system

Abstract

We provide the system. [Solution] Data collection means, A data analysis means for analyzing information related to the environmental, social, and governance aspects of a company collected by the aforementioned data collection means, and for extracting indicators based on that analysis. An evaluation means for evaluating a company's performance based on indicators extracted by the aforementioned data analysis means, An improvement suggestion means that recommends improvement measures based on the results evaluated by the evaluation means, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, as awareness of environmental and social issues has increased, it has been required to accurately evaluate the environmental, social, and governance (ESG) performance of enterprises and propose effective improvement measures. However, conventional evaluation methods often rely on manual data collection and analysis, requiring a large amount of time and human resources. Furthermore, proposing improvement measures requires specialized knowledge, and there has been a problem that it is difficult for enterprises to take countermeasures on their own.

Means for Solving the Problems

[0005] To solve the above problems, this invention collects information related to a company's environmental, social, and governance aspects using data collection means, analyzes this information using data analysis means to extract indicators, and then evaluates the company's performance based on the extracted indicators using evaluation means, and recommends specific improvement measures based on the results using improvement suggestion means. In addition, it is possible to automatically answer relevant questions from the company using question answering means, and also makes suggestions for improving sustainability using business model suggestion means. In this way, the invention provides a system that can efficiently and practically improve a company's ESG performance.

[0006] "Data collection means" refers to a system that has the function of continuously collecting and appropriately recording information related to the environment, society, and governance from companies.

[0007] "Data analysis methods" refer to processes that analyze collected ESG-related information and extract various indicators to obtain data on a company's performance.

[0008] An "evaluation tool" is a tool that systematically evaluates a company's ESG performance based on analyzed data and has the function of comparing it with other criteria and industry standards.

[0009] "Improvement suggestion methods" are tools that allow companies to propose concrete improvement measures that they can consider and implement, based on the evaluation results.

[0010] A "question response system" is a system that has the function of automatically responding to questions from companies regarding ESG and related environmental, social, and governance issues.

[0011] A "business model proposal tool" is a tool that analyzes a company's current business model and proposes a new business model to improve its sustainability. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The system of this invention collects ESG (Environmental, Social, and Governance) related information from companies, automatically evaluates their performance, and suggests improvement measures. First, a user, who is a company representative, uses a terminal to input various ESG-related data and uploads it to the system.

[0034] Data collection and management

[0035] The server automatically categorizes the received data and stores it in a database. The stored data includes, for example, CO2 emissions, employee diversity indicators, and information on governance structure.

[0036] The server organizes and cleanses the data to prepare it for analysis.

[0037] Data analysis and evaluation

[0038] The server analyzes the collected data using a Large-Scale Language Model (LLM). This model utilizes deep learning techniques to extract company ESG indicators based on the input data.

[0039] The server evaluates a company's ESG performance based on the extracted indicators and outputs it to the terminal as a visualized report.

[0040] Proposal for improvement measures

[0041] The server identifies a company's weaknesses based on the evaluation results and generates specific measures for improvement. For example, it can propose the introduction of energy-saving technologies to a manufacturing company with high energy consumption.

[0042] The terminal presents this proposal to the user in a dashboard format and provides the functionality to generate a detailed execution plan.

[0043] Question answering function

[0044] Users submit questions about the environment, society, and governance to the system via their devices.

[0045] The server responds to these questions with automatically generated answers based on historical data and industry information. This feature allows users to obtain information instantly.

[0046] Proposal for a sustainable business model

[0047] The server analyzes a company's existing business model and helps it switch to a model that considers future sustainability. For example, it supports companies in improving their sustainability by proposing solutions that include streamlining supply chains and promoting the use of renewable energy.

[0048] Thus, the system of the present invention aims to improve overall ESG performance and provides companies with efficient and strategic operational support.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] Users use their devices to input ESG-related company data and upload it to the system. This data includes environmental performance indicators, social contribution activities, and governance structures.

[0052] Step 2:

[0053] When the server stores received data in the database, it cleanses the data. It detects missing or abnormal values ​​and corrects or imputes them as needed.

[0054] Step 3:

[0055] The server sends the cleansed data to a Large-Scale Language Model (LLM) to begin analysis. The model analyzes the data and extracts indicators related to the environment, society, and governance.

[0056] Step 4:

[0057] The server performs scoring based on extracted ESG indicators to evaluate a company's performance. The evaluation is done by comparing it to industry standards and historical data.

[0058] Step 5:

[0059] Based on the evaluation results, the server develops necessary improvement measures for the company. For example, it may propose energy-saving measures or improvements to employee diversity.

[0060] Step 6:

[0061] The terminal provides the user with evaluation results and improvement suggestions obtained from the server, displaying them visually in a dashboard format. Based on this information, the user can develop a concrete improvement plan.

[0062] Step 7:

[0063] Users use a terminal to input specific ESG-related questions into the system. These questions include those about sustainability strategies and industry benchmarks.

[0064] Step 8:

[0065] The server analyzes the entered question and generates an answer using its internal database and external information. The generated response is automatically provided to the user.

[0066] Step 9:

[0067] The server analyzes a company's current business model and makes new suggestions to enhance sustainability. For example, it proposes the use of renewable energy and measures to improve supply chain efficiency.

[0068] Step 10:

[0069] The terminal will manage the progress of proposed sustainable business models and improvement measures, and will provide users with a means to generate and provide reports as needed.

[0070] (Example 1)

[0071] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0072] Rapid and accurate assessment of a company's ESG (Environmental, Social, and Governance) performance and provision of effective improvement measures are crucial for achieving sustainable management. However, traditional methods have been complex and time-consuming in terms of data collection and analysis, and the proposed improvement measures have often lacked sufficient specificity. Furthermore, the lack of visualized information to guide managers in quickly developing countermeasures has limited the effectiveness of efficient operational support.

[0073] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0074] In this invention, the server includes data management means for classifying and storing data, data cleansing means for preparing the stored data for analysis, and data analysis means for extracting corporate indicators using a generated AI model. This enables highly accurate data analysis and the proposal of concrete improvement measures that reflect the current state of the company. Furthermore, by providing visualized information, it is possible to build a foundation for corporate managers to make quick decisions.

[0075] "Data management means" refers to the function of classifying ESG-related data collected from companies and storing it in a database so that efficient analysis can be performed.

[0076] "Data cleansing means" refers to a function that processes collected data to correct any missing or abnormal data and prepare it for analysis.

[0077] A "generative AI model" refers to an algorithm that uses machine learning techniques to automatically extract company metrics from input data.

[0078] "Data analysis methods" refer to the function of extracting a company's ESG indicators using data that is ready for analysis, and using these as the basis for evaluation.

[0079] "Evaluation method" refers to a function that comprehensively evaluates a company's ESG performance based on extracted indicators, and calculates and visualizes the results.

[0080] The "method for proposing improvement measures" refers to the function of formulating and proposing specific improvement measures based on the evaluated performance results.

[0081] "Business structure proposal tools" refer to the function of analyzing a company's existing business model and proposing new structures and strategies to improve sustainability.

[0082] A "question answering tool" refers to a function that automatically generates and provides immediate responses to a company's ESG-related questions based on past data and industry knowledge.

[0083] "Visual display means" refers to a function that visually displays analyzed data and proposed improvement measures using diagrams, graphs, etc., so that users can easily understand them.

[0084] Embodiments of the present invention provide a system that efficiently evaluates a company's ESG (environmental, social, and governance) performance and proposes effective improvement measures. The system primarily operates by performing various data processing operations on a server based on data input by the user.

[0085] Data entry and management:

[0086] Users input ESG data about a company into a computer terminal. This data includes items such as CO2 emissions, employee diversity, and governance structure. The terminal verifies the data format and transmits the data to the server via a secure connection.

[0087] Data organization and storage:

[0088] The server analyzes the received data using a data classification algorithm and stores it appropriately in the database. It also improves data quality by performing data cleansing to correct missing or abnormal data.

[0089] Data analysis:

[0090] The server analyzes cleansed data using a Large-Scale Language Model (LLM) to extract company ESG indicators. Here, generative AI models are employed, along with advanced machine learning techniques to identify significant patterns and trends from the data.

[0091] Evaluation of results and proposal of improvement measures:

[0092] The server generates a report that visually presents the analysis results using evaluation tools, clearly identifying the company's strengths and weaknesses. This report presents specific improvement measures, such as the introduction of energy-saving technologies in energy-intensive industries and initiatives to enhance diversity.

[0093] Specific example:

[0094] For example, when a manufacturing company uses the system, it can input CO2 emission data, and the server can then suggest specific measures for energy efficiency. Based on these suggestions, the company can review its manufacturing processes.

[0095] Example of a prompt:

[0096] "Please provide specific suggestions for improving our company's ESG performance."

[0097] This system allows companies to obtain concrete action plans to enhance sustainability, enabling them to implement strategic improvements quickly and efficiently.

[0098] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0099] Step 1:

[0100] Users input company ESG data into a terminal. This data includes CO2 emissions and employee diversity indicators. The terminal verifies format consistency of the entered data and sends it to the server. This prepares the input data, allowing it to proceed to the next processing step.

[0101] Step 2:

[0102] The server automatically classifies and organizes the received data and stores it in a database. Specifically, it uses a data classification algorithm to distribute the data into categories related to environment, society, and governance. After the data classification is complete, it is stored in the database and ready for analysis.

[0103] Step 3:

[0104] The server performs data cleansing on the stored data. This cleansing process involves imputing missing values ​​and correcting outliers, creating a high-quality dataset suitable for analysis. This process improves the accuracy of the analysis and prepares input data that yields reliable results.

[0105] Step 4:

[0106] The server performs data analysis using a generative AI model. Specifically, it utilizes deep learning algorithms to extract ESG performance indicators for companies from data that is ready for analysis. This process generates indicator data that quantifies and visually evaluates a company's strengths and weaknesses.

[0107] Step 5:

[0108] The server evaluates the analysis results and generates a report using visualization tools. This report uses graphs and charts to show the current state of the company's ESG performance and areas for improvement. The generated report is output and displayed on the terminal.

[0109] Step 6:

[0110] The server develops improvement plans based on the visualized evaluation results. These improvement plans include specific measures for improving energy efficiency and diversity, for example. The proposed improvement plans are generated and sent to the terminal.

[0111] Step 7:

[0112] The terminal presents the user with reports and improvement suggestions received from the server. The user can then develop strategies to improve the company's ESG performance based on concrete action plans. This completes the entire system's processing.

[0113] (Application Example 1)

[0114] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0115] In today's environment, there is a lack of effective ways for companies to collect and analyze environmental, social, and governance (ESG) information based on sustainability and to directly communicate it to consumers. This makes it difficult for consumers to utilize companies' ESG initiatives in their actual choices and purchasing decisions.

[0116] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0117] In this invention, the server includes a device for collecting data, a device for analyzing the data to extract indicators related to the environment, society, and governance, and a device for evaluating performance based on the indicators. This visually displays the environmental, social, and governance information of a company to entities, enabling consumers to make better choices based on this information.

[0118] A "data collection device" is a device for effectively acquiring and storing information related to a company's environmental, social, and governance aspects.

[0119] A "data analysis device" is a device that has the capability to organize collected data and extract necessary indicators.

[0120] A "performance evaluation device" is a device used to evaluate a company's environmental, social, and governance-related performance based on extracted indicators.

[0121] A "proposal-making device" is a device that generates and presents specific measures to recommend improvement strategies for companies based on evaluation results.

[0122] A "device for visually displaying store environmental, social, and governance information for a specific entity" is a device that visually shows and provides information to consumers and users about a company's or store's efforts to protect the environment and contribute to society.

[0123] This invention is a system that acquires, analyzes, and visually displays information related to a company's environmental, social, and governance aspects. The main components of the system are a server, terminals, and users.

[0124] The server is equipped with data collection devices that efficiently acquire ESG information provided by companies and automatically classify it. For example, it stores information on companies' CO2 emissions and governance structures in a database.

[0125] Next, the server processes the collected data using data analysis equipment and extracts indicators related to the environment, society, and governance. During this process, a generative AI model is used to analyze the data and quantify the company's ESG performance.

[0126] The terminal is equipped with a device for evaluating performance, assessing the company's performance based on metrics transmitted from the server. Based on the evaluation results, it generates a visual report to recommend improvement measures. This report is displayed on the dashboard in a way that is accessible to the user.

[0127] Furthermore, the terminal, through a suggestion-making device, presents users with specific measures for corporate improvement. Users operate the application via the terminal and understand the store's environmental, social, and governance information based on the visually presented information. This information is provided to consumers in specific entities and influences their purchasing behavior.

[0128] This system will allow, for example, customers to scan a QR code (registered trademark) in a store using their smartphone to view details about the store's environmental protection activities and diversity promotion initiatives. In this case, an example of a prompt used for the generating AI model would be the question, "Please tell me about this store's ESG initiatives."

[0129] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0130] Step 1:

[0131] The server receives and classifies ESG information provided by companies using a data collection device. It takes information on companies' CO2 emissions and governance structures as input and stores this information in a database in an organized data format as output.

[0132] Step 2:

[0133] The server analyzes collected data using a generative AI model and extracts environmental, social, and governance indicators. It uses classified data from a database as input and calculates a company's ESG indicators as output. Deep learning technology is used for data calculation to determine these indicators.

[0134] Step 3:

[0135] The terminal receives ESG indicators sent from the server and evaluates the company's performance based on them. It takes ESG indicators as input and generates a report visualizing the evaluation results as output. Infographics technology is used for visualization.

[0136] Step 4:

[0137] The device generates and presents a dashboard to the user that suggests improvement measures based on the evaluation results. It uses the evaluated data as input and displays improvement measures in a dashboard format that is easy for the user to understand as output.

[0138] Step 5:

[0139] Users utilize their devices to refer to visualized evaluation results and suggestions, and to understand environmental, social, and governance information about specific entities. Specifically, they obtain and display necessary information by scanning a QR code with their smartphone.

[0140] Step 6:

[0141] The server uses a generative AI model to automatically generate and respond to user prompts, such as "Please tell me about this store's ESG initiatives." It receives user questions as input and provides answers based on historical data and industry information as output.

[0142] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0143] This invention combines a system that evaluates a company's ESG (Environmental, Social, and Governance) performance and proposes improvement measures with an emotion engine that recognizes user emotions. By providing feedback that takes the user's emotional state into account, this system achieves more effective and user-friendly interaction.

[0144] Data collection and analysis

[0145] Users operate a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes indicators of environmental impact, diversity of talent, and governance frameworks.

[0146] The server receives the data, performs a cleansing process, and then analyzes it using data analysis tools. Large-scale language models (LLMs) are used to extract ESG indicators for companies.

[0147] Emotion recognition and feedback

[0148] The server uses an emotion engine to recognize emotions based on user behavior and input data in the user interface. This engine determines in real time whether the user is feeling stressed or experiencing positive emotions.

[0149] The device adjusts the feedback provided to the user based on the emotions it recognizes. For example, if the user is feeling stressed, it displays supplementary information and makes suggestions simpler.

[0150] Performance evaluation and improvement suggestions

[0151] The server evaluates a company's ESG performance based on analyzed metrics and reports this to the user. The evaluation is compared to industry standards and historical data to enhance its reliability.

[0152] The server considers the data obtained from the emotion engine and suggests improvements based on the user's emotional state. For example, it might adjust the difficulty level of the suggestions or change the way choices are presented.

[0153] Enhanced user interaction

[0154] Users experience a more positive interaction with the system by receiving emotion-based suggestions. The system facilitates the implementation of improvement measures by enabling flexible responses tailored to the user's situation.

[0155] Thus, the present invention provides a system that not only supports the overall improvement of ESG performance but also understands user emotions and provides flexible feedback accordingly, thereby enabling the effective promotion of ESG activities.

[0156] The following describes the processing flow.

[0157] Step 1:

[0158] Users use a terminal to input and upload company ESG data. This data includes specific CO2 emissions, details of social contribution activities, and information about the company's governance structure.

[0159] Step 2:

[0160] Before storing received data in the database, the server performs data cleansing. This includes handling missing data and standardization work to maintain consistency.

[0161] Step 3:

[0162] The server sends the cleansed data to a Large-Scale Language Model (LLM) to extract ESG-related metrics. Here, it analyzes how each metric compares to industry averages and historical benchmarks.

[0163] Step 4:

[0164] The server scores a company's ESG performance based on the extracted metrics and generates an evaluation result. This information is then compiled into a report format using visualization tools.

[0165] Step 5:

[0166] The server generates improvement suggestions based on the evaluation results. This includes a process of adjusting the suggestions using user emotion recognition data. For example, if the user is experiencing stress, the suggestions are simplified and broken down into more manageable steps.

[0167] Step 6:

[0168] The device presents the evaluation results and improvement suggestions to the user. This information is presented in a user-friendly format, including feedback based on emotional data collected by the emotion engine.

[0169] Step 7:

[0170] Users review improvement suggestions and provide feedback on them. The system records data so that their feelings and opinions are reflected in future suggestions.

[0171] Step 8:

[0172] The server collects user feedback and stores it in a database. This feedback will be used to refine future suggestions and improve the system.

[0173] Through this series of processes, the system can support the promotion of ESG activities and make flexible proposals that take user sentiment into consideration.

[0174] (Example 2)

[0175] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0176] In evaluating a company's environmental, social, and governance (ESG) performance and proposing improvement measures, there is a growing need to provide user-friendly interactions and more effectively solve problems by offering feedback that takes user emotions into consideration. Traditional systems often provide one-sided feedback that does not consider user emotions, which can cause stress for users, and this needs to be improved.

[0177] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0178] In this invention, the server includes data analysis means, emotion recognition means, and feedback generation means. This enables more effective interaction while reducing the user's burden by providing appropriate feedback according to the user's emotional state and through evaluation of ESG performance and suggestion of improvement measures.

[0179] "Data collection methods" refer to means of collecting information related to a company's environmental, social, and governance aspects.

[0180] "Data analysis means" refers to methods for analyzing collected information and extracting ESG indicators based on that analysis.

[0181] "Evaluation methods" refer to the means used to assess a company's performance based on extracted indicators.

[0182] "Improvement suggestion methods" are means of recommending improvement measures based on the evaluated results and the user's emotional state.

[0183] "Emotion recognition means" refers to a means of recognizing a user's emotional state.

[0184] A "feedback generation method" is a means for generating feedback that corresponds to the recognized emotions of the user.

[0185] This invention incorporates a function that provides user-centric feedback while evaluating a company's ESG (environmental, social, and governance) performance and proposing improvement measures. This system is realized by using data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means.

[0186] Data collection

[0187] Users use a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes, for example, CO2 emissions, employee diversity scores, and governance policies.

[0188] Data Analysis

[0189] The server receives data sent from users and performs a cleansing process. Then, it analyzes the data using a Large-Scale Language Model (LLM) and extracts ESG indicators. The LLM uses natural language processing techniques to identify patterns in the data and gain deep insights.

[0190] emotion recognition

[0191] The server uses an emotion engine to recognize the user's emotional state in real time. This engine determines stress levels and positive emotions based on the user's terminal operations and input.

[0192] Provide feedback

[0193] The device adjusts its feedback based on the emotion recognition results. For example, if the user is feeling stressed, the device provides a specific and concise explanation and displays support information as needed.

[0194] As a concrete example, when a company conducts a sustainability assessment, users input their company's environmental data, which is then analyzed by a server. Along with the analysis results, the user's emotional state is taken into consideration, and more actionable improvement measures are proposed to the user.

[0195] Examples of prompt statements are as follows:

[0196] "Please enter your company's environmental impact data. What improvements do you feel are needed? If you are experiencing stress, what kind of support would be helpful?"

[0197] This system configuration allows for more effective support of ESG activities.

[0198] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0199] Step 1:

[0200] Data entry

[0201] Users input company ESG data using a terminal. This data specifically includes CO2 emissions, employee diversity scores, and governance policies. User input is received via a dedicated form and sent to the server. The entered information serves as foundational data for system analysis.

[0202] Step 2:

[0203] Data cleansing

[0204] The server verifies the received data and performs a cleansing process. This process detects and corrects or supplements any inappropriate or missing data. For example, it may include detecting and removing outliers and converting to a standard format. The output is clean, reliable data.

[0205] Step 3:

[0206] Data Analysis

[0207] The server analyzes the cleansed data. During this process, a Large-Scale Language Model (LLM) is used to extract data patterns. Specifically, it analyzes trends in CO2 emission reduction and the progress of diversity improvement. The model uses natural language processing techniques to automatically extract relationships and key indicators, providing them as analysis results. This forms the basis for the next evaluation step.

[0208] Step 4:

[0209] emotion recognition

[0210] The server uses an emotion engine to recognize the user's emotional state. This recognition is based on the user's terminal operations (mouse movements, click speed) and input content. The server attempts to understand the user's psychological state by identifying signs of stress, positive attitudes, etc. As output, the user's emotional profile is generated.

[0211] Step 5:

[0212] Feedback generation

[0213] The device generates feedback based on analysis results and emotional profiles. In doing so, it provides information in a format appropriate to the user's emotional state. For example, if the user is feeling anxious, it will present concise action points. The generated feedback is designed to make it easy for the user to implement the suggested improvements.

[0214] Step 6:

[0215] Improvement suggestions

[0216] Based on the evaluated results and the user's sentiment, the server presents specific suggestions for improving the company's ESG performance. These suggestions are presented in an easy-to-understand format, taking the user's emotional state into consideration. This allows users to naturally accept the suggestions and utilize them to contribute to the company's sustainable growth.

[0217] (Application Example 2)

[0218] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0219] Many organizations evaluate and improve metrics related to the environment, society, and governance, but a challenge remains in providing feedback that fully considers consumer sentiment and thus failing to optimize the customer experience.

[0220] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0221] In this invention, the server includes data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means. This enables the provision of flexible and effective feedback based on consumer emotions while evaluating the organization's performance.

[0222] "Data collection means" refers to devices or methods for collecting information related to an organization's environment, society, and governance.

[0223] "Data analysis means" refers to devices and methods for analyzing collected information and extracting necessary indicators.

[0224] "Evaluation tools" refer to devices or methods for evaluating an organization's performance based on analyzed indicators.

[0225] "Emotion recognition means" refers to devices or methods for acquiring consumer emotional data and recognizing those emotions.

[0226] A "feedback generation means" is a device or method that provides appropriate feedback to consumers based on the results of emotion recognition.

[0227] The embodiments for carrying out the invention are described below. First, the system collects information related to the organization's environment, society, and governance using data collection means. Next, a server uses a cloud platform such as Google Cloud to perform data analysis, analyze the collected information, and extract indicators as a result of the analysis. This provides basic data for evaluating the organization's performance.

[0228] Furthermore, the server uses emotion recognition to analyze emotion data acquired from smart glasses and in-store sensors. This analysis utilizes Google Cloud's emotion analysis API to recognize the emotions consumers are expressing towards products and services. This emotion data is then used as a means of generating feedback. The server generates information and advice based on the consumer's emotions and displays it on smart glasses and in-store displays.

[0229] As a concrete example, when a customer picks up a product and shows interest, smart glasses could analyze the consumer's facial expressions and gaze, displaying information about the product's environmental impact and advice to encourage purchase. An example of a prompt might be, "Provide ESG information for the product the customer is interested in. Also, based on the customer's emotional responses, highlight points that are likely to be of particular interest." This would allow organizations to provide consumers with a more personalized purchasing experience.

[0230] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0231] Step 1:

[0232] The server receives information from users related to the organization's environment, society, and governance using data collection means. This includes numerical and text data provided through input devices. The input data is stored in a database.

[0233] Step 2:

[0234] The server analyzes the received data using data analysis tools. At this stage, Google Cloud's data analysis tools are used to extract specific metrics from the input data. The output is a set of metrics that represent the organization's performance.

[0235] Step 3:

[0236] The server uses evaluation tools to assess the organization's financial and non-financial performance based on the metrics extracted in the previous step. The input is a set of metrics, and the output is the organization's evaluation result. This evaluation result is displayed on a dashboard in the cloud.

[0237] Step 4:

[0238] The user initiates their actions in a physical store through smart glasses. Here, an emotion recognition system collects the user's facial expression and gaze data. The input is raw data acquired from the camera, and the output is emotion data for analysis.

[0239] Step 5:

[0240] The server analyzes the acquired sentiment data using Google Cloud's Sentiment Analysis API to identify the user's emotional state. The input is sentiment data, and the output is the label of the recognized emotion. This is then passed on to the feedback generation system.

[0241] Step 6:

[0242] The server generates feedback to provide to the user based on evaluation results and emotional state. Using a generative AI model and prompts, it generates personalized information and advice. The output is a feedback message displayed on smart glasses or in-store displays.

[0243] Step 7:

[0244] The terminal displays the generated feedback on the user's device in real time. This allows the user to instantly receive personalized information about the product or service. The input is the feedback message, and the output is its visualization on the user interface.

[0245] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0246] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0252] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0256] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0257] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0258] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0259] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0260] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0261] The system of this invention collects ESG (Environmental, Social, and Governance) related information from companies, automatically evaluates their performance, and suggests improvement measures. First, a user, who is a company representative, uses a terminal to input various ESG-related data and uploads it to the system.

[0262] Data collection and management

[0263] The server automatically categorizes the received data and stores it in a database. The stored data includes, for example, CO2 emissions, employee diversity indicators, and information on governance structure.

[0264] The server organizes and cleanses the data to prepare it for analysis.

[0265] Data analysis and evaluation

[0266] The server analyzes the collected data using a Large-Scale Language Model (LLM). This model utilizes deep learning techniques to extract company ESG indicators based on the input data.

[0267] The server evaluates a company's ESG performance based on the extracted indicators and outputs it to the terminal as a visualized report.

[0268] Proposal for improvement measures

[0269] The server identifies a company's weaknesses based on the evaluation results and generates specific measures for improvement. For example, it can propose the introduction of energy-saving technologies to a manufacturing company with high energy consumption.

[0270] The terminal presents this proposal to the user in a dashboard format and provides the functionality to generate a detailed execution plan.

[0271] Question answering function

[0272] Users submit questions about the environment, society, and governance to the system via their devices.

[0273] The server responds to these questions with automatically generated answers based on historical data and industry information. This feature allows users to obtain information instantly.

[0274] Proposal for a sustainable business model

[0275] The server analyzes the enterprise's existing business model and supports the switch to a model considering future sustainability. For example, it supports the improvement of the enterprise's sustainability through proposals including the optimization of the supply chain and the promotion of the use of renewable energy.

[0276] Thus, the system of the present invention aims at the comprehensive improvement of ESG performance and provides enterprises with efficient and strategic operation support.

[0277] The processing flow will be described below.

[0278] Step 1:

[0279] The user uses the terminal to input ESG-related enterprise data and upload it to the system. The data includes environmental performance indicators, social contribution activities, governance structures, etc.

[0280] Step 2:

[0281] When storing the received data in the database, the server cleans the data. It detects missing values and outliers and performs corrections and supplements as necessary.

[0282] Step 3:

[0283] The server sends the cleansed data to a large language model (LLM) and starts the analysis. The model analyzes the data and extracts indicators related to environment, society, and governance.

[0284] Step 4:

[0285] The server performs scoring based on the extracted ESG indicators and evaluates the enterprise's performance. The evaluation is carried out by comparing with industry standards and past data.

[0286] Step 5:

[0287] Based on the evaluation results, the server develops necessary improvement measures for the company. For example, it may propose energy-saving measures or improvements to employee diversity.

[0288] Step 6:

[0289] The terminal provides the user with evaluation results and improvement suggestions obtained from the server, displaying them visually in a dashboard format. Based on this information, the user can develop a concrete improvement plan.

[0290] Step 7:

[0291] Users use a terminal to input specific ESG-related questions into the system. These questions include those about sustainability strategies and industry benchmarks.

[0292] Step 8:

[0293] The server analyzes the entered question and generates an answer using its internal database and external information. The generated response is automatically provided to the user.

[0294] Step 9:

[0295] The server analyzes a company's current business model and makes new suggestions to enhance sustainability. For example, it proposes the use of renewable energy and measures to improve supply chain efficiency.

[0296] Step 10:

[0297] The terminal will manage the progress of proposed sustainable business models and improvement measures, and will provide users with a means to generate and provide reports as needed.

[0298] (Example 1)

[0299] Next, we will describe Example 1. 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."

[0300] Rapid and accurate assessment of a company's ESG (Environmental, Social, and Governance) performance and provision of effective improvement measures are crucial for achieving sustainable management. However, traditional methods have been complex and time-consuming in terms of data collection and analysis, and the proposed improvement measures have often lacked sufficient specificity. Furthermore, the lack of visualized information to guide managers in quickly developing countermeasures has limited the effectiveness of efficient operational support.

[0301] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0302] In this invention, the server includes data management means for classifying and storing data, data cleansing means for preparing the stored data for analysis, and data analysis means for extracting corporate indicators using a generated AI model. This enables highly accurate data analysis and the proposal of concrete improvement measures that reflect the current state of the company. Furthermore, by providing visualized information, it is possible to build a foundation for corporate managers to make quick decisions.

[0303] "Data management means" refers to the function of classifying ESG-related data collected from companies and storing it in a database so that efficient analysis can be performed.

[0304] "Data cleansing means" refers to a function that processes collected data to correct any missing or abnormal data and prepare it for analysis.

[0305] A "generative AI model" refers to an algorithm that uses machine learning techniques to automatically extract company metrics from input data.

[0306] "Data analysis methods" refer to the function of extracting a company's ESG indicators using data that is ready for analysis, and using these as the basis for evaluation.

[0307] "Evaluation means" refers to the function of comprehensively evaluating a company's ESG performance based on the extracted indicators and calculating and visualizing the results.

[0308] "Improvement measure proposal means" refers to the function of formulating and proposing specific improvement measures based on the evaluated performance results.

[0309] "Business structure proposal means" refers to the function of analyzing a company's existing business model and proposing new structures and strategies to improve sustainability.

[0310] "Question and answer means" refers to the function of generating and providing an automatic response based on past data and industry knowledge to questions regarding a company's ESG immediately.

[0311] "Visual display means" refers to the function of visually displaying the analyzed data and proposed improvement measures in figures, graphs, etc., so that users can easily understand them.

[0312] Embodiments of the present invention provide a system for efficiently evaluating a company's ESG (Environmental, Social, Governance) performance and proposing effective improvement measures. The system mainly operates by executing various data processes on a server based on data input by a user.

[0313] Data input and management:

[0314] The user inputs ESG data related to a company into a computer terminal. This data includes items such as CO2 emissions, employee diversity, and governance structure. The terminal checks the data format and transmits the data to the server through a secure connection.

[0315] Data sorting and storage:

[0316] The server analyzes the received data using a data classification algorithm and stores it appropriately in the database. It also improves data quality by performing data cleansing to correct missing or abnormal data.

[0317] Data analysis:

[0318] The server analyzes cleansed data using a Large-Scale Language Model (LLM) to extract company ESG indicators. Here, generative AI models are employed, along with advanced machine learning techniques to identify significant patterns and trends from the data.

[0319] Evaluation of results and proposal of improvement measures:

[0320] The server generates a report that visually presents the analysis results using evaluation tools, clearly identifying the company's strengths and weaknesses. This report presents specific improvement measures, such as the introduction of energy-saving technologies in energy-intensive industries and initiatives to enhance diversity.

[0321] Specific example:

[0322] For example, when a manufacturing company uses the system, it can input CO2 emission data, and the server can then suggest specific measures for energy efficiency. Based on these suggestions, the company can review its manufacturing processes.

[0323] Example of a prompt:

[0324] "Please provide specific suggestions for improving our company's ESG performance."

[0325] This system allows companies to obtain concrete action plans to enhance sustainability, enabling them to implement strategic improvements quickly and efficiently.

[0326] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0327] Step 1:

[0328] Users input company ESG data into a terminal. This data includes CO2 emissions and employee diversity indicators. The terminal verifies format consistency of the entered data and sends it to the server. This prepares the input data, allowing it to proceed to the next processing step.

[0329] Step 2:

[0330] The server automatically classifies and organizes the received data and stores it in a database. Specifically, it uses a data classification algorithm to distribute the data into categories related to environment, society, and governance. After the data classification is complete, it is stored in the database and ready for analysis.

[0331] Step 3:

[0332] The server performs data cleansing on the stored data. This cleansing process involves imputing missing values ​​and correcting outliers, creating a high-quality dataset suitable for analysis. This process improves the accuracy of the analysis and prepares input data that yields reliable results.

[0333] Step 4:

[0334] The server performs data analysis using a generative AI model. Specifically, it utilizes deep learning algorithms to extract ESG performance indicators for companies from data that is ready for analysis. This process generates indicator data that quantifies and visually evaluates a company's strengths and weaknesses.

[0335] Step 5:

[0336] The server evaluates the analysis results and generates a report using visualization tools. This report uses graphs and charts to show the current state of the company's ESG performance and areas for improvement. The generated report is output and displayed on the terminal.

[0337] Step 6:

[0338] The server develops improvement plans based on the visualized evaluation results. These improvement plans include specific measures for improving energy efficiency and diversity, for example. The proposed improvement plans are generated and sent to the terminal.

[0339] Step 7:

[0340] The terminal presents the user with reports and improvement suggestions received from the server. The user can then develop strategies to improve the company's ESG performance based on concrete action plans. This completes the entire system's processing.

[0341] (Application Example 1)

[0342] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0343] In today's environment, there is a lack of effective ways for companies to collect and analyze environmental, social, and governance (ESG) information based on sustainability and to directly communicate it to consumers. This makes it difficult for consumers to utilize companies' ESG initiatives in their actual choices and purchasing decisions.

[0344] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0345] In this invention, the server includes a device for collecting data, a device for analyzing the data to extract indicators related to the environment, society, and governance, and a device for evaluating performance based on the indicators. This visually displays the environmental, social, and governance information of a company to entities, enabling consumers to make better choices based on this information.

[0346] A "data collection device" is a device for effectively acquiring and storing information related to a company's environmental, social, and governance aspects.

[0347] A "data analysis device" is a device that has the capability to organize collected data and extract necessary indicators.

[0348] A "performance evaluation device" is a device used to evaluate a company's environmental, social, and governance-related performance based on extracted indicators.

[0349] A "proposal-making device" is a device that generates and presents specific measures to recommend improvement strategies for companies based on evaluation results.

[0350] A "device for visually displaying store environmental, social, and governance information for a specific entity" is a device that visually shows and provides information to consumers and users about a company's or store's efforts to protect the environment and contribute to society.

[0351] This invention is a system that acquires, analyzes, and visually displays information related to a company's environmental, social, and governance aspects. The main components of the system are a server, terminals, and users.

[0352] The server is equipped with data collection devices that efficiently acquire ESG information provided by companies and automatically classify it. For example, it stores information on companies' CO2 emissions and governance structures in a database.

[0353] Next, the server processes the collected data using data analysis equipment and extracts indicators related to the environment, society, and governance. During this process, a generative AI model is used to analyze the data and quantify the company's ESG performance.

[0354] The terminal is equipped with a device for evaluating performance, assessing the company's performance based on metrics transmitted from the server. Based on the evaluation results, it generates a visual report to recommend improvement measures. This report is displayed on the dashboard in a way that is accessible to the user.

[0355] Furthermore, the terminal, through a suggestion-making device, presents users with specific measures for corporate improvement. Users operate the application via the terminal and understand the store's environmental, social, and governance information based on the visually presented information. This information is provided to consumers in specific entities and influences their purchasing behavior.

[0356] This system will allow, for example, customers to scan a QR code in a store using their smartphone to view details about the store's environmental protection activities and diversity promotion initiatives. In this case, an example of a prompt used for the generating AI model would be the question, "Please tell me about this store's ESG initiatives."

[0357] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0358] Step 1:

[0359] The server receives and classifies ESG information provided by companies using a data collection device. It takes information on companies' CO2 emissions and governance structures as input and stores this information in a database in an organized data format as output.

[0360] Step 2:

[0361] The server analyzes collected data using a generative AI model and extracts environmental, social, and governance indicators. It uses classified data from a database as input and calculates a company's ESG indicators as output. Deep learning technology is used for data calculation to determine these indicators.

[0362] Step 3:

[0363] The terminal receives ESG indicators sent from the server and evaluates the company's performance based on them. It takes ESG indicators as input and generates a report visualizing the evaluation results as output. Infographics technology is used for visualization.

[0364] Step 4:

[0365] The device generates and presents a dashboard to the user that suggests improvement measures based on the evaluation results. It uses the evaluated data as input and displays improvement measures in a dashboard format that is easy for the user to understand as output.

[0366] Step 5:

[0367] Users utilize their devices to refer to visualized evaluation results and suggestions, and to understand environmental, social, and governance information about specific entities. Specifically, they obtain and display necessary information by scanning a QR code with their smartphone.

[0368] Step 6:

[0369] The server uses a generative AI model to automatically generate and respond to user prompts, such as "Please tell me about this store's ESG initiatives." It receives user questions as input and provides answers based on historical data and industry information as output.

[0370] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0371] This invention combines a system that evaluates a company's ESG (Environmental, Social, and Governance) performance and proposes improvement measures with an emotion engine that recognizes user emotions. By providing feedback that takes the user's emotional state into account, this system achieves more effective and user-friendly interaction.

[0372] Data collection and analysis

[0373] Users operate a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes indicators of environmental impact, diversity of talent, and governance frameworks.

[0374] The server receives the data, performs a cleansing process, and then analyzes it using data analysis tools. Large-scale language models (LLMs) are used to extract ESG indicators for companies.

[0375] Emotion recognition and feedback

[0376] The server uses an emotion engine to recognize emotions based on user behavior and input data in the user interface. This engine determines in real time whether the user is feeling stressed or experiencing positive emotions.

[0377] The device adjusts the feedback provided to the user based on the emotions it recognizes. For example, if the user is feeling stressed, it displays supplementary information and makes suggestions simpler.

[0378] Performance evaluation and improvement suggestions

[0379] The server evaluates a company's ESG performance based on analyzed metrics and reports this to the user. The evaluation is compared to industry standards and historical data to enhance its reliability.

[0380] The server considers the data obtained from the emotion engine and suggests improvements based on the user's emotional state. For example, it might adjust the difficulty level of the suggestions or change the way choices are presented.

[0381] Enhanced user interaction

[0382] Users experience a more positive interaction with the system by receiving emotion-based suggestions. The system facilitates the implementation of improvement measures by enabling flexible responses tailored to the user's situation.

[0383] Thus, the present invention provides a system that not only supports the overall improvement of ESG performance but also understands user emotions and provides flexible feedback accordingly, thereby enabling the effective promotion of ESG activities.

[0384] The following describes the processing flow.

[0385] Step 1:

[0386] Users use a terminal to input and upload company ESG data. This data includes specific CO2 emissions, details of social contribution activities, and information about the company's governance structure.

[0387] Step 2:

[0388] Before storing received data in the database, the server performs data cleansing. This includes handling missing data and standardization work to maintain consistency.

[0389] Step 3:

[0390] The server sends the cleansed data to a Large-Scale Language Model (LLM) to extract ESG-related metrics. Here, it analyzes how each metric compares to industry averages and historical benchmarks.

[0391] Step 4:

[0392] The server scores a company's ESG performance based on the extracted metrics and generates an evaluation result. This information is then compiled into a report format using visualization tools.

[0393] Step 5:

[0394] The server generates improvement suggestions based on the evaluation results. This includes a process of adjusting the suggestions using user emotion recognition data. For example, if the user is experiencing stress, the suggestions are simplified and broken down into more manageable steps.

[0395] Step 6:

[0396] The device presents the evaluation results and improvement suggestions to the user. This information is presented in a user-friendly format, including feedback based on emotional data collected by the emotion engine.

[0397] Step 7:

[0398] Users review improvement suggestions and provide feedback on them. The system records data so that their feelings and opinions are reflected in future suggestions.

[0399] Step 8:

[0400] The server collects user feedback and stores it in a database. This feedback will be used to refine future suggestions and improve the system.

[0401] Through this series of processes, the system can support the promotion of ESG activities and make flexible proposals that take user sentiment into consideration.

[0402] (Example 2)

[0403] Next, we will describe Example 2. 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".

[0404] In evaluating a company's environmental, social, and governance (ESG) performance and proposing improvement measures, there is a growing need to provide user-friendly interactions and more effectively solve problems by offering feedback that takes user emotions into consideration. Traditional systems often provide one-sided feedback that does not consider user emotions, which can cause stress for users, and this needs to be improved.

[0405] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0406] In this invention, the server includes data analysis means, emotion recognition means, and feedback generation means. This enables more effective interaction while reducing the user's burden by providing appropriate feedback according to the user's emotional state and through evaluation of ESG performance and suggestion of improvement measures.

[0407] "Data collection methods" refer to means of collecting information related to a company's environmental, social, and governance aspects.

[0408] "Data analysis means" refers to methods for analyzing collected information and extracting ESG indicators based on that analysis.

[0409] "Evaluation methods" refer to the means used to assess a company's performance based on extracted indicators.

[0410] "Improvement suggestion methods" are means of recommending improvement measures based on the evaluated results and the user's emotional state.

[0411] "Emotion recognition means" refers to a means of recognizing a user's emotional state.

[0412] A "feedback generation method" is a means for generating feedback that corresponds to the recognized emotions of the user.

[0413] This invention incorporates a function that provides user-centric feedback while evaluating a company's ESG (environmental, social, and governance) performance and proposing improvement measures. This system is realized by using data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means.

[0414] Data collection

[0415] Users use a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes, for example, CO2 emissions, employee diversity scores, and governance policies.

[0416] Data Analysis

[0417] The server receives data sent from users and performs a cleansing process. Then, it analyzes the data using a Large-Scale Language Model (LLM) and extracts ESG indicators. The LLM uses natural language processing techniques to identify patterns in the data and gain deep insights.

[0418] emotion recognition

[0419] The server uses an emotion engine to recognize the user's emotional state in real time. This engine determines stress levels and positive emotions based on the user's terminal operations and input.

[0420] Provide feedback

[0421] The device adjusts its feedback based on the emotion recognition results. For example, if the user is feeling stressed, the device provides a specific and concise explanation and displays support information as needed.

[0422] As a concrete example, when a company conducts a sustainability assessment, users input their company's environmental data, which is then analyzed by a server. Along with the analysis results, the user's emotional state is taken into consideration, and more actionable improvement measures are proposed to the user.

[0423] Examples of prompt statements are as follows:

[0424] "Please enter your company's environmental impact data. What improvements do you feel are needed? If you are experiencing stress, what kind of support would be helpful?"

[0425] This system configuration allows for more effective support of ESG activities.

[0426] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0427] Step 1:

[0428] Data entry

[0429] Users input company ESG data using a terminal. This data specifically includes CO2 emissions, employee diversity scores, and governance policies. User input is received via a dedicated form and sent to the server. The entered information serves as foundational data for system analysis.

[0430] Step 2:

[0431] Data cleansing

[0432] The server verifies the received data and performs a cleansing process. This process detects and corrects or supplements any inappropriate or missing data. For example, it may include detecting and removing outliers and converting to a standard format. The output is clean, reliable data.

[0433] Step 3:

[0434] Data Analysis

[0435] The server analyzes the cleansed data. During this process, a Large-Scale Language Model (LLM) is used to extract data patterns. Specifically, it analyzes trends in CO2 emission reduction and the progress of diversity improvement. The model uses natural language processing techniques to automatically extract relationships and key indicators, providing them as analysis results. This forms the basis for the next evaluation step.

[0436] Step 4:

[0437] emotion recognition

[0438] The server uses an emotion engine to recognize the user's emotional state. This recognition is based on the user's terminal operations (mouse movements, click speed) and input content. The server attempts to understand the user's psychological state by identifying signs of stress, positive attitudes, etc. As output, the user's emotional profile is generated.

[0439] Step 5:

[0440] Feedback generation

[0441] The device generates feedback based on analysis results and emotional profiles. In doing so, it provides information in a format appropriate to the user's emotional state. For example, if the user is feeling anxious, it will present concise action points. The generated feedback is designed to make it easy for the user to implement the suggested improvements.

[0442] Step 6:

[0443] Improvement suggestions

[0444] Based on the evaluated results and the user's sentiment, the server presents specific suggestions for improving the company's ESG performance. These suggestions are presented in an easy-to-understand format, taking the user's emotional state into consideration. This allows users to naturally accept the suggestions and utilize them to contribute to the company's sustainable growth.

[0445] (Application Example 2)

[0446] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0447] Many organizations evaluate and improve metrics related to the environment, society, and governance, but a challenge remains in providing feedback that fully considers consumer sentiment and thus failing to optimize the customer experience.

[0448] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0449] In this invention, the server includes data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means. This enables the provision of flexible and effective feedback based on consumer emotions while evaluating the organization's performance.

[0450] "Data collection means" refers to devices or methods for collecting information related to an organization's environment, society, and governance.

[0451] "Data analysis means" refers to devices and methods for analyzing collected information and extracting necessary indicators.

[0452] "Evaluation tools" refer to devices or methods for evaluating an organization's performance based on analyzed indicators.

[0453] "Emotion recognition means" refers to devices or methods for acquiring consumer emotional data and recognizing those emotions.

[0454] A "feedback generation means" is a device or method that provides appropriate feedback to consumers based on the results of emotion recognition.

[0455] The embodiments for carrying out the invention will now be described. First, the system collects information related to the organization's environment, society, and governance using data collection means. Next, a server uses a cloud platform such as Google Cloud to perform data analysis means, analyze the collected information, and extract indicators as a result of the analysis. This provides basic data for evaluating the organization's performance.

[0456] Furthermore, the server uses emotion recognition to analyze emotion data acquired from smart glasses and in-store sensors. This analysis utilizes Google Cloud's emotion analysis API to recognize the emotions consumers are expressing towards products and services. This emotion data is then used as a means of generating feedback. The server generates information and advice based on the consumer's emotions and displays it on smart glasses and in-store displays.

[0457] As a concrete example, when a customer picks up a product and shows interest, smart glasses could analyze the consumer's facial expressions and gaze, displaying information about the product's environmental impact and advice to encourage purchase. An example of a prompt might be, "Provide ESG information for the product the customer is interested in. Also, based on the customer's emotional responses, highlight points that are likely to be of particular interest." This would allow organizations to provide consumers with a more personalized purchasing experience.

[0458] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0459] Step 1:

[0460] The server receives information from users related to the organization's environment, society, and governance using data collection means. This includes numerical and text data provided through input devices. The input data is stored in a database.

[0461] Step 2:

[0462] The server analyzes the received data using data analysis tools. At this stage, Google Cloud's data analysis tools are used to extract specific metrics from the input data. The output is a set of metrics that represent the organization's performance.

[0463] Step 3:

[0464] The server uses evaluation tools to assess the organization's financial and non-financial performance based on the metrics extracted in the previous step. The input is a set of metrics, and the output is the organization's evaluation result. This evaluation result is displayed on a dashboard in the cloud.

[0465] Step 4:

[0466] The user initiates their actions in a physical store through smart glasses. Here, an emotion recognition system collects the user's facial expression and gaze data. The input is raw data acquired from the camera, and the output is emotion data for analysis.

[0467] Step 5:

[0468] The server analyzes the acquired sentiment data using Google Cloud's Sentiment Analysis API to identify the user's emotional state. The input is sentiment data, and the output is the label of the recognized emotion. This is then passed on to the feedback generation system.

[0469] Step 6:

[0470] The server generates feedback to provide to the user based on evaluation results and emotional state. Using a generative AI model and prompts, it generates personalized information and advice. The output is a feedback message displayed on smart glasses or in-store displays.

[0471] Step 7:

[0472] The terminal displays the generated feedback on the user's device in real time. This allows the user to instantly receive personalized information about the product or service. The input is the feedback message, and the output is its visualization on the user interface.

[0473] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0474] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0475] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0476] [Third Embodiment]

[0477] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0478] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0479] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0480] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0481] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0482] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0483] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0484] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0485] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0486] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0487] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0488] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0489] The system of this invention collects ESG (Environmental, Social, and Governance) related information from companies, automatically evaluates their performance, and suggests improvement measures. First, a user, who is a company representative, uses a terminal to input various ESG-related data and uploads it to the system.

[0490] Data collection and management

[0491] The server automatically categorizes the received data and stores it in a database. The stored data includes, for example, CO2 emissions, employee diversity indicators, and information on governance structure.

[0492] The server organizes and cleanses the data to prepare it for analysis.

[0493] Data analysis and evaluation

[0494] The server analyzes the collected data using a Large-Scale Language Model (LLM). This model utilizes deep learning techniques to extract company ESG indicators based on the input data.

[0495] The server evaluates a company's ESG performance based on the extracted indicators and outputs it to the terminal as a visualized report.

[0496] Proposal for improvement measures

[0497] The server identifies a company's weaknesses based on the evaluation results and generates specific measures for improvement. For example, it can propose the introduction of energy-saving technologies to a manufacturing company with high energy consumption.

[0498] The terminal presents this proposal to the user in a dashboard format and provides the functionality to generate a detailed execution plan.

[0499] Question answering function

[0500] Users submit questions about the environment, society, and governance to the system via their devices.

[0501] The server responds to these questions with automatically generated answers based on historical data and industry information. This feature allows users to obtain information instantly.

[0502] Proposal for a sustainable business model

[0503] The server analyzes a company's existing business model and helps it switch to a model that considers future sustainability. For example, it supports companies in improving their sustainability by proposing solutions that include streamlining supply chains and promoting the use of renewable energy.

[0504] Thus, the system of the present invention aims to improve overall ESG performance and provides companies with efficient and strategic operational support.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] Users use their devices to input ESG-related company data and upload it to the system. This data includes environmental performance indicators, social contribution activities, and governance structures.

[0508] Step 2:

[0509] When the server stores received data in the database, it cleanses the data. It detects missing or abnormal values ​​and corrects or imputes them as needed.

[0510] Step 3:

[0511] The server sends the cleansed data to a Large-Scale Language Model (LLM) to begin analysis. The model analyzes the data and extracts indicators related to the environment, society, and governance.

[0512] Step 4:

[0513] The server performs scoring based on extracted ESG indicators to evaluate a company's performance. The evaluation is done by comparing it to industry standards and historical data.

[0514] Step 5:

[0515] Based on the evaluation results, the server develops necessary improvement measures for the company. For example, it may propose energy-saving measures or improvements to employee diversity.

[0516] Step 6:

[0517] The terminal provides the user with evaluation results and improvement suggestions obtained from the server, displaying them visually in a dashboard format. Based on this information, the user can develop a concrete improvement plan.

[0518] Step 7:

[0519] Users use a terminal to input specific ESG-related questions into the system. These questions include those about sustainability strategies and industry benchmarks.

[0520] Step 8:

[0521] The server analyzes the entered question and generates an answer using its internal database and external information. The generated response is automatically provided to the user.

[0522] Step 9:

[0523] The server analyzes a company's current business model and makes new suggestions to enhance sustainability. For example, it proposes the use of renewable energy and measures to improve supply chain efficiency.

[0524] Step 10:

[0525] The terminal will manage the progress of proposed sustainable business models and improvement measures, and will provide users with a means to generate and provide reports as needed.

[0526] (Example 1)

[0527] Next, we will describe Example 1. 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."

[0528] Rapid and accurate assessment of a company's ESG (Environmental, Social, and Governance) performance and provision of effective improvement measures are crucial for achieving sustainable management. However, traditional methods have been complex and time-consuming in terms of data collection and analysis, and the proposed improvement measures have often lacked sufficient specificity. Furthermore, the lack of visualized information to guide managers in quickly developing countermeasures has limited the effectiveness of efficient operational support.

[0529] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0530] In this invention, the server includes data management means for classifying and storing data, data cleansing means for preparing the stored data for analysis, and data analysis means for extracting corporate indicators using a generated AI model. This enables highly accurate data analysis and the proposal of concrete improvement measures that reflect the current state of the company. Furthermore, by providing visualized information, it is possible to build a foundation for corporate managers to make quick decisions.

[0531] "Data management means" refers to the function of classifying ESG-related data collected from companies and storing it in a database so that efficient analysis can be performed.

[0532] "Data cleansing means" refers to a function that processes collected data to correct any missing or abnormal data and prepare it for analysis.

[0533] A "generative AI model" refers to an algorithm that uses machine learning techniques to automatically extract company metrics from input data.

[0534] "Data analysis methods" refer to the function of extracting a company's ESG indicators using data that is ready for analysis, and using these as the basis for evaluation.

[0535] "Evaluation method" refers to a function that comprehensively evaluates a company's ESG performance based on extracted indicators, and calculates and visualizes the results.

[0536] The "method for proposing improvement measures" refers to the function of formulating and proposing specific improvement measures based on the evaluated performance results.

[0537] "Business structure proposal tools" refer to the function of analyzing a company's existing business model and proposing new structures and strategies to improve sustainability.

[0538] A "question answering tool" refers to a function that automatically generates and provides immediate responses to a company's ESG-related questions based on past data and industry knowledge.

[0539] "Visual display means" refers to a function that visually displays analyzed data and proposed improvement measures using diagrams, graphs, etc., so that users can easily understand them.

[0540] Embodiments of the present invention provide a system that efficiently evaluates a company's ESG (environmental, social, and governance) performance and proposes effective improvement measures. The system primarily operates by performing various data processing operations on a server based on data input by the user.

[0541] Data entry and management:

[0542] Users input ESG data about a company into a computer terminal. This data includes items such as CO2 emissions, employee diversity, and governance structure. The terminal verifies the data format and transmits the data to the server via a secure connection.

[0543] Data organization and storage:

[0544] The server analyzes the received data using a data classification algorithm and stores it appropriately in the database. It also improves data quality by performing data cleansing to correct missing or abnormal data.

[0545] Data analysis:

[0546] The server analyzes cleansed data using a Large-Scale Language Model (LLM) to extract company ESG indicators. Here, generative AI models are employed, along with advanced machine learning techniques to identify significant patterns and trends from the data.

[0547] Evaluation of results and proposal of improvement measures:

[0548] The server generates a report that visually presents the analysis results using evaluation tools, clearly identifying the company's strengths and weaknesses. This report presents specific improvement measures, such as the introduction of energy-saving technologies in energy-intensive industries and initiatives to enhance diversity.

[0549] Specific example:

[0550] For example, when a manufacturing company uses the system, it can input CO2 emission data, and the server can then suggest specific measures for energy efficiency. Based on these suggestions, the company can review its manufacturing processes.

[0551] Example of a prompt:

[0552] "Please provide specific suggestions for improving our company's ESG performance."

[0553] This system allows companies to obtain concrete action plans to enhance sustainability, enabling them to implement strategic improvements quickly and efficiently.

[0554] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0555] Step 1:

[0556] Users input company ESG data into a terminal. This data includes CO2 emissions and employee diversity indicators. The terminal verifies format consistency of the entered data and sends it to the server. This prepares the input data, allowing it to proceed to the next processing step.

[0557] Step 2:

[0558] The server automatically classifies and organizes the received data and stores it in a database. Specifically, it uses a data classification algorithm to distribute the data into categories related to environment, society, and governance. After the data classification is complete, it is stored in the database and ready for analysis.

[0559] Step 3:

[0560] The server performs data cleansing on the stored data. This cleansing process involves imputing missing values ​​and correcting outliers, creating a high-quality dataset suitable for analysis. This process improves the accuracy of the analysis and prepares input data that yields reliable results.

[0561] Step 4:

[0562] The server performs data analysis using a generative AI model. Specifically, it utilizes deep learning algorithms to extract ESG performance indicators for companies from data that is ready for analysis. This process generates indicator data that quantifies and visually evaluates a company's strengths and weaknesses.

[0563] Step 5:

[0564] The server evaluates the analysis results and generates a report using visualization tools. This report uses graphs and charts to show the current state of the company's ESG performance and areas for improvement. The generated report is output and displayed on the terminal.

[0565] Step 6:

[0566] The server develops improvement plans based on the visualized evaluation results. These improvement plans include specific measures for improving energy efficiency and diversity, for example. The proposed improvement plans are generated and sent to the terminal.

[0567] Step 7:

[0568] The terminal presents the user with reports and improvement suggestions received from the server. The user can then develop strategies to improve the company's ESG performance based on concrete action plans. This completes the entire system's processing.

[0569] (Application Example 1)

[0570] Next, we will explain Application Example 1. In the following explanation, 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."

[0571] In today's environment, there is a lack of effective ways for companies to collect and analyze environmental, social, and governance (ESG) information based on sustainability and to directly communicate it to consumers. This makes it difficult for consumers to utilize companies' ESG initiatives in their actual choices and purchasing decisions.

[0572] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0573] In this invention, the server includes a device for collecting data, a device for analyzing the data to extract indicators related to the environment, society, and governance, and a device for evaluating performance based on the indicators. This visually displays the environmental, social, and governance information of a company to entities, enabling consumers to make better choices based on this information.

[0574] A "data collection device" is a device for effectively acquiring and storing information related to a company's environmental, social, and governance aspects.

[0575] A "data analysis device" is a device that has the capability to organize collected data and extract necessary indicators.

[0576] A "performance evaluation device" is a device used to evaluate a company's environmental, social, and governance-related performance based on extracted indicators.

[0577] A "proposal-making device" is a device that generates and presents specific measures to recommend improvement strategies for companies based on evaluation results.

[0578] A "device for visually displaying store environmental, social, and governance information for a specific entity" is a device that visually shows and provides information to consumers and users about a company's or store's efforts to protect the environment and contribute to society.

[0579] This invention is a system that acquires, analyzes, and visually displays information related to a company's environmental, social, and governance aspects. The main components of the system are a server, terminals, and users.

[0580] The server is equipped with data collection devices that efficiently acquire ESG information provided by companies and automatically classify it. For example, it stores information on companies' CO2 emissions and governance structures in a database.

[0581] Next, the server processes the collected data using data analysis equipment and extracts indicators related to the environment, society, and governance. During this process, a generative AI model is used to analyze the data and quantify the company's ESG performance.

[0582] The terminal is equipped with a device for evaluating performance, assessing the company's performance based on metrics transmitted from the server. Based on the evaluation results, it generates a visual report to recommend improvement measures. This report is displayed on the dashboard in a way that is accessible to the user.

[0583] Furthermore, the terminal, through a suggestion-making device, presents users with specific measures for corporate improvement. Users operate the application via the terminal and understand the store's environmental, social, and governance information based on the visually presented information. This information is provided to consumers in specific entities and influences their purchasing behavior.

[0584] This system will allow, for example, customers to scan a QR code in a store using their smartphone to view details about the store's environmental protection activities and diversity promotion initiatives. In this case, an example of a prompt used for the generating AI model would be the question, "Please tell me about this store's ESG initiatives."

[0585] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0586] Step 1:

[0587] The server receives and classifies ESG information provided by companies using a data collection device. It takes information on companies' CO2 emissions and governance structures as input and stores this information in a database in an organized data format as output.

[0588] Step 2:

[0589] The server analyzes collected data using a generative AI model and extracts environmental, social, and governance indicators. It uses classified data from a database as input and calculates a company's ESG indicators as output. Deep learning technology is used for data calculation to determine these indicators.

[0590] Step 3:

[0591] The terminal receives ESG indicators sent from the server and evaluates the company's performance based on them. It takes ESG indicators as input and generates a report visualizing the evaluation results as output. Infographics technology is used for visualization.

[0592] Step 4:

[0593] The device generates and presents a dashboard to the user that suggests improvement measures based on the evaluation results. It uses the evaluated data as input and displays improvement measures in a dashboard format that is easy for the user to understand as output.

[0594] Step 5:

[0595] Users utilize their devices to refer to visualized evaluation results and suggestions, and to understand environmental, social, and governance information about specific entities. Specifically, they obtain and display necessary information by scanning a QR code with their smartphone.

[0596] Step 6:

[0597] The server uses a generative AI model to automatically generate and respond to user prompts, such as "Please tell me about this store's ESG initiatives." It receives user questions as input and provides answers based on historical data and industry information as output.

[0598] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0599] This invention combines a system that evaluates a company's ESG (Environmental, Social, and Governance) performance and proposes improvement measures with an emotion engine that recognizes user emotions. By providing feedback that takes the user's emotional state into account, this system achieves more effective and user-friendly interaction.

[0600] Data collection and analysis

[0601] Users operate a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes indicators of environmental impact, diversity of talent, and governance frameworks.

[0602] The server receives the data, performs a cleansing process, and then analyzes it using data analysis tools. Large-scale language models (LLMs) are used to extract ESG indicators for companies.

[0603] Emotion recognition and feedback

[0604] The server uses an emotion engine to recognize emotions based on user behavior and input data in the user interface. This engine determines in real time whether the user is feeling stressed or experiencing positive emotions.

[0605] The device adjusts the feedback provided to the user based on the emotions it recognizes. For example, if the user is feeling stressed, it displays supplementary information and makes suggestions simpler.

[0606] Performance evaluation and improvement suggestions

[0607] The server evaluates a company's ESG performance based on analyzed metrics and reports this to the user. The evaluation is compared to industry standards and historical data to enhance its reliability.

[0608] The server considers the data obtained from the emotion engine and suggests improvements based on the user's emotional state. For example, it might adjust the difficulty level of the suggestions or change the way choices are presented.

[0609] Enhanced user interaction

[0610] Users experience a more positive interaction with the system by receiving emotion-based suggestions. The system facilitates the implementation of improvement measures by enabling flexible responses tailored to the user's situation.

[0611] Thus, the present invention provides a system that not only supports the overall improvement of ESG performance but also understands user emotions and provides flexible feedback accordingly, thereby enabling the effective promotion of ESG activities.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] Users use a terminal to input and upload company ESG data. This data includes specific CO2 emissions, details of social contribution activities, and information about the company's governance structure.

[0615] Step 2:

[0616] Before storing received data in the database, the server performs data cleansing. This includes handling missing data and standardization work to maintain consistency.

[0617] Step 3:

[0618] The server sends the cleansed data to a Large-Scale Language Model (LLM) to extract ESG-related metrics. Here, it analyzes how each metric compares to industry averages and historical benchmarks.

[0619] Step 4:

[0620] The server scores a company's ESG performance based on the extracted metrics and generates an evaluation result. This information is then compiled into a report format using visualization tools.

[0621] Step 5:

[0622] The server generates improvement suggestions based on the evaluation results. This includes a process of adjusting the suggestions using user emotion recognition data. For example, if the user is experiencing stress, the suggestions are simplified and broken down into more manageable steps.

[0623] Step 6:

[0624] The device presents the evaluation results and improvement suggestions to the user. This information is presented in a user-friendly format, including feedback based on emotional data collected by the emotion engine.

[0625] Step 7:

[0626] Users review improvement suggestions and provide feedback on them. The system records data so that their feelings and opinions are reflected in future suggestions.

[0627] Step 8:

[0628] The server collects user feedback and stores it in a database. This feedback will be used to refine future suggestions and improve the system.

[0629] Through this series of processes, the system can support the promotion of ESG activities and make flexible proposals that take user sentiment into consideration.

[0630] (Example 2)

[0631] Next, we will describe Example 2. 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."

[0632] In evaluating a company's environmental, social, and governance (ESG) performance and proposing improvement measures, there is a growing need to provide user-friendly interactions and more effectively solve problems by offering feedback that takes user emotions into consideration. Traditional systems often provide one-sided feedback that does not consider user emotions, which can cause stress for users, and this needs to be improved.

[0633] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0634] In this invention, the server includes data analysis means, emotion recognition means, and feedback generation means. This enables more effective interaction while reducing the user's burden by providing appropriate feedback according to the user's emotional state and through evaluation of ESG performance and suggestion of improvement measures.

[0635] "Data collection methods" refer to means of collecting information related to a company's environmental, social, and governance aspects.

[0636] "Data analysis means" refers to methods for analyzing collected information and extracting ESG indicators based on that analysis.

[0637] "Evaluation methods" refer to the means used to assess a company's performance based on extracted indicators.

[0638] "Improvement suggestion methods" are means of recommending improvement measures based on the evaluated results and the user's emotional state.

[0639] "Emotion recognition means" refers to a means of recognizing a user's emotional state.

[0640] A "feedback generation method" is a means for generating feedback that corresponds to the recognized emotions of the user.

[0641] This invention incorporates a function that provides user-centric feedback while evaluating a company's ESG (environmental, social, and governance) performance and proposing improvement measures. This system is realized by using data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means.

[0642] Data collection

[0643] Users use a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes, for example, CO2 emissions, employee diversity scores, and governance policies.

[0644] Data Analysis

[0645] The server receives data sent from users and performs a cleansing process. Then, it analyzes the data using a Large-Scale Language Model (LLM) and extracts ESG indicators. The LLM uses natural language processing techniques to identify patterns in the data and gain deep insights.

[0646] emotion recognition

[0647] The server uses an emotion engine to recognize the user's emotional state in real time. This engine determines stress levels and positive emotions based on the user's terminal operations and input.

[0648] Provide feedback

[0649] The device adjusts its feedback based on the emotion recognition results. For example, if the user is feeling stressed, the device provides a specific and concise explanation and displays support information as needed.

[0650] As a concrete example, when a company conducts a sustainability assessment, users input their company's environmental data, which is then analyzed by a server. Along with the analysis results, the user's emotional state is taken into consideration, and more actionable improvement measures are proposed to the user.

[0651] Examples of prompt statements are as follows:

[0652] "Please enter your company's environmental impact data. What improvements do you feel are needed? If you are experiencing stress, what kind of support would be helpful?"

[0653] This system configuration allows for more effective support of ESG activities.

[0654] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0655] Step 1:

[0656] Data entry

[0657] Users input company ESG data using a terminal. This data specifically includes CO2 emissions, employee diversity scores, and governance policies. User input is received via a dedicated form and sent to the server. The entered information serves as foundational data for system analysis.

[0658] Step 2:

[0659] Data cleansing

[0660] The server verifies the received data and performs a cleansing process. This process detects and corrects or supplements any inappropriate or missing data. For example, it may include detecting and removing outliers and converting to a standard format. The output is clean, reliable data.

[0661] Step 3:

[0662] Data Analysis

[0663] The server analyzes the cleansed data. During this process, a Large-Scale Language Model (LLM) is used to extract data patterns. Specifically, it analyzes trends in CO2 emission reduction and the progress of diversity improvement. The model uses natural language processing techniques to automatically extract relationships and key indicators, providing them as analysis results. This forms the basis for the next evaluation step.

[0664] Step 4:

[0665] emotion recognition

[0666] The server uses an emotion engine to recognize the user's emotional state. This recognition is based on the user's terminal operations (mouse movements, click speed) and input content. The server attempts to understand the user's psychological state by identifying signs of stress, positive attitudes, etc. As output, the user's emotional profile is generated.

[0667] Step 5:

[0668] Feedback generation

[0669] The device generates feedback based on analysis results and emotional profiles. In doing so, it provides information in a format appropriate to the user's emotional state. For example, if the user is feeling anxious, it will present concise action points. The generated feedback is designed to make it easy for the user to implement the suggested improvements.

[0670] Step 6:

[0671] Improvement suggestions

[0672] Based on the evaluated results and the user's sentiment, the server presents specific suggestions for improving the company's ESG performance. These suggestions are presented in an easy-to-understand format, taking the user's emotional state into consideration. This allows users to naturally accept the suggestions and utilize them to contribute to the company's sustainable growth.

[0673] (Application Example 2)

[0674] Next, we will explain application example 2. In the following explanation, 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."

[0675] Many organizations evaluate and improve metrics related to the environment, society, and governance, but a challenge remains in providing feedback that fully considers consumer sentiment and thus failing to optimize the customer experience.

[0676] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0677] In this invention, the server includes data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means. This enables the provision of flexible and effective feedback based on consumer emotions while evaluating the organization's performance.

[0678] "Data collection means" refers to devices or methods for collecting information related to an organization's environment, society, and governance.

[0679] "Data analysis means" refers to devices and methods for analyzing collected information and extracting necessary indicators.

[0680] "Evaluation tools" refer to devices or methods for evaluating an organization's performance based on analyzed indicators.

[0681] "Emotion recognition means" refers to devices or methods for acquiring consumer emotional data and recognizing those emotions.

[0682] A "feedback generation means" is a device or method that provides appropriate feedback to consumers based on the results of emotion recognition.

[0683] The embodiments for carrying out the invention will now be described. First, the system collects information related to the organization's environment, society, and governance using data collection means. Next, a server uses a cloud platform such as Google Cloud to perform data analysis means, analyze the collected information, and extract indicators as a result of the analysis. This provides basic data for evaluating the organization's performance.

[0684] Furthermore, the server uses emotion recognition to analyze emotion data acquired from smart glasses and in-store sensors. This analysis utilizes Google Cloud's emotion analysis API to recognize the emotions consumers are expressing towards products and services. This emotion data is then used as a means of generating feedback. The server generates information and advice based on the consumer's emotions and displays it on smart glasses and in-store displays.

[0685] As a concrete example, when a customer picks up a product and shows interest, smart glasses could analyze the consumer's facial expressions and gaze, displaying information about the product's environmental impact and advice to encourage purchase. An example of a prompt might be, "Provide ESG information for the product the customer is interested in. Also, based on the customer's emotional responses, highlight points that are likely to be of particular interest." This would allow organizations to provide consumers with a more personalized purchasing experience.

[0686] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0687] Step 1:

[0688] The server receives information from users related to the organization's environment, society, and governance using data collection means. This includes numerical and text data provided through input devices. The input data is stored in a database.

[0689] Step 2:

[0690] The server analyzes the received data using data analysis tools. At this stage, Google Cloud's data analysis tools are used to extract specific metrics from the input data. The output is a set of metrics that represent the organization's performance.

[0691] Step 3:

[0692] The server uses evaluation tools to assess the organization's financial and non-financial performance based on the metrics extracted in the previous step. The input is a set of metrics, and the output is the organization's evaluation result. This evaluation result is displayed on a dashboard in the cloud.

[0693] Step 4:

[0694] The user initiates their actions in a physical store through smart glasses. Here, an emotion recognition system collects the user's facial expression and gaze data. The input is raw data acquired from the camera, and the output is emotion data for analysis.

[0695] Step 5:

[0696] The server analyzes the acquired sentiment data using Google Cloud's Sentiment Analysis API to identify the user's emotional state. The input is sentiment data, and the output is the label of the recognized emotion. This is then passed on to the feedback generation system.

[0697] Step 6:

[0698] The server generates feedback to provide to the user based on evaluation results and emotional state. Using a generative AI model and prompts, it generates personalized information and advice. The output is a feedback message displayed on smart glasses or in-store displays.

[0699] Step 7:

[0700] The terminal displays the generated feedback on the user's device in real time. This allows the user to instantly receive personalized information about the product or service. The input is the feedback message, and the output is its visualization on the user interface.

[0701] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0702] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0703] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0704] [Fourth Embodiment]

[0705] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0706] As shown in Figure 7, the 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.

[0707] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0708] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0709] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0710] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0711] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0712] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0713] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0714] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0715] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0716] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0717] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0718] The system of this invention collects ESG (Environmental, Social, and Governance) related information from companies, automatically evaluates their performance, and suggests improvement measures. First, a user, who is a company representative, uses a terminal to input various ESG-related data and uploads it to the system.

[0719] Data collection and management

[0720] The server automatically categorizes the received data and stores it in a database. The stored data includes, for example, CO2 emissions, employee diversity indicators, and information on governance structure.

[0721] The server organizes and cleanses the data to prepare it for analysis.

[0722] Data analysis and evaluation

[0723] The server analyzes the collected data using a Large-Scale Language Model (LLM). This model utilizes deep learning techniques to extract company ESG indicators based on the input data.

[0724] The server evaluates a company's ESG performance based on the extracted indicators and outputs it to the terminal as a visualized report.

[0725] Proposal for improvement measures

[0726] The server identifies a company's weaknesses based on the evaluation results and generates specific measures for improvement. For example, it can propose the introduction of energy-saving technologies to a manufacturing company with high energy consumption.

[0727] The terminal presents this proposal to the user in a dashboard format and provides the functionality to generate a detailed execution plan.

[0728] Question answering function

[0729] Users submit questions about the environment, society, and governance to the system via their devices.

[0730] The server responds to these questions with automatically generated answers based on historical data and industry information. This feature allows users to obtain information instantly.

[0731] Proposal for a sustainable business model

[0732] The server analyzes a company's existing business model and helps it switch to a model that considers future sustainability. For example, it supports companies in improving their sustainability by proposing solutions that include streamlining supply chains and promoting the use of renewable energy.

[0733] Thus, the system of the present invention aims to improve overall ESG performance and provides companies with efficient and strategic operational support.

[0734] The following describes the processing flow.

[0735] Step 1:

[0736] Users use their devices to input ESG-related company data and upload it to the system. This data includes environmental performance indicators, social contribution activities, and governance structures.

[0737] Step 2:

[0738] When the server stores received data in the database, it cleanses the data. It detects missing or abnormal values ​​and corrects or imputes them as needed.

[0739] Step 3:

[0740] The server sends the cleansed data to a Large-Scale Language Model (LLM) to begin analysis. The model analyzes the data and extracts indicators related to the environment, society, and governance.

[0741] Step 4:

[0742] The server performs scoring based on extracted ESG indicators to evaluate a company's performance. The evaluation is done by comparing it to industry standards and historical data.

[0743] Step 5:

[0744] Based on the evaluation results, the server develops necessary improvement measures for the company. For example, it may propose energy-saving measures or improvements to employee diversity.

[0745] Step 6:

[0746] The terminal provides the user with evaluation results and improvement suggestions obtained from the server, displaying them visually in a dashboard format. Based on this information, the user can develop a concrete improvement plan.

[0747] Step 7:

[0748] Users use a terminal to input specific ESG-related questions into the system. These questions include those about sustainability strategies and industry benchmarks.

[0749] Step 8:

[0750] The server analyzes the entered question and generates an answer using its internal database and external information. The generated response is automatically provided to the user.

[0751] Step 9:

[0752] The server analyzes a company's current business model and makes new suggestions to enhance sustainability. For example, it proposes the use of renewable energy and measures to improve supply chain efficiency.

[0753] Step 10:

[0754] The terminal will manage the progress of proposed sustainable business models and improvement measures, and will provide users with a means to generate and provide reports as needed.

[0755] (Example 1)

[0756] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0757] Rapid and accurate assessment of a company's ESG (Environmental, Social, and Governance) performance and provision of effective improvement measures are crucial for achieving sustainable management. However, traditional methods have been complex and time-consuming in terms of data collection and analysis, and the proposed improvement measures have often lacked sufficient specificity. Furthermore, the lack of visualized information to guide managers in quickly developing countermeasures has limited the effectiveness of efficient operational support.

[0758] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0759] In this invention, the server includes data management means for classifying and storing data, data cleansing means for preparing the stored data for analysis, and data analysis means for extracting corporate indicators using a generated AI model. This enables highly accurate data analysis and the proposal of concrete improvement measures that reflect the current state of the company. Furthermore, by providing visualized information, it is possible to build a foundation for corporate managers to make quick decisions.

[0760] "Data management means" refers to the function of classifying ESG-related data collected from companies and storing it in a database so that efficient analysis can be performed.

[0761] "Data cleansing means" refers to a function that processes collected data to correct any missing or abnormal data and prepare it for analysis.

[0762] A "generative AI model" refers to an algorithm that uses machine learning techniques to automatically extract company metrics from input data.

[0763] "Data analysis methods" refer to the function of extracting a company's ESG indicators using data that is ready for analysis, and using these as the basis for evaluation.

[0764] "Evaluation method" refers to a function that comprehensively evaluates a company's ESG performance based on extracted indicators, and calculates and visualizes the results.

[0765] The "method for proposing improvement measures" refers to the function of formulating and proposing specific improvement measures based on the evaluated performance results.

[0766] "Business structure proposal tools" refer to the function of analyzing a company's existing business model and proposing new structures and strategies to improve sustainability.

[0767] A "question answering tool" refers to a function that automatically generates and provides immediate responses to a company's ESG-related questions based on past data and industry knowledge.

[0768] "Visual display means" refers to a function that visually displays analyzed data and proposed improvement measures using diagrams, graphs, etc., so that users can easily understand them.

[0769] Embodiments of the present invention provide a system that efficiently evaluates a company's ESG (environmental, social, and governance) performance and proposes effective improvement measures. The system primarily operates by performing various data processing operations on a server based on data input by the user.

[0770] Data entry and management:

[0771] Users input ESG data about a company into a computer terminal. This data includes items such as CO2 emissions, employee diversity, and governance structure. The terminal verifies the data format and transmits the data to the server via a secure connection.

[0772] Data organization and storage:

[0773] The server analyzes the received data using a data classification algorithm and stores it appropriately in the database. It also improves data quality by performing data cleansing to correct missing or abnormal data.

[0774] Data analysis:

[0775] The server analyzes cleansed data using a Large-Scale Language Model (LLM) to extract company ESG indicators. Here, generative AI models are employed, along with advanced machine learning techniques to identify significant patterns and trends from the data.

[0776] Evaluation of results and proposal of improvement measures:

[0777] The server generates a report that visually presents the analysis results using evaluation tools, clearly identifying the company's strengths and weaknesses. This report presents specific improvement measures, such as the introduction of energy-saving technologies in energy-intensive industries and initiatives to enhance diversity.

[0778] Specific example:

[0779] For example, when a manufacturing company uses the system, it can input CO2 emission data, and the server can then suggest specific measures for energy efficiency. Based on these suggestions, the company can review its manufacturing processes.

[0780] Example of a prompt:

[0781] "Please provide specific suggestions for improving our company's ESG performance."

[0782] This system allows companies to obtain concrete action plans to enhance sustainability, enabling them to implement strategic improvements quickly and efficiently.

[0783] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0784] Step 1:

[0785] Users input company ESG data into a terminal. This data includes CO2 emissions and employee diversity indicators. The terminal verifies format consistency of the entered data and sends it to the server. This prepares the input data, allowing it to proceed to the next processing step.

[0786] Step 2:

[0787] The server automatically classifies and organizes the received data and stores it in a database. Specifically, it uses a data classification algorithm to distribute the data into categories related to environment, society, and governance. After the data classification is complete, it is stored in the database and ready for analysis.

[0788] Step 3:

[0789] The server performs data cleansing on the stored data. This cleansing process involves imputing missing values ​​and correcting outliers, creating a high-quality dataset suitable for analysis. This process improves the accuracy of the analysis and prepares input data that yields reliable results.

[0790] Step 4:

[0791] The server performs data analysis using a generative AI model. Specifically, it utilizes deep learning algorithms to extract ESG performance indicators for companies from data that is ready for analysis. This process generates indicator data that quantifies and visually evaluates a company's strengths and weaknesses.

[0792] Step 5:

[0793] The server evaluates the analysis results and generates a report using visualization tools. This report uses graphs and charts to show the current state of the company's ESG performance and areas for improvement. The generated report is output and displayed on the terminal.

[0794] Step 6:

[0795] The server develops improvement plans based on the visualized evaluation results. These improvement plans include specific measures for improving energy efficiency and diversity, for example. The proposed improvement plans are generated and sent to the terminal.

[0796] Step 7:

[0797] The terminal presents the user with reports and improvement suggestions received from the server. The user can then develop strategies to improve the company's ESG performance based on concrete action plans. This completes the entire system's processing.

[0798] (Application Example 1)

[0799] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0800] In today's environment, there is a lack of effective ways for companies to collect and analyze environmental, social, and governance (ESG) information based on sustainability and to directly communicate it to consumers. This makes it difficult for consumers to utilize companies' ESG initiatives in their actual choices and purchasing decisions.

[0801] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0802] In this invention, the server includes a device for collecting data, a device for analyzing the data to extract indicators related to the environment, society, and governance, and a device for evaluating performance based on the indicators. This visually displays the environmental, social, and governance information of a company to entities, enabling consumers to make better choices based on this information.

[0803] A "data collection device" is a device for effectively acquiring and storing information related to a company's environmental, social, and governance aspects.

[0804] A "data analysis device" is a device that has the capability to organize collected data and extract necessary indicators.

[0805] A "performance evaluation device" is a device used to evaluate a company's environmental, social, and governance-related performance based on extracted indicators.

[0806] A "proposal-making device" is a device that generates and presents specific measures to recommend improvement strategies for companies based on evaluation results.

[0807] A "device for visually displaying store environmental, social, and governance information for a specific entity" is a device that visually shows and provides information to consumers and users about a company's or store's efforts to protect the environment and contribute to society.

[0808] This invention is a system that acquires, analyzes, and visually displays information related to a company's environmental, social, and governance aspects. The main components of the system are a server, terminals, and users.

[0809] The server is equipped with data collection devices that efficiently acquire ESG information provided by companies and automatically classify it. For example, it stores information on companies' CO2 emissions and governance structures in a database.

[0810] Next, the server processes the collected data using data analysis equipment and extracts indicators related to the environment, society, and governance. During this process, a generative AI model is used to analyze the data and quantify the company's ESG performance.

[0811] The terminal is equipped with a device for evaluating performance, assessing the company's performance based on metrics transmitted from the server. Based on the evaluation results, it generates a visual report to recommend improvement measures. This report is displayed on the dashboard in a way that is accessible to the user.

[0812] Furthermore, the terminal, through a suggestion-making device, presents users with specific measures for corporate improvement. Users operate the application via the terminal and understand the store's environmental, social, and governance information based on the visually presented information. This information is provided to consumers in specific entities and influences their purchasing behavior.

[0813] This system will allow, for example, customers to scan a QR code in a store using their smartphone to view details about the store's environmental protection activities and diversity promotion initiatives. In this case, an example of a prompt used for the generating AI model would be the question, "Please tell me about this store's ESG initiatives."

[0814] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0815] Step 1:

[0816] The server receives and classifies ESG information provided by companies using a data collection device. It takes information on companies' CO2 emissions and governance structures as input and stores this information in a database in an organized data format as output.

[0817] Step 2:

[0818] The server analyzes collected data using a generative AI model and extracts environmental, social, and governance indicators. It uses classified data from a database as input and calculates a company's ESG indicators as output. Deep learning technology is used for data calculation to determine these indicators.

[0819] Step 3:

[0820] The terminal receives ESG indicators sent from the server and evaluates the company's performance based on them. It takes ESG indicators as input and generates a report visualizing the evaluation results as output. Infographics technology is used for visualization.

[0821] Step 4:

[0822] The device generates and presents a dashboard to the user that suggests improvement measures based on the evaluation results. It uses the evaluated data as input and displays improvement measures in a dashboard format that is easy for the user to understand as output.

[0823] Step 5:

[0824] Users utilize their devices to refer to visualized evaluation results and suggestions, and to understand environmental, social, and governance information about specific entities. Specifically, they obtain and display necessary information by scanning a QR code with their smartphone.

[0825] Step 6:

[0826] The server uses a generative AI model to automatically generate and respond to user prompts, such as "Please tell me about this store's ESG initiatives." It receives user questions as input and provides answers based on historical data and industry information as output.

[0827] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0828] This invention combines a system that evaluates a company's ESG (Environmental, Social, and Governance) performance and proposes improvement measures with an emotion engine that recognizes user emotions. By providing feedback that takes the user's emotional state into account, this system achieves more effective and user-friendly interaction.

[0829] Data collection and analysis

[0830] Users operate a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes indicators of environmental impact, diversity of talent, and governance frameworks.

[0831] The server receives the data, performs a cleansing process, and then analyzes it using data analysis tools. Large-scale language models (LLMs) are used to extract ESG indicators for companies.

[0832] Emotion recognition and feedback

[0833] The server uses an emotion engine to recognize emotions based on user behavior and input data in the user interface. This engine determines in real time whether the user is feeling stressed or experiencing positive emotions.

[0834] The device adjusts the feedback provided to the user based on the emotions it recognizes. For example, if the user is feeling stressed, it displays supplementary information and makes suggestions simpler.

[0835] Performance evaluation and improvement suggestions

[0836] The server evaluates a company's ESG performance based on analyzed metrics and reports this to the user. The evaluation is compared to industry standards and historical data to enhance its reliability.

[0837] The server considers the data obtained from the emotion engine and suggests improvements based on the user's emotional state. For example, it might adjust the difficulty level of the suggestions or change the way choices are presented.

[0838] Enhanced user interaction

[0839] Users experience a more positive interaction with the system by receiving emotion-based suggestions. The system facilitates the implementation of improvement measures by enabling flexible responses tailored to the user's situation.

[0840] Thus, the present invention provides a system that not only supports the overall improvement of ESG performance but also understands user emotions and provides flexible feedback accordingly, thereby enabling the effective promotion of ESG activities.

[0841] The following describes the processing flow.

[0842] Step 1:

[0843] Users use a terminal to input and upload company ESG data. This data includes specific CO2 emissions, details of social contribution activities, and information about the company's governance structure.

[0844] Step 2:

[0845] Before storing received data in the database, the server performs data cleansing. This includes handling missing data and standardization work to maintain consistency.

[0846] Step 3:

[0847] The server sends the cleansed data to a Large-Scale Language Model (LLM) to extract ESG-related metrics. Here, it analyzes how each metric compares to industry averages and historical benchmarks.

[0848] Step 4:

[0849] The server scores a company's ESG performance based on the extracted metrics and generates an evaluation result. This information is then compiled into a report format using visualization tools.

[0850] Step 5:

[0851] The server generates improvement suggestions based on the evaluation results. This includes a process of adjusting the suggestions using user emotion recognition data. For example, if the user is experiencing stress, the suggestions are simplified and broken down into more manageable steps.

[0852] Step 6:

[0853] The device presents the evaluation results and improvement suggestions to the user. This information is presented in a user-friendly format, including feedback based on emotional data collected by the emotion engine.

[0854] Step 7:

[0855] Users review improvement suggestions and provide feedback on them. The system records data so that their feelings and opinions are reflected in future suggestions.

[0856] Step 8:

[0857] The server collects user feedback and stores it in a database. This feedback will be used to refine future suggestions and improve the system.

[0858] Through this series of processes, the system can support the promotion of ESG activities and make flexible proposals that take user sentiment into consideration.

[0859] (Example 2)

[0860] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0861] In evaluating a company's environmental, social, and governance (ESG) performance and proposing improvement measures, there is a growing need to provide user-friendly interactions and more effectively solve problems by offering feedback that takes user emotions into consideration. Traditional systems often provide one-sided feedback that does not consider user emotions, which can cause stress for users, and this needs to be improved.

[0862] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0863] In this invention, the server includes data analysis means, emotion recognition means, and feedback generation means. This enables more effective interaction while reducing the user's burden by providing appropriate feedback according to the user's emotional state and through evaluation of ESG performance and suggestion of improvement measures.

[0864] "Data collection methods" refer to means of collecting information related to a company's environmental, social, and governance aspects.

[0865] "Data analysis means" refers to methods for analyzing collected information and extracting ESG indicators based on that analysis.

[0866] "Evaluation methods" refer to the means used to assess a company's performance based on extracted indicators.

[0867] "Improvement suggestion methods" are means of recommending improvement measures based on the evaluated results and the user's emotional state.

[0868] "Emotion recognition means" refers to a means of recognizing a user's emotional state.

[0869] A "feedback generation method" is a means for generating feedback that corresponds to the recognized emotions of the user.

[0870] This invention incorporates a function that provides user-centric feedback while evaluating a company's ESG (environmental, social, and governance) performance and proposing improvement measures. This system is realized by using data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means.

[0871] Data collection

[0872] Users use a terminal to input data related to a company's ESG (Environmental, Social, and Governance) aspects. This data includes, for example, CO2 emissions, employee diversity scores, and governance policies.

[0873] Data Analysis

[0874] The server receives data sent from users and performs a cleansing process. Then, it analyzes the data using a Large-Scale Language Model (LLM) and extracts ESG indicators. The LLM uses natural language processing techniques to identify patterns in the data and gain deep insights.

[0875] emotion recognition

[0876] The server uses an emotion engine to recognize the user's emotional state in real time. This engine determines stress levels and positive emotions based on the user's terminal operations and input.

[0877] Provide feedback

[0878] The device adjusts its feedback based on the emotion recognition results. For example, if the user is feeling stressed, the device provides a specific and concise explanation and displays support information as needed.

[0879] As a concrete example, when a company conducts a sustainability assessment, users input their company's environmental data, which is then analyzed by a server. Along with the analysis results, the user's emotional state is taken into consideration, and more actionable improvement measures are proposed to the user.

[0880] Examples of prompt statements are as follows:

[0881] "Please enter your company's environmental impact data. What improvements do you feel are needed? If you are experiencing stress, what kind of support would be helpful?"

[0882] This system configuration allows for more effective support of ESG activities.

[0883] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0884] Step 1:

[0885] Data entry

[0886] Users input company ESG data using a terminal. This data specifically includes CO2 emissions, employee diversity scores, and governance policies. User input is received via a dedicated form and sent to the server. The entered information serves as foundational data for system analysis.

[0887] Step 2:

[0888] Data cleansing

[0889] The server verifies the received data and performs a cleansing process. This process detects and corrects or supplements any inappropriate or missing data. For example, it may include detecting and removing outliers and converting to a standard format. The output is clean, reliable data.

[0890] Step 3:

[0891] Data Analysis

[0892] The server analyzes the cleansed data. During this process, a Large-Scale Language Model (LLM) is used to extract data patterns. Specifically, it analyzes trends in CO2 emission reduction and the progress of diversity improvement. The model uses natural language processing techniques to automatically extract relationships and key indicators, providing them as analysis results. This forms the basis for the next evaluation step.

[0893] Step 4:

[0894] emotion recognition

[0895] The server uses an emotion engine to recognize the user's emotional state. This recognition is based on the user's terminal operations (mouse movements, click speed) and input content. The server attempts to understand the user's psychological state by identifying signs of stress, positive attitudes, etc. As output, the user's emotional profile is generated.

[0896] Step 5:

[0897] Feedback generation

[0898] The device generates feedback based on analysis results and emotional profiles. In doing so, it provides information in a format appropriate to the user's emotional state. For example, if the user is feeling anxious, it will present concise action points. The generated feedback is designed to make it easy for the user to implement the suggested improvements.

[0899] Step 6:

[0900] Improvement suggestions

[0901] Based on the evaluated results and the user's sentiment, the server presents specific suggestions for improving the company's ESG performance. These suggestions are presented in an easy-to-understand format, taking the user's emotional state into consideration. This allows users to naturally accept the suggestions and utilize them to contribute to the company's sustainable growth.

[0902] (Application Example 2)

[0903] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0904] Many organizations evaluate and improve metrics related to the environment, society, and governance, but a challenge remains in providing feedback that fully considers consumer sentiment and thus failing to optimize the customer experience.

[0905] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0906] In this invention, the server includes data collection means, data analysis means, evaluation means, emotion recognition means, and feedback generation means. This enables the provision of flexible and effective feedback based on consumer emotions while evaluating the organization's performance.

[0907] "Data collection means" refers to devices or methods for collecting information related to an organization's environment, society, and governance.

[0908] "Data analysis means" refers to devices and methods for analyzing collected information and extracting necessary indicators.

[0909] "Evaluation tools" refer to devices or methods for evaluating an organization's performance based on analyzed indicators.

[0910] "Emotion recognition means" refers to devices or methods for acquiring consumer emotional data and recognizing those emotions.

[0911] A "feedback generation means" is a device or method that provides appropriate feedback to consumers based on the results of emotion recognition.

[0912] The embodiments for carrying out the invention will now be described. First, the system collects information related to the organization's environment, society, and governance using data collection means. Next, a server uses a cloud platform such as Google Cloud to perform data analysis means, analyze the collected information, and extract indicators as a result of the analysis. This provides basic data for evaluating the organization's performance.

[0913] Furthermore, the server uses emotion recognition to analyze emotion data acquired from smart glasses and in-store sensors. This analysis utilizes Google Cloud's emotion analysis API to recognize the emotions consumers are expressing towards products and services. This emotion data is then used as a means of generating feedback. The server generates information and advice based on the consumer's emotions and displays it on smart glasses and in-store displays.

[0914] As a concrete example, when a customer picks up a product and shows interest, smart glasses could analyze the consumer's facial expressions and gaze, displaying information about the product's environmental impact and advice to encourage purchase. An example of a prompt might be, "Provide ESG information for the product the customer is interested in. Also, based on the customer's emotional responses, highlight points that are likely to be of particular interest." This would allow organizations to provide consumers with a more personalized purchasing experience.

[0915] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0916] Step 1:

[0917] The server receives information from users related to the organization's environment, society, and governance using data collection means. This includes numerical and text data provided through input devices. The input data is stored in a database.

[0918] Step 2:

[0919] The server analyzes the received data using data analysis tools. At this stage, Google Cloud's data analysis tools are used to extract specific metrics from the input data. The output is a set of metrics that represent the organization's performance.

[0920] Step 3:

[0921] The server uses evaluation tools to assess the organization's financial and non-financial performance based on the metrics extracted in the previous step. The input is a set of metrics, and the output is the organization's evaluation result. This evaluation result is displayed on a dashboard in the cloud.

[0922] Step 4:

[0923] The user initiates their actions in a physical store through smart glasses. Here, an emotion recognition system collects the user's facial expression and gaze data. The input is raw data acquired from the camera, and the output is emotion data for analysis.

[0924] Step 5:

[0925] The server analyzes the acquired sentiment data using Google Cloud's Sentiment Analysis API to identify the user's emotional state. The input is sentiment data, and the output is the label of the recognized emotion. This is then passed on to the feedback generation system.

[0926] Step 6:

[0927] The server generates feedback to provide to the user based on evaluation results and emotional state. Using a generative AI model and prompts, it generates personalized information and advice. The output is a feedback message displayed on smart glasses or in-store displays.

[0928] Step 7:

[0929] The terminal displays the generated feedback on the user's device in real time. This allows the user to instantly receive personalized information about the product or service. The input is the feedback message, and the output is its visualization on the user interface.

[0930] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0931] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0932] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0933] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0934] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0935] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0936] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0937] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0938] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0939] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0940] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0941] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0942] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0943] 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.

[0944] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0945] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0946] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0947] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0948] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0949] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0950] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0951] The following is further disclosed regarding the embodiments described above.

[0952] (Claim 1)

[0953] Data collection means,

[0954] A data analysis means for analyzing information related to the environmental, social, and governance aspects of a company collected by the aforementioned data collection means, and for extracting indicators based on that analysis.

[0955] An evaluation means for evaluating a company's performance based on indicators extracted by the aforementioned data analysis means,

[0956] An improvement suggestion means that recommends improvement measures based on the results evaluated by the evaluation means,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, further comprising a question answering means for automatically responding to questions based on information collected from companies.

[0960] (Claim 3)

[0961] The system according to claim 1, further comprising a means for analyzing a company's business model and making suggestions for improving its sustainability.

[0962] "Example 1"

[0963] (Claim 1)

[0964] A data management system for classifying and storing data,

[0965] A data cleansing method that prepares data for analysis based on the stored data,

[0966] A data analysis method that extracts corporate metrics using a generative AI model,

[0967] An evaluation method that visualizes and evaluates a company's performance based on extracted indicators,

[0968] A method for proposing improvement measures based on evaluation results,

[0969] A business structure proposal tool that analyzes the current business structure and makes proposals that take sustainability into consideration,

[0970] A system that includes this.

[0971] (Claim 2)

[0972] The system according to claim 1, further comprising a question answering means that automatically generates a response using collected information.

[0973] (Claim 3)

[0974] The system according to claim 1, further comprising visual display means for generating an action plan for a company from a sustainability perspective.

[0975] "Application Example 1"

[0976] (Claim 1)

[0977] A device for collecting data,

[0978] A device for analyzing data to extract indicators related to the environment, society, and governance by analyzing the aforementioned data,

[0979] A device for evaluating performance based on the aforementioned indicators,

[0980] A device that makes suggestions recommending improvement measures based on the aforementioned evaluation results,

[0981] A device that visually displays store environmental, social, and governance information for a specific entity,

[0982] A system that includes this.

[0983] (Claim 2)

[0984] The system according to claim 1, further comprising a question-answering device for automatically responding to questions based on information collected from companies.

[0985] (Claim 3)

[0986] The system according to claim 1, further comprising a business model proposal device that analyzes a company's business model and makes suggestions for improving sustainability.

[0987] "Example 2 of combining an emotion engine"

[0988] (Claim 1)

[0989] Data collection means,

[0990] A data analysis means for analyzing information related to the environmental, social, and governance aspects of a company collected by the aforementioned data collection means, and for extracting indicators based on that analysis.

[0991] An evaluation means for evaluating a company's performance based on indicators extracted by the aforementioned data analysis means,

[0992] An improvement suggestion means that recommends improvement measures based on the results evaluated by the evaluation means and the user's emotional state,

[0993] An emotion recognition means for recognizing the emotional state of the user,

[0994] A feedback generation means that generates feedback corresponding to the aforementioned emotion,

[0995] A system that includes this.

[0996] (Claim 2)

[0997] The system according to claim 1, further comprising a question answering means for automatically responding to questions based on information collected from companies.

[0998] (Claim 3)

[0999] The system according to claim 1, further comprising a means for analyzing a company's business model and making suggestions for improving its sustainability.

[1000] "Application example 2 of combining emotional engines"

[1001] (Claim 1)

[1002] Data collection means,

[1003] A data analysis means for analyzing information related to the organization's environment, society, and governance collected by the aforementioned data collection means, and for extracting indicators based on that analysis,

[1004] An evaluation means for evaluating the performance of an organization based on indicators extracted by the aforementioned data analysis means,

[1005] An improvement suggestion means that recommends improvement measures based on the results evaluated by the evaluation means,

[1006] Means of recognizing emotions,

[1007] A feedback generation means that recognizes consumer emotions towards products or services provided by an organization based on emotion data acquired by the emotion recognition means, and provides feedback that takes these emotions into account.

[1008] A system that includes this.

[1009] (Claim 2)

[1010] The system according to claim 1, further comprising question answering means for automatically responding to questions based on information collected from an organization.

[1011] (Claim 3)

[1012] The system according to claim 1, further comprising a strategic proposal means for analyzing an organization's business strategy and making suggestions for improving sustainability. [Explanation of Symbols]

[1013] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Data collection means, A data analysis means for analyzing information related to the company's environmental, social, and governance aspects collected by the aforementioned data collection means, and for extracting indicators based on that analysis. An evaluation means for evaluating a company's performance based on indicators extracted by the aforementioned data analysis means, An improvement suggestion means that recommends improvement measures based on the results evaluated by the evaluation means, A system that includes this.

2. The system according to claim 1, further comprising a question answering means for automatically responding to questions based on information collected from companies.

3. The system according to claim 1, further comprising a means for analyzing a company's business model and making suggestions for improving its sustainability.

Images