] 2. The server analyzes this data using LLM to generate evaluation indicators such as "energy efficiency" and "recycling rate."

[1892] 3. The user uploads daily energy consumption data from the device to the server.

[1893] 4. The server uses an AI model to analyze the daily data and obtains the evaluation result: "This month's energy consumption has been successfully reduced by 10%."

[1894] 5. The emotion engine recognizes the emotion data when the user inputs the day's work report by voice and sends the data to the server.

[1895] 6. The server converts the emotion data into evaluation metrics, integrates them with performance evaluations, and generates an outcome report.

[1896] 7. The server provides the user with a report summarizing the generated results and emotion data.

[1897] 8. The server then performs an SDGs rating based on the data, assigns an A rank, and displays the rating results to the user.

[1898] In this way, by incorporating user sentiment data into the evaluation of SDGs and ESG initiatives, the system provides a more comprehensive and appropriate evaluation, efficiently supporting the sustainable initiatives of small and medium-sized enterprises.

[1899] The processing flow will be explained below.

[1900] Step 1:

[1901] As an initial setting, users input data related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal.

[1902] Step 2:

[1903] The terminal transmits the entered initial data to the central server.

[1904] Step 3:

[1905] The server passes the received initial data to the LLM (Large Scale Language Model).

[1906] Step 4:

[1907] The server uses LLM to analyze the data and generate performance indicators based on SDGs and ESG criteria, such as "energy efficiency" and "carbon emission reduction."

[1908] Step 5:

[1909] The server stores the generated evaluation indexes in a database and notifies the user of the information.

[1910] Step 6:

[1911] The user inputs daily activity data (for example, daily energy consumption data and recycling activity records) into the terminal.

[1912] Step 7:

[1913] The device sends daily activity data to a server.

[1914] Step 8:

[1915] The server passes the received daily activity data to the AI ​​model.

[1916] Step 9:

[1917] The server uses an AI model to automatically analyze activity data based on evaluation indicators and evaluate activity performance, generating specific evaluation results such as "successfully reduced energy consumption by 10%."

[1918] Step 10:

[1919] The server stores the evaluation results in a database and notifies the user of the information.

[1920] Step 11:

[1921] As the user uses the system, the emotion engine recognizes emotional data from the user's voice, text, facial expressions, etc.

[1922] Step 12:

[1923] The emotion engine analyzes the recognized emotion data as generated data and converts it into appropriate evaluation indicators.

[1924] Step 13:

[1925] The server integrates the emotion data and the activity data and adjusts the evaluation of the activity performance based on the user's emotion.

[1926] Step 14:

[1927] The server collects and organizes all data collected so far, along with the evaluation results and emotion data.

[1928] Step 15:

[1929] The server uses the collected data to generate a detailed performance report with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results." It also includes user sentiment data.

[1930] Step 16:

[1931] The server provides the generated performance report in a user-viewable format to the web interface.

[1932] Step 17:

[1933] Users can use their devices to check the results reports and download them if necessary.

[1934] Step 18:

[1935] The server performs calculations based on the latest evaluation data and sentiment data to rank companies' efforts toward SDGs and ESG.

[1936] Step 19:

[1937] The server rates companies on a six-point scale from A to F. The results of this rating are stored in a database and the information is sent to the user.

[1938] Step 20:

[1939] Users can use the device to check their own ratings and compare them with other companies.

[1940] Example 2

[1941] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1942] Conventional systems lack the means to efficiently evaluate and report on initiatives related to the Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG), and in particular lack the means to reflect user sentiment in the evaluation. As a result, it is difficult to accurately grasp the performance of activities and the effectiveness of initiatives, and more effective evaluation and improvement methods are needed.

[1943] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1944] In this invention, the server includes means for inputting initial data into a user terminal, means for transmitting the input initial data to a central server, means for formulating evaluation indexes based on the generated data, and means for automatically measuring activity performance based on the evaluation indexes. This enables the collection of initial data, the formulation of evaluation indexes, and the measurement of activity performance. The server also includes means for saving the measurement results in a database, means for generating an outcome report from the saved data, means for displaying the generated outcome report, means for recognizing emotional data and converting it into an evaluation index, and means for integrating the emotional data to adjust the evaluation of activity performance. This enables a more accurate and comprehensive evaluation that reflects the user's emotional data in the evaluation.

[1945] "Initial data" refers to basic data that allows users to input information related to the SDGs and ESG (e.g., energy consumption, recycling rate, exhaust gas volume, etc.).

[1946] A "user terminal" is a computing device used by a user to enter data and view performance reports.

[1947] A "central server" is a computing system that receives, analyzes, and evaluates data transmitted from user terminals.

[1948] "Generated data" refers to data that is newly generated based on collected information and analysis results.

[1949] "Evaluation indicators" are specific indicators (e.g., "energy efficiency" or "carbon emission reduction") used to evaluate a company's performance based on the SDGs and ESG standards.

[1950] "Activity Performance" is the outcome of a company's efforts, calculated based on daily data entered by the user.

[1951] "Measurement results" are evaluation data of activity performance analyzed using AI models and evaluation indicators.

[1952] A "database" is a data storage system for storing and managing measurement results, initial data, and generated data.

[1953] The "Results Report" is a detailed report on SDGs and ESG generated based on data collected by a central server.

[1954] "Emotion data" refers to data related to emotions recognized from the user's voice, text, facial expressions, etc.

[1955] The "emotion engine" is a component that analyzes the user's voice, text, facial expressions, etc. to generate and recognize emotional data.

[1956] "Rating" is the process of evaluating a company's efforts toward the SDGs and ESG and assigning it a rank (for example, from A to F).

[1957] A "web interface" is a user interface that allows users to view performance reports, rating results, etc. via the Internet.

[1958] MODE FOR CARRYING OUT THE INVENTION

[1959] The present invention is a system that enables small and medium-sized enterprises to efficiently evaluate their efforts toward SDGs (Sustainable Development Goals) and ESG (Environment, Social, and Governance) and more effectively grasp, report, and improve the results of their efforts by recognizing and utilizing user emotions. Specific embodiments of this system are described below.

[1960] System configuration

[1961] The system consists of the following main components:

[1962] 1. User Device

[1963] 2. Central Server

[1964] 3. Database

[1965] 4. Results report generation module

[1966] 5. Display and display interface

[1967] 6. Emotion Engine

[1968] Hardware and Software

[1969] User terminal: Uses a computing device such as a PC or smartphone.

[1970] Central server: A high-performance cloud server is used to process and store data, and is particularly responsible for sending and receiving data using APIs.

[1971] Database: An SQL database is used to store and manage evaluation data and initial data.

[1972] Results report generation module: Implemented using a program using Python or JavaScript.

[1973] Display and Presentation Interface: Build a web-based interface using HTML, CSS, and JavaScript.

[1974] Emotion Engine: Uses Python to parse emotion data using natural language processing (NLP) libraries and facial recognition algorithms.

[1975] Data processing and calculation

[1976] Entering and saving initial data

[1977] The user inputs the energy consumption, recycling rate, and exhaust gas volume into the terminal. For example, the user can provide specific figures such as "energy consumption: 1000 kWh" and "recycling rate: 80%."

[1978] The device sends the entered data in JSON format to a central server.

[1979] Generating evaluation metrics

[1980] The server passes the received initial data to the LLM and generates evaluation indicators (e.g., "energy efficiency" or "carbon emission reduction").

[1981] The generated metrics are stored in an SQL database.

[1982] Measuring and storing activity performance

[1983] The user inputs daily activity data (for example, daily energy consumption, "Energy consumption: 950 kWh") from the terminal and transmits it to the server.

[1984] The server uses an AI model to analyze the data and generate a result, such as "energy consumption successfully reduced by 10%."

[1985] The measurement results are stored in a database.

[1986] Recognizing and Using Emotional Data

[1987] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions, and generates positive and negative scores using, for example, text analysis and facial recognition technology.

[1988] The server converts the emotion data into evaluation metrics and integrates them into the evaluation of activity performance.

[1989] Generate and view performance reports

[1990] At the end of the month, the server aggregates all the data and generates a performance report with items such as "This month's energy consumption and reduction rate" and "Results of recycling efforts."

[1991] The results report is provided to the user via a web interface and can be saved, for example in PDF format, via a "download" button.

[1992] SDGs / ESG Ratings

[1993] The server integrates the latest evaluation data and sentiment data to rank companies' SDGs and ESG initiatives, and stores the ranking results in a database.

[1994] Users can use the terminal to check their own rating information and compare it with other companies.

[1995] Examples of specific examples and prompts

[1996] As a concrete example, the sequence of events from when a user inputs initial data to when the server generates evaluation metrics is as follows:

[1997] When a user enters data such as "energy consumption: 1000 kWh" and "recycling rate: 80%" into a terminal and sends the data to the server, the server requests analysis from LLM, generates evaluation indicators such as "energy efficiency" and "carbon emission reduction," and stores them in a database.

[1998] Example prompt sentence:

[1999] "Generate metrics to assess a company's sustainability based on the following SDGs: energy consumption, recycling rate, carbon emissions."

[2000] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2001] Step 1: Enter and submit initial data

[2002] The user inputs initial data (energy consumption, recycling rate, exhaust gas volume, etc.) into the terminal. For example, the energy consumption is "1000 kWh" and the recycling rate is "80%."

[2003] The device converts the entered data into JSON format and sends it to the central server via an HTTP POST request.

[2004] Input: Energy consumption, recycling rate, exhaust gas volume (specific numerical data)

[2005] Output: JSON formatted data sent

[2006] Step 2: Analyze initial data and generate evaluation metrics

[2007] The server passes the received initial data to an LLM (large-scale language model) for analysis.

[2008] Based on the analysis results returned by the LLM, the server generates evaluation indicators based on SDGs and ESG, such as "energy efficiency" and "carbon emission reduction."

[2009] The server stores the generated evaluation indexes in a database.

[2010] Input: Initial data sent to the server in JSON format

[2011] Output: Evaluation metrics stored in a database

[2012] Step 3: Enter and submit your daily activity data

[2013] The user inputs daily activity data (e.g., daily energy consumption, recycling activity records) into the terminal. For example, data such as "energy consumption: 950 kWh" is input.

[2014] The device converts this daily activity data into JSON format and sends it to a central server via an HTTP POST request.

[2015] Input: Daily energy consumption, recycling activity records (specific numerical data)

[2016] Output: Daily data sent in JSON format

[2017] Step 4: Analyze and evaluate activity data

[2018] The server passes the received daily activity data to the AI ​​model for analysis.

[2019] The server uses an AI model to analyze activity data based on evaluation metrics.

[2020] As a result of the analysis, the server generates a specific evaluation, such as "successfully reduced energy consumption by 10%."

[2021] The measurement results are stored in a database.

[2022] Input: Daily activity data in JSON format sent to the server

[2023] Output: Evaluation results stored in a database

[2024] Step 5: Recognize and analyze emotion data

[2025] The emotion engine recognizes emotion data from the user's voice, text, facial expressions, etc. For example, inputs include voice recordings, text input, and camera images.

[2026] The emotion engine analyzes the recognized emotion data and converts it into an appropriate evaluation index, for example, generating a positive or negative score.

[2027] The emotion engine sends the analysis results to a central server.

[2028] Input: User voice, text, and facial expression data

[2029] Output: Analyzed emotion data (evaluation index)

[2030] Step 6: Integrating emotion and activity data

[2031] The server integrates the emotion data with daily activity data and adjusts the evaluation of activity performance based on the user's emotion using a weighting algorithm.

[2032] The server stores the integrated evaluation results in a database.

[2033] Input: Emotion data, daily activity data

[2034] Output: Adjusted evaluation results stored in a database

[2035] Step 7: Generate and view the results report

[2036] At the end of the month, the server aggregates and analyzes all the data collected so far and generates a detailed performance report, with sections such as "This month's energy consumption and reduction rate" and "Recycling effort results."

[2037] The server converts the generated results report into a format that can be displayed in the web interface. A template engine is used to generate the HTML report.

[2038] Users can use their devices to view the results report through a web interface and download it in PDF format if desired.

[2039] Input: All data collected so far

[2040] Output: Generated outcome report

[2041] Step 8: SDG / ESG Rating

[2042] The server will rank companies on their SDGs and ESG initiatives based on the latest evaluation and sentiment data, using a six-point scale from A to F.

[2043] The server stores the rating results in a database and notifies the user via an API.

[2044] Users can use the terminal to check their own ratings and compare them with other companies.

[2045] Input: Latest evaluation data, emotion data

[2046] Output: Rating results stored in the database and information communicated to the user

[2047] (Application example 2)

[2048] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2049] When small and medium-sized enterprises evaluate their Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG) initiatives, traditional systems typically evaluate only environmental data. However, this can result in an inaccurate assessment of a company's overall performance. In particular, evaluations that ignore the impact of employee emotions and motivation on performance are incomplete and difficult to reflect actual results. Furthermore, the lack of real-time data collection and evaluation makes it difficult to take timely action.

[2050] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2051] In this invention, the server includes means for formulating evaluation indexes based on generated data, means for automatically measuring activity performance based on the evaluation indexes, means for saving the measurement results in a database, means for generating a performance report from the saved data, means for displaying the generated performance report, means for collecting environmental data in real time, means for recognizing and analyzing emotional data, means for adjusting activity performance by integrating the environmental data and the emotional data, and means for including the emotional data in the performance report. This enables companies to perform comprehensive and accurate activity performance evaluations in real time that take into account not only environmental data but also employee emotional data.

[2052] "Generated Data" refers to the set of data obtained by the system from its initial setup and daily activities.

[2053] "Evaluation index" refers to a criterion for evaluating activity performance that is analyzed based on generated data.

[2054] "Activity performance" refers to the implementation status and results of a company's sustainable initiatives.

[2055] A "database" is an information management system for storing generated data, measurement results, evaluation indicators, etc.

[2056] A "results report" is a report generated by organizing and analyzing the saved data and its evaluation results.

[2057] The "display means" refers to an interface for providing the generated performance report, rating results, etc. to the user.

[2058] "Environmental data" refers to information related to the environment, such as energy consumption, recycling rates, and the amount of pollutants in the air.

[2059] "Emotion data" refers to information about emotions obtained from the user's voice, text, facial expressions, etc.

[2060] The "means for adjusting the evaluation index" refers to a function for resetting the evaluation index based on the environmental data and the emotion data.

[2061] "Rating" refers to ranking the level of a company's efforts based on the generated activity performance measurement results.

[2062] An "LLM (Large-Scale Language Model)" is a model that uses natural language processing technology to analyze large amounts of data and extract knowledge and information.

[2063] This invention is a system that efficiently evaluates the Sustainable Development Goals (SDGs) and Environmental, Social and Governance (ESG) initiatives of small and medium-sized enterprises, and recognizes and utilizes user sentiment. The system consists of the following main components:

[2064] System configuration

[2065] User terminal: A device used by factory managers and employees to input data and interact with the system. This can be a smartphone, tablet, or PC.

[2066] Central Server: This is the main computer system that analyzes, evaluates, ranks, and generates reports. It requires a high-performance processor and a large amount of memory.

[2067] Database: A data management system for permanently storing generated data, evaluation indicators, activity performance data, etc.

[2068] Emotion engine: A software module for recognizing emotions from a user's voice, text, and facial expressions. It uses deep learning libraries such as TensorFlow and PyTorch.

[2069] Display interface: This is the interface for providing the generated performance reports and evaluation results to the user. It is displayed in a web browser or mobile application.

[2070] Program processing overview

[2071] The central server receives environmental data and emotional data sent from user devices in real time. The server formulates evaluation indicators based on this data and automatically measures and evaluates activity performance based on the generated evaluation indicators. The evaluation results are stored in a database, and at the end of the month, a performance report is generated and displayed to the user. Emotional data is used to adjust the evaluation of activity performance.

[2072] Specific example explanation

[2073] For example, a factory manager can input their daily energy consumption data into the system via their smartphone, and the data will be sent to a central server. The server will then use an emotion engine to recognize the emotion "satisfied" from the manager's voice report. It will then integrate environmental and emotion data to adjust activity performance. This allows the system to provide a more comprehensive and accurate evaluation, and at the end of the month, a performance report will be generated, including "energy efficiency this month" and "employee satisfaction."

[2074] Prompt Sentence Examples

[2075] "Analyze the voice data, recognize the user's emotions, and output the following: emotions such as 'satisfied', 'dissatisfied', 'fatigued', etc."

[2076] User says: "My energy consumption is below my goal today."

[2077] Expected Output: Emotion: Satisfied

[2078] As described above, this invention is a system that efficiently evaluates, reports, and improves SDGs and ESG initiatives by integrating environmental data and emotional data to evaluate activity performance.

[2079] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2080] Step 1:

[2081] The user inputs environmental data such as energy consumption and recycling rate into the terminal as initial data. The input data is sent from the user terminal to the central server. At this time, the input data is sent to the server in text format.

[2082] Step 2:

[2083] The central server analyzes the received initial data and formulates evaluation indicators using a large-scale language model (LLM). Specifically, the generated data is passed to the LLM, and specific evaluation indicators such as "energy efficiency" and "recycling rate" are generated based on the results of analyzing the environmental data. The server stores these evaluation indicators in a database.

[2084] Step 3:

[2085] Users input their daily activity data (e.g., daily energy consumption data and recycling activity records) into their terminals, which are then transmitted to a central server.

[2086] Step 4:

[2087] The central server passes the received daily activity data to the AI ​​model, which then automatically measures activity performance based on the evaluation index. Specifically, the activity data is compared with the evaluation index and a specific evaluation result, such as "successfully reduced energy consumption by 10%," is generated. This result is stored in a database.

[2088] Step 5:

[2089] The emotion engine recognizes emotional data from the user's voice, text, and facial expressions. When a user reports work to the system by voice using a smartphone or tablet, the voice data is input into the emotion engine. The emotion engine analyzes the voice data and recognizes emotions such as "satisfaction" or "fatigue." The resulting emotional data is sent to the server.

[2090] Step 6:

[2091] The central server integrates the emotion data and activity data to adjust the evaluation of activity performance. Specifically, it resets the evaluation indicators based on the emotion data and recalculates the evaluation results. This evaluation adjustment enables more accurate evaluation. This data is also stored in the database.

[2092] Step 7:

[2093] At the end of the month, the central server compiles all the collected data, evaluation results, and emotional data to generate a performance report. The report includes information such as this month's energy consumption and reduction rate, the results of recycling efforts, and employee emotional data. This performance report is presented to users in a format they can view through the display interface.

[2094] Step 8:

[2095] Finally, the central server will rate the company's SDGs and ESG initiatives based on the latest evaluation data and sentiment data. The results of this rating are rated on a six-point scale from A to F and displayed for users to check on their devices. Users can also compare their performance with other companies.

[2096] This will enable the system to efficiently support the sustainability efforts of small and medium-sized enterprises and provide more comprehensive and accurate assessments.

[2097] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2099] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2100] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2101] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2102] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2103] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2104] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2105] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2106] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2107] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2108] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2109] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2110] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2111] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2112] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2113] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2114] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2115] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2116] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2117] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2118] The following is further disclosed regarding the above embodiment.

[2119] (Claim 1)

[2120] A means for formulating evaluation indicators based on the generated data;

[2121] means for automatically measuring activity performance based on evaluation metrics;

[2122] means for storing the measurement results in a database;

[2123] means for generating a performance report from the stored data;

[2124] a means for displaying the generated outcome report;

[2125] A system including:

[2126] (Claim 2)

[2127] means for passing the generated data to a large scale language model (LLM);

[2128] a means for generating evaluation metrics from the data analyzed by the LLM;

[2129] The system of claim 1 further comprising:

[2130] (Claim 3)

[2131] a means of rating the company's efforts based on the generated activity performance measurements;

[2132] a means for displaying the rating results;

[2133] The system of claim 1 further comprising:

[2134] "Example 1"

[2135] (Claim 1)

[2136] means for receiving and storing initial data entered by a user;

[2137] a means for converting the initial data into a format for analysis;

[2138] A means for passing the converted data into an analysis format to a large-scale language model (LLM);

[2139] A means for generating evaluation metrics from the data analyzed by the LLM and storing them in a database;

[2140] A means for a user to input daily activity data and transmit it to a server;

[2141] means for converting the transmitted daily activity data into a format for analysis;

[2142] A means for passing the data converted into an analytical format to an AI model and automatically measuring activity performance based on evaluation indicators;

[2143] means for storing the measurement results in a database;

[2144] means for generating monthly performance reports from the stored data and displaying them to the user via a web interface;

[2145] A system including:

[2146] (Claim 2)

[2147] a means of rating the company's efforts based on the generated activity performance measurements;

[2148] means for displaying the rating results to a user through a web interface;

[2149] The system of claim 1 further comprising:

[2150] (Claim 3)

[2151] In the system according to claim 1 or claim 2,

[2152] The system further includes means for providing the performance report in a downloadable format to the user.

[2153] "Application Example 1"

[2154] (Claim 1)

[2155] A means for formulating evaluation indicators based on the generated data;

[2156] means for automatically measuring activity performance based on evaluation metrics;

[2157] means for storing the measurement results in a database;

[2158] means for generating a performance report from the stored data;

[2159] a means for displaying the generated outcome report;

[2160] means for the robot to collect environmental data and operational data;

[2161] means for transmitting the collected data to a cloud server;

[2162] A means for converting the analysis results into an evaluation report on a cloud server;

[2163] A system including:

[2164] (Claim 2)

[2165] means for passing the generated data to a large scale language model (LLM);

[2166] a means for generating evaluation metrics from the data analyzed by the LLM;

[2167] A means for the robot to collect data in real time;

[2168] means for transmitting the collected data over a network;

[2169] The system of claim 1 further comprising:

[2170] (Claim 3)

[2171] means for generating an evaluation report based on the generated activity performance measurements;

[2172] A means for displaying the evaluation report via a display or mobile device;

[2173] The system of claim 1 further comprising:

[2174] "Example 2: Combining Emotion Engines"

[2175] (Claim 1)

[2176] means for inputting initial data into a user terminal;

[2177] means for transmitting the input initial data to a central server;

[2178] A means for formulating evaluation indicators based on the generated data;

[2179] means for automatically measuring activity performance based on evaluation metrics;

[2180] means for storing the measurement results in a database;

[2181] means for generating a performance report from the stored data;

[2182] a means for displaying the generated outcome report;

[2183] A means for recognizing emotion data and converting it into an evaluation index;

[2184] a means for integrating emotional data to adjust evaluation of activity performance;

[2185] A system including:

[2186] (Claim 2)

[2187] A means of passing initial data to the LLM,

[2188] a means for generating evaluation metrics from the initial data analyzed by the LLM;

[2189] The system of claim 1 further comprising:

[2190] (Claim 3)

[2191] a means of rating the company's efforts based on the generated activity performance measurements;

[2192] a means for storing the rating results in a database and notifying the user terminal;

[2193] The system of claim 1 further comprising:

[2194] "Application example 2 when combining emotion engines"

[2195] (Claim 1)

[2196] A means for formulating evaluation indicators based on the generated data;

[2197] means for automatically measuring activity performance based on evaluation metrics;

[2198] means for storing the measurement results in a database;

[2199] means for generating a performance report from the stored data;

[2200] a means for displaying the generated outcome report;

[2201] a means for collecting environmental data in real time;

[2202] a means for recognizing and analyzing emotion data;

[2203] a means of integrating environmental data and emotional data to adjust activity performance;

[2204] a means of including sentiment data in outcome reports;

[2205] A system including:

[2206] (Claim 2)

[2207] means for passing the generated data to a large scale language model (LLM);

[2208] a means for generating evaluation metrics from the data analyzed by the LLM;

[2209] a means for adjusting the evaluation index based on the environmental data and the emotion data;

[2210] The system of claim 1 further comprising:

[2211] (Claim 3)

[2212] a means of rating the company's efforts based on the generated activity performance measurements;

[2213] a means for displaying the rating results;

[2214] means for adjusting the ratings based on the sentiment data;

[2215] The system of claim 1 further comprising: [Explanation of symbols]

[2216] 10, 210, 310, 410 Data Processing Systems 12 Data Processing De...

Claims

1. A means for formulating evaluation indicators based on the generated data; means for automatically measuring activity performance based on evaluation metrics; means for storing the measurement results in a database; means for generating a performance report from the stored data; a means for displaying the generated outcome report; A system including:

2. means for passing the generated data to an LLM; a means for generating evaluation metrics from the data analyzed by the LLM; The system of claim 1 further comprising:

3. a means of rating the company's efforts based on the generated activity performance measurements; a means for displaying the rating results; The system of claim 1 further comprising:

Images